aboutsummaryrefslogtreecommitdiffstats
path: root/fs/nfsd/nfs4acl.c
blob: b6ed38380ab805179f8354ab9454fc533e50da53 (plain) (blame)
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
/*
 *  fs/nfs4acl/acl.c
 *
 *  Common NFSv4 ACL handling code.
 *
 *  Copyright (c) 2002, 2003 The Regents of the University of Michigan.
 *  All rights reserved.
 *
 *  Marius Aamodt Eriksen <marius@umich.edu>
 *  Jeff Sedlak <jsedlak@umich.edu>
 *  J. Bruce Fields <bfields@umich.edu>
 *
 *  Redistribution and use in source and binary forms, with or without
 *  modification, are permitted provided that the following conditions
 *  are met:
 *
 *  1. Redistributions of source code must retain the above copyright
 *     notice, this list of conditions and the following disclaimer.
 *  2. Redistributions in binary form must reproduce the above copyright
 *     notice, this list of conditions and the following disclaimer in the
 *     documentation and/or other materials provided with the distribution.
 *  3. Neither the name of the University nor the names of its
 *     contributors may be used to endorse or promote products derived
 *     from this software without specific prior written permission.
 *
 *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
 *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
 *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
 *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <linux/string.h>
#include <linux/slab.h>
#include <linux/list.h>
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/module.h>
#include <linux/nfs_fs.h>
#include <linux/posix_acl.h>
#include <linux/nfs4.h>
#include <linux/nfs4_acl.h>


/* mode bit translations: */
#define NFS4_READ_MODE (NFS4_ACE_READ_DATA)
#define NFS4_WRITE_MODE (NFS4_ACE_WRITE_DATA | NFS4_ACE_APPEND_DATA)
#define NFS4_EXECUTE_MODE NFS4_ACE_EXECUTE
#define NFS4_ANYONE_MODE (NFS4_ACE_READ_ATTRIBUTES | NFS4_ACE_READ_ACL | NFS4_ACE_SYNCHRONIZE)
#define NFS4_OWNER_MODE (NFS4_ACE_WRITE_ATTRIBUTES | NFS4_ACE_WRITE_ACL)

/* We don't support these bits; insist they be neither allowed nor denied */
#define NFS4_MASK_UNSUPP (NFS4_ACE_DELETE | NFS4_ACE_WRITE_OWNER \
		| NFS4_ACE_READ_NAMED_ATTRS | NFS4_ACE_WRITE_NAMED_ATTRS)

/* flags used to simulate posix default ACLs */
#define NFS4_INHERITANCE_FLAGS (NFS4_ACE_FILE_INHERIT_ACE \
		| NFS4_ACE_DIRECTORY_INHERIT_ACE)

#define NFS4_SUPPORTED_FLAGS (NFS4_INHERITANCE_FLAGS \
		| NFS4_ACE_INHERIT_ONLY_ACE \
		| NFS4_ACE_IDENTIFIER_GROUP)

#define MASK_EQUAL(mask1, mask2) \
	( ((mask1) & NFS4_ACE_MASK_ALL) == ((mask2) & NFS4_ACE_MASK_ALL) )

static u32
mask_from_posix(unsigned short perm, unsigned int flags)
{
	int mask = NFS4_ANYONE_MODE;

	if (flags & NFS4_ACL_OWNER)
		mask |= NFS4_OWNER_MODE;
	if (perm & ACL_READ)
		mask |= NFS4_READ_MODE;
	if (perm & ACL_WRITE)
		mask |= NFS4_WRITE_MODE;
	if ((perm & ACL_WRITE) && (flags & NFS4_ACL_DIR))
		mask |= NFS4_ACE_DELETE_CHILD;
	if (perm & ACL_EXECUTE)
		mask |= NFS4_EXECUTE_MODE;
	return mask;
}

static u32
deny_mask_from_posix(unsigned short perm, u32 flags)
{
	u32 mask = 0;

	if (perm & ACL_READ)
		mask |= NFS4_READ_MODE;
	if (perm & ACL_WRITE)
		mask |= NFS4_WRITE_MODE;
	if ((perm & ACL_WRITE) && (flags & NFS4_ACL_DIR))
		mask |= NFS4_ACE_DELETE_CHILD;
	if (perm & ACL_EXECUTE)
		mask |= NFS4_EXECUTE_MODE;
	return mask;
}

/* XXX: modify functions to return NFS errors; they're only ever
 * used by nfs code, after all.... */

/* We only map from NFSv4 to POSIX ACLs when setting ACLs, when we err on the
 * side of being more restrictive, so the mode bit mapping below is
 * pessimistic.  An optimistic version would be needed to handle DENY's,
 * but we espect to coalesce all ALLOWs and DENYs before mapping to mode
 * bits. */

static void
low_mode_from_nfs4(u32 perm, unsigned short *mode, unsigned int flags)
{
	u32 write_mode = NFS4_WRITE_MODE;

	if (flags & NFS4_ACL_DIR)
		write_mode |= NFS4_ACE_DELETE_CHILD;
	*mode = 0;
	if ((perm & NFS4_READ_MODE) == NFS4_READ_MODE)
		*mode |= ACL_READ;
	if ((perm & write_mode) == write_mode)
		*mode |= ACL_WRITE;
	if ((perm & NFS4_EXECUTE_MODE) == NFS4_EXECUTE_MODE)
		*mode |= ACL_EXECUTE;
}

struct ace_container {
	struct nfs4_ace  *ace;
	struct list_head  ace_l;
};

static short ace2type(struct nfs4_ace *);
static void _posix_to_nfsv4_one(struct posix_acl *, struct nfs4_acl *,
				unsigned int);

struct nfs4_acl *
nfs4_acl_posix_to_nfsv4(struct posix_acl *pacl, struct posix_acl *dpacl,
			unsigned int flags)
{
	struct nfs4_acl *acl;
	int size = 0;

	if (pacl) {
		if (posix_acl_valid(pacl) < 0)
			return ERR_PTR(-EINVAL);
		size += 2*pacl->a_count;
	}
	if (dpacl) {
		if (posix_acl_valid(dpacl) < 0)
			return ERR_PTR(-EINVAL);
		size += 2*dpacl->a_count;
	}

	/* Allocate for worst case: one (deny, allow) pair each: */
	acl = nfs4_acl_new(size);
	if (acl == NULL)
		return ERR_PTR(-ENOMEM);

	if (pacl)
		_posix_to_nfsv4_one(pacl, acl, flags & ~NFS4_ACL_TYPE_DEFAULT);

	if (dpacl)
		_posix_to_nfsv4_one(dpacl, acl, flags | NFS4_ACL_TYPE_DEFAULT);

	return acl;
}

struct posix_acl_summary {
	unsigned short owner;
	unsigned short users;
	unsigned short group;
	unsigned short groups;
	unsigned short other;
	unsigned short mask;
};

static void
summarize_posix_acl(struct posix_acl *acl, struct posix_acl_summary *pas)
{
	struct posix_acl_entry *pa, *pe;

	/*
	 * Only pas.users and pas.groups need initialization; previous
	 * posix_acl_valid() calls ensure that the other fields will be
	 * initialized in the following loop.  But, just to placate gcc:
	 */
	memset(pas, 0, sizeof(*pas));
	pas->mask = 07;

	pe = acl->a_entries + acl->a_count;

	FOREACH_ACL_ENTRY(pa, acl, pe) {
		switch (pa->e_tag) {
			case ACL_USER_OBJ:
				pas->owner = pa->e_perm;
				break;
			case ACL_GROUP_OBJ:
				pas->group = pa->e_perm;
				break;
			case ACL_USER:
				pas->users |= pa->e_perm;
				break;
			case ACL_GROUP:
				pas->groups |= pa->e_perm;
				break;
			case ACL_OTHER:
				pas->other = pa->e_perm;
				break;
			case ACL_MASK:
				pas->mask = pa->e_perm;
				break;
		}
	}
	/* We'll only care about effective permissions: */
	pas->users &= pas->mask;
	pas->group &= pas->mask;
	pas->groups &= pas->mask;
}

/* We assume the acl has been verified with posix_acl_valid. */
static void
_posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
						unsigned int flags)
{
	struct posix_acl_entry *pa, *group_owner_entry;
	struct nfs4_ace *ace;
	struct posix_acl_summary pas;
	unsigned short deny;
	int eflag = ((flags & NFS4_ACL_TYPE_DEFAULT) ?
		NFS4_INHERITANCE_FLAGS | NFS4_ACE_INHERIT_ONLY_ACE : 0);

	BUG_ON(pacl->a_count < 3);
	summarize_posix_acl(pacl, &pas);

	pa = pacl->a_entries;
	ace = acl->aces + acl->naces;

	/* We could deny everything not granted by the owner: */
	deny = ~pas.owner;
	/*
	 * but it is equivalent (and simpler) to deny only what is not
	 * granted by later entries:
	 */
	deny &= pas.users | pas.group | pas.groups | pas.other;
	if (deny) {
		ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
		ace->flag = eflag;
		ace->access_mask = deny_mask_from_posix(deny, flags);
		ace->whotype = NFS4_ACL_WHO_OWNER;
		ace++;
		acl->naces++;
	}

	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
	ace->flag = eflag;
	ace->access_mask = mask_from_posix(pa->e_perm, flags | NFS4_ACL_OWNER);
	ace->whotype = NFS4_ACL_WHO_OWNER;
	ace++;
	acl->naces++;
	pa++;

	while (pa->e_tag == ACL_USER) {
		deny = ~(pa->e_perm & pas.mask);
		deny &= pas.groups | pas.group | pas.other;
		if (deny) {
			ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
			ace->flag = eflag;
			ace->access_mask = deny_mask_from_posix(deny, flags);
			ace->whotype = NFS4_ACL_WHO_NAMED;
			ace->who = pa->e_id;
			ace++;
			acl->naces++;
		}
		ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
		ace->flag = eflag;
		ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
						   flags);
		ace->whotype = NFS4_ACL_WHO_NAMED;
		ace->who = pa->e_id;
		ace++;
		acl->naces++;
		pa++;
	}

	/* In the case of groups, we apply allow ACEs first, then deny ACEs,
	 * since a user can be in more than one group.  */

	/* allow ACEs */

	group_owner_entry = pa;

	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
	ace->flag = eflag;
	ace->access_mask = mask_from_posix(pas.group, flags);
	ace->whotype = NFS4_ACL_WHO_GROUP;
	ace++;
	acl->naces++;
	pa++;

	while (pa->e_tag == ACL_GROUP) {
		ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
		ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
		ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
						   flags);
		ace->whotype = NFS4_ACL_WHO_NAMED;
		ace->who = pa->e_id;
		ace++;
		acl->naces++;
		pa++;
	}

	/* deny ACEs */

	pa = group_owner_entry;

	deny = ~pas.group & pas.other;
	if (deny) {
		ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
		ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
		ace->access_mask = deny_mask_from_posix(deny, flags);
		ace->whotype = NFS4_ACL_WHO_GROUP;
		ace++;
		acl->naces++;
	}
	pa++;

	while (pa->e_tag == ACL_GROUP) {
		deny = ~(pa->e_perm & pas.mask);
		deny &= pas.other;
		if (deny) {
			ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
			ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
			ace->access_mask = mask_from_posix(deny, flags);
			ace->whotype = NFS4_ACL_WHO_NAMED;
			ace->who = pa->e_id;
			ace++;
			acl->naces++;
		}
		pa++;
	}

	if (pa->e_tag == ACL_MASK)
		pa++;
	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
	ace->flag = eflag;
	ace->access_mask = mask_from_posix(pa->e_perm, flags);
	ace->whotype = NFS4_ACL_WHO_EVERYONE;
	acl->naces++;
}

static void
sort_pacl_range(struct posix_acl *pacl, int start, int end) {
	int sorted = 0, i;
	struct posix_acl_entry tmp;

	/* We just do a bubble sort; easy to do in place, and we're not
	 * expecting acl's to be long enough to justify anything more. */
	while (!sorted) {
		sorted = 1;
		for (i = start; i < end; i++) {
			if (pacl->a_entries[i].e_id
					> pacl->a_entries[i+1].e_id) {
				sorted = 0;
				tmp = pacl->a_entries[i];
				pacl->a_entries[i] = pacl->a_entries[i+1];
				pacl->a_entries[i+1] = tmp;
			}
		}
	}
}

static void
sort_pacl(struct posix_acl *pacl)
{
	/* posix_acl_valid requires that users and groups be in order
	 * by uid/gid. */
	int i, j;

	if (pacl->a_count <= 4)
		return; /* no users or groups */
	i = 1;
	while (pacl->a_entries[i].e_tag == ACL_USER)
		i++;
	sort_pacl_range(pacl, 1, i-1);

	BUG_ON(pacl->a_entries[i].e_tag != ACL_GROUP_OBJ);
	j = i++;
	while (pacl->a_entries[j].e_tag == ACL_GROUP)
		j++;
	sort_pacl_range(pacl, i, j-1);
	return;
}

/*
 * While processing the NFSv4 ACE, this maintains bitmasks representing
 * which permission bits have been allowed and which denied to a given
 * entity: */
struct posix_ace_state {
	u32 allow;
	u32 deny;
};

struct posix_user_ace_state {
	uid_t uid;
	struct posix_ace_state perms;
};

struct posix_ace_state_array {
	int n;
	struct posix_user_ace_state aces[];
};

/*
 * While processing the NFSv4 ACE, this maintains the partial permissions
 * calculated so far: */

struct posix_acl_state {
	int empty;
	struct posix_ace_state owner;
	struct posix_ace_state group;
	struct posix_ace_state other;
	struct posix_ace_state everyone;
	struct posix_ace_state mask; /* Deny unused in this case */
	struct posix_ace_state_array *users;
	struct posix_ace_state_array *groups;
};

static int
init_state(struct posix_acl_state *state, int cnt)
{
	int alloc;

	memset(state, 0, sizeof(struct posix_acl_state));
	state->empty = 1;
	/*
	 * In the worst case, each individual acl could be for a distinct
	 * named user or group, but we don't no which, so we allocate
	 * enough space for either:
	 */
	alloc = sizeof(struct posix_ace_state_array)
		+ cnt*sizeof(struct posix_ace_state);
	state->users = kzalloc(alloc, GFP_KERNEL);
	if (!state->users)
		return -ENOMEM;
	state->groups = kzalloc(alloc, GFP_KERNEL);
	if (!state->groups) {
		kfree(state->users);
		return -ENOMEM;
	}
	return 0;
}

static void
free_state(struct posix_acl_state *state) {
	kfree(state->users);
	kfree(state->groups);
}

static inline void add_to_mask(struct posix_acl_state *state, struct posix_ace_state *astate)
{
	state->mask.allow |= astate->allow;
}

/*
 * Certain bits (SYNCHRONIZE, DELETE, WRITE_OWNER, READ/WRITE_NAMED_ATTRS,
 * READ_ATTRIBUTES, READ_ACL) are currently unenforceable and don't translate
 * to traditional read/write/execute permissions.
 *
 * It's problematic to reject acls that use certain mode bits, because it
 * places the burden on users to learn the rules about which bits one
 * particular server sets, without giving the user a lot of help--we return an
 * error that could mean any number of different things.  To make matters
 * worse, the problematic bits might be introduced by some application that's
 * automatically mapping from some other acl model.
 *
 * So wherever possible we accept anything, possibly erring on the side of
 * denying more permissions than necessary.
 *
 * However we do reject *explicit* DENY's of a few bits representing
 * permissions we could never deny:
 */

static inline int check_deny(u32 mask, int isowner)
{
	if (mask & (NFS4_ACE_READ_ATTRIBUTES | NFS4_ACE_READ_ACL))
		return -EINVAL;
	if (!isowner)
		return 0;
	if (mask & (NFS4_ACE_WRITE_ATTRIBUTES | NFS4_ACE_WRITE_ACL))
		return -EINVAL;
	return 0;
}

static struct posix_acl *
posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
{
	struct posix_acl_entry *pace;
	struct posix_acl *pacl;
	int nace;
	int i, error = 0;

	/*
	 * ACLs with no ACEs are treated differently in the inheritable
	 * and effective cases: when there are no inheritable ACEs, we
	 * set a zero-length default posix acl:
	 */
	if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT)) {
		pacl = posix_acl_alloc(0, GFP_KERNEL);
		return pacl ? pacl : ERR_PTR(-ENOMEM);
	}
	/*
	 * When there are no effective ACEs, the following will end
	 * up setting a 3-element effective posix ACL with all
	 * permissions zero.
	 */
	nace = 4 + state->users->n + state->groups->n;
	pacl = posix_acl_alloc(nace, GFP_KERNEL);
	if (!pacl)
		return ERR_PTR(-ENOMEM);

	pace = pacl->a_entries;
	pace->e_tag = ACL_USER_OBJ;
	error = check_deny(state->owner.deny, 1);
	if (error)
		goto out_err;
	low_mode_from_nfs4(state->owner.allow, &pace->e_perm, flags);
	pace->e_id = ACL_UNDEFINED_ID;

	for (i=0; i < state->users->n; i++) {
		pace++;
		pace->e_tag = ACL_USER;
		error = check_deny(state->users->aces[i].perms.deny, 0);
		if (error)
			goto out_err;
		low_mode_from_nfs4(state->users->aces[i].perms.allow,
					&pace->e_perm, flags);
		pace->e_id = state->users->aces[i].uid;
		add_to_mask(state, &state->users->aces[i].perms);
	}

	pace++;
	pace->e_tag = ACL_GROUP_OBJ;
	error = check_deny(state->group.deny, 0);
	if (error)
		goto out_err;
	low_mode_from_nfs4(state->group.allow, &pace->e_perm, flags);
	pace->e_id = ACL_UNDEFINED_ID;
	add_to_mask(state, &state->group);

	for (i=0; i < state->groups->n; i++) {
		pace++;
		pace->e_tag = ACL_GROUP;
		error = check_deny(state->groups->aces[i].perms.deny, 0);
		if (error)
			goto out_err;
		low_mode_from_nfs4(state->groups->aces[i].perms.allow,
					&pace->e_perm, flags);
		pace->e_id = state->groups->aces[i].uid;
		add_to_mask(state, &state->groups->aces[i].perms);
	}

	pace++;
	pace->e_tag = ACL_MASK;
	low_mode_from_nfs4(state->mask.allow, &pace->e_perm, flags);
	pace->e_id = ACL_UNDEFINED_ID;

	pace++;
	pace->e_tag = ACL_OTHER;
	error = check_deny(state->other.deny, 0);
	if (error)
		goto out_err;
	low_mode_from_nfs4(state->other.allow, &pace->e_perm, flags);
	pace->e_id = ACL_UNDEFINED_ID;

	return pacl;
out_err:
	posix_acl_release(pacl);
	return ERR_PTR(error);
}

static inline void allow_bits(struct posix_ace_state *astate, u32 mask)
{
	/* Allow all bits in the mask not already denied: */
	astate->allow |= mask & ~astate->deny;
}

static inline void deny_bits(struct posix_ace_state *astate, u32 mask)
{
	/* Deny all bits in the mask not already allowed: */
	astate->deny |= mask & ~astate->allow;
}

static int find_uid(struct posix_acl_state *state, struct posix_ace_state_array *a, uid_t uid)
{
	int i;

	for (i = 0; i < a->n; i++)
		if (a->aces[i].uid == uid)
			return i;
	/* Not found: */
	a->n++;
	a->aces[i].uid = uid;
	a->aces[i].perms.allow = state->everyone.allow;
	a->aces[i].perms.deny  = state->everyone.deny;

	return i;
}

static void deny_bits_array(struct posix_ace_state_array *a, u32 mask)
{
	int i;

	for (i=0; i < a->n; i++)
		deny_bits(&a->aces[i].perms, mask);
}

static void allow_bits_array(struct posix_ace_state_array *a, u32 mask)
{
	int i;

	for (i=0; i < a->n; i++)
		allow_bits(&a->aces[i].perms, mask);
}

static void process_one_v4_ace(struct posix_acl_state *state,
				struct nfs4_ace *ace)
{
	u32 mask = ace->access_mask;
	int i;

	state->empty = 0;

	switch (ace2type(ace)) {
	case ACL_USER_OBJ:
		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
			allow_bits(&state->owner, mask);
		} else {
			deny_bits(&state->owner, mask);
		}
		break;
	case ACL_USER:
		i = find_uid(state, state->users, ace->who);
		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
			allow_bits(&state->users->aces[i].perms, mask);
		} else {
			deny_bits(&state->users->aces[i].perms, mask);
			mask = state->users->aces[i].perms.deny;
			deny_bits(&state->owner, mask);
		}
		break;
	case ACL_GROUP_OBJ:
		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
			allow_bits(&state->group, mask);
		} else {
			deny_bits(&state->group, mask);
			mask = state->group.deny;
			deny_bits(&state->owner, mask);
			deny_bits(&state->everyone, mask);
			deny_bits_array(state->users, mask);
			deny_bits_array(state->groups, mask);
		}
		break;
	case ACL_GROUP:
		i = find_uid(state, state->groups, ace->who);
		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
			allow_bits(&state->groups->aces[i].perms, mask);
		} else {
			deny_bits(&state->groups->aces[i].perms, mask);
			mask = state->groups->aces[i].perms.deny;
			deny_bits(&state->owner, mask);
			deny_bits(&state->group, mask);
			deny_bits(&state->everyone, mask);
			deny_bits_array(state->users, mask);
			deny_bits_array(state->groups, mask);
		}
		break;
	case ACL_OTHER:
		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
			allow_bits(&state->owner, mask);
			allow_bits(&state->group, mask);
			allow_bits(&state->other, mask);
			allow_bits(&state->everyone, mask);
			allow_bits_array(state->users, mask);
			allow_bits_array(state->groups, mask);
		} else {
			deny_bits(&state->owner, mask);
			deny_bits(&state->group, mask);
			deny_bits(&state->other, mask);
			deny_bits(&state->everyone, mask);
			deny_bits_array(state->users, mask);
			deny_bits_array(state->groups, mask);
		}
	}
}

int nfs4_acl_nfsv4_to_posix(struct nfs4_acl *acl, struct posix_acl **pacl,
			    struct posix_acl **dpacl, unsigned int flags)
{
	struct posix_acl_state effective_acl_state, default_acl_state;
	struct nfs4_ace *ace;
	int ret;

	ret = init_state(&effective_acl_state, acl->naces);
	if (ret)
		return ret;
	ret = init_state(&default_acl_state, acl->naces);
	if (ret)
		goto out_estate;
	ret = -EINVAL;
	for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) {
		if (ace->type != NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE &&
		    ace->type != NFS4_ACE_ACCESS_DENIED_ACE_TYPE)
			goto out_dstate;
		if (ace->flag & ~NFS4_SUPPORTED_FLAGS)
			goto out_dstate;
		if ((ace->flag & NFS4_INHERITANCE_FLAGS) == 0) {
			process_one_v4_ace(&effective_acl_state, ace);
			continue;
		}
		if (!(flags & NFS4_ACL_DIR))
			goto out_dstate;
		/*
		 * Note that when only one of FILE_INHERIT or DIRECTORY_INHERIT
		 * is set, we're effectively turning on the other.  That's OK,
		 * according to rfc 3530.
		 */
		process_one_v4_ace(&default_acl_state, ace);

		if (!(ace->flag & NFS4_ACE_INHERIT_ONLY_ACE))
			process_one_v4_ace(&effective_acl_state, ace);
	}
	*pacl = posix_state_to_acl(&effective_acl_state, flags);
	if (IS_ERR(*pacl)) {
		ret = PTR_ERR(*pacl);
		*pacl = NULL;
		goto out_dstate;
	}
	*dpacl = posix_state_to_acl(&default_acl_state,
						flags | NFS4_ACL_TYPE_DEFAULT);
	if (IS_ERR(*dpacl)) {
		ret = PTR_ERR(*dpacl);
		*dpacl = NULL;
		posix_acl_release(*pacl);
		*pacl = NULL;
		goto out_dstate;
	}
	sort_pacl(*pacl);
	sort_pacl(*dpacl);
	ret = 0;
out_dstate:
	free_state(&default_acl_state);
out_estate:
	free_state(&effective_acl_state);
	return ret;
}

static short
ace2type(struct nfs4_ace *ace)
{
	switch (ace->whotype) {
		case NFS4_ACL_WHO_NAMED:
			return (ace->flag & NFS4_ACE_IDENTIFIER_GROUP ?
					ACL_GROUP : ACL_USER);
		case NFS4_ACL_WHO_OWNER:
			return ACL_USER_OBJ;
		case NFS4_ACL_WHO_GROUP:
			return ACL_GROUP_OBJ;
		case NFS4_ACL_WHO_EVERYONE:
			return ACL_OTHER;
	}
	BUG();
	return -1;
}

EXPORT_SYMBOL(nfs4_acl_posix_to_nfsv4);
EXPORT_SYMBOL(nfs4_acl_nfsv4_to_posix);

struct nfs4_acl *
nfs4_acl_new(int n)
{
	struct nfs4_acl *acl;

	acl = kmalloc(sizeof(*acl) + n*sizeof(struct nfs4_ace), GFP_KERNEL);
	if (acl == NULL)
		return NULL;
	acl->naces = 0;
	return acl;
}

static struct {
	char *string;
	int   stringlen;
	int type;
} s2t_map[] = {
	{
		.string    = "OWNER@",
		.stringlen = sizeof("OWNER@") - 1,
		.type      = NFS4_ACL_WHO_OWNER,
	},
	{
		.string    = "GROUP@",
		.stringlen = sizeof("GROUP@") - 1,
		.type      = NFS4_ACL_WHO_GROUP,
	},
	{
		.string    = "EVERYONE@",
		.stringlen = sizeof("EVERYONE@") - 1,
		.type      = NFS4_ACL_WHO_EVERYONE,
	},
};

int
nfs4_acl_get_whotype(char *p, u32 len)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
		if (s2t_map[i].stringlen == len &&
				0 == memcmp(s2t_map[i].string, p, len))
			return s2t_map[i].type;
	}
	return NFS4_ACL_WHO_NAMED;
}

int
nfs4_acl_write_who(int who, char *p)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
		if (s2t_map[i].type == who) {
			memcpy(p, s2t_map[i].string, s2t_map[i].stringlen);
			return s2t_map[i].stringlen;
		}
	}
	BUG();
	return -1;
}

EXPORT_SYMBOL(nfs4_acl_new);
EXPORT_SYMBOL(nfs4_acl_get_whotype);
EXPORT_SYMBOL(nfs4_acl_write_who);
='n3244' href='#n3244'>3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555
/*
 *  kernel/sched.c
 *
 *  Kernel scheduler and related syscalls
 *
 *  Copyright (C) 1991-2002  Linus Torvalds
 *
 *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
 *		make semaphores SMP safe
 *  1998-11-19	Implemented schedule_timeout() and related stuff
 *		by Andrea Arcangeli
 *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
 *		hybrid priority-list and round-robin design with
 *		an array-switch method of distributing timeslices
 *		and per-CPU runqueues.  Cleanups and useful suggestions
 *		by Davide Libenzi, preemptible kernel bits by Robert Love.
 *  2003-09-03	Interactivity tuning by Con Kolivas.
 *  2004-04-02	Scheduler domains code by Nick Piggin
 *  2007-04-15  Work begun on replacing all interactivity tuning with a
 *              fair scheduling design by Con Kolivas.
 *  2007-05-05  Load balancing (smp-nice) and other improvements
 *              by Peter Williams
 *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
 *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri
 *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins,
 *              Thomas Gleixner, Mike Kravetz
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <linux/uaccess.h>
#include <linux/highmem.h>
#include <linux/smp_lock.h>
#include <asm/mmu_context.h>
#include <linux/interrupt.h>
#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/kernel_stat.h>
#include <linux/debug_locks.h>
#include <linux/perf_counter.h>
#include <linux/security.h>
#include <linux/notifier.h>
#include <linux/profile.h>
#include <linux/freezer.h>
#include <linux/vmalloc.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/pid_namespace.h>
#include <linux/smp.h>
#include <linux/threads.h>
#include <linux/timer.h>
#include <linux/rcupdate.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/percpu.h>
#include <linux/kthread.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sysctl.h>
#include <linux/syscalls.h>
#include <linux/times.h>
#include <linux/tsacct_kern.h>
#include <linux/kprobes.h>
#include <linux/delayacct.h>
#include <linux/reciprocal_div.h>
#include <linux/unistd.h>
#include <linux/pagemap.h>
#include <linux/hrtimer.h>
#include <linux/tick.h>
#include <linux/debugfs.h>
#include <linux/ctype.h>
#include <linux/ftrace.h>

#include <asm/tlb.h>
#include <asm/irq_regs.h>

#include "sched_cpupri.h"

#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>

/*
 * Convert user-nice values [ -20 ... 0 ... 19 ]
 * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
 * and back.
 */
#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)

/*
 * 'User priority' is the nice value converted to something we
 * can work with better when scaling various scheduler parameters,
 * it's a [ 0 ... 39 ] range.
 */
#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))

/*
 * Helpers for converting nanosecond timing to jiffy resolution
 */
#define NS_TO_JIFFIES(TIME)	((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))

#define NICE_0_LOAD		SCHED_LOAD_SCALE
#define NICE_0_SHIFT		SCHED_LOAD_SHIFT

/*
 * These are the 'tuning knobs' of the scheduler:
 *
 * default timeslice is 100 msecs (used only for SCHED_RR tasks).
 * Timeslices get refilled after they expire.
 */
#define DEF_TIMESLICE		(100 * HZ / 1000)

/*
 * single value that denotes runtime == period, ie unlimited time.
 */
#define RUNTIME_INF	((u64)~0ULL)

#ifdef CONFIG_SMP

static void double_rq_lock(struct rq *rq1, struct rq *rq2);

/*
 * Divide a load by a sched group cpu_power : (load / sg->__cpu_power)
 * Since cpu_power is a 'constant', we can use a reciprocal divide.
 */
static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load)
{
	return reciprocal_divide(load, sg->reciprocal_cpu_power);
}

/*
 * Each time a sched group cpu_power is changed,
 * we must compute its reciprocal value
 */
static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val)
{
	sg->__cpu_power += val;
	sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power);
}
#endif

static inline int rt_policy(int policy)
{
	if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR))
		return 1;
	return 0;
}

static inline int task_has_rt_policy(struct task_struct *p)
{
	return rt_policy(p->policy);
}

/*
 * This is the priority-queue data structure of the RT scheduling class:
 */
struct rt_prio_array {
	DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */
	struct list_head queue[MAX_RT_PRIO];
};

struct rt_bandwidth {
	/* nests inside the rq lock: */
	spinlock_t		rt_runtime_lock;
	ktime_t			rt_period;
	u64			rt_runtime;
	struct hrtimer		rt_period_timer;
};

static struct rt_bandwidth def_rt_bandwidth;

static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);

static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
{
	struct rt_bandwidth *rt_b =
		container_of(timer, struct rt_bandwidth, rt_period_timer);
	ktime_t now;
	int overrun;
	int idle = 0;

	for (;;) {
		now = hrtimer_cb_get_time(timer);
		overrun = hrtimer_forward(timer, now, rt_b->rt_period);

		if (!overrun)
			break;

		idle = do_sched_rt_period_timer(rt_b, overrun);
	}

	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
}

static
void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
{
	rt_b->rt_period = ns_to_ktime(period);
	rt_b->rt_runtime = runtime;

	spin_lock_init(&rt_b->rt_runtime_lock);

	hrtimer_init(&rt_b->rt_period_timer,
			CLOCK_MONOTONIC, HRTIMER_MODE_REL);
	rt_b->rt_period_timer.function = sched_rt_period_timer;
}

static inline int rt_bandwidth_enabled(void)
{
	return sysctl_sched_rt_runtime >= 0;
}

static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
{
	ktime_t now;

	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
		return;

	if (hrtimer_active(&rt_b->rt_period_timer))
		return;

	spin_lock(&rt_b->rt_runtime_lock);
	for (;;) {
		unsigned long delta;
		ktime_t soft, hard;

		if (hrtimer_active(&rt_b->rt_period_timer))
			break;

		now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
		hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);

		soft = hrtimer_get_softexpires(&rt_b->rt_period_timer);
		hard = hrtimer_get_expires(&rt_b->rt_period_timer);
		delta = ktime_to_ns(ktime_sub(hard, soft));
		__hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
				HRTIMER_MODE_ABS_PINNED, 0);
	}
	spin_unlock(&rt_b->rt_runtime_lock);
}

#ifdef CONFIG_RT_GROUP_SCHED
static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b)
{
	hrtimer_cancel(&rt_b->rt_period_timer);
}
#endif

/*
 * sched_domains_mutex serializes calls to arch_init_sched_domains,
 * detach_destroy_domains and partition_sched_domains.
 */
static DEFINE_MUTEX(sched_domains_mutex);

#ifdef CONFIG_GROUP_SCHED

#include <linux/cgroup.h>

struct cfs_rq;

static LIST_HEAD(task_groups);

/* task group related information */
struct task_group {
#ifdef CONFIG_CGROUP_SCHED
	struct cgroup_subsys_state css;
#endif

#ifdef CONFIG_USER_SCHED
	uid_t uid;
#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
	/* schedulable entities of this group on each cpu */
	struct sched_entity **se;
	/* runqueue "owned" by this group on each cpu */
	struct cfs_rq **cfs_rq;
	unsigned long shares;
#endif

#ifdef CONFIG_RT_GROUP_SCHED
	struct sched_rt_entity **rt_se;
	struct rt_rq **rt_rq;

	struct rt_bandwidth rt_bandwidth;
#endif

	struct rcu_head rcu;
	struct list_head list;

	struct task_group *parent;
	struct list_head siblings;
	struct list_head children;
};

#ifdef CONFIG_USER_SCHED

/* Helper function to pass uid information to create_sched_user() */
void set_tg_uid(struct user_struct *user)
{
	user->tg->uid = user->uid;
}

/*
 * Root task group.
 * 	Every UID task group (including init_task_group aka UID-0) will
 * 	be a child to this group.
 */
struct task_group root_task_group;

#ifdef CONFIG_FAIR_GROUP_SCHED
/* Default task group's sched entity on each cpu */
static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
/* Default task group's cfs_rq on each cpu */
static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
#endif /* CONFIG_FAIR_GROUP_SCHED */

#ifdef CONFIG_RT_GROUP_SCHED
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp;
#endif /* CONFIG_RT_GROUP_SCHED */
#else /* !CONFIG_USER_SCHED */
#define root_task_group init_task_group
#endif /* CONFIG_USER_SCHED */

/* task_group_lock serializes add/remove of task groups and also changes to
 * a task group's cpu shares.
 */
static DEFINE_SPINLOCK(task_group_lock);

#ifdef CONFIG_SMP
static int root_task_group_empty(void)
{
	return list_empty(&root_task_group.children);
}
#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_USER_SCHED
# define INIT_TASK_GROUP_LOAD	(2*NICE_0_LOAD)
#else /* !CONFIG_USER_SCHED */
# define INIT_TASK_GROUP_LOAD	NICE_0_LOAD
#endif /* CONFIG_USER_SCHED */

/*
 * A weight of 0 or 1 can cause arithmetics problems.
 * A weight of a cfs_rq is the sum of weights of which entities
 * are queued on this cfs_rq, so a weight of a entity should not be
 * too large, so as the shares value of a task group.
 * (The default weight is 1024 - so there's no practical
 *  limitation from this.)
 */
#define MIN_SHARES	2
#define MAX_SHARES	(1UL << 18)

static int init_task_group_load = INIT_TASK_GROUP_LOAD;
#endif

/* Default task group.
 *	Every task in system belong to this group at bootup.
 */
struct task_group init_task_group;

/* return group to which a task belongs */
static inline struct task_group *task_group(struct task_struct *p)
{
	struct task_group *tg;

#ifdef CONFIG_USER_SCHED
	rcu_read_lock();
	tg = __task_cred(p)->user->tg;
	rcu_read_unlock();
#elif defined(CONFIG_CGROUP_SCHED)
	tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
				struct task_group, css);
#else
	tg = &init_task_group;
#endif
	return tg;
}

/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
{
#ifdef CONFIG_FAIR_GROUP_SCHED
	p->se.cfs_rq = task_group(p)->cfs_rq[cpu];
	p->se.parent = task_group(p)->se[cpu];
#endif

#ifdef CONFIG_RT_GROUP_SCHED
	p->rt.rt_rq  = task_group(p)->rt_rq[cpu];
	p->rt.parent = task_group(p)->rt_se[cpu];
#endif
}

#else

#ifdef CONFIG_SMP
static int root_task_group_empty(void)
{
	return 1;
}
#endif

static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
static inline struct task_group *task_group(struct task_struct *p)
{
	return NULL;
}

#endif	/* CONFIG_GROUP_SCHED */

/* CFS-related fields in a runqueue */
struct cfs_rq {
	struct load_weight load;
	unsigned long nr_running;

	u64 exec_clock;
	u64 min_vruntime;

	struct rb_root tasks_timeline;
	struct rb_node *rb_leftmost;

	struct list_head tasks;
	struct list_head *balance_iterator;

	/*
	 * 'curr' points to currently running entity on this cfs_rq.
	 * It is set to NULL otherwise (i.e when none are currently running).
	 */
	struct sched_entity *curr, *next, *last;

	unsigned int nr_spread_over;

#ifdef CONFIG_FAIR_GROUP_SCHED
	struct rq *rq;	/* cpu runqueue to which this cfs_rq is attached */

	/*
	 * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
	 * a hierarchy). Non-leaf lrqs hold other higher schedulable entities
	 * (like users, containers etc.)
	 *
	 * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
	 * list is used during load balance.
	 */
	struct list_head leaf_cfs_rq_list;
	struct task_group *tg;	/* group that "owns" this runqueue */

#ifdef CONFIG_SMP
	/*
	 * the part of load.weight contributed by tasks
	 */
	unsigned long task_weight;

	/*
	 *   h_load = weight * f(tg)
	 *
	 * Where f(tg) is the recursive weight fraction assigned to
	 * this group.
	 */
	unsigned long h_load;

	/*
	 * this cpu's part of tg->shares
	 */
	unsigned long shares;

	/*
	 * load.weight at the time we set shares
	 */
	unsigned long rq_weight;
#endif
#endif
};

/* Real-Time classes' related field in a runqueue: */
struct rt_rq {
	struct rt_prio_array active;
	unsigned long rt_nr_running;
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
	struct {
		int curr; /* highest queued rt task prio */
#ifdef CONFIG_SMP
		int next; /* next highest */
#endif
	} highest_prio;
#endif
#ifdef CONFIG_SMP
	unsigned long rt_nr_migratory;
	int overloaded;
	struct plist_head pushable_tasks;
#endif
	int rt_throttled;
	u64 rt_time;
	u64 rt_runtime;
	/* Nests inside the rq lock: */
	spinlock_t rt_runtime_lock;

#ifdef CONFIG_RT_GROUP_SCHED
	unsigned long rt_nr_boosted;

	struct rq *rq;
	struct list_head leaf_rt_rq_list;
	struct task_group *tg;
	struct sched_rt_entity *rt_se;
#endif
};

#ifdef CONFIG_SMP

/*
 * We add the notion of a root-domain which will be used to define per-domain
 * variables. Each exclusive cpuset essentially defines an island domain by
 * fully partitioning the member cpus from any other cpuset. Whenever a new
 * exclusive cpuset is created, we also create and attach a new root-domain
 * object.
 *
 */
struct root_domain {
	atomic_t refcount;
	cpumask_var_t span;
	cpumask_var_t online;

	/*
	 * The "RT overload" flag: it gets set if a CPU has more than
	 * one runnable RT task.
	 */
	cpumask_var_t rto_mask;
	atomic_t rto_count;
#ifdef CONFIG_SMP
	struct cpupri cpupri;
#endif
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
	/*
	 * Preferred wake up cpu nominated by sched_mc balance that will be
	 * used when most cpus are idle in the system indicating overall very
	 * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2)
	 */
	unsigned int sched_mc_preferred_wakeup_cpu;
#endif
};

/*
 * By default the system creates a single root-domain with all cpus as
 * members (mimicking the global state we have today).
 */
static struct root_domain def_root_domain;

#endif

/*
 * This is the main, per-CPU runqueue data structure.
 *
 * Locking rule: those places that want to lock multiple runqueues
 * (such as the load balancing or the thread migration code), lock
 * acquire operations must be ordered by ascending &runqueue.
 */
struct rq {
	/* runqueue lock: */
	spinlock_t lock;

	/*
	 * nr_running and cpu_load should be in the same cacheline because
	 * remote CPUs use both these fields when doing load calculation.
	 */
	unsigned long nr_running;
	#define CPU_LOAD_IDX_MAX 5
	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
#ifdef CONFIG_NO_HZ
	unsigned long last_tick_seen;
	unsigned char in_nohz_recently;
#endif
	/* capture load from *all* tasks on this cpu: */
	struct load_weight load;
	unsigned long nr_load_updates;
	u64 nr_switches;
	u64 nr_migrations_in;

	struct cfs_rq cfs;
	struct rt_rq rt;

#ifdef CONFIG_FAIR_GROUP_SCHED
	/* list of leaf cfs_rq on this cpu: */
	struct list_head leaf_cfs_rq_list;
#endif
#ifdef CONFIG_RT_GROUP_SCHED
	struct list_head leaf_rt_rq_list;
#endif

	/*
	 * This is part of a global counter where only the total sum
	 * over all CPUs matters. A task can increase this counter on
	 * one CPU and if it got migrated afterwards it may decrease
	 * it on another CPU. Always updated under the runqueue lock:
	 */
	unsigned long nr_uninterruptible;

	struct task_struct *curr, *idle;
	unsigned long next_balance;
	struct mm_struct *prev_mm;

	u64 clock;

	atomic_t nr_iowait;

#ifdef CONFIG_SMP
	struct root_domain *rd;
	struct sched_domain *sd;

	unsigned char idle_at_tick;
	/* For active balancing */
	int active_balance;
	int push_cpu;
	/* cpu of this runqueue: */
	int cpu;
	int online;

	unsigned long avg_load_per_task;

	struct task_struct *migration_thread;
	struct list_head migration_queue;
#endif

	/* calc_load related fields */
	unsigned long calc_load_update;
	long calc_load_active;

#ifdef CONFIG_SCHED_HRTICK
#ifdef CONFIG_SMP
	int hrtick_csd_pending;
	struct call_single_data hrtick_csd;
#endif
	struct hrtimer hrtick_timer;
#endif

#ifdef CONFIG_SCHEDSTATS
	/* latency stats */
	struct sched_info rq_sched_info;
	unsigned long long rq_cpu_time;
	/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */

	/* sys_sched_yield() stats */
	unsigned int yld_count;

	/* schedule() stats */
	unsigned int sched_switch;
	unsigned int sched_count;
	unsigned int sched_goidle;

	/* try_to_wake_up() stats */
	unsigned int ttwu_count;
	unsigned int ttwu_local;

	/* BKL stats */
	unsigned int bkl_count;
#endif
};

static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);

static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync)
{
	rq->curr->sched_class->check_preempt_curr(rq, p, sync);
}

static inline int cpu_of(struct rq *rq)
{
#ifdef CONFIG_SMP
	return rq->cpu;
#else
	return 0;
#endif
}

/*
 * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
 * See detach_destroy_domains: synchronize_sched for details.
 *
 * The domain tree of any CPU may only be accessed from within
 * preempt-disabled sections.
 */
#define for_each_domain(cpu, __sd) \
	for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)

#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
#define this_rq()		(&__get_cpu_var(runqueues))
#define task_rq(p)		cpu_rq(task_cpu(p))
#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)

inline void update_rq_clock(struct rq *rq)
{
	rq->clock = sched_clock_cpu(cpu_of(rq));
}

/*
 * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
 */
#ifdef CONFIG_SCHED_DEBUG
# define const_debug __read_mostly
#else
# define const_debug static const
#endif

/**
 * runqueue_is_locked
 *
 * Returns true if the current cpu runqueue is locked.
 * This interface allows printk to be called with the runqueue lock
 * held and know whether or not it is OK to wake up the klogd.
 */
int runqueue_is_locked(void)
{
	int cpu = get_cpu();
	struct rq *rq = cpu_rq(cpu);
	int ret;

	ret = spin_is_locked(&rq->lock);
	put_cpu();
	return ret;
}

/*
 * Debugging: various feature bits
 */

#define SCHED_FEAT(name, enabled)	\
	__SCHED_FEAT_##name ,

enum {
#include "sched_features.h"
};

#undef SCHED_FEAT

#define SCHED_FEAT(name, enabled)	\
	(1UL << __SCHED_FEAT_##name) * enabled |

const_debug unsigned int sysctl_sched_features =
#include "sched_features.h"
	0;

#undef SCHED_FEAT

#ifdef CONFIG_SCHED_DEBUG
#define SCHED_FEAT(name, enabled)	\
	#name ,

static __read_mostly char *sched_feat_names[] = {
#include "sched_features.h"
	NULL
};

#undef SCHED_FEAT

static int sched_feat_show(struct seq_file *m, void *v)
{
	int i;

	for (i = 0; sched_feat_names[i]; i++) {
		if (!(sysctl_sched_features & (1UL << i)))
			seq_puts(m, "NO_");
		seq_printf(m, "%s ", sched_feat_names[i]);
	}
	seq_puts(m, "\n");

	return 0;
}

static ssize_t
sched_feat_write(struct file *filp, const char __user *ubuf,
		size_t cnt, loff_t *ppos)
{
	char buf[64];
	char *cmp = buf;
	int neg = 0;
	int i;

	if (cnt > 63)
		cnt = 63;

	if (copy_from_user(&buf, ubuf, cnt))
		return -EFAULT;

	buf[cnt] = 0;

	if (strncmp(buf, "NO_", 3) == 0) {
		neg = 1;
		cmp += 3;
	}

	for (i = 0; sched_feat_names[i]; i++) {
		int len = strlen(sched_feat_names[i]);

		if (strncmp(cmp, sched_feat_names[i], len) == 0) {
			if (neg)
				sysctl_sched_features &= ~(1UL << i);
			else
				sysctl_sched_features |= (1UL << i);
			break;
		}
	}

	if (!sched_feat_names[i])
		return -EINVAL;

	filp->f_pos += cnt;

	return cnt;
}

static int sched_feat_open(struct inode *inode, struct file *filp)
{
	return single_open(filp, sched_feat_show, NULL);
}

static struct file_operations sched_feat_fops = {
	.open		= sched_feat_open,
	.write		= sched_feat_write,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

static __init int sched_init_debug(void)
{
	debugfs_create_file("sched_features", 0644, NULL, NULL,
			&sched_feat_fops);

	return 0;
}
late_initcall(sched_init_debug);

#endif

#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))

/*
 * Number of tasks to iterate in a single balance run.
 * Limited because this is done with IRQs disabled.
 */
const_debug unsigned int sysctl_sched_nr_migrate = 32;

/*
 * ratelimit for updating the group shares.
 * default: 0.25ms
 */
unsigned int sysctl_sched_shares_ratelimit = 250000;

/*
 * Inject some fuzzyness into changing the per-cpu group shares
 * this avoids remote rq-locks at the expense of fairness.
 * default: 4
 */
unsigned int sysctl_sched_shares_thresh = 4;

/*
 * period over which we measure -rt task cpu usage in us.
 * default: 1s
 */
unsigned int sysctl_sched_rt_period = 1000000;

static __read_mostly int scheduler_running;

/*
 * part of the period that we allow rt tasks to run in us.
 * default: 0.95s
 */
int sysctl_sched_rt_runtime = 950000;

static inline u64 global_rt_period(void)
{
	return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
}

static inline u64 global_rt_runtime(void)
{
	if (sysctl_sched_rt_runtime < 0)
		return RUNTIME_INF;

	return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}

#ifndef prepare_arch_switch
# define prepare_arch_switch(next)	do { } while (0)
#endif
#ifndef finish_arch_switch
# define finish_arch_switch(prev)	do { } while (0)
#endif

static inline int task_current(struct rq *rq, struct task_struct *p)
{
	return rq->curr == p;
}

#ifndef __ARCH_WANT_UNLOCKED_CTXSW
static inline int task_running(struct rq *rq, struct task_struct *p)
{
	return task_current(rq, p);
}

static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
}

static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_DEBUG_SPINLOCK
	/* this is a valid case when another task releases the spinlock */
	rq->lock.owner = current;
#endif
	/*
	 * If we are tracking spinlock dependencies then we have to
	 * fix up the runqueue lock - which gets 'carried over' from
	 * prev into current:
	 */
	spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);

	spin_unlock_irq(&rq->lock);
}

#else /* __ARCH_WANT_UNLOCKED_CTXSW */
static inline int task_running(struct rq *rq, struct task_struct *p)
{
#ifdef CONFIG_SMP
	return p->oncpu;
#else
	return task_current(rq, p);
#endif
}

static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
#ifdef CONFIG_SMP
	/*
	 * We can optimise this out completely for !SMP, because the
	 * SMP rebalancing from interrupt is the only thing that cares
	 * here.
	 */
	next->oncpu = 1;
#endif
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
	spin_unlock_irq(&rq->lock);
#else
	spin_unlock(&rq->lock);
#endif
}

static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
{
#ifdef CONFIG_SMP
	/*
	 * After ->oncpu is cleared, the task can be moved to a different CPU.
	 * We must ensure this doesn't happen until the switch is completely
	 * finished.
	 */
	smp_wmb();
	prev->oncpu = 0;
#endif
#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
	local_irq_enable();
#endif
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */

/*
 * __task_rq_lock - lock the runqueue a given task resides on.
 * Must be called interrupts disabled.
 */
static inline struct rq *__task_rq_lock(struct task_struct *p)
	__acquires(rq->lock)
{
	for (;;) {
		struct rq *rq = task_rq(p);
		spin_lock(&rq->lock);
		if (likely(rq == task_rq(p)))
			return rq;
		spin_unlock(&rq->lock);
	}
}

/*
 * task_rq_lock - lock the runqueue a given task resides on and disable
 * interrupts. Note the ordering: we can safely lookup the task_rq without
 * explicitly disabling preemption.
 */
static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
	__acquires(rq->lock)
{
	struct rq *rq;

	for (;;) {
		local_irq_save(*flags);
		rq = task_rq(p);
		spin_lock(&rq->lock);
		if (likely(rq == task_rq(p)))
			return rq;
		spin_unlock_irqrestore(&rq->lock, *flags);
	}
}

void task_rq_unlock_wait(struct task_struct *p)
{
	struct rq *rq = task_rq(p);

	smp_mb(); /* spin-unlock-wait is not a full memory barrier */
	spin_unlock_wait(&rq->lock);
}

static void __task_rq_unlock(struct rq *rq)
	__releases(rq->lock)
{
	spin_unlock(&rq->lock);
}

static inline void task_rq_unlock(struct rq *rq, unsigned long *flags)
	__releases(rq->lock)
{
	spin_unlock_irqrestore(&rq->lock, *flags);
}

/*
 * this_rq_lock - lock this runqueue and disable interrupts.
 */
static struct rq *this_rq_lock(void)
	__acquires(rq->lock)
{
	struct rq *rq;

	local_irq_disable();
	rq = this_rq();
	spin_lock(&rq->lock);

	return rq;
}

#ifdef CONFIG_SCHED_HRTICK
/*
 * Use HR-timers to deliver accurate preemption points.
 *
 * Its all a bit involved since we cannot program an hrt while holding the
 * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a
 * reschedule event.
 *
 * When we get rescheduled we reprogram the hrtick_timer outside of the
 * rq->lock.
 */

/*
 * Use hrtick when:
 *  - enabled by features
 *  - hrtimer is actually high res
 */
static inline int hrtick_enabled(struct rq *rq)
{
	if (!sched_feat(HRTICK))
		return 0;
	if (!cpu_active(cpu_of(rq)))
		return 0;
	return hrtimer_is_hres_active(&rq->hrtick_timer);
}

static void hrtick_clear(struct rq *rq)
{
	if (hrtimer_active(&rq->hrtick_timer))
		hrtimer_cancel(&rq->hrtick_timer);
}

/*
 * High-resolution timer tick.
 * Runs from hardirq context with interrupts disabled.
 */
static enum hrtimer_restart hrtick(struct hrtimer *timer)
{
	struct rq *rq = container_of(timer, struct rq, hrtick_timer);

	WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());

	spin_lock(&rq->lock);
	update_rq_clock(rq);
	rq->curr->sched_class->task_tick(rq, rq->curr, 1);
	spin_unlock(&rq->lock);

	return HRTIMER_NORESTART;
}

#ifdef CONFIG_SMP
/*
 * called from hardirq (IPI) context
 */
static void __hrtick_start(void *arg)
{
	struct rq *rq = arg;

	spin_lock(&rq->lock);
	hrtimer_restart(&rq->hrtick_timer);
	rq->hrtick_csd_pending = 0;
	spin_unlock(&rq->lock);
}

/*
 * Called to set the hrtick timer state.
 *
 * called with rq->lock held and irqs disabled
 */
static void hrtick_start(struct rq *rq, u64 delay)
{
	struct hrtimer *timer = &rq->hrtick_timer;
	ktime_t time = ktime_add_ns(timer->base->get_time(), delay);

	hrtimer_set_expires(timer, time);

	if (rq == this_rq()) {
		hrtimer_restart(timer);
	} else if (!rq->hrtick_csd_pending) {
		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
		rq->hrtick_csd_pending = 1;
	}
}

static int
hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
	int cpu = (int)(long)hcpu;

	switch (action) {
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		hrtick_clear(cpu_rq(cpu));
		return NOTIFY_OK;
	}

	return NOTIFY_DONE;
}

static __init void init_hrtick(void)
{
	hotcpu_notifier(hotplug_hrtick, 0);
}
#else
/*
 * Called to set the hrtick timer state.
 *
 * called with rq->lock held and irqs disabled
 */
static void hrtick_start(struct rq *rq, u64 delay)
{
	__hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0,
			HRTIMER_MODE_REL_PINNED, 0);
}

static inline void init_hrtick(void)
{
}
#endif /* CONFIG_SMP */

static void init_rq_hrtick(struct rq *rq)
{
#ifdef CONFIG_SMP
	rq->hrtick_csd_pending = 0;

	rq->hrtick_csd.flags = 0;
	rq->hrtick_csd.func = __hrtick_start;
	rq->hrtick_csd.info = rq;
#endif

	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
	rq->hrtick_timer.function = hrtick;
}
#else	/* CONFIG_SCHED_HRTICK */
static inline void hrtick_clear(struct rq *rq)
{
}

static inline void init_rq_hrtick(struct rq *rq)
{
}

static inline void init_hrtick(void)
{
}
#endif	/* CONFIG_SCHED_HRTICK */

/*
 * resched_task - mark a task 'to be rescheduled now'.
 *
 * On UP this means the setting of the need_resched flag, on SMP it
 * might also involve a cross-CPU call to trigger the scheduler on
 * the target CPU.
 */
#ifdef CONFIG_SMP

#ifndef tsk_is_polling
#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
#endif

static void resched_task(struct task_struct *p)
{
	int cpu;

	assert_spin_locked(&task_rq(p)->lock);

	if (test_tsk_need_resched(p))
		return;

	set_tsk_need_resched(p);

	cpu = task_cpu(p);
	if (cpu == smp_processor_id())
		return;

	/* NEED_RESCHED must be visible before we test polling */
	smp_mb();
	if (!tsk_is_polling(p))
		smp_send_reschedule(cpu);
}

static void resched_cpu(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long flags;

	if (!spin_trylock_irqsave(&rq->lock, flags))
		return;
	resched_task(cpu_curr(cpu));
	spin_unlock_irqrestore(&rq->lock, flags);
}

#ifdef CONFIG_NO_HZ
/*
 * When add_timer_on() enqueues a timer into the timer wheel of an
 * idle CPU then this timer might expire before the next timer event
 * which is scheduled to wake up that CPU. In case of a completely
 * idle system the next event might even be infinite time into the
 * future. wake_up_idle_cpu() ensures that the CPU is woken up and
 * leaves the inner idle loop so the newly added timer is taken into
 * account when the CPU goes back to idle and evaluates the timer
 * wheel for the next timer event.
 */
void wake_up_idle_cpu(int cpu)
{
	struct rq *rq = cpu_rq(cpu);

	if (cpu == smp_processor_id())
		return;

	/*
	 * This is safe, as this function is called with the timer
	 * wheel base lock of (cpu) held. When the CPU is on the way
	 * to idle and has not yet set rq->curr to idle then it will
	 * be serialized on the timer wheel base lock and take the new
	 * timer into account automatically.
	 */
	if (rq->curr != rq->idle)
		return;

	/*
	 * We can set TIF_RESCHED on the idle task of the other CPU
	 * lockless. The worst case is that the other CPU runs the
	 * idle task through an additional NOOP schedule()
	 */
	set_tsk_need_resched(rq->idle);

	/* NEED_RESCHED must be visible before we test polling */
	smp_mb();
	if (!tsk_is_polling(rq->idle))
		smp_send_reschedule(cpu);
}
#endif /* CONFIG_NO_HZ */

#else /* !CONFIG_SMP */
static void resched_task(struct task_struct *p)
{
	assert_spin_locked(&task_rq(p)->lock);
	set_tsk_need_resched(p);
}
#endif /* CONFIG_SMP */

#if BITS_PER_LONG == 32
# define WMULT_CONST	(~0UL)
#else
# define WMULT_CONST	(1UL << 32)
#endif

#define WMULT_SHIFT	32

/*
 * Shift right and round:
 */
#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y))

/*
 * delta *= weight / lw
 */
static unsigned long
calc_delta_mine(unsigned long delta_exec, unsigned long weight,
		struct load_weight *lw)
{
	u64 tmp;

	if (!lw->inv_weight) {
		if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST))
			lw->inv_weight = 1;
		else
			lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2)
				/ (lw->weight+1);
	}

	tmp = (u64)delta_exec * weight;
	/*
	 * Check whether we'd overflow the 64-bit multiplication:
	 */
	if (unlikely(tmp > WMULT_CONST))
		tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight,
			WMULT_SHIFT/2);
	else
		tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT);

	return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX);
}

static inline void update_load_add(struct load_weight *lw, unsigned long inc)
{
	lw->weight += inc;
	lw->inv_weight = 0;
}

static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
{
	lw->weight -= dec;
	lw->inv_weight = 0;
}

/*
 * To aid in avoiding the subversion of "niceness" due to uneven distribution
 * of tasks with abnormal "nice" values across CPUs the contribution that
 * each task makes to its run queue's load is weighted according to its
 * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a
 * scaled version of the new time slice allocation that they receive on time
 * slice expiry etc.
 */

#define WEIGHT_IDLEPRIO                3
#define WMULT_IDLEPRIO         1431655765

/*
 * Nice levels are multiplicative, with a gentle 10% change for every
 * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
 * nice 1, it will get ~10% less CPU time than another CPU-bound task
 * that remained on nice 0.
 *
 * The "10% effect" is relative and cumulative: from _any_ nice level,
 * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
 * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
 * If a task goes up by ~10% and another task goes down by ~10% then
 * the relative distance between them is ~25%.)
 */
static const int prio_to_weight[40] = {
 /* -20 */     88761,     71755,     56483,     46273,     36291,
 /* -15 */     29154,     23254,     18705,     14949,     11916,
 /* -10 */      9548,      7620,      6100,      4904,      3906,
 /*  -5 */      3121,      2501,      1991,      1586,      1277,
 /*   0 */      1024,       820,       655,       526,       423,
 /*   5 */       335,       272,       215,       172,       137,
 /*  10 */       110,        87,        70,        56,        45,
 /*  15 */        36,        29,        23,        18,        15,
};

/*
 * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated.
 *
 * In cases where the weight does not change often, we can use the
 * precalculated inverse to speed up arithmetics by turning divisions
 * into multiplications:
 */
static const u32 prio_to_wmult[40] = {
 /* -20 */     48388,     59856,     76040,     92818,    118348,
 /* -15 */    147320,    184698,    229616,    287308,    360437,
 /* -10 */    449829,    563644,    704093,    875809,   1099582,
 /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
 /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
 /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
 /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
 /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};

static void activate_task(struct rq *rq, struct task_struct *p, int wakeup);

/*
 * runqueue iterator, to support SMP load-balancing between different
 * scheduling classes, without having to expose their internal data
 * structures to the load-balancing proper:
 */
struct rq_iterator {
	void *arg;
	struct task_struct *(*start)(void *);
	struct task_struct *(*next)(void *);
};

#ifdef CONFIG_SMP
static unsigned long
balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
	      unsigned long max_load_move, struct sched_domain *sd,
	      enum cpu_idle_type idle, int *all_pinned,
	      int *this_best_prio, struct rq_iterator *iterator);

static int
iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
		   struct sched_domain *sd, enum cpu_idle_type idle,
		   struct rq_iterator *iterator);
#endif

/* Time spent by the tasks of the cpu accounting group executing in ... */
enum cpuacct_stat_index {
	CPUACCT_STAT_USER,	/* ... user mode */
	CPUACCT_STAT_SYSTEM,	/* ... kernel mode */

	CPUACCT_STAT_NSTATS,
};

#ifdef CONFIG_CGROUP_CPUACCT
static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
static void cpuacct_update_stats(struct task_struct *tsk,
		enum cpuacct_stat_index idx, cputime_t val);
#else
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
static inline void cpuacct_update_stats(struct task_struct *tsk,
		enum cpuacct_stat_index idx, cputime_t val) {}
#endif

static inline void inc_cpu_load(struct rq *rq, unsigned long load)
{
	update_load_add(&rq->load, load);
}

static inline void dec_cpu_load(struct rq *rq, unsigned long load)
{
	update_load_sub(&rq->load, load);
}

#if (defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)) || defined(CONFIG_RT_GROUP_SCHED)
typedef int (*tg_visitor)(struct task_group *, void *);

/*
 * Iterate the full tree, calling @down when first entering a node and @up when
 * leaving it for the final time.
 */
static int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
{
	struct task_group *parent, *child;
	int ret;

	rcu_read_lock();
	parent = &root_task_group;
down:
	ret = (*down)(parent, data);
	if (ret)
		goto out_unlock;
	list_for_each_entry_rcu(child, &parent->children, siblings) {
		parent = child;
		goto down;

up:
		continue;
	}
	ret = (*up)(parent, data);
	if (ret)
		goto out_unlock;

	child = parent;
	parent = parent->parent;
	if (parent)
		goto up;
out_unlock:
	rcu_read_unlock();

	return ret;
}

static int tg_nop(struct task_group *tg, void *data)
{
	return 0;
}
#endif

#ifdef CONFIG_SMP
static unsigned long source_load(int cpu, int type);
static unsigned long target_load(int cpu, int type);
static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);

static unsigned long cpu_avg_load_per_task(int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long nr_running = ACCESS_ONCE(rq->nr_running);

	if (nr_running)
		rq->avg_load_per_task = rq->load.weight / nr_running;
	else
		rq->avg_load_per_task = 0;

	return rq->avg_load_per_task;
}

#ifdef CONFIG_FAIR_GROUP_SCHED

static void __set_se_shares(struct sched_entity *se, unsigned long shares);

/*
 * Calculate and set the cpu's group shares.
 */
static void
update_group_shares_cpu(struct task_group *tg, int cpu,
			unsigned long sd_shares, unsigned long sd_rq_weight)
{
	unsigned long shares;
	unsigned long rq_weight;

	if (!tg->se[cpu])
		return;

	rq_weight = tg->cfs_rq[cpu]->rq_weight;

	/*
	 *           \Sum shares * rq_weight
	 * shares =  -----------------------
	 *               \Sum rq_weight
	 *
	 */
	shares = (sd_shares * rq_weight) / sd_rq_weight;
	shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);

	if (abs(shares - tg->se[cpu]->load.weight) >
			sysctl_sched_shares_thresh) {
		struct rq *rq = cpu_rq(cpu);
		unsigned long flags;

		spin_lock_irqsave(&rq->lock, flags);
		tg->cfs_rq[cpu]->shares = shares;

		__set_se_shares(tg->se[cpu], shares);
		spin_unlock_irqrestore(&rq->lock, flags);
	}
}

/*
 * Re-compute the task group their per cpu shares over the given domain.
 * This needs to be done in a bottom-up fashion because the rq weight of a
 * parent group depends on the shares of its child groups.
 */
static int tg_shares_up(struct task_group *tg, void *data)
{
	unsigned long weight, rq_weight = 0;
	unsigned long shares = 0;
	struct sched_domain *sd = data;
	int i;

	for_each_cpu(i, sched_domain_span(sd)) {
		/*
		 * If there are currently no tasks on the cpu pretend there
		 * is one of average load so that when a new task gets to
		 * run here it will not get delayed by group starvation.
		 */
		weight = tg->cfs_rq[i]->load.weight;
		if (!weight)
			weight = NICE_0_LOAD;

		tg->cfs_rq[i]->rq_weight = weight;
		rq_weight += weight;
		shares += tg->cfs_rq[i]->shares;
	}

	if ((!shares && rq_weight) || shares > tg->shares)
		shares = tg->shares;

	if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE))
		shares = tg->shares;

	for_each_cpu(i, sched_domain_span(sd))
		update_group_shares_cpu(tg, i, shares, rq_weight);

	return 0;
}

/*
 * Compute the cpu's hierarchical load factor for each task group.
 * This needs to be done in a top-down fashion because the load of a child
 * group is a fraction of its parents load.
 */
static int tg_load_down(struct task_group *tg, void *data)
{
	unsigned long load;
	long cpu = (long)data;

	if (!tg->parent) {
		load = cpu_rq(cpu)->load.weight;
	} else {
		load = tg->parent->cfs_rq[cpu]->h_load;
		load *= tg->cfs_rq[cpu]->shares;
		load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
	}

	tg->cfs_rq[cpu]->h_load = load;

	return 0;
}

static void update_shares(struct sched_domain *sd)
{
	u64 now = cpu_clock(raw_smp_processor_id());
	s64 elapsed = now - sd->last_update;

	if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
		sd->last_update = now;
		walk_tg_tree(tg_nop, tg_shares_up, sd);
	}
}

static void update_shares_locked(struct rq *rq, struct sched_domain *sd)
{
	spin_unlock(&rq->lock);
	update_shares(sd);
	spin_lock(&rq->lock);
}

static void update_h_load(long cpu)
{
	walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
}

#else

static inline void update_shares(struct sched_domain *sd)
{
}

static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd)
{
}

#endif

#ifdef CONFIG_PREEMPT

/*
 * fair double_lock_balance: Safely acquires both rq->locks in a fair
 * way at the expense of forcing extra atomic operations in all
 * invocations.  This assures that the double_lock is acquired using the
 * same underlying policy as the spinlock_t on this architecture, which
 * reduces latency compared to the unfair variant below.  However, it
 * also adds more overhead and therefore may reduce throughput.
 */
static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
	__releases(this_rq->lock)
	__acquires(busiest->lock)
	__acquires(this_rq->lock)
{
	spin_unlock(&this_rq->lock);
	double_rq_lock(this_rq, busiest);

	return 1;
}

#else
/*
 * Unfair double_lock_balance: Optimizes throughput at the expense of
 * latency by eliminating extra atomic operations when the locks are
 * already in proper order on entry.  This favors lower cpu-ids and will
 * grant the double lock to lower cpus over higher ids under contention,
 * regardless of entry order into the function.
 */
static int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
	__releases(this_rq->lock)
	__acquires(busiest->lock)
	__acquires(this_rq->lock)
{
	int ret = 0;

	if (unlikely(!spin_trylock(&busiest->lock))) {
		if (busiest < this_rq) {
			spin_unlock(&this_rq->lock);
			spin_lock(&busiest->lock);
			spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING);
			ret = 1;
		} else
			spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING);
	}
	return ret;
}

#endif /* CONFIG_PREEMPT */

/*
 * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
 */
static int double_lock_balance(struct rq *this_rq, struct rq *busiest)
{
	if (unlikely(!irqs_disabled())) {
		/* printk() doesn't work good under rq->lock */
		spin_unlock(&this_rq->lock);
		BUG_ON(1);
	}

	return _double_lock_balance(this_rq, busiest);
}

static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
	__releases(busiest->lock)
{
	spin_unlock(&busiest->lock);
	lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}
#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares)
{
#ifdef CONFIG_SMP
	cfs_rq->shares = shares;
#endif
}
#endif

static void calc_load_account_active(struct rq *this_rq);

#include "sched_stats.h"
#include "sched_idletask.c"
#include "sched_fair.c"
#include "sched_rt.c"
#ifdef CONFIG_SCHED_DEBUG
# include "sched_debug.c"
#endif

#define sched_class_highest (&rt_sched_class)
#define for_each_class(class) \
   for (class = sched_class_highest; class; class = class->next)

static void inc_nr_running(struct rq *rq)
{
	rq->nr_running++;
}

static void dec_nr_running(struct rq *rq)
{
	rq->nr_running--;
}

static void set_load_weight(struct task_struct *p)
{
	if (task_has_rt_policy(p)) {
		p->se.load.weight = prio_to_weight[0] * 2;
		p->se.load.inv_weight = prio_to_wmult[0] >> 1;
		return;
	}

	/*
	 * SCHED_IDLE tasks get minimal weight:
	 */
	if (p->policy == SCHED_IDLE) {
		p->se.load.weight = WEIGHT_IDLEPRIO;
		p->se.load.inv_weight = WMULT_IDLEPRIO;
		return;
	}

	p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO];
	p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO];
}

static void update_avg(u64 *avg, u64 sample)
{
	s64 diff = sample - *avg;
	*avg += diff >> 3;
}

static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
{
	if (wakeup)
		p->se.start_runtime = p->se.sum_exec_runtime;

	sched_info_queued(p);
	p->sched_class->enqueue_task(rq, p, wakeup);
	p->se.on_rq = 1;
}

static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep)
{
	if (sleep) {
		if (p->se.last_wakeup) {
			update_avg(&p->se.avg_overlap,
				p->se.sum_exec_runtime - p->se.last_wakeup);
			p->se.last_wakeup = 0;
		} else {
			update_avg(&p->se.avg_wakeup,
				sysctl_sched_wakeup_granularity);
		}
	}

	sched_info_dequeued(p);
	p->sched_class->dequeue_task(rq, p, sleep);
	p->se.on_rq = 0;
}

/*
 * __normal_prio - return the priority that is based on the static prio
 */
static inline int __normal_prio(struct task_struct *p)
{
	return p->static_prio;
}

/*
 * Calculate the expected normal priority: i.e. priority
 * without taking RT-inheritance into account. Might be
 * boosted by interactivity modifiers. Changes upon fork,
 * setprio syscalls, and whenever the interactivity
 * estimator recalculates.
 */
static inline int normal_prio(struct task_struct *p)
{
	int prio;

	if (task_has_rt_policy(p))
		prio = MAX_RT_PRIO-1 - p->rt_priority;
	else
		prio = __normal_prio(p);
	return prio;
}

/*
 * Calculate the current priority, i.e. the priority
 * taken into account by the scheduler. This value might
 * be boosted by RT tasks, or might be boosted by
 * interactivity modifiers. Will be RT if the task got
 * RT-boosted. If not then it returns p->normal_prio.
 */
static int effective_prio(struct task_struct *p)
{
	p->normal_prio = normal_prio(p);
	/*
	 * If we are RT tasks or we were boosted to RT priority,
	 * keep the priority unchanged. Otherwise, update priority
	 * to the normal priority:
	 */
	if (!rt_prio(p->prio))
		return p->normal_prio;
	return p->prio;
}

/*
 * activate_task - move a task to the runqueue.
 */
static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
{
	if (task_contributes_to_load(p))
		rq->nr_uninterruptible--;

	enqueue_task(rq, p, wakeup);
	inc_nr_running(rq);
}

/*
 * deactivate_task - remove a task from the runqueue.
 */
static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep)
{
	if (task_contributes_to_load(p))
		rq->nr_uninterruptible++;

	dequeue_task(rq, p, sleep);
	dec_nr_running(rq);
}

/**
 * task_curr - is this task currently executing on a CPU?
 * @p: the task in question.
 */
inline int task_curr(const struct task_struct *p)
{
	return cpu_curr(task_cpu(p)) == p;
}

static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
	set_task_rq(p, cpu);
#ifdef CONFIG_SMP
	/*
	 * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
	 * successfuly executed on another CPU. We must ensure that updates of
	 * per-task data have been completed by this moment.
	 */
	smp_wmb();
	task_thread_info(p)->cpu = cpu;
#endif
}

static inline void check_class_changed(struct rq *rq, struct task_struct *p,
				       const struct sched_class *prev_class,
				       int oldprio, int running)
{
	if (prev_class != p->sched_class) {
		if (prev_class->switched_from)
			prev_class->switched_from(rq, p, running);
		p->sched_class->switched_to(rq, p, running);
	} else
		p->sched_class->prio_changed(rq, p, oldprio, running);
}

#ifdef CONFIG_SMP

/* Used instead of source_load when we know the type == 0 */
static unsigned long weighted_cpuload(const int cpu)
{
	return cpu_rq(cpu)->load.weight;
}

/*
 * Is this task likely cache-hot:
 */
static int
task_hot(struct task_struct *p, u64 now, struct sched_domain *sd)
{
	s64 delta;

	/*
	 * Buddy candidates are cache hot:
	 */
	if (sched_feat(CACHE_HOT_BUDDY) &&
			(&p->se == cfs_rq_of(&p->se)->next ||
			 &p->se == cfs_rq_of(&p->se)->last))
		return 1;

	if (p->sched_class != &fair_sched_class)
		return 0;

	if (sysctl_sched_migration_cost == -1)
		return 1;
	if (sysctl_sched_migration_cost == 0)
		return 0;

	delta = now - p->se.exec_start;

	return delta < (s64)sysctl_sched_migration_cost;
}


void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
	int old_cpu = task_cpu(p);
	struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
	struct cfs_rq *old_cfsrq = task_cfs_rq(p),
		      *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu);
	u64 clock_offset;

	clock_offset = old_rq->clock - new_rq->clock;

	trace_sched_migrate_task(p, new_cpu);

#ifdef CONFIG_SCHEDSTATS
	if (p->se.wait_start)
		p->se.wait_start -= clock_offset;
	if (p->se.sleep_start)
		p->se.sleep_start -= clock_offset;
	if (p->se.block_start)
		p->se.block_start -= clock_offset;
#endif
	if (old_cpu != new_cpu) {
		p->se.nr_migrations++;
		new_rq->nr_migrations_in++;
#ifdef CONFIG_SCHEDSTATS
		if (task_hot(p, old_rq->clock, NULL))
			schedstat_inc(p, se.nr_forced2_migrations);
#endif
		perf_counter_task_migration(p, new_cpu);
	}
	p->se.vruntime -= old_cfsrq->min_vruntime -
					 new_cfsrq->min_vruntime;

	__set_task_cpu(p, new_cpu);
}

struct migration_req {
	struct list_head list;

	struct task_struct *task;
	int dest_cpu;

	struct completion done;
};

/*
 * The task's runqueue lock must be held.
 * Returns true if you have to wait for migration thread.
 */
static int
migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req)
{
	struct rq *rq = task_rq(p);

	/*
	 * If the task is not on a runqueue (and not running), then
	 * it is sufficient to simply update the task's cpu field.
	 */
	if (!p->se.on_rq && !task_running(rq, p)) {
		set_task_cpu(p, dest_cpu);
		return 0;
	}

	init_completion(&req->done);
	req->task = p;
	req->dest_cpu = dest_cpu;
	list_add(&req->list, &rq->migration_queue);

	return 1;
}

/*
 * wait_task_context_switch -	wait for a thread to complete at least one
 *				context switch.
 *
 * @p must not be current.
 */
void wait_task_context_switch(struct task_struct *p)
{
	unsigned long nvcsw, nivcsw, flags;
	int running;
	struct rq *rq;

	nvcsw	= p->nvcsw;
	nivcsw	= p->nivcsw;
	for (;;) {
		/*
		 * The runqueue is assigned before the actual context
		 * switch. We need to take the runqueue lock.
		 *
		 * We could check initially without the lock but it is
		 * very likely that we need to take the lock in every
		 * iteration.
		 */
		rq = task_rq_lock(p, &flags);
		running = task_running(rq, p);
		task_rq_unlock(rq, &flags);

		if (likely(!running))
			break;
		/*
		 * The switch count is incremented before the actual
		 * context switch. We thus wait for two switches to be
		 * sure at least one completed.
		 */
		if ((p->nvcsw - nvcsw) > 1)
			break;
		if ((p->nivcsw - nivcsw) > 1)
			break;

		cpu_relax();
	}
}

/*
 * wait_task_inactive - wait for a thread to unschedule.
 *
 * If @match_state is nonzero, it's the @p->state value just checked and
 * not expected to change.  If it changes, i.e. @p might have woken up,
 * then return zero.  When we succeed in waiting for @p to be off its CPU,
 * we return a positive number (its total switch count).  If a second call
 * a short while later returns the same number, the caller can be sure that
 * @p has remained unscheduled the whole time.
 *
 * The caller must ensure that the task *will* unschedule sometime soon,
 * else this function might spin for a *long* time. This function can't
 * be called with interrupts off, or it may introduce deadlock with
 * smp_call_function() if an IPI is sent by the same process we are
 * waiting to become inactive.
 */
unsigned long wait_task_inactive(struct task_struct *p, long match_state)
{
	unsigned long flags;
	int running, on_rq;
	unsigned long ncsw;
	struct rq *rq;

	for (;;) {
		/*
		 * We do the initial early heuristics without holding
		 * any task-queue locks at all. We'll only try to get
		 * the runqueue lock when things look like they will
		 * work out!
		 */
		rq = task_rq(p);

		/*
		 * If the task is actively running on another CPU
		 * still, just relax and busy-wait without holding
		 * any locks.
		 *
		 * NOTE! Since we don't hold any locks, it's not
		 * even sure that "rq" stays as the right runqueue!
		 * But we don't care, since "task_running()" will
		 * return false if the runqueue has changed and p
		 * is actually now running somewhere else!
		 */
		while (task_running(rq, p)) {
			if (match_state && unlikely(p->state != match_state))
				return 0;
			cpu_relax();
		}

		/*
		 * Ok, time to look more closely! We need the rq
		 * lock now, to be *sure*. If we're wrong, we'll
		 * just go back and repeat.
		 */
		rq = task_rq_lock(p, &flags);
		trace_sched_wait_task(rq, p);
		running = task_running(rq, p);
		on_rq = p->se.on_rq;
		ncsw = 0;
		if (!match_state || p->state == match_state)
			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
		task_rq_unlock(rq, &flags);

		/*
		 * If it changed from the expected state, bail out now.
		 */
		if (unlikely(!ncsw))
			break;

		/*
		 * Was it really running after all now that we
		 * checked with the proper locks actually held?
		 *
		 * Oops. Go back and try again..
		 */
		if (unlikely(running)) {
			cpu_relax();
			continue;
		}

		/*
		 * It's not enough that it's not actively running,
		 * it must be off the runqueue _entirely_, and not
		 * preempted!
		 *
		 * So if it was still runnable (but just not actively
		 * running right now), it's preempted, and we should
		 * yield - it could be a while.
		 */
		if (unlikely(on_rq)) {
			schedule_timeout_uninterruptible(1);
			continue;
		}

		/*
		 * Ahh, all good. It wasn't running, and it wasn't
		 * runnable, which means that it will never become
		 * running in the future either. We're all done!
		 */
		break;
	}

	return ncsw;
}

/***
 * kick_process - kick a running thread to enter/exit the kernel
 * @p: the to-be-kicked thread
 *
 * Cause a process which is running on another CPU to enter
 * kernel-mode, without any delay. (to get signals handled.)
 *
 * NOTE: this function doesnt have to take the runqueue lock,
 * because all it wants to ensure is that the remote task enters
 * the kernel. If the IPI races and the task has been migrated
 * to another CPU then no harm is done and the purpose has been
 * achieved as well.
 */
void kick_process(struct task_struct *p)
{
	int cpu;

	preempt_disable();
	cpu = task_cpu(p);
	if ((cpu != smp_processor_id()) && task_curr(p))
		smp_send_reschedule(cpu);
	preempt_enable();
}
EXPORT_SYMBOL_GPL(kick_process);

/*
 * Return a low guess at the load of a migration-source cpu weighted
 * according to the scheduling class and "nice" value.
 *
 * We want to under-estimate the load of migration sources, to
 * balance conservatively.
 */
static unsigned long source_load(int cpu, int type)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long total = weighted_cpuload(cpu);

	if (type == 0 || !sched_feat(LB_BIAS))
		return total;

	return min(rq->cpu_load[type-1], total);
}

/*
 * Return a high guess at the load of a migration-target cpu weighted
 * according to the scheduling class and "nice" value.
 */
static unsigned long target_load(int cpu, int type)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long total = weighted_cpuload(cpu);

	if (type == 0 || !sched_feat(LB_BIAS))
		return total;

	return max(rq->cpu_load[type-1], total);
}

/*
 * find_idlest_group finds and returns the least busy CPU group within the
 * domain.
 */
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
{
	struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
	unsigned long min_load = ULONG_MAX, this_load = 0;
	int load_idx = sd->forkexec_idx;
	int imbalance = 100 + (sd->imbalance_pct-100)/2;

	do {
		unsigned long load, avg_load;
		int local_group;
		int i;

		/* Skip over this group if it has no CPUs allowed */
		if (!cpumask_intersects(sched_group_cpus(group),
					&p->cpus_allowed))
			continue;

		local_group = cpumask_test_cpu(this_cpu,
					       sched_group_cpus(group));

		/* Tally up the load of all CPUs in the group */
		avg_load = 0;

		for_each_cpu(i, sched_group_cpus(group)) {
			/* Bias balancing toward cpus of our domain */
			if (local_group)
				load = source_load(i, load_idx);
			else
				load = target_load(i, load_idx);

			avg_load += load;
		}

		/* Adjust by relative CPU power of the group */
		avg_load = sg_div_cpu_power(group,
				avg_load * SCHED_LOAD_SCALE);

		if (local_group) {
			this_load = avg_load;
			this = group;
		} else if (avg_load < min_load) {
			min_load = avg_load;
			idlest = group;
		}
	} while (group = group->next, group != sd->groups);

	if (!idlest || 100*this_load < imbalance*min_load)
		return NULL;
	return idlest;
}

/*
 * find_idlest_cpu - find the idlest cpu among the cpus in group.
 */
static int
find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
{
	unsigned long load, min_load = ULONG_MAX;
	int idlest = -1;
	int i;

	/* Traverse only the allowed CPUs */
	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
		load = weighted_cpuload(i);

		if (load < min_load || (load == min_load && i == this_cpu)) {
			min_load = load;
			idlest = i;
		}
	}

	return idlest;
}

/*
 * sched_balance_self: balance the current task (running on cpu) in domains
 * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
 * SD_BALANCE_EXEC.
 *
 * Balance, ie. select the least loaded group.
 *
 * Returns the target CPU number, or the same CPU if no balancing is needed.
 *
 * preempt must be disabled.
 */
static int sched_balance_self(int cpu, int flag)
{
	struct task_struct *t = current;
	struct sched_domain *tmp, *sd = NULL;

	for_each_domain(cpu, tmp) {
		/*
		 * If power savings logic is enabled for a domain, stop there.
		 */
		if (tmp->flags & SD_POWERSAVINGS_BALANCE)
			break;
		if (tmp->flags & flag)
			sd = tmp;
	}

	if (sd)
		update_shares(sd);

	while (sd) {
		struct sched_group *group;
		int new_cpu, weight;

		if (!(sd->flags & flag)) {
			sd = sd->child;
			continue;
		}

		group = find_idlest_group(sd, t, cpu);
		if (!group) {
			sd = sd->child;
			continue;
		}

		new_cpu = find_idlest_cpu(group, t, cpu);
		if (new_cpu == -1 || new_cpu == cpu) {
			/* Now try balancing at a lower domain level of cpu */
			sd = sd->child;
			continue;
		}

		/* Now try balancing at a lower domain level of new_cpu */
		cpu = new_cpu;
		weight = cpumask_weight(sched_domain_span(sd));
		sd = NULL;
		for_each_domain(cpu, tmp) {
			if (weight <= cpumask_weight(sched_domain_span(tmp)))
				break;
			if (tmp->flags & flag)
				sd = tmp;
		}
		/* while loop will break here if sd == NULL */
	}

	return cpu;
}

#endif /* CONFIG_SMP */

/**
 * task_oncpu_function_call - call a function on the cpu on which a task runs
 * @p:		the task to evaluate
 * @func:	the function to be called
 * @info:	the function call argument
 *
 * Calls the function @func when the task is currently running. This might
 * be on the current CPU, which just calls the function directly
 */
void task_oncpu_function_call(struct task_struct *p,
			      void (*func) (void *info), void *info)
{
	int cpu;

	preempt_disable();
	cpu = task_cpu(p);
	if (task_curr(p))
		smp_call_function_single(cpu, func, info, 1);
	preempt_enable();
}

/***
 * try_to_wake_up - wake up a thread
 * @p: the to-be-woken-up thread
 * @state: the mask of task states that can be woken
 * @sync: do a synchronous wakeup?
 *
 * Put it on the run-queue if it's not already there. The "current"
 * thread is always on the run-queue (except when the actual
 * re-schedule is in progress), and as such you're allowed to do
 * the simpler "current->state = TASK_RUNNING" to mark yourself
 * runnable without the overhead of this.
 *
 * returns failure only if the task is already active.
 */
static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync)
{
	int cpu, orig_cpu, this_cpu, success = 0;
	unsigned long flags;
	long old_state;
	struct rq *rq;

	if (!sched_feat(SYNC_WAKEUPS))
		sync = 0;

#ifdef CONFIG_SMP
	if (sched_feat(LB_WAKEUP_UPDATE) && !root_task_group_empty()) {
		struct sched_domain *sd;

		this_cpu = raw_smp_processor_id();
		cpu = task_cpu(p);

		for_each_domain(this_cpu, sd) {
			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
				update_shares(sd);
				break;
			}
		}
	}
#endif

	smp_wmb();
	rq = task_rq_lock(p, &flags);
	update_rq_clock(rq);
	old_state = p->state;
	if (!(old_state & state))
		goto out;

	if (p->se.on_rq)
		goto out_running;

	cpu = task_cpu(p);
	orig_cpu = cpu;
	this_cpu = smp_processor_id();

#ifdef CONFIG_SMP
	if (unlikely(task_running(rq, p)))
		goto out_activate;

	cpu = p->sched_class->select_task_rq(p, sync);
	if (cpu != orig_cpu) {
		set_task_cpu(p, cpu);
		task_rq_unlock(rq, &flags);
		/* might preempt at this point */
		rq = task_rq_lock(p, &flags);
		old_state = p->state;
		if (!(old_state & state))
			goto out;
		if (p->se.on_rq)
			goto out_running;

		this_cpu = smp_processor_id();
		cpu = task_cpu(p);
	}

#ifdef CONFIG_SCHEDSTATS
	schedstat_inc(rq, ttwu_count);
	if (cpu == this_cpu)
		schedstat_inc(rq, ttwu_local);
	else {
		struct sched_domain *sd;
		for_each_domain(this_cpu, sd) {
			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
				schedstat_inc(sd, ttwu_wake_remote);
				break;
			}
		}
	}
#endif /* CONFIG_SCHEDSTATS */

out_activate:
#endif /* CONFIG_SMP */
	schedstat_inc(p, se.nr_wakeups);
	if (sync)
		schedstat_inc(p, se.nr_wakeups_sync);
	if (orig_cpu != cpu)
		schedstat_inc(p, se.nr_wakeups_migrate);
	if (cpu == this_cpu)
		schedstat_inc(p, se.nr_wakeups_local);
	else
		schedstat_inc(p, se.nr_wakeups_remote);
	activate_task(rq, p, 1);
	success = 1;

	/*
	 * Only attribute actual wakeups done by this task.
	 */
	if (!in_interrupt()) {
		struct sched_entity *se = &current->se;
		u64 sample = se->sum_exec_runtime;

		if (se->last_wakeup)
			sample -= se->last_wakeup;
		else
			sample -= se->start_runtime;
		update_avg(&se->avg_wakeup, sample);

		se->last_wakeup = se->sum_exec_runtime;
	}

out_running:
	trace_sched_wakeup(rq, p, success);
	check_preempt_curr(rq, p, sync);

	p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
	if (p->sched_class->task_wake_up)
		p->sched_class->task_wake_up(rq, p);
#endif
out:
	task_rq_unlock(rq, &flags);

	return success;
}

/**
 * wake_up_process - Wake up a specific process
 * @p: The process to be woken up.
 *
 * Attempt to wake up the nominated process and move it to the set of runnable
 * processes.  Returns 1 if the process was woken up, 0 if it was already
 * running.
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */
int wake_up_process(struct task_struct *p)
{
	return try_to_wake_up(p, TASK_ALL, 0);
}
EXPORT_SYMBOL(wake_up_process);

int wake_up_state(struct task_struct *p, unsigned int state)
{
	return try_to_wake_up(p, state, 0);
}

/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 *
 * __sched_fork() is basic setup used by init_idle() too:
 */
static void __sched_fork(struct task_struct *p)
{
	p->se.exec_start		= 0;
	p->se.sum_exec_runtime		= 0;
	p->se.prev_sum_exec_runtime	= 0;
	p->se.nr_migrations		= 0;
	p->se.last_wakeup		= 0;
	p->se.avg_overlap		= 0;
	p->se.start_runtime		= 0;
	p->se.avg_wakeup		= sysctl_sched_wakeup_granularity;

#ifdef CONFIG_SCHEDSTATS
	p->se.wait_start		= 0;
	p->se.sum_sleep_runtime		= 0;
	p->se.sleep_start		= 0;
	p->se.block_start		= 0;
	p->se.sleep_max			= 0;
	p->se.block_max			= 0;
	p->se.exec_max			= 0;
	p->se.slice_max			= 0;
	p->se.wait_max			= 0;
#endif

	INIT_LIST_HEAD(&p->rt.run_list);
	p->se.on_rq = 0;
	INIT_LIST_HEAD(&p->se.group_node);

#ifdef CONFIG_PREEMPT_NOTIFIERS
	INIT_HLIST_HEAD(&p->preempt_notifiers);
#endif

	/*
	 * We mark the process as running here, but have not actually
	 * inserted it onto the runqueue yet. This guarantees that
	 * nobody will actually run it, and a signal or other external
	 * event cannot wake it up and insert it on the runqueue either.
	 */
	p->state = TASK_RUNNING;
}

/*
 * fork()/clone()-time setup:
 */
void sched_fork(struct task_struct *p, int clone_flags)
{
	int cpu = get_cpu();

	__sched_fork(p);

#ifdef CONFIG_SMP
	cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
#endif
	set_task_cpu(p, cpu);

	/*
	 * Make sure we do not leak PI boosting priority to the child:
	 */
	p->prio = current->normal_prio;
	if (!rt_prio(p->prio))
		p->sched_class = &fair_sched_class;

#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
	if (likely(sched_info_on()))
		memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
	p->oncpu = 0;
#endif
#ifdef CONFIG_PREEMPT
	/* Want to start with kernel preemption disabled. */
	task_thread_info(p)->preempt_count = 1;
#endif
	plist_node_init(&p->pushable_tasks, MAX_PRIO);

	put_cpu();
}

/*
 * wake_up_new_task - wake up a newly created task for the first time.
 *
 * This function will do some initial scheduler statistics housekeeping
 * that must be done for every newly created context, then puts the task
 * on the runqueue and wakes it.
 */
void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
{
	unsigned long flags;
	struct rq *rq;

	rq = task_rq_lock(p, &flags);
	BUG_ON(p->state != TASK_RUNNING);
	update_rq_clock(rq);

	p->prio = effective_prio(p);

	if (!p->sched_class->task_new || !current->se.on_rq) {
		activate_task(rq, p, 0);
	} else {
		/*
		 * Let the scheduling class do new task startup
		 * management (if any):
		 */
		p->sched_class->task_new(rq, p);
		inc_nr_running(rq);
	}
	trace_sched_wakeup_new(rq, p, 1);
	check_preempt_curr(rq, p, 0);
#ifdef CONFIG_SMP
	if (p->sched_class->task_wake_up)
		p->sched_class->task_wake_up(rq, p);
#endif
	task_rq_unlock(rq, &flags);
}

#ifdef CONFIG_PREEMPT_NOTIFIERS

/**
 * preempt_notifier_register - tell me when current is being preempted & rescheduled
 * @notifier: notifier struct to register
 */
void preempt_notifier_register(struct preempt_notifier *notifier)
{
	hlist_add_head(&notifier->link, &current->preempt_notifiers);
}
EXPORT_SYMBOL_GPL(preempt_notifier_register);

/**
 * preempt_notifier_unregister - no longer interested in preemption notifications
 * @notifier: notifier struct to unregister
 *
 * This is safe to call from within a preemption notifier.
 */
void preempt_notifier_unregister(struct preempt_notifier *notifier)
{
	hlist_del(&notifier->link);
}
EXPORT_SYMBOL_GPL(preempt_notifier_unregister);

static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
	struct preempt_notifier *notifier;
	struct hlist_node *node;

	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
		notifier->ops->sched_in(notifier, raw_smp_processor_id());
}

static void
fire_sched_out_preempt_notifiers(struct task_struct *curr,
				 struct task_struct *next)
{
	struct preempt_notifier *notifier;
	struct hlist_node *node;

	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
		notifier->ops->sched_out(notifier, next);
}

#else /* !CONFIG_PREEMPT_NOTIFIERS */

static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
{
}

static void
fire_sched_out_preempt_notifiers(struct task_struct *curr,
				 struct task_struct *next)
{
}

#endif /* CONFIG_PREEMPT_NOTIFIERS */

/**
 * prepare_task_switch - prepare to switch tasks
 * @rq: the runqueue preparing to switch
 * @prev: the current task that is being switched out
 * @next: the task we are going to switch to.
 *
 * This is called with the rq lock held and interrupts off. It must
 * be paired with a subsequent finish_task_switch after the context
 * switch.
 *
 * prepare_task_switch sets up locking and calls architecture specific
 * hooks.
 */
static inline void
prepare_task_switch(struct rq *rq, struct task_struct *prev,
		    struct task_struct *next)
{
	fire_sched_out_preempt_notifiers(prev, next);
	prepare_lock_switch(rq, next);
	prepare_arch_switch(next);
}

/**
 * finish_task_switch - clean up after a task-switch
 * @rq: runqueue associated with task-switch
 * @prev: the thread we just switched away from.
 *
 * finish_task_switch must be called after the context switch, paired
 * with a prepare_task_switch call before the context switch.
 * finish_task_switch will reconcile locking set up by prepare_task_switch,
 * and do any other architecture-specific cleanup actions.
 *
 * Note that we may have delayed dropping an mm in context_switch(). If
 * so, we finish that here outside of the runqueue lock. (Doing it
 * with the lock held can cause deadlocks; see schedule() for
 * details.)
 */
static void finish_task_switch(struct rq *rq, struct task_struct *prev)
	__releases(rq->lock)
{
	struct mm_struct *mm = rq->prev_mm;
	long prev_state;
#ifdef CONFIG_SMP
	int post_schedule = 0;

	if (current->sched_class->needs_post_schedule)
		post_schedule = current->sched_class->needs_post_schedule(rq);
#endif

	rq->prev_mm = NULL;

	/*
	 * A task struct has one reference for the use as "current".
	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
	 * schedule one last time. The schedule call will never return, and
	 * the scheduled task must drop that reference.
	 * The test for TASK_DEAD must occur while the runqueue locks are
	 * still held, otherwise prev could be scheduled on another cpu, die
	 * there before we look at prev->state, and then the reference would
	 * be dropped twice.
	 *		Manfred Spraul <manfred@colorfullife.com>
	 */
	prev_state = prev->state;
	finish_arch_switch(prev);
	perf_counter_task_sched_in(current, cpu_of(rq));
	finish_lock_switch(rq, prev);
#ifdef CONFIG_SMP
	if (post_schedule)
		current->sched_class->post_schedule(rq);
#endif

	fire_sched_in_preempt_notifiers(current);
	if (mm)
		mmdrop(mm);
	if (unlikely(prev_state == TASK_DEAD)) {
		/*
		 * Remove function-return probe instances associated with this
		 * task and put them back on the free list.
		 */
		kprobe_flush_task(prev);
		put_task_struct(prev);
	}
}

/**
 * schedule_tail - first thing a freshly forked thread must call.
 * @prev: the thread we just switched away from.
 */
asmlinkage void schedule_tail(struct task_struct *prev)
	__releases(rq->lock)
{
	struct rq *rq = this_rq();

	finish_task_switch(rq, prev);
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
	/* In this case, finish_task_switch does not reenable preemption */
	preempt_enable();
#endif
	if (current->set_child_tid)
		put_user(task_pid_vnr(current), current->set_child_tid);
}

/*
 * context_switch - switch to the new MM and the new
 * thread's register state.
 */
static inline void
context_switch(struct rq *rq, struct task_struct *prev,
	       struct task_struct *next)
{
	struct mm_struct *mm, *oldmm;

	prepare_task_switch(rq, prev, next);
	trace_sched_switch(rq, prev, next);
	mm = next->mm;
	oldmm = prev->active_mm;
	/*
	 * For paravirt, this is coupled with an exit in switch_to to
	 * combine the page table reload and the switch backend into
	 * one hypercall.
	 */
	arch_start_context_switch(prev);

	if (unlikely(!mm)) {
		next->active_mm = oldmm;
		atomic_inc(&oldmm->mm_count);
		enter_lazy_tlb(oldmm, next);
	} else
		switch_mm(oldmm, mm, next);

	if (unlikely(!prev->mm)) {
		prev->active_mm = NULL;
		rq->prev_mm = oldmm;
	}
	/*
	 * Since the runqueue lock will be released by the next
	 * task (which is an invalid locking op but in the case
	 * of the scheduler it's an obvious special-case), so we
	 * do an early lockdep release here:
	 */
#ifndef __ARCH_WANT_UNLOCKED_CTXSW
	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
#endif

	/* Here we just switch the register state and the stack. */
	switch_to(prev, next, prev);

	barrier();
	/*
	 * this_rq must be evaluated again because prev may have moved
	 * CPUs since it called schedule(), thus the 'rq' on its stack
	 * frame will be invalid.
	 */
	finish_task_switch(this_rq(), prev);
}

/*
 * nr_running, nr_uninterruptible and nr_context_switches:
 *
 * externally visible scheduler statistics: current number of runnable
 * threads, current number of uninterruptible-sleeping threads, total
 * number of context switches performed since bootup.
 */
unsigned long nr_running(void)
{
	unsigned long i, sum = 0;

	for_each_online_cpu(i)
		sum += cpu_rq(i)->nr_running;

	return sum;
}

unsigned long nr_uninterruptible(void)
{
	unsigned long i, sum = 0;

	for_each_possible_cpu(i)
		sum += cpu_rq(i)->nr_uninterruptible;

	/*
	 * Since we read the counters lockless, it might be slightly
	 * inaccurate. Do not allow it to go below zero though:
	 */
	if (unlikely((long)sum < 0))
		sum = 0;

	return sum;
}

unsigned long long nr_context_switches(void)
{
	int i;
	unsigned long long sum = 0;

	for_each_possible_cpu(i)
		sum += cpu_rq(i)->nr_switches;

	return sum;
}

unsigned long nr_iowait(void)
{
	unsigned long i, sum = 0;

	for_each_possible_cpu(i)
		sum += atomic_read(&cpu_rq(i)->nr_iowait);

	return sum;
}

/* Variables and functions for calc_load */
static atomic_long_t calc_load_tasks;
static unsigned long calc_load_update;
unsigned long avenrun[3];
EXPORT_SYMBOL(avenrun);

/**
 * get_avenrun - get the load average array
 * @loads:	pointer to dest load array
 * @offset:	offset to add
 * @shift:	shift count to shift the result left
 *
 * These values are estimates at best, so no need for locking.
 */
void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
{
	loads[0] = (avenrun[0] + offset) << shift;
	loads[1] = (avenrun[1] + offset) << shift;
	loads[2] = (avenrun[2] + offset) << shift;
}

static unsigned long
calc_load(unsigned long load, unsigned long exp, unsigned long active)
{
	load *= exp;
	load += active * (FIXED_1 - exp);
	return load >> FSHIFT;
}

/*
 * calc_load - update the avenrun load estimates 10 ticks after the
 * CPUs have updated calc_load_tasks.
 */
void calc_global_load(void)
{
	unsigned long upd = calc_load_update + 10;
	long active;

	if (time_before(jiffies, upd))
		return;

	active = atomic_long_read(&calc_load_tasks);
	active = active > 0 ? active * FIXED_1 : 0;

	avenrun[0] = calc_load(avenrun[0], EXP_1, active);
	avenrun[1] = calc_load(avenrun[1], EXP_5, active);
	avenrun[2] = calc_load(avenrun[2], EXP_15, active);

	calc_load_update += LOAD_FREQ;
}

/*
 * Either called from update_cpu_load() or from a cpu going idle
 */
static void calc_load_account_active(struct rq *this_rq)
{
	long nr_active, delta;

	nr_active = this_rq->nr_running;
	nr_active += (long) this_rq->nr_uninterruptible;

	if (nr_active != this_rq->calc_load_active) {
		delta = nr_active - this_rq->calc_load_active;
		this_rq->calc_load_active = nr_active;
		atomic_long_add(delta, &calc_load_tasks);
	}
}

/*
 * Externally visible per-cpu scheduler statistics:
 * cpu_nr_migrations(cpu) - number of migrations into that cpu
 */
u64 cpu_nr_migrations(int cpu)
{
	return cpu_rq(cpu)->nr_migrations_in;
}

/*
 * Update rq->cpu_load[] statistics. This function is usually called every
 * scheduler tick (TICK_NSEC).
 */
static void update_cpu_load(struct rq *this_rq)
{
	unsigned long this_load = this_rq->load.weight;
	int i, scale;

	this_rq->nr_load_updates++;

	/* Update our load: */
	for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
		unsigned long old_load, new_load;

		/* scale is effectively 1 << i now, and >> i divides by scale */

		old_load = this_rq->cpu_load[i];
		new_load = this_load;
		/*
		 * Round up the averaging division if load is increasing. This
		 * prevents us from getting stuck on 9 if the load is 10, for
		 * example.
		 */
		if (new_load > old_load)
			new_load += scale-1;
		this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i;
	}

	if (time_after_eq(jiffies, this_rq->calc_load_update)) {
		this_rq->calc_load_update += LOAD_FREQ;
		calc_load_account_active(this_rq);
	}
}

#ifdef CONFIG_SMP

/*
 * double_rq_lock - safely lock two runqueues
 *
 * Note this does not disable interrupts like task_rq_lock,
 * you need to do so manually before calling.
 */
static void double_rq_lock(struct rq *rq1, struct rq *rq2)
	__acquires(rq1->lock)
	__acquires(rq2->lock)
{
	BUG_ON(!irqs_disabled());
	if (rq1 == rq2) {
		spin_lock(&rq1->lock);
		__acquire(rq2->lock);	/* Fake it out ;) */
	} else {
		if (rq1 < rq2) {
			spin_lock(&rq1->lock);
			spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
		} else {
			spin_lock(&rq2->lock);
			spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
		}
	}
	update_rq_clock(rq1);
	update_rq_clock(rq2);
}

/*
 * double_rq_unlock - safely unlock two runqueues
 *
 * Note this does not restore interrupts like task_rq_unlock,
 * you need to do so manually after calling.
 */
static void double_rq_unlock(struct rq *rq1, struct rq *rq2)
	__releases(rq1->lock)
	__releases(rq2->lock)
{
	spin_unlock(&rq1->lock);
	if (rq1 != rq2)
		spin_unlock(&rq2->lock);
	else
		__release(rq2->lock);
}

/*
 * If dest_cpu is allowed for this process, migrate the task to it.
 * This is accomplished by forcing the cpu_allowed mask to only
 * allow dest_cpu, which will force the cpu onto dest_cpu. Then
 * the cpu_allowed mask is restored.
 */
static void sched_migrate_task(struct task_struct *p, int dest_cpu)
{
	struct migration_req req;
	unsigned long flags;
	struct rq *rq;

	rq = task_rq_lock(p, &flags);
	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)
	    || unlikely(!cpu_active(dest_cpu)))
		goto out;

	/* force the process onto the specified CPU */
	if (migrate_task(p, dest_cpu, &req)) {
		/* Need to wait for migration thread (might exit: take ref). */
		struct task_struct *mt = rq->migration_thread;

		get_task_struct(mt);
		task_rq_unlock(rq, &flags);
		wake_up_process(mt);
		put_task_struct(mt);
		wait_for_completion(&req.done);

		return;
	}
out:
	task_rq_unlock(rq, &flags);
}

/*
 * sched_exec - execve() is a valuable balancing opportunity, because at
 * this point the task has the smallest effective memory and cache footprint.
 */
void sched_exec(void)
{
	int new_cpu, this_cpu = get_cpu();
	new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
	put_cpu();
	if (new_cpu != this_cpu)
		sched_migrate_task(current, new_cpu);
}

/*
 * pull_task - move a task from a remote runqueue to the local runqueue.
 * Both runqueues must be locked.
 */
static void pull_task(struct rq *src_rq, struct task_struct *p,
		      struct rq *this_rq, int this_cpu)
{
	deactivate_task(src_rq, p, 0);
	set_task_cpu(p, this_cpu);
	activate_task(this_rq, p, 0);
	/*
	 * Note that idle threads have a prio of MAX_PRIO, for this test
	 * to be always true for them.
	 */
	check_preempt_curr(this_rq, p, 0);
}

/*
 * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
 */
static
int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu,
		     struct sched_domain *sd, enum cpu_idle_type idle,
		     int *all_pinned)
{
	int tsk_cache_hot = 0;
	/*
	 * We do not migrate tasks that are:
	 * 1) running (obviously), or
	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
	 * 3) are cache-hot on their current CPU.
	 */
	if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) {
		schedstat_inc(p, se.nr_failed_migrations_affine);
		return 0;
	}
	*all_pinned = 0;

	if (task_running(rq, p)) {
		schedstat_inc(p, se.nr_failed_migrations_running);
		return 0;
	}

	/*
	 * Aggressive migration if:
	 * 1) task is cache cold, or
	 * 2) too many balance attempts have failed.
	 */

	tsk_cache_hot = task_hot(p, rq->clock, sd);
	if (!tsk_cache_hot ||
		sd->nr_balance_failed > sd->cache_nice_tries) {
#ifdef CONFIG_SCHEDSTATS
		if (tsk_cache_hot) {
			schedstat_inc(sd, lb_hot_gained[idle]);
			schedstat_inc(p, se.nr_forced_migrations);
		}
#endif
		return 1;
	}

	if (tsk_cache_hot) {
		schedstat_inc(p, se.nr_failed_migrations_hot);
		return 0;
	}
	return 1;
}

static unsigned long
balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
	      unsigned long max_load_move, struct sched_domain *sd,
	      enum cpu_idle_type idle, int *all_pinned,
	      int *this_best_prio, struct rq_iterator *iterator)
{
	int loops = 0, pulled = 0, pinned = 0;
	struct task_struct *p;
	long rem_load_move = max_load_move;

	if (max_load_move == 0)
		goto out;

	pinned = 1;

	/*
	 * Start the load-balancing iterator:
	 */
	p = iterator->start(iterator->arg);
next:
	if (!p || loops++ > sysctl_sched_nr_migrate)
		goto out;

	if ((p->se.load.weight >> 1) > rem_load_move ||
	    !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
		p = iterator->next(iterator->arg);
		goto next;
	}

	pull_task(busiest, p, this_rq, this_cpu);
	pulled++;
	rem_load_move -= p->se.load.weight;

#ifdef CONFIG_PREEMPT
	/*
	 * NEWIDLE balancing is a source of latency, so preemptible kernels
	 * will stop after the first task is pulled to minimize the critical
	 * section.
	 */
	if (idle == CPU_NEWLY_IDLE)
		goto out;
#endif

	/*
	 * We only want to steal up to the prescribed amount of weighted load.
	 */
	if (rem_load_move > 0) {
		if (p->prio < *this_best_prio)
			*this_best_prio = p->prio;
		p = iterator->next(iterator->arg);
		goto next;
	}
out:
	/*
	 * Right now, this is one of only two places pull_task() is called,
	 * so we can safely collect pull_task() stats here rather than
	 * inside pull_task().
	 */
	schedstat_add(sd, lb_gained[idle], pulled);

	if (all_pinned)
		*all_pinned = pinned;

	return max_load_move - rem_load_move;
}

/*
 * move_tasks tries to move up to max_load_move weighted load from busiest to
 * this_rq, as part of a balancing operation within domain "sd".
 * Returns 1 if successful and 0 otherwise.
 *
 * Called with both runqueues locked.
 */
static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
		      unsigned long max_load_move,
		      struct sched_domain *sd, enum cpu_idle_type idle,
		      int *all_pinned)
{
	const struct sched_class *class = sched_class_highest;
	unsigned long total_load_moved = 0;
	int this_best_prio = this_rq->curr->prio;

	do {
		total_load_moved +=
			class->load_balance(this_rq, this_cpu, busiest,
				max_load_move - total_load_moved,
				sd, idle, all_pinned, &this_best_prio);
		class = class->next;

#ifdef CONFIG_PREEMPT
		/*
		 * NEWIDLE balancing is a source of latency, so preemptible
		 * kernels will stop after the first task is pulled to minimize
		 * the critical section.
		 */
		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
			break;
#endif
	} while (class && max_load_move > total_load_moved);

	return total_load_moved > 0;
}

static int
iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
		   struct sched_domain *sd, enum cpu_idle_type idle,
		   struct rq_iterator *iterator)
{
	struct task_struct *p = iterator->start(iterator->arg);
	int pinned = 0;

	while (p) {
		if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
			pull_task(busiest, p, this_rq, this_cpu);
			/*
			 * Right now, this is only the second place pull_task()
			 * is called, so we can safely collect pull_task()
			 * stats here rather than inside pull_task().
			 */
			schedstat_inc(sd, lb_gained[idle]);

			return 1;
		}
		p = iterator->next(iterator->arg);
	}

	return 0;
}

/*
 * move_one_task tries to move exactly one task from busiest to this_rq, as
 * part of active balancing operations within "domain".
 * Returns 1 if successful and 0 otherwise.
 *
 * Called with both runqueues locked.
 */
static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
			 struct sched_domain *sd, enum cpu_idle_type idle)
{
	const struct sched_class *class;

	for (class = sched_class_highest; class; class = class->next)
		if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle))
			return 1;

	return 0;
}
/********** Helpers for find_busiest_group ************************/
/*
 * sd_lb_stats - Structure to store the statistics of a sched_domain
 * 		during load balancing.
 */
struct sd_lb_stats {
	struct sched_group *busiest; /* Busiest group in this sd */
	struct sched_group *this;  /* Local group in this sd */
	unsigned long total_load;  /* Total load of all groups in sd */
	unsigned long total_pwr;   /*	Total power of all groups in sd */
	unsigned long avg_load;	   /* Average load across all groups in sd */

	/** Statistics of this group */
	unsigned long this_load;
	unsigned long this_load_per_task;
	unsigned long this_nr_running;

	/* Statistics of the busiest group */
	unsigned long max_load;
	unsigned long busiest_load_per_task;
	unsigned long busiest_nr_running;

	int group_imb; /* Is there imbalance in this sd */
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
	int power_savings_balance; /* Is powersave balance needed for this sd */
	struct sched_group *group_min; /* Least loaded group in sd */
	struct sched_group *group_leader; /* Group which relieves group_min */
	unsigned long min_load_per_task; /* load_per_task in group_min */
	unsigned long leader_nr_running; /* Nr running of group_leader */
	unsigned long min_nr_running; /* Nr running of group_min */
#endif
};

/*
 * sg_lb_stats - stats of a sched_group required for load_balancing
 */
struct sg_lb_stats {
	unsigned long avg_load; /*Avg load across the CPUs of the group */
	unsigned long group_load; /* Total load over the CPUs of the group */
	unsigned long sum_nr_running; /* Nr tasks running in the group */
	unsigned long sum_weighted_load; /* Weighted load of group's tasks */
	unsigned long group_capacity;
	int group_imb; /* Is there an imbalance in the group ? */
};

/**
 * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
 * @group: The group whose first cpu is to be returned.
 */
static inline unsigned int group_first_cpu(struct sched_group *group)
{
	return cpumask_first(sched_group_cpus(group));
}

/**
 * get_sd_load_idx - Obtain the load index for a given sched domain.
 * @sd: The sched_domain whose load_idx is to be obtained.
 * @idle: The Idle status of the CPU for whose sd load_icx is obtained.
 */
static inline int get_sd_load_idx(struct sched_domain *sd,
					enum cpu_idle_type idle)
{
	int load_idx;

	switch (idle) {
	case CPU_NOT_IDLE:
		load_idx = sd->busy_idx;
		break;

	case CPU_NEWLY_IDLE:
		load_idx = sd->newidle_idx;
		break;
	default:
		load_idx = sd->idle_idx;
		break;
	}

	return load_idx;
}


#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
/**
 * init_sd_power_savings_stats - Initialize power savings statistics for
 * the given sched_domain, during load balancing.
 *
 * @sd: Sched domain whose power-savings statistics are to be initialized.
 * @sds: Variable containing the statistics for sd.
 * @idle: Idle status of the CPU at which we're performing load-balancing.
 */
static inline void init_sd_power_savings_stats(struct sched_domain *sd,
	struct sd_lb_stats *sds, enum cpu_idle_type idle)
{
	/*
	 * Busy processors will not participate in power savings
	 * balance.
	 */
	if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
		sds->power_savings_balance = 0;
	else {
		sds->power_savings_balance = 1;
		sds->min_nr_running = ULONG_MAX;
		sds->leader_nr_running = 0;
	}
}

/**
 * update_sd_power_savings_stats - Update the power saving stats for a
 * sched_domain while performing load balancing.
 *
 * @group: sched_group belonging to the sched_domain under consideration.
 * @sds: Variable containing the statistics of the sched_domain
 * @local_group: Does group contain the CPU for which we're performing
 * 		load balancing ?
 * @sgs: Variable containing the statistics of the group.
 */
static inline void update_sd_power_savings_stats(struct sched_group *group,
	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
{

	if (!sds->power_savings_balance)
		return;

	/*
	 * If the local group is idle or completely loaded
	 * no need to do power savings balance at this domain
	 */
	if (local_group && (sds->this_nr_running >= sgs->group_capacity ||
				!sds->this_nr_running))
		sds->power_savings_balance = 0;

	/*
	 * If a group is already running at full capacity or idle,
	 * don't include that group in power savings calculations
	 */
	if (!sds->power_savings_balance ||
		sgs->sum_nr_running >= sgs->group_capacity ||
		!sgs->sum_nr_running)
		return;

	/*
	 * Calculate the group which has the least non-idle load.
	 * This is the group from where we need to pick up the load
	 * for saving power
	 */
	if ((sgs->sum_nr_running < sds->min_nr_running) ||
	    (sgs->sum_nr_running == sds->min_nr_running &&
	     group_first_cpu(group) > group_first_cpu(sds->group_min))) {
		sds->group_min = group;
		sds->min_nr_running = sgs->sum_nr_running;
		sds->min_load_per_task = sgs->sum_weighted_load /
						sgs->sum_nr_running;
	}

	/*
	 * Calculate the group which is almost near its
	 * capacity but still has some space to pick up some load
	 * from other group and save more power
	 */
	if (sgs->sum_nr_running > sgs->group_capacity - 1)
		return;

	if (sgs->sum_nr_running > sds->leader_nr_running ||
	    (sgs->sum_nr_running == sds->leader_nr_running &&
	     group_first_cpu(group) < group_first_cpu(sds->group_leader))) {
		sds->group_leader = group;
		sds->leader_nr_running = sgs->sum_nr_running;
	}
}

/**
 * check_power_save_busiest_group - see if there is potential for some power-savings balance
 * @sds: Variable containing the statistics of the sched_domain
 *	under consideration.
 * @this_cpu: Cpu at which we're currently performing load-balancing.
 * @imbalance: Variable to store the imbalance.
 *
 * Description:
 * Check if we have potential to perform some power-savings balance.
 * If yes, set the busiest group to be the least loaded group in the
 * sched_domain, so that it's CPUs can be put to idle.
 *
 * Returns 1 if there is potential to perform power-savings balance.
 * Else returns 0.
 */
static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
					int this_cpu, unsigned long *imbalance)
{
	if (!sds->power_savings_balance)
		return 0;

	if (sds->this != sds->group_leader ||
			sds->group_leader == sds->group_min)
		return 0;

	*imbalance = sds->min_load_per_task;
	sds->busiest = sds->group_min;

	if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) {
		cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu =
			group_first_cpu(sds->group_leader);
	}

	return 1;

}
#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
static inline void init_sd_power_savings_stats(struct sched_domain *sd,
	struct sd_lb_stats *sds, enum cpu_idle_type idle)
{
	return;
}

static inline void update_sd_power_savings_stats(struct sched_group *group,
	struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs)
{
	return;
}

static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
					int this_cpu, unsigned long *imbalance)
{
	return 0;
}
#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */


/**
 * update_sg_lb_stats - Update sched_group's statistics for load balancing.
 * @group: sched_group whose statistics are to be updated.
 * @this_cpu: Cpu for which load balance is currently performed.
 * @idle: Idle status of this_cpu
 * @load_idx: Load index of sched_domain of this_cpu for load calc.
 * @sd_idle: Idle status of the sched_domain containing group.
 * @local_group: Does group contain this_cpu.
 * @cpus: Set of cpus considered for load balancing.
 * @balance: Should we balance.
 * @sgs: variable to hold the statistics for this group.
 */
static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
			enum cpu_idle_type idle, int load_idx, int *sd_idle,
			int local_group, const struct cpumask *cpus,
			int *balance, struct sg_lb_stats *sgs)
{
	unsigned long load, max_cpu_load, min_cpu_load;
	int i;
	unsigned int balance_cpu = -1, first_idle_cpu = 0;
	unsigned long sum_avg_load_per_task;
	unsigned long avg_load_per_task;

	if (local_group)
		balance_cpu = group_first_cpu(group);

	/* Tally up the load of all CPUs in the group */
	sum_avg_load_per_task = avg_load_per_task = 0;
	max_cpu_load = 0;
	min_cpu_load = ~0UL;

	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
		struct rq *rq = cpu_rq(i);

		if (*sd_idle && rq->nr_running)
			*sd_idle = 0;

		/* Bias balancing toward cpus of our domain */
		if (local_group) {
			if (idle_cpu(i) && !first_idle_cpu) {
				first_idle_cpu = 1;
				balance_cpu = i;
			}

			load = target_load(i, load_idx);
		} else {
			load = source_load(i, load_idx);
			if (load > max_cpu_load)
				max_cpu_load = load;
			if (min_cpu_load > load)
				min_cpu_load = load;
		}

		sgs->group_load += load;
		sgs->sum_nr_running += rq->nr_running;
		sgs->sum_weighted_load += weighted_cpuload(i);

		sum_avg_load_per_task += cpu_avg_load_per_task(i);
	}

	/*
	 * First idle cpu or the first cpu(busiest) in this sched group
	 * is eligible for doing load balancing at this and above
	 * domains. In the newly idle case, we will allow all the cpu's
	 * to do the newly idle load balance.
	 */
	if (idle != CPU_NEWLY_IDLE && local_group &&
	    balance_cpu != this_cpu && balance) {
		*balance = 0;
		return;
	}

	/* Adjust by relative CPU power of the group */
	sgs->avg_load = sg_div_cpu_power(group,
			sgs->group_load * SCHED_LOAD_SCALE);


	/*
	 * Consider the group unbalanced when the imbalance is larger
	 * than the average weight of two tasks.
	 *
	 * APZ: with cgroup the avg task weight can vary wildly and
	 *      might not be a suitable number - should we keep a
	 *      normalized nr_running number somewhere that negates
	 *      the hierarchy?
	 */
	avg_load_per_task = sg_div_cpu_power(group,
			sum_avg_load_per_task * SCHED_LOAD_SCALE);

	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
		sgs->group_imb = 1;

	sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;

}

/**
 * update_sd_lb_stats - Update sched_group's statistics for load balancing.
 * @sd: sched_domain whose statistics are to be updated.
 * @this_cpu: Cpu for which load balance is currently performed.
 * @idle: Idle status of this_cpu
 * @sd_idle: Idle status of the sched_domain containing group.
 * @cpus: Set of cpus considered for load balancing.
 * @balance: Should we balance.
 * @sds: variable to hold the statistics for this sched_domain.
 */
static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
			enum cpu_idle_type idle, int *sd_idle,
			const struct cpumask *cpus, int *balance,
			struct sd_lb_stats *sds)
{
	struct sched_group *group = sd->groups;
	struct sg_lb_stats sgs;
	int load_idx;

	init_sd_power_savings_stats(sd, sds, idle);
	load_idx = get_sd_load_idx(sd, idle);

	do {
		int local_group;

		local_group = cpumask_test_cpu(this_cpu,
					       sched_group_cpus(group));
		memset(&sgs, 0, sizeof(sgs));
		update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
				local_group, cpus, balance, &sgs);

		if (local_group && balance && !(*balance))
			return;

		sds->total_load += sgs.group_load;
		sds->total_pwr += group->__cpu_power;

		if (local_group) {
			sds->this_load = sgs.avg_load;
			sds->this = group;
			sds->this_nr_running = sgs.sum_nr_running;
			sds->this_load_per_task = sgs.sum_weighted_load;
		} else if (sgs.avg_load > sds->max_load &&
			   (sgs.sum_nr_running > sgs.group_capacity ||
				sgs.group_imb)) {
			sds->max_load = sgs.avg_load;
			sds->busiest = group;
			sds->busiest_nr_running = sgs.sum_nr_running;
			sds->busiest_load_per_task = sgs.sum_weighted_load;
			sds->group_imb = sgs.group_imb;
		}

		update_sd_power_savings_stats(group, sds, local_group, &sgs);
		group = group->next;
	} while (group != sd->groups);

}

/**
 * fix_small_imbalance - Calculate the minor imbalance that exists
 *			amongst the groups of a sched_domain, during
 *			load balancing.
 * @sds: Statistics of the sched_domain whose imbalance is to be calculated.
 * @this_cpu: The cpu at whose sched_domain we're performing load-balance.
 * @imbalance: Variable to store the imbalance.
 */
static inline void fix_small_imbalance(struct sd_lb_stats *sds,
				int this_cpu, unsigned long *imbalance)
{
	unsigned long tmp, pwr_now = 0, pwr_move = 0;
	unsigned int imbn = 2;

	if (sds->this_nr_running) {
		sds->this_load_per_task /= sds->this_nr_running;
		if (sds->busiest_load_per_task >
				sds->this_load_per_task)
			imbn = 1;
	} else
		sds->this_load_per_task =
			cpu_avg_load_per_task(this_cpu);

	if (sds->max_load - sds->this_load + sds->busiest_load_per_task >=
			sds->busiest_load_per_task * imbn) {
		*imbalance = sds->busiest_load_per_task;
		return;
	}

	/*
	 * OK, we don't have enough imbalance to justify moving tasks,
	 * however we may be able to increase total CPU power used by
	 * moving them.
	 */

	pwr_now += sds->busiest->__cpu_power *
			min(sds->busiest_load_per_task, sds->max_load);
	pwr_now += sds->this->__cpu_power *
			min(sds->this_load_per_task, sds->this_load);
	pwr_now /= SCHED_LOAD_SCALE;

	/* Amount of load we'd subtract */
	tmp = sg_div_cpu_power(sds->busiest,
			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
	if (sds->max_load > tmp)
		pwr_move += sds->busiest->__cpu_power *
			min(sds->busiest_load_per_task, sds->max_load - tmp);

	/* Amount of load we'd add */
	if (sds->max_load * sds->busiest->__cpu_power <
		sds->busiest_load_per_task * SCHED_LOAD_SCALE)
		tmp = sg_div_cpu_power(sds->this,
			sds->max_load * sds->busiest->__cpu_power);
	else
		tmp = sg_div_cpu_power(sds->this,
			sds->busiest_load_per_task * SCHED_LOAD_SCALE);
	pwr_move += sds->this->__cpu_power *
			min(sds->this_load_per_task, sds->this_load + tmp);
	pwr_move /= SCHED_LOAD_SCALE;

	/* Move if we gain throughput */
	if (pwr_move > pwr_now)
		*imbalance = sds->busiest_load_per_task;
}

/**
 * calculate_imbalance - Calculate the amount of imbalance present within the
 *			 groups of a given sched_domain during load balance.
 * @sds: statistics of the sched_domain whose imbalance is to be calculated.
 * @this_cpu: Cpu for which currently load balance is being performed.
 * @imbalance: The variable to store the imbalance.
 */
static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
		unsigned long *imbalance)
{
	unsigned long max_pull;
	/*
	 * In the presence of smp nice balancing, certain scenarios can have
	 * max load less than avg load(as we skip the groups at or below
	 * its cpu_power, while calculating max_load..)
	 */
	if (sds->max_load < sds->avg_load) {
		*imbalance = 0;
		return fix_small_imbalance(sds, this_cpu, imbalance);
	}

	/* Don't want to pull so many tasks that a group would go idle */
	max_pull = min(sds->max_load - sds->avg_load,
			sds->max_load - sds->busiest_load_per_task);

	/* How much load to actually move to equalise the imbalance */
	*imbalance = min(max_pull * sds->busiest->__cpu_power,
		(sds->avg_load - sds->this_load) * sds->this->__cpu_power)
			/ SCHED_LOAD_SCALE;

	/*
	 * if *imbalance is less than the average load per runnable task
	 * there is no gaurantee that any tasks will be moved so we'll have
	 * a think about bumping its value to force at least one task to be
	 * moved
	 */
	if (*imbalance < sds->busiest_load_per_task)
		return fix_small_imbalance(sds, this_cpu, imbalance);

}
/******* find_busiest_group() helpers end here *********************/

/**
 * find_busiest_group - Returns the busiest group within the sched_domain
 * if there is an imbalance. If there isn't an imbalance, and
 * the user has opted for power-savings, it returns a group whose
 * CPUs can be put to idle by rebalancing those tasks elsewhere, if
 * such a group exists.
 *
 * Also calculates the amount of weighted load which should be moved
 * to restore balance.
 *
 * @sd: The sched_domain whose busiest group is to be returned.
 * @this_cpu: The cpu for which load balancing is currently being performed.
 * @imbalance: Variable which stores amount of weighted load which should
 *		be moved to restore balance/put a group to idle.
 * @idle: The idle status of this_cpu.
 * @sd_idle: The idleness of sd
 * @cpus: The set of CPUs under consideration for load-balancing.
 * @balance: Pointer to a variable indicating if this_cpu
 *	is the appropriate cpu to perform load balancing at this_level.
 *
 * Returns:	- the busiest group if imbalance exists.
 *		- If no imbalance and user has opted for power-savings balance,
 *		   return the least loaded group whose CPUs can be
 *		   put to idle by rebalancing its tasks onto our group.
 */
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
		   unsigned long *imbalance, enum cpu_idle_type idle,
		   int *sd_idle, const struct cpumask *cpus, int *balance)
{
	struct sd_lb_stats sds;

	memset(&sds, 0, sizeof(sds));

	/*
	 * Compute the various statistics relavent for load balancing at
	 * this level.
	 */
	update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus,
					balance, &sds);

	/* Cases where imbalance does not exist from POV of this_cpu */
	/* 1) this_cpu is not the appropriate cpu to perform load balancing
	 *    at this level.
	 * 2) There is no busy sibling group to pull from.
	 * 3) This group is the busiest group.
	 * 4) This group is more busy than the avg busieness at this
	 *    sched_domain.
	 * 5) The imbalance is within the specified limit.
	 * 6) Any rebalance would lead to ping-pong
	 */
	if (balance && !(*balance))
		goto ret;

	if (!sds.busiest || sds.busiest_nr_running == 0)
		goto out_balanced;

	if (sds.this_load >= sds.max_load)
		goto out_balanced;

	sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;

	if (sds.this_load >= sds.avg_load)
		goto out_balanced;

	if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
		goto out_balanced;

	sds.busiest_load_per_task /= sds.busiest_nr_running;
	if (sds.group_imb)
		sds.busiest_load_per_task =
			min(sds.busiest_load_per_task, sds.avg_load);

	/*
	 * We're trying to get all the cpus to the average_load, so we don't
	 * want to push ourselves above the average load, nor do we wish to
	 * reduce the max loaded cpu below the average load, as either of these
	 * actions would just result in more rebalancing later, and ping-pong
	 * tasks around. Thus we look for the minimum possible imbalance.
	 * Negative imbalances (*we* are more loaded than anyone else) will
	 * be counted as no imbalance for these purposes -- we can't fix that
	 * by pulling tasks to us. Be careful of negative numbers as they'll
	 * appear as very large values with unsigned longs.
	 */
	if (sds.max_load <= sds.busiest_load_per_task)
		goto out_balanced;

	/* Looks like there is an imbalance. Compute it */
	calculate_imbalance(&sds, this_cpu, imbalance);
	return sds.busiest;

out_balanced:
	/*
	 * There is no obvious imbalance. But check if we can do some balancing
	 * to save power.
	 */
	if (check_power_save_busiest_group(&sds, this_cpu, imbalance))
		return sds.busiest;
ret:
	*imbalance = 0;
	return NULL;
}

/*
 * find_busiest_queue - find the busiest runqueue among the cpus in group.
 */
static struct rq *
find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
		   unsigned long imbalance, const struct cpumask *cpus)
{
	struct rq *busiest = NULL, *rq;
	unsigned long max_load = 0;
	int i;

	for_each_cpu(i, sched_group_cpus(group)) {
		unsigned long wl;

		if (!cpumask_test_cpu(i, cpus))
			continue;

		rq = cpu_rq(i);
		wl = weighted_cpuload(i);

		if (rq->nr_running == 1 && wl > imbalance)
			continue;

		if (wl > max_load) {
			max_load = wl;
			busiest = rq;
		}
	}

	return busiest;
}

/*
 * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
 * so long as it is large enough.
 */
#define MAX_PINNED_INTERVAL	512

/* Working cpumask for load_balance and load_balance_newidle. */
static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);

/*
 * Check this_cpu to ensure it is balanced within domain. Attempt to move
 * tasks if there is an imbalance.
 */
static int load_balance(int this_cpu, struct rq *this_rq,
			struct sched_domain *sd, enum cpu_idle_type idle,
			int *balance)
{
	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
	struct sched_group *group;
	unsigned long imbalance;
	struct rq *busiest;
	unsigned long flags;
	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);

	cpumask_setall(cpus);

	/*
	 * When power savings policy is enabled for the parent domain, idle
	 * sibling can pick up load irrespective of busy siblings. In this case,
	 * let the state of idle sibling percolate up as CPU_IDLE, instead of
	 * portraying it as CPU_NOT_IDLE.
	 */
	if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER &&
	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
		sd_idle = 1;

	schedstat_inc(sd, lb_count[idle]);

redo:
	update_shares(sd);
	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
				   cpus, balance);

	if (*balance == 0)
		goto out_balanced;

	if (!group) {
		schedstat_inc(sd, lb_nobusyg[idle]);
		goto out_balanced;
	}

	busiest = find_busiest_queue(group, idle, imbalance, cpus);
	if (!busiest) {
		schedstat_inc(sd, lb_nobusyq[idle]);
		goto out_balanced;
	}

	BUG_ON(busiest == this_rq);

	schedstat_add(sd, lb_imbalance[idle], imbalance);

	ld_moved = 0;
	if (busiest->nr_running > 1) {
		/*
		 * Attempt to move tasks. If find_busiest_group has found
		 * an imbalance but busiest->nr_running <= 1, the group is
		 * still unbalanced. ld_moved simply stays zero, so it is
		 * correctly treated as an imbalance.
		 */
		local_irq_save(flags);
		double_rq_lock(this_rq, busiest);
		ld_moved = move_tasks(this_rq, this_cpu, busiest,
				      imbalance, sd, idle, &all_pinned);
		double_rq_unlock(this_rq, busiest);
		local_irq_restore(flags);

		/*
		 * some other cpu did the load balance for us.
		 */
		if (ld_moved && this_cpu != smp_processor_id())
			resched_cpu(this_cpu);

		/* All tasks on this runqueue were pinned by CPU affinity */
		if (unlikely(all_pinned)) {
			cpumask_clear_cpu(cpu_of(busiest), cpus);
			if (!cpumask_empty(cpus))
				goto redo;
			goto out_balanced;
		}
	}

	if (!ld_moved) {
		schedstat_inc(sd, lb_failed[idle]);
		sd->nr_balance_failed++;

		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {

			spin_lock_irqsave(&busiest->lock, flags);

			/* don't kick the migration_thread, if the curr
			 * task on busiest cpu can't be moved to this_cpu
			 */
			if (!cpumask_test_cpu(this_cpu,
					      &busiest->curr->cpus_allowed)) {
				spin_unlock_irqrestore(&busiest->lock, flags);
				all_pinned = 1;
				goto out_one_pinned;
			}

			if (!busiest->active_balance) {
				busiest->active_balance = 1;
				busiest->push_cpu = this_cpu;
				active_balance = 1;
			}
			spin_unlock_irqrestore(&busiest->lock, flags);
			if (active_balance)
				wake_up_process(busiest->migration_thread);

			/*
			 * We've kicked active balancing, reset the failure
			 * counter.
			 */
			sd->nr_balance_failed = sd->cache_nice_tries+1;
		}
	} else
		sd->nr_balance_failed = 0;

	if (likely(!active_balance)) {
		/* We were unbalanced, so reset the balancing interval */
		sd->balance_interval = sd->min_interval;
	} else {
		/*
		 * If we've begun active balancing, start to back off. This
		 * case may not be covered by the all_pinned logic if there
		 * is only 1 task on the busy runqueue (because we don't call
		 * move_tasks).
		 */
		if (sd->balance_interval < sd->max_interval)
			sd->balance_interval *= 2;
	}

	if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
		ld_moved = -1;

	goto out;

out_balanced:
	schedstat_inc(sd, lb_balanced[idle]);

	sd->nr_balance_failed = 0;

out_one_pinned:
	/* tune up the balancing interval */
	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
			(sd->balance_interval < sd->max_interval))
		sd->balance_interval *= 2;

	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
		ld_moved = -1;
	else
		ld_moved = 0;
out:
	if (ld_moved)
		update_shares(sd);
	return ld_moved;
}

/*
 * Check this_cpu to ensure it is balanced within domain. Attempt to move
 * tasks if there is an imbalance.
 *
 * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE).
 * this_rq is locked.
 */
static int
load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
{
	struct sched_group *group;
	struct rq *busiest = NULL;
	unsigned long imbalance;
	int ld_moved = 0;
	int sd_idle = 0;
	int all_pinned = 0;
	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);

	cpumask_setall(cpus);

	/*
	 * When power savings policy is enabled for the parent domain, idle
	 * sibling can pick up load irrespective of busy siblings. In this case,
	 * let the state of idle sibling percolate up as IDLE, instead of
	 * portraying it as CPU_NOT_IDLE.
	 */
	if (sd->flags & SD_SHARE_CPUPOWER &&
	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
		sd_idle = 1;

	schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]);
redo:
	update_shares_locked(this_rq, sd);
	group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
				   &sd_idle, cpus, NULL);
	if (!group) {
		schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]);
		goto out_balanced;
	}

	busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus);
	if (!busiest) {
		schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]);
		goto out_balanced;
	}

	BUG_ON(busiest == this_rq);

	schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance);

	ld_moved = 0;
	if (busiest->nr_running > 1) {
		/* Attempt to move tasks */
		double_lock_balance(this_rq, busiest);
		/* this_rq->clock is already updated */
		update_rq_clock(busiest);
		ld_moved = move_tasks(this_rq, this_cpu, busiest,
					imbalance, sd, CPU_NEWLY_IDLE,
					&all_pinned);
		double_unlock_balance(this_rq, busiest);

		if (unlikely(all_pinned)) {
			cpumask_clear_cpu(cpu_of(busiest), cpus);
			if (!cpumask_empty(cpus))
				goto redo;
		}
	}

	if (!ld_moved) {
		int active_balance = 0;

		schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]);
		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
		    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
			return -1;

		if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP)
			return -1;

		if (sd->nr_balance_failed++ < 2)
			return -1;

		/*
		 * The only task running in a non-idle cpu can be moved to this
		 * cpu in an attempt to completely freeup the other CPU
		 * package. The same method used to move task in load_balance()
		 * have been extended for load_balance_newidle() to speedup
		 * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2)
		 *
		 * The package power saving logic comes from
		 * find_busiest_group().  If there are no imbalance, then
		 * f_b_g() will return NULL.  However when sched_mc={1,2} then
		 * f_b_g() will select a group from which a running task may be
		 * pulled to this cpu in order to make the other package idle.
		 * If there is no opportunity to make a package idle and if
		 * there are no imbalance, then f_b_g() will return NULL and no
		 * action will be taken in load_balance_newidle().
		 *
		 * Under normal task pull operation due to imbalance, there
		 * will be more than one task in the source run queue and
		 * move_tasks() will succeed.  ld_moved will be true and this
		 * active balance code will not be triggered.
		 */

		/* Lock busiest in correct order while this_rq is held */
		double_lock_balance(this_rq, busiest);

		/*
		 * don't kick the migration_thread, if the curr
		 * task on busiest cpu can't be moved to this_cpu
		 */
		if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
			double_unlock_balance(this_rq, busiest);
			all_pinned = 1;
			return ld_moved;
		}

		if (!busiest->active_balance) {
			busiest->active_balance = 1;
			busiest->push_cpu = this_cpu;
			active_balance = 1;
		}

		double_unlock_balance(this_rq, busiest);
		/*
		 * Should not call ttwu while holding a rq->lock
		 */
		spin_unlock(&this_rq->lock);
		if (active_balance)
			wake_up_process(busiest->migration_thread);
		spin_lock(&this_rq->lock);

	} else
		sd->nr_balance_failed = 0;

	update_shares_locked(this_rq, sd);
	return ld_moved;

out_balanced:
	schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]);
	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER &&
	    !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE))
		return -1;
	sd->nr_balance_failed = 0;

	return 0;
}

/*
 * idle_balance is called by schedule() if this_cpu is about to become
 * idle. Attempts to pull tasks from other CPUs.
 */
static void idle_balance(int this_cpu, struct rq *this_rq)
{
	struct sched_domain *sd;
	int pulled_task = 0;
	unsigned long next_balance = jiffies + HZ;

	for_each_domain(this_cpu, sd) {
		unsigned long interval;

		if (!(sd->flags & SD_LOAD_BALANCE))
			continue;

		if (sd->flags & SD_BALANCE_NEWIDLE)
			/* If we've pulled tasks over stop searching: */
			pulled_task = load_balance_newidle(this_cpu, this_rq,
							   sd);

		interval = msecs_to_jiffies(sd->balance_interval);
		if (time_after(next_balance, sd->last_balance + interval))
			next_balance = sd->last_balance + interval;
		if (pulled_task)
			break;
	}
	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
		/*
		 * We are going idle. next_balance may be set based on
		 * a busy processor. So reset next_balance.
		 */
		this_rq->next_balance = next_balance;
	}
}

/*
 * active_load_balance is run by migration threads. It pushes running tasks
 * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
 * running on each physical CPU where possible, and avoids physical /
 * logical imbalances.
 *
 * Called with busiest_rq locked.
 */
static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
{
	int target_cpu = busiest_rq->push_cpu;
	struct sched_domain *sd;
	struct rq *target_rq;

	/* Is there any task to move? */
	if (busiest_rq->nr_running <= 1)
		return;

	target_rq = cpu_rq(target_cpu);

	/*
	 * This condition is "impossible", if it occurs
	 * we need to fix it. Originally reported by
	 * Bjorn Helgaas on a 128-cpu setup.
	 */
	BUG_ON(busiest_rq == target_rq);

	/* move a task from busiest_rq to target_rq */
	double_lock_balance(busiest_rq, target_rq);
	update_rq_clock(busiest_rq);
	update_rq_clock(target_rq);

	/* Search for an sd spanning us and the target CPU. */
	for_each_domain(target_cpu, sd) {
		if ((sd->flags & SD_LOAD_BALANCE) &&
		    cpumask_test_cpu(busiest_cpu, sched_domain_span(sd)))
				break;
	}

	if (likely(sd)) {
		schedstat_inc(sd, alb_count);

		if (move_one_task(target_rq, target_cpu, busiest_rq,
				  sd, CPU_IDLE))
			schedstat_inc(sd, alb_pushed);
		else
			schedstat_inc(sd, alb_failed);
	}
	double_unlock_balance(busiest_rq, target_rq);
}

#ifdef CONFIG_NO_HZ
static struct {
	atomic_t load_balancer;
	cpumask_var_t cpu_mask;
	cpumask_var_t ilb_grp_nohz_mask;
} nohz ____cacheline_aligned = {
	.load_balancer = ATOMIC_INIT(-1),
};

int get_nohz_load_balancer(void)
{
	return atomic_read(&nohz.load_balancer);
}

#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
/**
 * lowest_flag_domain - Return lowest sched_domain containing flag.
 * @cpu:	The cpu whose lowest level of sched domain is to
 *		be returned.
 * @flag:	The flag to check for the lowest sched_domain
 *		for the given cpu.
 *
 * Returns the lowest sched_domain of a cpu which contains the given flag.
 */
static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
{
	struct sched_domain *sd;

	for_each_domain(cpu, sd)
		if (sd && (sd->flags & flag))
			break;

	return sd;
}

/**
 * for_each_flag_domain - Iterates over sched_domains containing the flag.
 * @cpu:	The cpu whose domains we're iterating over.
 * @sd:		variable holding the value of the power_savings_sd
 *		for cpu.
 * @flag:	The flag to filter the sched_domains to be iterated.
 *
 * Iterates over all the scheduler domains for a given cpu that has the 'flag'
 * set, starting from the lowest sched_domain to the highest.
 */
#define for_each_flag_domain(cpu, sd, flag) \
	for (sd = lowest_flag_domain(cpu, flag); \
		(sd && (sd->flags & flag)); sd = sd->parent)

/**
 * is_semi_idle_group - Checks if the given sched_group is semi-idle.
 * @ilb_group:	group to be checked for semi-idleness
 *
 * Returns:	1 if the group is semi-idle. 0 otherwise.
 *
 * We define a sched_group to be semi idle if it has atleast one idle-CPU
 * and atleast one non-idle CPU. This helper function checks if the given
 * sched_group is semi-idle or not.
 */
static inline int is_semi_idle_group(struct sched_group *ilb_group)
{
	cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
					sched_group_cpus(ilb_group));

	/*
	 * A sched_group is semi-idle when it has atleast one busy cpu
	 * and atleast one idle cpu.
	 */
	if (cpumask_empty(nohz.ilb_grp_nohz_mask))
		return 0;

	if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
		return 0;

	return 1;
}
/**
 * find_new_ilb - Finds the optimum idle load balancer for nomination.
 * @cpu:	The cpu which is nominating a new idle_load_balancer.
 *
 * Returns:	Returns the id of the idle load balancer if it exists,
 *		Else, returns >= nr_cpu_ids.
 *
 * This algorithm picks the idle load balancer such that it belongs to a
 * semi-idle powersavings sched_domain. The idea is to try and avoid
 * completely idle packages/cores just for the purpose of idle load balancing
 * when there are other idle cpu's which are better suited for that job.
 */
static int find_new_ilb(int cpu)
{
	struct sched_domain *sd;
	struct sched_group *ilb_group;

	/*
	 * Have idle load balancer selection from semi-idle packages only
	 * when power-aware load balancing is enabled
	 */
	if (!(sched_smt_power_savings || sched_mc_power_savings))
		goto out_done;

	/*
	 * Optimize for the case when we have no idle CPUs or only one
	 * idle CPU. Don't walk the sched_domain hierarchy in such cases
	 */
	if (cpumask_weight(nohz.cpu_mask) < 2)
		goto out_done;

	for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
		ilb_group = sd->groups;

		do {
			if (is_semi_idle_group(ilb_group))
				return cpumask_first(nohz.ilb_grp_nohz_mask);

			ilb_group = ilb_group->next;

		} while (ilb_group != sd->groups);
	}

out_done:
	return cpumask_first(nohz.cpu_mask);
}
#else /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
static inline int find_new_ilb(int call_cpu)
{
	return cpumask_first(nohz.cpu_mask);
}
#endif

/*
 * This routine will try to nominate the ilb (idle load balancing)
 * owner among the cpus whose ticks are stopped. ilb owner will do the idle
 * load balancing on behalf of all those cpus. If all the cpus in the system
 * go into this tickless mode, then there will be no ilb owner (as there is
 * no need for one) and all the cpus will sleep till the next wakeup event
 * arrives...
 *
 * For the ilb owner, tick is not stopped. And this tick will be used
 * for idle load balancing. ilb owner will still be part of
 * nohz.cpu_mask..
 *
 * While stopping the tick, this cpu will become the ilb owner if there
 * is no other owner. And will be the owner till that cpu becomes busy
 * or if all cpus in the system stop their ticks at which point
 * there is no need for ilb owner.
 *
 * When the ilb owner becomes busy, it nominates another owner, during the
 * next busy scheduler_tick()
 */
int select_nohz_load_balancer(int stop_tick)
{
	int cpu = smp_processor_id();

	if (stop_tick) {
		cpu_rq(cpu)->in_nohz_recently = 1;

		if (!cpu_active(cpu)) {
			if (atomic_read(&nohz.load_balancer) != cpu)
				return 0;

			/*
			 * If we are going offline and still the leader,
			 * give up!
			 */
			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
				BUG();

			return 0;
		}

		cpumask_set_cpu(cpu, nohz.cpu_mask);

		/* time for ilb owner also to sleep */
		if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
			if (atomic_read(&nohz.load_balancer) == cpu)
				atomic_set(&nohz.load_balancer, -1);
			return 0;
		}

		if (atomic_read(&nohz.load_balancer) == -1) {
			/* make me the ilb owner */
			if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1)
				return 1;
		} else if (atomic_read(&nohz.load_balancer) == cpu) {
			int new_ilb;

			if (!(sched_smt_power_savings ||
						sched_mc_power_savings))
				return 1;
			/*
			 * Check to see if there is a more power-efficient
			 * ilb.
			 */
			new_ilb = find_new_ilb(cpu);
			if (new_ilb < nr_cpu_ids && new_ilb != cpu) {
				atomic_set(&nohz.load_balancer, -1);
				resched_cpu(new_ilb);
				return 0;
			}
			return 1;
		}
	} else {
		if (!cpumask_test_cpu(cpu, nohz.cpu_mask))
			return 0;

		cpumask_clear_cpu(cpu, nohz.cpu_mask);

		if (atomic_read(&nohz.load_balancer) == cpu)
			if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
				BUG();
	}
	return 0;
}
#endif

static DEFINE_SPINLOCK(balancing);

/*
 * It checks each scheduling domain to see if it is due to be balanced,
 * and initiates a balancing operation if so.
 *
 * Balancing parameters are set up in arch_init_sched_domains.
 */
static void rebalance_domains(int cpu, enum cpu_idle_type idle)
{
	int balance = 1;
	struct rq *rq = cpu_rq(cpu);
	unsigned long interval;
	struct sched_domain *sd;
	/* Earliest time when we have to do rebalance again */
	unsigned long next_balance = jiffies + 60*HZ;
	int update_next_balance = 0;
	int need_serialize;

	for_each_domain(cpu, sd) {
		if (!(sd->flags & SD_LOAD_BALANCE))
			continue;

		interval = sd->balance_interval;
		if (idle != CPU_IDLE)
			interval *= sd->busy_factor;

		/* scale ms to jiffies */
		interval = msecs_to_jiffies(interval);
		if (unlikely(!interval))
			interval = 1;
		if (interval > HZ*NR_CPUS/10)
			interval = HZ*NR_CPUS/10;

		need_serialize = sd->flags & SD_SERIALIZE;

		if (need_serialize) {
			if (!spin_trylock(&balancing))
				goto out;
		}

		if (time_after_eq(jiffies, sd->last_balance + interval)) {
			if (load_balance(cpu, rq, sd, idle, &balance)) {
				/*
				 * We've pulled tasks over so either we're no
				 * longer idle, or one of our SMT siblings is
				 * not idle.
				 */
				idle = CPU_NOT_IDLE;
			}
			sd->last_balance = jiffies;
		}
		if (need_serialize)
			spin_unlock(&balancing);
out:
		if (time_after(next_balance, sd->last_balance + interval)) {
			next_balance = sd->last_balance + interval;
			update_next_balance = 1;
		}

		/*
		 * Stop the load balance at this level. There is another
		 * CPU in our sched group which is doing load balancing more
		 * actively.
		 */
		if (!balance)
			break;
	}

	/*
	 * next_balance will be updated only when there is a need.
	 * When the cpu is attached to null domain for ex, it will not be
	 * updated.
	 */
	if (likely(update_next_balance))
		rq->next_balance = next_balance;
}

/*
 * run_rebalance_domains is triggered when needed from the scheduler tick.
 * In CONFIG_NO_HZ case, the idle load balance owner will do the
 * rebalancing for all the cpus for whom scheduler ticks are stopped.
 */
static void run_rebalance_domains(struct softirq_action *h)
{
	int this_cpu = smp_processor_id();
	struct rq *this_rq = cpu_rq(this_cpu);
	enum cpu_idle_type idle = this_rq->idle_at_tick ?
						CPU_IDLE : CPU_NOT_IDLE;

	rebalance_domains(this_cpu, idle);

#ifdef CONFIG_NO_HZ
	/*
	 * If this cpu is the owner for idle load balancing, then do the
	 * balancing on behalf of the other idle cpus whose ticks are
	 * stopped.
	 */
	if (this_rq->idle_at_tick &&
	    atomic_read(&nohz.load_balancer) == this_cpu) {
		struct rq *rq;
		int balance_cpu;

		for_each_cpu(balance_cpu, nohz.cpu_mask) {
			if (balance_cpu == this_cpu)
				continue;

			/*
			 * If this cpu gets work to do, stop the load balancing
			 * work being done for other cpus. Next load
			 * balancing owner will pick it up.
			 */
			if (need_resched())
				break;

			rebalance_domains(balance_cpu, CPU_IDLE);

			rq = cpu_rq(balance_cpu);
			if (time_after(this_rq->next_balance, rq->next_balance))
				this_rq->next_balance = rq->next_balance;
		}
	}
#endif
}

static inline int on_null_domain(int cpu)
{
	return !rcu_dereference(cpu_rq(cpu)->sd);
}

/*
 * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing.
 *
 * In case of CONFIG_NO_HZ, this is the place where we nominate a new
 * idle load balancing owner or decide to stop the periodic load balancing,
 * if the whole system is idle.
 */
static inline void trigger_load_balance(struct rq *rq, int cpu)
{
#ifdef CONFIG_NO_HZ
	/*
	 * If we were in the nohz mode recently and busy at the current
	 * scheduler tick, then check if we need to nominate new idle
	 * load balancer.
	 */
	if (rq->in_nohz_recently && !rq->idle_at_tick) {
		rq->in_nohz_recently = 0;

		if (atomic_read(&nohz.load_balancer) == cpu) {
			cpumask_clear_cpu(cpu, nohz.cpu_mask);
			atomic_set(&nohz.load_balancer, -1);
		}

		if (atomic_read(&nohz.load_balancer) == -1) {
			int ilb = find_new_ilb(cpu);

			if (ilb < nr_cpu_ids)
				resched_cpu(ilb);
		}
	}

	/*
	 * If this cpu is idle and doing idle load balancing for all the
	 * cpus with ticks stopped, is it time for that to stop?
	 */
	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu &&
	    cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
		resched_cpu(cpu);
		return;
	}

	/*
	 * If this cpu is idle and the idle load balancing is done by
	 * someone else, then no need raise the SCHED_SOFTIRQ
	 */
	if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu &&
	    cpumask_test_cpu(cpu, nohz.cpu_mask))
		return;
#endif
	/* Don't need to rebalance while attached to NULL domain */
	if (time_after_eq(jiffies, rq->next_balance) &&
	    likely(!on_null_domain(cpu)))
		raise_softirq(SCHED_SOFTIRQ);
}

#else	/* CONFIG_SMP */

/*
 * on UP we do not need to balance between CPUs:
 */
static inline void idle_balance(int cpu, struct rq *rq)
{
}

#endif

DEFINE_PER_CPU(struct kernel_stat, kstat);

EXPORT_PER_CPU_SYMBOL(kstat);

/*
 * Return any ns on the sched_clock that have not yet been accounted in
 * @p in case that task is currently running.
 *
 * Called with task_rq_lock() held on @rq.
 */
static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
{
	u64 ns = 0;

	if (task_current(rq, p)) {
		update_rq_clock(rq);
		ns = rq->clock - p->se.exec_start;
		if ((s64)ns < 0)
			ns = 0;
	}

	return ns;
}

unsigned long long task_delta_exec(struct task_struct *p)
{
	unsigned long flags;
	struct rq *rq;
	u64 ns = 0;

	rq = task_rq_lock(p, &flags);
	ns = do_task_delta_exec(p, rq);
	task_rq_unlock(rq, &flags);

	return ns;
}

/*
 * Return accounted runtime for the task.
 * In case the task is currently running, return the runtime plus current's
 * pending runtime that have not been accounted yet.
 */
unsigned long long task_sched_runtime(struct task_struct *p)
{
	unsigned long flags;
	struct rq *rq;
	u64 ns = 0;

	rq = task_rq_lock(p, &flags);
	ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
	task_rq_unlock(rq, &flags);

	return ns;
}

/*
 * Return sum_exec_runtime for the thread group.
 * In case the task is currently running, return the sum plus current's
 * pending runtime that have not been accounted yet.
 *
 * Note that the thread group might have other running tasks as well,
 * so the return value not includes other pending runtime that other
 * running tasks might have.
 */
unsigned long long thread_group_sched_runtime(struct task_struct *p)
{
	struct task_cputime totals;
	unsigned long flags;
	struct rq *rq;
	u64 ns;

	rq = task_rq_lock(p, &flags);
	thread_group_cputime(p, &totals);
	ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
	task_rq_unlock(rq, &flags);

	return ns;
}

/*
 * Account user cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @cputime: the cpu time spent in user space since the last update
 * @cputime_scaled: cputime scaled by cpu frequency
 */
void account_user_time(struct task_struct *p, cputime_t cputime,
		       cputime_t cputime_scaled)
{
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
	cputime64_t tmp;

	/* Add user time to process. */
	p->utime = cputime_add(p->utime, cputime);
	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
	account_group_user_time(p, cputime);

	/* Add user time to cpustat. */
	tmp = cputime_to_cputime64(cputime);
	if (TASK_NICE(p) > 0)
		cpustat->nice = cputime64_add(cpustat->nice, tmp);
	else
		cpustat->user = cputime64_add(cpustat->user, tmp);

	cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime);
	/* Account for user time used */
	acct_update_integrals(p);
}

/*
 * Account guest cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @cputime: the cpu time spent in virtual machine since the last update
 * @cputime_scaled: cputime scaled by cpu frequency
 */
static void account_guest_time(struct task_struct *p, cputime_t cputime,
			       cputime_t cputime_scaled)
{
	cputime64_t tmp;
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;

	tmp = cputime_to_cputime64(cputime);

	/* Add guest time to process. */
	p->utime = cputime_add(p->utime, cputime);
	p->utimescaled = cputime_add(p->utimescaled, cputime_scaled);
	account_group_user_time(p, cputime);
	p->gtime = cputime_add(p->gtime, cputime);

	/* Add guest time to cpustat. */
	cpustat->user = cputime64_add(cpustat->user, tmp);
	cpustat->guest = cputime64_add(cpustat->guest, tmp);
}

/*
 * Account system cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @hardirq_offset: the offset to subtract from hardirq_count()
 * @cputime: the cpu time spent in kernel space since the last update
 * @cputime_scaled: cputime scaled by cpu frequency
 */
void account_system_time(struct task_struct *p, int hardirq_offset,
			 cputime_t cputime, cputime_t cputime_scaled)
{
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
	cputime64_t tmp;

	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
		account_guest_time(p, cputime, cputime_scaled);
		return;
	}

	/* Add system time to process. */
	p->stime = cputime_add(p->stime, cputime);
	p->stimescaled = cputime_add(p->stimescaled, cputime_scaled);
	account_group_system_time(p, cputime);

	/* Add system time to cpustat. */
	tmp = cputime_to_cputime64(cputime);
	if (hardirq_count() - hardirq_offset)
		cpustat->irq = cputime64_add(cpustat->irq, tmp);
	else if (softirq_count())
		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
	else
		cpustat->system = cputime64_add(cpustat->system, tmp);

	cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);

	/* Account for system time used */
	acct_update_integrals(p);
}

/*
 * Account for involuntary wait time.
 * @steal: the cpu time spent in involuntary wait
 */
void account_steal_time(cputime_t cputime)
{
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
	cputime64_t cputime64 = cputime_to_cputime64(cputime);

	cpustat->steal = cputime64_add(cpustat->steal, cputime64);
}

/*
 * Account for idle time.
 * @cputime: the cpu time spent in idle wait
 */
void account_idle_time(cputime_t cputime)
{
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
	cputime64_t cputime64 = cputime_to_cputime64(cputime);
	struct rq *rq = this_rq();

	if (atomic_read(&rq->nr_iowait) > 0)
		cpustat->iowait = cputime64_add(cpustat->iowait, cputime64);
	else
		cpustat->idle = cputime64_add(cpustat->idle, cputime64);
}

#ifndef CONFIG_VIRT_CPU_ACCOUNTING

/*
 * Account a single tick of cpu time.
 * @p: the process that the cpu time gets accounted to
 * @user_tick: indicates if the tick is a user or a system tick
 */
void account_process_tick(struct task_struct *p, int user_tick)
{
	cputime_t one_jiffy = jiffies_to_cputime(1);
	cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy);
	struct rq *rq = this_rq();

	if (user_tick)
		account_user_time(p, one_jiffy, one_jiffy_scaled);
	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
		account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
				    one_jiffy_scaled);
	else
		account_idle_time(one_jiffy);
}

/*
 * Account multiple ticks of steal time.
 * @p: the process from which the cpu time has been stolen
 * @ticks: number of stolen ticks
 */
void account_steal_ticks(unsigned long ticks)
{
	account_steal_time(jiffies_to_cputime(ticks));
}

/*
 * Account multiple ticks of idle time.
 * @ticks: number of stolen ticks
 */
void account_idle_ticks(unsigned long ticks)
{
	account_idle_time(jiffies_to_cputime(ticks));
}

#endif

/*
 * Use precise platform statistics if available:
 */
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
cputime_t task_utime(struct task_struct *p)
{
	return p->utime;
}

cputime_t task_stime(struct task_struct *p)
{
	return p->stime;
}
#else
cputime_t task_utime(struct task_struct *p)
{
	clock_t utime = cputime_to_clock_t(p->utime),
		total = utime + cputime_to_clock_t(p->stime);
	u64 temp;

	/*
	 * Use CFS's precise accounting:
	 */
	temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);

	if (total) {
		temp *= utime;
		do_div(temp, total);
	}
	utime = (clock_t)temp;

	p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
	return p->prev_utime;
}

cputime_t task_stime(struct task_struct *p)
{
	clock_t stime;

	/*
	 * Use CFS's precise accounting. (we subtract utime from
	 * the total, to make sure the total observed by userspace
	 * grows monotonically - apps rely on that):
	 */
	stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
			cputime_to_clock_t(task_utime(p));

	if (stime >= 0)
		p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));

	return p->prev_stime;
}
#endif

inline cputime_t task_gtime(struct task_struct *p)
{
	return p->gtime;
}

/*
 * This function gets called by the timer code, with HZ frequency.
 * We call it with interrupts disabled.
 *
 * It also gets called by the fork code, when changing the parent's
 * timeslices.
 */
void scheduler_tick(void)
{
	int cpu = smp_processor_id();
	struct rq *rq = cpu_rq(cpu);
	struct task_struct *curr = rq->curr;

	sched_clock_tick();

	spin_lock(&rq->lock);
	update_rq_clock(rq);
	update_cpu_load(rq);
	curr->sched_class->task_tick(rq, curr, 0);
	spin_unlock(&rq->lock);

	perf_counter_task_tick(curr, cpu);

#ifdef CONFIG_SMP
	rq->idle_at_tick = idle_cpu(cpu);
	trigger_load_balance(rq, cpu);
#endif
}

notrace unsigned long get_parent_ip(unsigned long addr)
{
	if (in_lock_functions(addr)) {
		addr = CALLER_ADDR2;
		if (in_lock_functions(addr))
			addr = CALLER_ADDR3;
	}
	return addr;
}

#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
				defined(CONFIG_PREEMPT_TRACER))

void __kprobes add_preempt_count(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
	/*
	 * Underflow?
	 */
	if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
		return;
#endif
	preempt_count() += val;
#ifdef CONFIG_DEBUG_PREEMPT
	/*
	 * Spinlock count overflowing soon?
	 */
	DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
				PREEMPT_MASK - 10);
#endif
	if (preempt_count() == val)
		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
}
EXPORT_SYMBOL(add_preempt_count);

void __kprobes sub_preempt_count(int val)
{
#ifdef CONFIG_DEBUG_PREEMPT
	/*
	 * Underflow?
	 */
	if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
		return;
	/*
	 * Is the spinlock portion underflowing?
	 */
	if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
			!(preempt_count() & PREEMPT_MASK)))
		return;
#endif

	if (preempt_count() == val)
		trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
	preempt_count() -= val;
}
EXPORT_SYMBOL(sub_preempt_count);

#endif

/*
 * Print scheduling while atomic bug:
 */
static noinline void __schedule_bug(struct task_struct *prev)
{
	struct pt_regs *regs = get_irq_regs();

	printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
		prev->comm, prev->pid, preempt_count());

	debug_show_held_locks(prev);
	print_modules();
	if (irqs_disabled())
		print_irqtrace_events(prev);

	if (regs)
		show_regs(regs);
	else
		dump_stack();
}

/*
 * Various schedule()-time debugging checks and statistics:
 */
static inline void schedule_debug(struct task_struct *prev)
{
	/*
	 * Test if we are atomic. Since do_exit() needs to call into
	 * schedule() atomically, we ignore that path for now.
	 * Otherwise, whine if we are scheduling when we should not be.
	 */
	if (unlikely(in_atomic_preempt_off() && !prev->exit_state))
		__schedule_bug(prev);

	profile_hit(SCHED_PROFILING, __builtin_return_address(0));

	schedstat_inc(this_rq(), sched_count);
#ifdef CONFIG_SCHEDSTATS
	if (unlikely(prev->lock_depth >= 0)) {
		schedstat_inc(this_rq(), bkl_count);
		schedstat_inc(prev, sched_info.bkl_count);
	}
#endif
}

static void put_prev_task(struct rq *rq, struct task_struct *prev)
{
	if (prev->state == TASK_RUNNING) {
		u64 runtime = prev->se.sum_exec_runtime;

		runtime -= prev->se.prev_sum_exec_runtime;
		runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);

		/*
		 * In order to avoid avg_overlap growing stale when we are
		 * indeed overlapping and hence not getting put to sleep, grow
		 * the avg_overlap on preemption.
		 *
		 * We use the average preemption runtime because that
		 * correlates to the amount of cache footprint a task can
		 * build up.
		 */
		update_avg(&prev->se.avg_overlap, runtime);
	}
	prev->sched_class->put_prev_task(rq, prev);
}

/*
 * Pick up the highest-prio task:
 */
static inline struct task_struct *
pick_next_task(struct rq *rq)
{
	const struct sched_class *class;
	struct task_struct *p;

	/*
	 * Optimization: we know that if all tasks are in
	 * the fair class we can call that function directly:
	 */
	if (likely(rq->nr_running == rq->cfs.nr_running)) {
		p = fair_sched_class.pick_next_task(rq);
		if (likely(p))
			return p;
	}

	class = sched_class_highest;
	for ( ; ; ) {
		p = class->pick_next_task(rq);
		if (p)
			return p;
		/*
		 * Will never be NULL as the idle class always
		 * returns a non-NULL p:
		 */
		class = class->next;
	}
}

/*
 * schedule() is the main scheduler function.
 */
asmlinkage void __sched schedule(void)
{
	struct task_struct *prev, *next;
	unsigned long *switch_count;
	struct rq *rq;
	int cpu;

need_resched:
	preempt_disable();
	cpu = smp_processor_id();
	rq = cpu_rq(cpu);
	rcu_qsctr_inc(cpu);
	prev = rq->curr;
	switch_count = &prev->nivcsw;

	release_kernel_lock(prev);
need_resched_nonpreemptible:

	schedule_debug(prev);

	if (sched_feat(HRTICK))
		hrtick_clear(rq);

	spin_lock_irq(&rq->lock);
	update_rq_clock(rq);
	clear_tsk_need_resched(prev);

	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
		if (unlikely(signal_pending_state(prev->state, prev)))
			prev->state = TASK_RUNNING;
		else
			deactivate_task(rq, prev, 1);
		switch_count = &prev->nvcsw;
	}

#ifdef CONFIG_SMP
	if (prev->sched_class->pre_schedule)
		prev->sched_class->pre_schedule(rq, prev);
#endif

	if (unlikely(!rq->nr_running))
		idle_balance(cpu, rq);

	put_prev_task(rq, prev);
	next = pick_next_task(rq);

	if (likely(prev != next)) {
		sched_info_switch(prev, next);
		perf_counter_task_sched_out(prev, next, cpu);

		rq->nr_switches++;
		rq->curr = next;
		++*switch_count;

		context_switch(rq, prev, next); /* unlocks the rq */
		/*
		 * the context switch might have flipped the stack from under
		 * us, hence refresh the local variables.
		 */
		cpu = smp_processor_id();
		rq = cpu_rq(cpu);
	} else
		spin_unlock_irq(&rq->lock);

	if (unlikely(reacquire_kernel_lock(current) < 0))
		goto need_resched_nonpreemptible;

	preempt_enable_no_resched();
	if (need_resched())
		goto need_resched;
}
EXPORT_SYMBOL(schedule);

#ifdef CONFIG_SMP
/*
 * Look out! "owner" is an entirely speculative pointer
 * access and not reliable.
 */
int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner)
{
	unsigned int cpu;
	struct rq *rq;

	if (!sched_feat(OWNER_SPIN))
		return 0;

#ifdef CONFIG_DEBUG_PAGEALLOC
	/*
	 * Need to access the cpu field knowing that
	 * DEBUG_PAGEALLOC could have unmapped it if
	 * the mutex owner just released it and exited.
	 */
	if (probe_kernel_address(&owner->cpu, cpu))
		goto out;
#else
	cpu = owner->cpu;
#endif

	/*
	 * Even if the access succeeded (likely case),
	 * the cpu field may no longer be valid.
	 */
	if (cpu >= nr_cpumask_bits)
		goto out;

	/*
	 * We need to validate that we can do a
	 * get_cpu() and that we have the percpu area.
	 */
	if (!cpu_online(cpu))
		goto out;

	rq = cpu_rq(cpu);

	for (;;) {
		/*
		 * Owner changed, break to re-assess state.
		 */
		if (lock->owner != owner)
			break;

		/*
		 * Is that owner really running on that cpu?
		 */
		if (task_thread_info(rq->curr) != owner || need_resched())
			return 0;

		cpu_relax();
	}
out:
	return 1;
}
#endif

#ifdef CONFIG_PREEMPT
/*
 * this is the entry point to schedule() from in-kernel preemption
 * off of preempt_enable. Kernel preemptions off return from interrupt
 * occur there and call schedule directly.
 */
asmlinkage void __sched preempt_schedule(void)
{
	struct thread_info *ti = current_thread_info();

	/*
	 * If there is a non-zero preempt_count or interrupts are disabled,
	 * we do not want to preempt the current task. Just return..
	 */
	if (likely(ti->preempt_count || irqs_disabled()))
		return;

	do {
		add_preempt_count(PREEMPT_ACTIVE);
		schedule();
		sub_preempt_count(PREEMPT_ACTIVE);

		/*
		 * Check again in case we missed a preemption opportunity
		 * between schedule and now.
		 */
		barrier();
	} while (need_resched());
}
EXPORT_SYMBOL(preempt_schedule);

/*
 * this is the entry point to schedule() from kernel preemption
 * off of irq context.
 * Note, that this is called and return with irqs disabled. This will
 * protect us against recursive calling from irq.
 */
asmlinkage void __sched preempt_schedule_irq(void)
{
	struct thread_info *ti = current_thread_info();

	/* Catch callers which need to be fixed */
	BUG_ON(ti->preempt_count || !irqs_disabled());

	do {
		add_preempt_count(PREEMPT_ACTIVE);
		local_irq_enable();
		schedule();
		local_irq_disable();
		sub_preempt_count(PREEMPT_ACTIVE);

		/*
		 * Check again in case we missed a preemption opportunity
		 * between schedule and now.
		 */
		barrier();
	} while (need_resched());
}

#endif /* CONFIG_PREEMPT */

int default_wake_function(wait_queue_t *curr, unsigned mode, int sync,
			  void *key)
{
	return try_to_wake_up(curr->private, mode, sync);
}
EXPORT_SYMBOL(default_wake_function);

/*
 * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
 * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
 * number) then we wake all the non-exclusive tasks and one exclusive task.
 *
 * There are circumstances in which we can try to wake a task which has already
 * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
 * zero in this (rare) case, and we handle it by continuing to scan the queue.
 */
static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
			int nr_exclusive, int sync, void *key)
{
	wait_queue_t *curr, *next;

	list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
		unsigned flags = curr->flags;

		if (curr->func(curr, mode, sync, key) &&
				(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
			break;
	}
}

/**
 * __wake_up - wake up threads blocked on a waitqueue.
 * @q: the waitqueue
 * @mode: which threads
 * @nr_exclusive: how many wake-one or wake-many threads to wake up
 * @key: is directly passed to the wakeup function
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */
void __wake_up(wait_queue_head_t *q, unsigned int mode,
			int nr_exclusive, void *key)
{
	unsigned long flags;

	spin_lock_irqsave(&q->lock, flags);
	__wake_up_common(q, mode, nr_exclusive, 0, key);
	spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL(__wake_up);

/*
 * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
 */
void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
{
	__wake_up_common(q, mode, 1, 0, NULL);
}

void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
{
	__wake_up_common(q, mode, 1, 0, key);
}

/**
 * __wake_up_sync_key - wake up threads blocked on a waitqueue.
 * @q: the waitqueue
 * @mode: which threads
 * @nr_exclusive: how many wake-one or wake-many threads to wake up
 * @key: opaque value to be passed to wakeup targets
 *
 * The sync wakeup differs that the waker knows that it will schedule
 * away soon, so while the target thread will be woken up, it will not
 * be migrated to another CPU - ie. the two threads are 'synchronized'
 * with each other. This can prevent needless bouncing between CPUs.
 *
 * On UP it can prevent extra preemption.
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */
void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
			int nr_exclusive, void *key)
{
	unsigned long flags;
	int sync = 1;

	if (unlikely(!q))
		return;

	if (unlikely(!nr_exclusive))
		sync = 0;

	spin_lock_irqsave(&q->lock, flags);
	__wake_up_common(q, mode, nr_exclusive, sync, key);
	spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL_GPL(__wake_up_sync_key);

/*
 * __wake_up_sync - see __wake_up_sync_key()
 */
void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
{
	__wake_up_sync_key(q, mode, nr_exclusive, NULL);
}
EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */

/**
 * complete: - signals a single thread waiting on this completion
 * @x:  holds the state of this particular completion
 *
 * This will wake up a single thread waiting on this completion. Threads will be
 * awakened in the same order in which they were queued.
 *
 * See also complete_all(), wait_for_completion() and related routines.
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */
void complete(struct completion *x)
{
	unsigned long flags;

	spin_lock_irqsave(&x->wait.lock, flags);
	x->done++;
	__wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
	spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete);

/**
 * complete_all: - signals all threads waiting on this completion
 * @x:  holds the state of this particular completion
 *
 * This will wake up all threads waiting on this particular completion event.
 *
 * It may be assumed that this function implies a write memory barrier before
 * changing the task state if and only if any tasks are woken up.
 */
void complete_all(struct completion *x)
{
	unsigned long flags;

	spin_lock_irqsave(&x->wait.lock, flags);
	x->done += UINT_MAX/2;
	__wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
	spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete_all);

static inline long __sched
do_wait_for_common(struct completion *x, long timeout, int state)
{
	if (!x->done) {
		DECLARE_WAITQUEUE(wait, current);

		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue_tail(&x->wait, &wait);
		do {
			if (signal_pending_state(state, current)) {
				timeout = -ERESTARTSYS;
				break;
			}
			__set_current_state(state);
			spin_unlock_irq(&x->wait.lock);
			timeout = schedule_timeout(timeout);
			spin_lock_irq(&x->wait.lock);
		} while (!x->done && timeout);
		__remove_wait_queue(&x->wait, &wait);
		if (!x->done)
			return timeout;
	}
	x->done--;
	return timeout ?: 1;
}

static long __sched
wait_for_common(struct completion *x, long timeout, int state)
{
	might_sleep();

	spin_lock_irq(&x->wait.lock);
	timeout = do_wait_for_common(x, timeout, state);
	spin_unlock_irq(&x->wait.lock);
	return timeout;
}

/**
 * wait_for_completion: - waits for completion of a task
 * @x:  holds the state of this particular completion
 *
 * This waits to be signaled for completion of a specific task. It is NOT
 * interruptible and there is no timeout.
 *
 * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
 * and interrupt capability. Also see complete().
 */
void __sched wait_for_completion(struct completion *x)
{
	wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion);

/**
 * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
 * @x:  holds the state of this particular completion
 * @timeout:  timeout value in jiffies
 *
 * This waits for either a completion of a specific task to be signaled or for a
 * specified timeout to expire. The timeout is in jiffies. It is not
 * interruptible.
 */
unsigned long __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
{
	return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion_timeout);

/**
 * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
 * @x:  holds the state of this particular completion
 *
 * This waits for completion of a specific task to be signaled. It is
 * interruptible.
 */
int __sched wait_for_completion_interruptible(struct completion *x)
{
	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
	if (t == -ERESTARTSYS)
		return t;
	return 0;
}
EXPORT_SYMBOL(wait_for_completion_interruptible);

/**
 * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
 * @x:  holds the state of this particular completion
 * @timeout:  timeout value in jiffies
 *
 * This waits for either a completion of a specific task to be signaled or for a
 * specified timeout to expire. It is interruptible. The timeout is in jiffies.
 */
unsigned long __sched
wait_for_completion_interruptible_timeout(struct completion *x,
					  unsigned long timeout)
{
	return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
}
EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);

/**
 * wait_for_completion_killable: - waits for completion of a task (killable)
 * @x:  holds the state of this particular completion
 *
 * This waits to be signaled for completion of a specific task. It can be
 * interrupted by a kill signal.
 */
int __sched wait_for_completion_killable(struct completion *x)
{
	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
	if (t == -ERESTARTSYS)
		return t;
	return 0;
}
EXPORT_SYMBOL(wait_for_completion_killable);

/**
 *	try_wait_for_completion - try to decrement a completion without blocking
 *	@x:	completion structure
 *
 *	Returns: 0 if a decrement cannot be done without blocking
 *		 1 if a decrement succeeded.
 *
 *	If a completion is being used as a counting completion,
 *	attempt to decrement the counter without blocking. This
 *	enables us to avoid waiting if the resource the completion
 *	is protecting is not available.
 */
bool try_wait_for_completion(struct completion *x)
{
	int ret = 1;

	spin_lock_irq(&x->wait.lock);
	if (!x->done)
		ret = 0;
	else
		x->done--;
	spin_unlock_irq(&x->wait.lock);
	return ret;
}
EXPORT_SYMBOL(try_wait_for_completion);

/**
 *	completion_done - Test to see if a completion has any waiters
 *	@x:	completion structure
 *
 *	Returns: 0 if there are waiters (wait_for_completion() in progress)
 *		 1 if there are no waiters.
 *
 */
bool completion_done(struct completion *x)
{
	int ret = 1;

	spin_lock_irq(&x->wait.lock);
	if (!x->done)
		ret = 0;
	spin_unlock_irq(&x->wait.lock);
	return ret;
}
EXPORT_SYMBOL(completion_done);

static long __sched
sleep_on_common(wait_queue_head_t *q, int state, long timeout)
{
	unsigned long flags;
	wait_queue_t wait;

	init_waitqueue_entry(&wait, current);

	__set_current_state(state);

	spin_lock_irqsave(&q->lock, flags);
	__add_wait_queue(q, &wait);
	spin_unlock(&q->lock);
	timeout = schedule_timeout(timeout);
	spin_lock_irq(&q->lock);
	__remove_wait_queue(q, &wait);
	spin_unlock_irqrestore(&q->lock, flags);

	return timeout;
}

void __sched interruptible_sleep_on(wait_queue_head_t *q)
{
	sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
EXPORT_SYMBOL(interruptible_sleep_on);

long __sched
interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
	return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
}
EXPORT_SYMBOL(interruptible_sleep_on_timeout);

void __sched sleep_on(wait_queue_head_t *q)
{
	sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
}
EXPORT_SYMBOL(sleep_on);

long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
	return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
}
EXPORT_SYMBOL(sleep_on_timeout);

#ifdef CONFIG_RT_MUTEXES

/*
 * rt_mutex_setprio - set the current priority of a task
 * @p: task
 * @prio: prio value (kernel-internal form)
 *
 * This function changes the 'effective' priority of a task. It does
 * not touch ->normal_prio like __setscheduler().
 *
 * Used by the rt_mutex code to implement priority inheritance logic.
 */
void rt_mutex_setprio(struct task_struct *p, int prio)
{
	unsigned long flags;
	int oldprio, on_rq, running;
	struct rq *rq;
	const struct sched_class *prev_class = p->sched_class;

	BUG_ON(prio < 0 || prio > MAX_PRIO);

	rq = task_rq_lock(p, &flags);
	update_rq_clock(rq);

	oldprio = p->prio;
	on_rq = p->se.on_rq;
	running = task_current(rq, p);
	if (on_rq)
		dequeue_task(rq, p, 0);
	if (running)
		p->sched_class->put_prev_task(rq, p);

	if (rt_prio(prio))
		p->sched_class = &rt_sched_class;
	else
		p->sched_class = &fair_sched_class;

	p->prio = prio;

	if (running)
		p->sched_class->set_curr_task(rq);
	if (on_rq) {
		enqueue_task(rq, p, 0);

		check_class_changed(rq, p, prev_class, oldprio, running);
	}
	task_rq_unlock(rq, &flags);
}

#endif

void set_user_nice(struct task_struct *p, long nice)
{
	int old_prio, delta, on_rq;
	unsigned long flags;
	struct rq *rq;

	if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
		return;
	/*
	 * We have to be careful, if called from sys_setpriority(),
	 * the task might be in the middle of scheduling on another CPU.
	 */
	rq = task_rq_lock(p, &flags);
	update_rq_clock(rq);
	/*
	 * The RT priorities are set via sched_setscheduler(), but we still
	 * allow the 'normal' nice value to be set - but as expected
	 * it wont have any effect on scheduling until the task is
	 * SCHED_FIFO/SCHED_RR:
	 */
	if (task_has_rt_policy(p)) {
		p->static_prio = NICE_TO_PRIO(nice);
		goto out_unlock;
	}
	on_rq = p->se.on_rq;
	if (on_rq)
		dequeue_task(rq, p, 0);

	p->static_prio = NICE_TO_PRIO(nice);
	set_load_weight(p);
	old_prio = p->prio;
	p->prio = effective_prio(p);
	delta = p->prio - old_prio;

	if (on_rq) {
		enqueue_task(rq, p, 0);
		/*
		 * If the task increased its priority or is running and
		 * lowered its priority, then reschedule its CPU:
		 */
		if (delta < 0 || (delta > 0 && task_running(rq, p)))
			resched_task(rq->curr);
	}
out_unlock:
	task_rq_unlock(rq, &flags);
}
EXPORT_SYMBOL(set_user_nice);

/*
 * can_nice - check if a task can reduce its nice value
 * @p: task
 * @nice: nice value
 */
int can_nice(const struct task_struct *p, const int nice)
{
	/* convert nice value [19,-20] to rlimit style value [1,40] */
	int nice_rlim = 20 - nice;

	return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
		capable(CAP_SYS_NICE));
}

#ifdef __ARCH_WANT_SYS_NICE

/*
 * sys_nice - change the priority of the current process.
 * @increment: priority increment
 *
 * sys_setpriority is a more generic, but much slower function that
 * does similar things.
 */
SYSCALL_DEFINE1(nice, int, increment)
{
	long nice, retval;

	/*
	 * Setpriority might change our priority at the same moment.
	 * We don't have to worry. Conceptually one call occurs first
	 * and we have a single winner.
	 */
	if (increment < -40)
		increment = -40;
	if (increment > 40)
		increment = 40;

	nice = TASK_NICE(current) + increment;
	if (nice < -20)
		nice = -20;
	if (nice > 19)
		nice = 19;

	if (increment < 0 && !can_nice(current, nice))
		return -EPERM;

	retval = security_task_setnice(current, nice);
	if (retval)
		return retval;

	set_user_nice(current, nice);
	return 0;
}

#endif

/**
 * task_prio - return the priority value of a given task.
 * @p: the task in question.
 *
 * This is the priority value as seen by users in /proc.
 * RT tasks are offset by -200. Normal tasks are centered
 * around 0, value goes from -16 to +15.
 */
int task_prio(const struct task_struct *p)
{
	return p->prio - MAX_RT_PRIO;
}

/**
 * task_nice - return the nice value of a given task.
 * @p: the task in question.
 */
int task_nice(const struct task_struct *p)
{
	return TASK_NICE(p);
}
EXPORT_SYMBOL(task_nice);

/**
 * idle_cpu - is a given cpu idle currently?
 * @cpu: the processor in question.
 */
int idle_cpu(int cpu)
{
	return cpu_curr(cpu) == cpu_rq(cpu)->idle;
}

/**
 * idle_task - return the idle task for a given cpu.
 * @cpu: the processor in question.
 */
struct task_struct *idle_task(int cpu)
{
	return cpu_rq(cpu)->idle;
}

/**
 * find_process_by_pid - find a process with a matching PID value.
 * @pid: the pid in question.
 */
static struct task_struct *find_process_by_pid(pid_t pid)
{
	return pid ? find_task_by_vpid(pid) : current;
}

/* Actually do priority change: must hold rq lock. */
static void
__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
{
	BUG_ON(p->se.on_rq);

	p->policy = policy;
	switch (p->policy) {
	case SCHED_NORMAL:
	case SCHED_BATCH:
	case SCHED_IDLE:
		p->sched_class = &fair_sched_class;
		break;
	case SCHED_FIFO:
	case SCHED_RR:
		p->sched_class = &rt_sched_class;
		break;
	}

	p->rt_priority = prio;
	p->normal_prio = normal_prio(p);
	/* we are holding p->pi_lock already */
	p->prio = rt_mutex_getprio(p);
	set_load_weight(p);
}

/*
 * check the target process has a UID that matches the current process's
 */
static bool check_same_owner(struct task_struct *p)
{
	const struct cred *cred = current_cred(), *pcred;
	bool match;

	rcu_read_lock();
	pcred = __task_cred(p);
	match = (cred->euid == pcred->euid ||
		 cred->euid == pcred->uid);
	rcu_read_unlock();
	return match;
}

static int __sched_setscheduler(struct task_struct *p, int policy,
				struct sched_param *param, bool user)
{
	int retval, oldprio, oldpolicy = -1, on_rq, running;
	unsigned long flags;
	const struct sched_class *prev_class = p->sched_class;
	struct rq *rq;

	/* may grab non-irq protected spin_locks */
	BUG_ON(in_interrupt());
recheck:
	/* double check policy once rq lock held */
	if (policy < 0)
		policy = oldpolicy = p->policy;
	else if (policy != SCHED_FIFO && policy != SCHED_RR &&
			policy != SCHED_NORMAL && policy != SCHED_BATCH &&
			policy != SCHED_IDLE)
		return -EINVAL;
	/*
	 * Valid priorities for SCHED_FIFO and SCHED_RR are
	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL,
	 * SCHED_BATCH and SCHED_IDLE is 0.
	 */
	if (param->sched_priority < 0 ||
	    (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
	    (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
		return -EINVAL;
	if (rt_policy(policy) != (param->sched_priority != 0))
		return -EINVAL;

	/*
	 * Allow unprivileged RT tasks to decrease priority:
	 */
	if (user && !capable(CAP_SYS_NICE)) {
		if (rt_policy(policy)) {
			unsigned long rlim_rtprio;

			if (!lock_task_sighand(p, &flags))
				return -ESRCH;
			rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
			unlock_task_sighand(p, &flags);

			/* can't set/change the rt policy */
			if (policy != p->policy && !rlim_rtprio)
				return -EPERM;

			/* can't increase priority */
			if (param->sched_priority > p->rt_priority &&
			    param->sched_priority > rlim_rtprio)
				return -EPERM;
		}
		/*
		 * Like positive nice levels, dont allow tasks to
		 * move out of SCHED_IDLE either:
		 */
		if (p->policy == SCHED_IDLE && policy != SCHED_IDLE)
			return -EPERM;

		/* can't change other user's priorities */
		if (!check_same_owner(p))
			return -EPERM;
	}

	if (user) {
#ifdef CONFIG_RT_GROUP_SCHED
		/*
		 * Do not allow realtime tasks into groups that have no runtime
		 * assigned.
		 */
		if (rt_bandwidth_enabled() && rt_policy(policy) &&
				task_group(p)->rt_bandwidth.rt_runtime == 0)
			return -EPERM;
#endif

		retval = security_task_setscheduler(p, policy, param);
		if (retval)
			return retval;
	}

	/*
	 * make sure no PI-waiters arrive (or leave) while we are
	 * changing the priority of the task:
	 */
	spin_lock_irqsave(&p->pi_lock, flags);
	/*
	 * To be able to change p->policy safely, the apropriate
	 * runqueue lock must be held.
	 */
	rq = __task_rq_lock(p);
	/* recheck policy now with rq lock held */
	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
		policy = oldpolicy = -1;
		__task_rq_unlock(rq);
		spin_unlock_irqrestore(&p->pi_lock, flags);
		goto recheck;
	}
	update_rq_clock(rq);
	on_rq = p->se.on_rq;
	running = task_current(rq, p);
	if (on_rq)
		deactivate_task(rq, p, 0);
	if (running)
		p->sched_class->put_prev_task(rq, p);

	oldprio = p->prio;
	__setscheduler(rq, p, policy, param->sched_priority);

	if (running)
		p->sched_class->set_curr_task(rq);
	if (on_rq) {
		activate_task(rq, p, 0);

		check_class_changed(rq, p, prev_class, oldprio, running);
	}
	__task_rq_unlock(rq);
	spin_unlock_irqrestore(&p->pi_lock, flags);

	rt_mutex_adjust_pi(p);

	return 0;
}

/**
 * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
 * @p: the task in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 *
 * NOTE that the task may be already dead.
 */
int sched_setscheduler(struct task_struct *p, int policy,
		       struct sched_param *param)
{
	return __sched_setscheduler(p, policy, param, true);
}
EXPORT_SYMBOL_GPL(sched_setscheduler);

/**
 * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
 * @p: the task in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 *
 * Just like sched_setscheduler, only don't bother checking if the
 * current context has permission.  For example, this is needed in
 * stop_machine(): we create temporary high priority worker threads,
 * but our caller might not have that capability.
 */
int sched_setscheduler_nocheck(struct task_struct *p, int policy,
			       struct sched_param *param)
{
	return __sched_setscheduler(p, policy, param, false);
}

static int
do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
{
	struct sched_param lparam;
	struct task_struct *p;
	int retval;

	if (!param || pid < 0)
		return -EINVAL;
	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
		return -EFAULT;

	rcu_read_lock();
	retval = -ESRCH;
	p = find_process_by_pid(pid);
	if (p != NULL)
		retval = sched_setscheduler(p, policy, &lparam);
	rcu_read_unlock();

	return retval;
}

/**
 * sys_sched_setscheduler - set/change the scheduler policy and RT priority
 * @pid: the pid in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 */
SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy,
		struct sched_param __user *, param)
{
	/* negative values for policy are not valid */
	if (policy < 0)
		return -EINVAL;

	return do_sched_setscheduler(pid, policy, param);
}

/**
 * sys_sched_setparam - set/change the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the new RT priority.
 */
SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
{
	return do_sched_setscheduler(pid, -1, param);
}

/**
 * sys_sched_getscheduler - get the policy (scheduling class) of a thread
 * @pid: the pid in question.
 */
SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
{
	struct task_struct *p;
	int retval;

	if (pid < 0)
		return -EINVAL;

	retval = -ESRCH;
	read_lock(&tasklist_lock);
	p = find_process_by_pid(pid);
	if (p) {
		retval = security_task_getscheduler(p);
		if (!retval)
			retval = p->policy;
	}
	read_unlock(&tasklist_lock);
	return retval;
}

/**
 * sys_sched_getscheduler - get the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the RT priority.
 */
SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
{
	struct sched_param lp;
	struct task_struct *p;
	int retval;

	if (!param || pid < 0)
		return -EINVAL;

	read_lock(&tasklist_lock);
	p = find_process_by_pid(pid);
	retval = -ESRCH;
	if (!p)
		goto out_unlock;

	retval = security_task_getscheduler(p);
	if (retval)
		goto out_unlock;

	lp.sched_priority = p->rt_priority;
	read_unlock(&tasklist_lock);

	/*
	 * This one might sleep, we cannot do it with a spinlock held ...
	 */
	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;

	return retval;

out_unlock:
	read_unlock(&tasklist_lock);
	return retval;
}

long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
	cpumask_var_t cpus_allowed, new_mask;
	struct task_struct *p;
	int retval;

	get_online_cpus();
	read_lock(&tasklist_lock);

	p = find_process_by_pid(pid);
	if (!p) {
		read_unlock(&tasklist_lock);
		put_online_cpus();
		return -ESRCH;
	}

	/*
	 * It is not safe to call set_cpus_allowed with the
	 * tasklist_lock held. We will bump the task_struct's
	 * usage count and then drop tasklist_lock.
	 */
	get_task_struct(p);
	read_unlock(&tasklist_lock);

	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
		retval = -ENOMEM;
		goto out_put_task;
	}
	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
		retval = -ENOMEM;
		goto out_free_cpus_allowed;
	}
	retval = -EPERM;
	if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
		goto out_unlock;

	retval = security_task_setscheduler(p, 0, NULL);
	if (retval)
		goto out_unlock;

	cpuset_cpus_allowed(p, cpus_allowed);
	cpumask_and(new_mask, in_mask, cpus_allowed);
 again:
	retval = set_cpus_allowed_ptr(p, new_mask);

	if (!retval) {
		cpuset_cpus_allowed(p, cpus_allowed);
		if (!cpumask_subset(new_mask, cpus_allowed)) {
			/*
			 * We must have raced with a concurrent cpuset
			 * update. Just reset the cpus_allowed to the
			 * cpuset's cpus_allowed
			 */
			cpumask_copy(new_mask, cpus_allowed);
			goto again;
		}
	}
out_unlock:
	free_cpumask_var(new_mask);
out_free_cpus_allowed:
	free_cpumask_var(cpus_allowed);
out_put_task:
	put_task_struct(p);
	put_online_cpus();
	return retval;
}

static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
			     struct cpumask *new_mask)
{
	if (len < cpumask_size())
		cpumask_clear(new_mask);
	else if (len > cpumask_size())
		len = cpumask_size();

	return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
}

/**
 * sys_sched_setaffinity - set the cpu affinity of a process
 * @pid: pid of the process
 * @len: length in bytes of the bitmask pointed to by user_mask_ptr
 * @user_mask_ptr: user-space pointer to the new cpu mask
 */
SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
		unsigned long __user *, user_mask_ptr)
{
	cpumask_var_t new_mask;
	int retval;

	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
		return -ENOMEM;

	retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
	if (retval == 0)
		retval = sched_setaffinity(pid, new_mask);
	free_cpumask_var(new_mask);
	return retval;
}

long sched_getaffinity(pid_t pid, struct cpumask *mask)
{
	struct task_struct *p;
	int retval;

	get_online_cpus();
	read_lock(&tasklist_lock);

	retval = -ESRCH;
	p = find_process_by_pid(pid);
	if (!p)
		goto out_unlock;

	retval = security_task_getscheduler(p);
	if (retval)
		goto out_unlock;

	cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);

out_unlock:
	read_unlock(&tasklist_lock);
	put_online_cpus();

	return retval;
}

/**
 * sys_sched_getaffinity - get the cpu affinity of a process
 * @pid: pid of the process
 * @len: length in bytes of the bitmask pointed to by user_mask_ptr
 * @user_mask_ptr: user-space pointer to hold the current cpu mask
 */
SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
		unsigned long __user *, user_mask_ptr)
{
	int ret;
	cpumask_var_t mask;

	if (len < cpumask_size())
		return -EINVAL;

	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
		return -ENOMEM;

	ret = sched_getaffinity(pid, mask);
	if (ret == 0) {
		if (copy_to_user(user_mask_ptr, mask, cpumask_size()))
			ret = -EFAULT;
		else
			ret = cpumask_size();
	}
	free_cpumask_var(mask);

	return ret;
}

/**
 * sys_sched_yield - yield the current processor to other threads.
 *
 * This function yields the current CPU to other tasks. If there are no
 * other threads running on this CPU then this function will return.
 */
SYSCALL_DEFINE0(sched_yield)
{
	struct rq *rq = this_rq_lock();

	schedstat_inc(rq, yld_count);
	current->sched_class->yield_task(rq);

	/*
	 * Since we are going to call schedule() anyway, there's
	 * no need to preempt or enable interrupts:
	 */
	__release(rq->lock);
	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
	_raw_spin_unlock(&rq->lock);
	preempt_enable_no_resched();

	schedule();

	return 0;
}

static void __cond_resched(void)
{
#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
	__might_sleep(__FILE__, __LINE__);
#endif
	/*
	 * The BKS might be reacquired before we have dropped
	 * PREEMPT_ACTIVE, which could trigger a second
	 * cond_resched() call.
	 */
	do {
		add_preempt_count(PREEMPT_ACTIVE);
		schedule();
		sub_preempt_count(PREEMPT_ACTIVE);
	} while (need_resched());
}

int __sched _cond_resched(void)
{
	if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) &&
					system_state == SYSTEM_RUNNING) {
		__cond_resched();
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL(_cond_resched);

/*
 * cond_resched_lock() - if a reschedule is pending, drop the given lock,
 * call schedule, and on return reacquire the lock.
 *
 * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
 * operations here to prevent schedule() from being called twice (once via
 * spin_unlock(), once by hand).
 */
int cond_resched_lock(spinlock_t *lock)
{
	int resched = need_resched() && system_state == SYSTEM_RUNNING;
	int ret = 0;

	if (spin_needbreak(lock) || resched) {
		spin_unlock(lock);
		if (resched && need_resched())
			__cond_resched();
		else
			cpu_relax();
		ret = 1;
		spin_lock(lock);
	}
	return ret;
}
EXPORT_SYMBOL(cond_resched_lock);

int __sched cond_resched_softirq(void)
{
	BUG_ON(!in_softirq());

	if (need_resched() && system_state == SYSTEM_RUNNING) {
		local_bh_enable();
		__cond_resched();
		local_bh_disable();
		return 1;
	}
	return 0;
}
EXPORT_SYMBOL(cond_resched_softirq);

/**
 * yield - yield the current processor to other threads.
 *
 * This is a shortcut for kernel-space yielding - it marks the
 * thread runnable and calls sys_sched_yield().
 */
void __sched yield(void)
{
	set_current_state(TASK_RUNNING);
	sys_sched_yield();
}
EXPORT_SYMBOL(yield);

/*
 * This task is about to go to sleep on IO. Increment rq->nr_iowait so
 * that process accounting knows that this is a task in IO wait state.
 *
 * But don't do that if it is a deliberate, throttling IO wait (this task
 * has set its backing_dev_info: the queue against which it should throttle)
 */
void __sched io_schedule(void)
{
	struct rq *rq = &__raw_get_cpu_var(runqueues);

	delayacct_blkio_start();
	atomic_inc(&rq->nr_iowait);
	schedule();
	atomic_dec(&rq->nr_iowait);
	delayacct_blkio_end();
}
EXPORT_SYMBOL(io_schedule);

long __sched io_schedule_timeout(long timeout)
{
	struct rq *rq = &__raw_get_cpu_var(runqueues);
	long ret;

	delayacct_blkio_start();
	atomic_inc(&rq->nr_iowait);
	ret = schedule_timeout(timeout);
	atomic_dec(&rq->nr_iowait);
	delayacct_blkio_end();
	return ret;
}

/**
 * sys_sched_get_priority_max - return maximum RT priority.
 * @policy: scheduling class.
 *
 * this syscall returns the maximum rt_priority that can be used
 * by a given scheduling class.
 */
SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
{
	int ret = -EINVAL;

	switch (policy) {
	case SCHED_FIFO:
	case SCHED_RR:
		ret = MAX_USER_RT_PRIO-1;
		break;
	case SCHED_NORMAL:
	case SCHED_BATCH:
	case SCHED_IDLE:
		ret = 0;
		break;
	}
	return ret;
}

/**
 * sys_sched_get_priority_min - return minimum RT priority.
 * @policy: scheduling class.
 *
 * this syscall returns the minimum rt_priority that can be used
 * by a given scheduling class.
 */
SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
{
	int ret = -EINVAL;

	switch (policy) {
	case SCHED_FIFO:
	case SCHED_RR:
		ret = 1;
		break;
	case SCHED_NORMAL:
	case SCHED_BATCH:
	case SCHED_IDLE:
		ret = 0;
	}
	return ret;
}

/**
 * sys_sched_rr_get_interval - return the default timeslice of a process.
 * @pid: pid of the process.
 * @interval: userspace pointer to the timeslice value.
 *
 * this syscall writes the default timeslice value of a given process
 * into the user-space timespec buffer. A value of '0' means infinity.
 */
SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
		struct timespec __user *, interval)
{
	struct task_struct *p;
	unsigned int time_slice;
	int retval;
	struct timespec t;

	if (pid < 0)
		return -EINVAL;

	retval = -ESRCH;
	read_lock(&tasklist_lock);
	p = find_process_by_pid(pid);
	if (!p)
		goto out_unlock;

	retval = security_task_getscheduler(p);
	if (retval)
		goto out_unlock;

	/*
	 * Time slice is 0 for SCHED_FIFO tasks and for SCHED_OTHER
	 * tasks that are on an otherwise idle runqueue:
	 */
	time_slice = 0;
	if (p->policy == SCHED_RR) {
		time_slice = DEF_TIMESLICE;
	} else if (p->policy != SCHED_FIFO) {
		struct sched_entity *se = &p->se;
		unsigned long flags;
		struct rq *rq;

		rq = task_rq_lock(p, &flags);
		if (rq->cfs.load.weight)
			time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
		task_rq_unlock(rq, &flags);
	}
	read_unlock(&tasklist_lock);
	jiffies_to_timespec(time_slice, &t);
	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
	return retval;

out_unlock:
	read_unlock(&tasklist_lock);
	return retval;
}

static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;

void sched_show_task(struct task_struct *p)
{
	unsigned long free = 0;
	unsigned state;

	state = p->state ? __ffs(p->state) + 1 : 0;
	printk(KERN_INFO "%-13.13s %c", p->comm,
		state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
#if BITS_PER_LONG == 32
	if (state == TASK_RUNNING)
		printk(KERN_CONT " running  ");
	else
		printk(KERN_CONT " %08lx ", thread_saved_pc(p));
#else
	if (state == TASK_RUNNING)
		printk(KERN_CONT "  running task    ");
	else
		printk(KERN_CONT " %016lx ", thread_saved_pc(p));
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
	free = stack_not_used(p);
#endif
	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
		task_pid_nr(p), task_pid_nr(p->real_parent),
		(unsigned long)task_thread_info(p)->flags);

	show_stack(p, NULL);
}

void show_state_filter(unsigned long state_filter)
{
	struct task_struct *g, *p;

#if BITS_PER_LONG == 32
	printk(KERN_INFO
		"  task                PC stack   pid father\n");
#else
	printk(KERN_INFO
		"  task                        PC stack   pid father\n");
#endif
	read_lock(&tasklist_lock);
	do_each_thread(g, p) {
		/*
		 * reset the NMI-timeout, listing all files on a slow
		 * console might take alot of time:
		 */
		touch_nmi_watchdog();
		if (!state_filter || (p->state & state_filter))
			sched_show_task(p);
	} while_each_thread(g, p);

	touch_all_softlockup_watchdogs();

#ifdef CONFIG_SCHED_DEBUG
	sysrq_sched_debug_show();
#endif
	read_unlock(&tasklist_lock);
	/*
	 * Only show locks if all tasks are dumped:
	 */
	if (state_filter == -1)
		debug_show_all_locks();
}

void __cpuinit init_idle_bootup_task(struct task_struct *idle)
{
	idle->sched_class = &idle_sched_class;
}

/**
 * init_idle - set up an idle thread for a given CPU
 * @idle: task in question
 * @cpu: cpu the idle task belongs to
 *
 * NOTE: this function does not set the idle thread's NEED_RESCHED
 * flag, to make booting more robust.
 */
void __cpuinit init_idle(struct task_struct *idle, int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	unsigned long flags;

	spin_lock_irqsave(&rq->lock, flags);

	__sched_fork(idle);
	idle->se.exec_start = sched_clock();

	idle->prio = idle->normal_prio = MAX_PRIO;
	cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
	__set_task_cpu(idle, cpu);

	rq->curr = rq->idle = idle;
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
	idle->oncpu = 1;
#endif
	spin_unlock_irqrestore(&rq->lock, flags);

	/* Set the preempt count _outside_ the spinlocks! */
#if defined(CONFIG_PREEMPT)
	task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
#else
	task_thread_info(idle)->preempt_count = 0;
#endif
	/*
	 * The idle tasks have their own, simple scheduling class:
	 */
	idle->sched_class = &idle_sched_class;
	ftrace_graph_init_task(idle);
}

/*
 * In a system that switches off the HZ timer nohz_cpu_mask
 * indicates which cpus entered this state. This is used
 * in the rcu update to wait only for active cpus. For system
 * which do not switch off the HZ timer nohz_cpu_mask should
 * always be CPU_BITS_NONE.
 */
cpumask_var_t nohz_cpu_mask;

/*
 * Increase the granularity value when there are more CPUs,
 * because with more CPUs the 'effective latency' as visible
 * to users decreases. But the relationship is not linear,
 * so pick a second-best guess by going with the log2 of the
 * number of CPUs.
 *
 * This idea comes from the SD scheduler of Con Kolivas:
 */
static inline void sched_init_granularity(void)
{
	unsigned int factor = 1 + ilog2(num_online_cpus());
	const unsigned long limit = 200000000;

	sysctl_sched_min_granularity *= factor;
	if (sysctl_sched_min_granularity > limit)
		sysctl_sched_min_granularity = limit;

	sysctl_sched_latency *= factor;
	if (sysctl_sched_latency > limit)
		sysctl_sched_latency = limit;

	sysctl_sched_wakeup_granularity *= factor;

	sysctl_sched_shares_ratelimit *= factor;
}

#ifdef CONFIG_SMP
/*
 * This is how migration works:
 *
 * 1) we queue a struct migration_req structure in the source CPU's
 *    runqueue and wake up that CPU's migration thread.
 * 2) we down() the locked semaphore => thread blocks.
 * 3) migration thread wakes up (implicitly it forces the migrated
 *    thread off the CPU)
 * 4) it gets the migration request and checks whether the migrated
 *    task is still in the wrong runqueue.
 * 5) if it's in the wrong runqueue then the migration thread removes
 *    it and puts it into the right queue.
 * 6) migration thread up()s the semaphore.
 * 7) we wake up and the migration is done.
 */

/*
 * Change a given task's CPU affinity. Migrate the thread to a
 * proper CPU and schedule it away if the CPU it's executing on
 * is removed from the allowed bitmask.
 *
 * NOTE: the caller must have a valid reference to the task, the
 * task must not exit() & deallocate itself prematurely. The
 * call is not atomic; no spinlocks may be held.
 */
int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
{
	struct migration_req req;
	unsigned long flags;
	struct rq *rq;
	int ret = 0;

	rq = task_rq_lock(p, &flags);
	if (!cpumask_intersects(new_mask, cpu_online_mask)) {
		ret = -EINVAL;
		goto out;
	}

	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
		     !cpumask_equal(&p->cpus_allowed, new_mask))) {
		ret = -EINVAL;
		goto out;
	}

	if (p->sched_class->set_cpus_allowed)
		p->sched_class->set_cpus_allowed(p, new_mask);
	else {
		cpumask_copy(&p->cpus_allowed, new_mask);
		p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
	}

	/* Can the task run on the task's current CPU? If so, we're done */
	if (cpumask_test_cpu(task_cpu(p), new_mask))
		goto out;

	if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
		/* Need help from migration thread: drop lock and wait. */
		task_rq_unlock(rq, &flags);
		wake_up_process(rq->migration_thread);
		wait_for_completion(&req.done);
		tlb_migrate_finish(p->mm);
		return 0;
	}
out:
	task_rq_unlock(rq, &flags);

	return ret;
}
EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);

/*
 * Move (not current) task off this cpu, onto dest cpu. We're doing
 * this because either it can't run here any more (set_cpus_allowed()
 * away from this CPU, or CPU going down), or because we're
 * attempting to rebalance this task on exec (sched_exec).
 *
 * So we race with normal scheduler movements, but that's OK, as long
 * as the task is no longer on this CPU.
 *
 * Returns non-zero if task was successfully migrated.
 */
static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
{
	struct rq *rq_dest, *rq_src;
	int ret = 0, on_rq;

	if (unlikely(!cpu_active(dest_cpu)))
		return ret;

	rq_src = cpu_rq(src_cpu);
	rq_dest = cpu_rq(dest_cpu);

	double_rq_lock(rq_src, rq_dest);
	/* Already moved. */
	if (task_cpu(p) != src_cpu)
		goto done;
	/* Affinity changed (again). */
	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
		goto fail;

	on_rq = p->se.on_rq;
	if (on_rq)
		deactivate_task(rq_src, p, 0);

	set_task_cpu(p, dest_cpu);
	if (on_rq) {
		activate_task(rq_dest, p, 0);
		check_preempt_curr(rq_dest, p, 0);
	}
done:
	ret = 1;
fail:
	double_rq_unlock(rq_src, rq_dest);
	return ret;
}

/*
 * migration_thread - this is a highprio system thread that performs
 * thread migration by bumping thread off CPU then 'pushing' onto
 * another runqueue.
 */
static int migration_thread(void *data)
{
	int cpu = (long)data;
	struct rq *rq;

	rq = cpu_rq(cpu);
	BUG_ON(rq->migration_thread != current);

	set_current_state(TASK_INTERRUPTIBLE);
	while (!kthread_should_stop()) {
		struct migration_req *req;
		struct list_head *head;

		spin_lock_irq(&rq->lock);

		if (cpu_is_offline(cpu)) {
			spin_unlock_irq(&rq->lock);
			break;
		}

		if (rq->active_balance) {
			active_load_balance(rq, cpu);
			rq->active_balance = 0;
		}

		head = &rq->migration_queue;

		if (list_empty(head)) {
			spin_unlock_irq(&rq->lock);
			schedule();
			set_current_state(TASK_INTERRUPTIBLE);
			continue;
		}
		req = list_entry(head->next, struct migration_req, list);
		list_del_init(head->next);

		spin_unlock(&rq->lock);
		__migrate_task(req->task, cpu, req->dest_cpu);
		local_irq_enable();

		complete(&req->done);
	}
	__set_current_state(TASK_RUNNING);

	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU

static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu)
{
	int ret;

	local_irq_disable();
	ret = __migrate_task(p, src_cpu, dest_cpu);
	local_irq_enable();
	return ret;
}

/*
 * Figure out where task on dead CPU should go, use force if necessary.
 */
static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
{
	int dest_cpu;
	const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu));

again:
	/* Look for allowed, online CPU in same node. */
	for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask)
		if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
			goto move;

	/* Any allowed, online CPU? */
	dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask);
	if (dest_cpu < nr_cpu_ids)
		goto move;

	/* No more Mr. Nice Guy. */
	if (dest_cpu >= nr_cpu_ids) {
		cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
		dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed);

		/*
		 * Don't tell them about moving exiting tasks or
		 * kernel threads (both mm NULL), since they never
		 * leave kernel.
		 */
		if (p->mm && printk_ratelimit()) {
			printk(KERN_INFO "process %d (%s) no "
			       "longer affine to cpu%d\n",
			       task_pid_nr(p), p->comm, dead_cpu);
		}
	}

move:
	/* It can have affinity changed while we were choosing. */
	if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
		goto again;
}

/*
 * While a dead CPU has no uninterruptible tasks queued at this point,
 * it might still have a nonzero ->nr_uninterruptible counter, because
 * for performance reasons the counter is not stricly tracking tasks to
 * their home CPUs. So we just add the counter to another CPU's counter,
 * to keep the global sum constant after CPU-down:
 */
static void migrate_nr_uninterruptible(struct rq *rq_src)
{
	struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask));
	unsigned long flags;

	local_irq_save(flags);
	double_rq_lock(rq_src, rq_dest);
	rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
	rq_src->nr_uninterruptible = 0;
	double_rq_unlock(rq_src, rq_dest);
	local_irq_restore(flags);
}

/* Run through task list and migrate tasks from the dead cpu. */
static void migrate_live_tasks(int src_cpu)
{
	struct task_struct *p, *t;

	read_lock(&tasklist_lock);

	do_each_thread(t, p) {
		if (p == current)
			continue;

		if (task_cpu(p) == src_cpu)
			move_task_off_dead_cpu(src_cpu, p);
	} while_each_thread(t, p);

	read_unlock(&tasklist_lock);
}

/*
 * Schedules idle task to be the next runnable task on current CPU.
 * It does so by boosting its priority to highest possible.
 * Used by CPU offline code.
 */
void sched_idle_next(void)
{
	int this_cpu = smp_processor_id();
	struct rq *rq = cpu_rq(this_cpu);
	struct task_struct *p = rq->idle;
	unsigned long flags;

	/* cpu has to be offline */
	BUG_ON(cpu_online(this_cpu));

	/*
	 * Strictly not necessary since rest of the CPUs are stopped by now
	 * and interrupts disabled on the current cpu.
	 */
	spin_lock_irqsave(&rq->lock, flags);

	__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);

	update_rq_clock(rq);
	activate_task(rq, p, 0);

	spin_unlock_irqrestore(&rq->lock, flags);
}

/*
 * Ensures that the idle task is using init_mm right before its cpu goes
 * offline.
 */
void idle_task_exit(void)
{
	struct mm_struct *mm = current->active_mm;

	BUG_ON(cpu_online(smp_processor_id()));

	if (mm != &init_mm)
		switch_mm(mm, &init_mm, current);
	mmdrop(mm);
}

/* called under rq->lock with disabled interrupts */
static void migrate_dead(unsigned int dead_cpu, struct task_struct *p)
{
	struct rq *rq = cpu_rq(dead_cpu);

	/* Must be exiting, otherwise would be on tasklist. */
	BUG_ON(!p->exit_state);

	/* Cannot have done final schedule yet: would have vanished. */
	BUG_ON(p->state == TASK_DEAD);

	get_task_struct(p);

	/*
	 * Drop lock around migration; if someone else moves it,
	 * that's OK. No task can be added to this CPU, so iteration is
	 * fine.
	 */
	spin_unlock_irq(&rq->lock);
	move_task_off_dead_cpu(dead_cpu, p);
	spin_lock_irq(&rq->lock);

	put_task_struct(p);
}

/* release_task() removes task from tasklist, so we won't find dead tasks. */
static void migrate_dead_tasks(unsigned int dead_cpu)
{
	struct rq *rq = cpu_rq(dead_cpu);
	struct task_struct *next;

	for ( ; ; ) {
		if (!rq->nr_running)
			break;
		update_rq_clock(rq);
		next = pick_next_task(rq);
		if (!next)
			break;
		next->sched_class->put_prev_task(rq, next);
		migrate_dead(dead_cpu, next);

	}
}

/*
 * remove the tasks which were accounted by rq from calc_load_tasks.
 */
static void calc_global_load_remove(struct rq *rq)
{
	atomic_long_sub(rq->calc_load_active, &calc_load_tasks);
}
#endif /* CONFIG_HOTPLUG_CPU */

#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)

static struct ctl_table sd_ctl_dir[] = {
	{
		.procname	= "sched_domain",
		.mode		= 0555,
	},
	{0, },
};

static struct ctl_table sd_ctl_root[] = {
	{
		.ctl_name	= CTL_KERN,
		.procname	= "kernel",
		.mode		= 0555,
		.child		= sd_ctl_dir,
	},
	{0, },
};

static struct ctl_table *sd_alloc_ctl_entry(int n)
{
	struct ctl_table *entry =
		kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);

	return entry;
}

static void sd_free_ctl_entry(struct ctl_table **tablep)
{
	struct ctl_table *entry;

	/*
	 * In the intermediate directories, both the child directory and
	 * procname are dynamically allocated and could fail but the mode
	 * will always be set. In the lowest directory the names are
	 * static strings and all have proc handlers.
	 */
	for (entry = *tablep; entry->mode; entry++) {
		if (entry->child)
			sd_free_ctl_entry(&entry->child);
		if (entry->proc_handler == NULL)
			kfree(entry->procname);
	}

	kfree(*tablep);
	*tablep = NULL;
}

static void
set_table_entry(struct ctl_table *entry,
		const char *procname, void *data, int maxlen,
		mode_t mode, proc_handler *proc_handler)
{
	entry->procname = procname;
	entry->data = data;
	entry->maxlen = maxlen;
	entry->mode = mode;
	entry->proc_handler = proc_handler;
}

static struct ctl_table *
sd_alloc_ctl_domain_table(struct sched_domain *sd)
{
	struct ctl_table *table = sd_alloc_ctl_entry(13);

	if (table == NULL)
		return NULL;

	set_table_entry(&table[0], "min_interval", &sd->min_interval,
		sizeof(long), 0644, proc_doulongvec_minmax);
	set_table_entry(&table[1], "max_interval", &sd->max_interval,
		sizeof(long), 0644, proc_doulongvec_minmax);
	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
		sizeof(int), 0644, proc_dointvec_minmax);
	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
		sizeof(int), 0644, proc_dointvec_minmax);
	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
		sizeof(int), 0644, proc_dointvec_minmax);
	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
		sizeof(int), 0644, proc_dointvec_minmax);
	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
		sizeof(int), 0644, proc_dointvec_minmax);
	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
		sizeof(int), 0644, proc_dointvec_minmax);
	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
		sizeof(int), 0644, proc_dointvec_minmax);
	set_table_entry(&table[9], "cache_nice_tries",
		&sd->cache_nice_tries,
		sizeof(int), 0644, proc_dointvec_minmax);
	set_table_entry(&table[10], "flags", &sd->flags,
		sizeof(int), 0644, proc_dointvec_minmax);
	set_table_entry(&table[11], "name", sd->name,
		CORENAME_MAX_SIZE, 0444, proc_dostring);
	/* &table[12] is terminator */

	return table;
}

static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
{
	struct ctl_table *entry, *table;
	struct sched_domain *sd;
	int domain_num = 0, i;
	char buf[32];

	for_each_domain(cpu, sd)
		domain_num++;
	entry = table = sd_alloc_ctl_entry(domain_num + 1);
	if (table == NULL)
		return NULL;

	i = 0;
	for_each_domain(cpu, sd) {
		snprintf(buf, 32, "domain%d", i);
		entry->procname = kstrdup(buf, GFP_KERNEL);
		entry->mode = 0555;
		entry->child = sd_alloc_ctl_domain_table(sd);
		entry++;
		i++;
	}
	return table;
}

static struct ctl_table_header *sd_sysctl_header;
static void register_sched_domain_sysctl(void)
{
	int i, cpu_num = num_online_cpus();
	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
	char buf[32];

	WARN_ON(sd_ctl_dir[0].child);
	sd_ctl_dir[0].child = entry;

	if (entry == NULL)
		return;

	for_each_online_cpu(i) {
		snprintf(buf, 32, "cpu%d", i);
		entry->procname = kstrdup(buf, GFP_KERNEL);
		entry->mode = 0555;
		entry->child = sd_alloc_ctl_cpu_table(i);
		entry++;
	}

	WARN_ON(sd_sysctl_header);
	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
}

/* may be called multiple times per register */
static void unregister_sched_domain_sysctl(void)
{
	if (sd_sysctl_header)
		unregister_sysctl_table(sd_sysctl_header);
	sd_sysctl_header = NULL;
	if (sd_ctl_dir[0].child)
		sd_free_ctl_entry(&sd_ctl_dir[0].child);
}
#else
static void register_sched_domain_sysctl(void)
{
}
static void unregister_sched_domain_sysctl(void)
{
}
#endif

static void set_rq_online(struct rq *rq)
{
	if (!rq->online) {
		const struct sched_class *class;

		cpumask_set_cpu(rq->cpu, rq->rd->online);
		rq->online = 1;

		for_each_class(class) {
			if (class->rq_online)
				class->rq_online(rq);
		}
	}
}

static void set_rq_offline(struct rq *rq)
{
	if (rq->online) {
		const struct sched_class *class;

		for_each_class(class) {
			if (class->rq_offline)
				class->rq_offline(rq);
		}

		cpumask_clear_cpu(rq->cpu, rq->rd->online);
		rq->online = 0;
	}
}

/*
 * migration_call - callback that gets triggered when a CPU is added.
 * Here we can start up the necessary migration thread for the new CPU.
 */
static int __cpuinit
migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
{
	struct task_struct *p;
	int cpu = (long)hcpu;
	unsigned long flags;
	struct rq *rq;

	switch (action) {

	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		p = kthread_create(migration_thread, hcpu, "migration/%d", cpu);
		if (IS_ERR(p))
			return NOTIFY_BAD;
		kthread_bind(p, cpu);
		/* Must be high prio: stop_machine expects to yield to it. */
		rq = task_rq_lock(p, &flags);
		__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
		task_rq_unlock(rq, &flags);
		get_task_struct(p);
		cpu_rq(cpu)->migration_thread = p;
		break;

	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		/* Strictly unnecessary, as first user will wake it. */
		wake_up_process(cpu_rq(cpu)->migration_thread);

		/* Update our root-domain */
		rq = cpu_rq(cpu);
		spin_lock_irqsave(&rq->lock, flags);
		rq->calc_load_update = calc_load_update;
		rq->calc_load_active = 0;
		if (rq->rd) {
			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));

			set_rq_online(rq);
		}
		spin_unlock_irqrestore(&rq->lock, flags);
		break;

#ifdef CONFIG_HOTPLUG_CPU
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
		if (!cpu_rq(cpu)->migration_thread)
			break;
		/* Unbind it from offline cpu so it can run. Fall thru. */
		kthread_bind(cpu_rq(cpu)->migration_thread,
			     cpumask_any(cpu_online_mask));
		kthread_stop(cpu_rq(cpu)->migration_thread);
		put_task_struct(cpu_rq(cpu)->migration_thread);
		cpu_rq(cpu)->migration_thread = NULL;
		break;

	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */
		migrate_live_tasks(cpu);
		rq = cpu_rq(cpu);
		kthread_stop(rq->migration_thread);
		put_task_struct(rq->migration_thread);
		rq->migration_thread = NULL;
		/* Idle task back to normal (off runqueue, low prio) */
		spin_lock_irq(&rq->lock);
		update_rq_clock(rq);
		deactivate_task(rq, rq->idle, 0);
		rq->idle->static_prio = MAX_PRIO;
		__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
		rq->idle->sched_class = &idle_sched_class;
		migrate_dead_tasks(cpu);
		spin_unlock_irq(&rq->lock);
		cpuset_unlock();
		migrate_nr_uninterruptible(rq);
		BUG_ON(rq->nr_running != 0);
		calc_global_load_remove(rq);
		/*
		 * No need to migrate the tasks: it was best-effort if
		 * they didn't take sched_hotcpu_mutex. Just wake up
		 * the requestors.
		 */
		spin_lock_irq(&rq->lock);
		while (!list_empty(&rq->migration_queue)) {
			struct migration_req *req;

			req = list_entry(rq->migration_queue.next,
					 struct migration_req, list);
			list_del_init(&req->list);
			spin_unlock_irq(&rq->lock);
			complete(&req->done);
			spin_lock_irq(&rq->lock);
		}
		spin_unlock_irq(&rq->lock);
		break;

	case CPU_DYING:
	case CPU_DYING_FROZEN:
		/* Update our root-domain */
		rq = cpu_rq(cpu);
		spin_lock_irqsave(&rq->lock, flags);
		if (rq->rd) {
			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
			set_rq_offline(rq);
		}
		spin_unlock_irqrestore(&rq->lock, flags);
		break;
#endif
	}
	return NOTIFY_OK;
}

/*
 * Register at high priority so that task migration (migrate_all_tasks)
 * happens before everything else.  This has to be lower priority than
 * the notifier in the perf_counter subsystem, though.
 */
static struct notifier_block __cpuinitdata migration_notifier = {
	.notifier_call = migration_call,
	.priority = 10
};

static int __init migration_init(void)
{
	void *cpu = (void *)(long)smp_processor_id();
	int err;

	/* Start one for the boot CPU: */
	err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
	BUG_ON(err == NOTIFY_BAD);
	migration_call(&migration_notifier, CPU_ONLINE, cpu);
	register_cpu_notifier(&migration_notifier);

	return err;
}
early_initcall(migration_init);
#endif

#ifdef CONFIG_SMP

#ifdef CONFIG_SCHED_DEBUG

static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
				  struct cpumask *groupmask)
{
	struct sched_group *group = sd->groups;
	char str[256];

	cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
	cpumask_clear(groupmask);

	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);

	if (!(sd->flags & SD_LOAD_BALANCE)) {
		printk("does not load-balance\n");
		if (sd->parent)
			printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
					" has parent");
		return -1;
	}

	printk(KERN_CONT "span %s level %s\n", str, sd->name);

	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
		printk(KERN_ERR "ERROR: domain->span does not contain "
				"CPU%d\n", cpu);
	}
	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
		printk(KERN_ERR "ERROR: domain->groups does not contain"
				" CPU%d\n", cpu);
	}

	printk(KERN_DEBUG "%*s groups:", level + 1, "");
	do {
		if (!group) {
			printk("\n");
			printk(KERN_ERR "ERROR: group is NULL\n");
			break;
		}

		if (!group->__cpu_power) {
			printk(KERN_CONT "\n");
			printk(KERN_ERR "ERROR: domain->cpu_power not "
					"set\n");
			break;
		}

		if (!cpumask_weight(sched_group_cpus(group))) {
			printk(KERN_CONT "\n");
			printk(KERN_ERR "ERROR: empty group\n");
			break;
		}

		if (cpumask_intersects(groupmask, sched_group_cpus(group))) {
			printk(KERN_CONT "\n");
			printk(KERN_ERR "ERROR: repeated CPUs\n");
			break;
		}

		cpumask_or(groupmask, groupmask, sched_group_cpus(group));

		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));

		printk(KERN_CONT " %s", str);
		if (group->__cpu_power != SCHED_LOAD_SCALE) {
			printk(KERN_CONT " (__cpu_power = %d)",
				group->__cpu_power);
		}

		group = group->next;
	} while (group != sd->groups);
	printk(KERN_CONT "\n");

	if (!cpumask_equal(sched_domain_span(sd), groupmask))
		printk(KERN_ERR "ERROR: groups don't span domain->span\n");

	if (sd->parent &&
	    !cpumask_subset(groupmask, sched_domain_span(sd->parent)))
		printk(KERN_ERR "ERROR: parent span is not a superset "
			"of domain->span\n");
	return 0;
}

static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
	cpumask_var_t groupmask;
	int level = 0;

	if (!sd) {
		printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
		return;
	}

	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);

	if (!alloc_cpumask_var(&groupmask, GFP_KERNEL)) {
		printk(KERN_DEBUG "Cannot load-balance (out of memory)\n");
		return;
	}

	for (;;) {
		if (sched_domain_debug_one(sd, cpu, level, groupmask))
			break;
		level++;
		sd = sd->parent;
		if (!sd)
			break;
	}
	free_cpumask_var(groupmask);
}
#else /* !CONFIG_SCHED_DEBUG */
# define sched_domain_debug(sd, cpu) do { } while (0)
#endif /* CONFIG_SCHED_DEBUG */

static int sd_degenerate(struct sched_domain *sd)
{
	if (cpumask_weight(sched_domain_span(sd)) == 1)
		return 1;

	/* Following flags need at least 2 groups */
	if (sd->flags & (SD_LOAD_BALANCE |
			 SD_BALANCE_NEWIDLE |
			 SD_BALANCE_FORK |
			 SD_BALANCE_EXEC |
			 SD_SHARE_CPUPOWER |
			 SD_SHARE_PKG_RESOURCES)) {
		if (sd->groups != sd->groups->next)
			return 0;
	}

	/* Following flags don't use groups */
	if (sd->flags & (SD_WAKE_IDLE |
			 SD_WAKE_AFFINE |
			 SD_WAKE_BALANCE))
		return 0;

	return 1;
}

static int
sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
{
	unsigned long cflags = sd->flags, pflags = parent->flags;

	if (sd_degenerate(parent))
		return 1;

	if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
		return 0;

	/* Does parent contain flags not in child? */
	/* WAKE_BALANCE is a subset of WAKE_AFFINE */
	if (cflags & SD_WAKE_AFFINE)
		pflags &= ~SD_WAKE_BALANCE;
	/* Flags needing groups don't count if only 1 group in parent */
	if (parent->groups == parent->groups->next) {
		pflags &= ~(SD_LOAD_BALANCE |
				SD_BALANCE_NEWIDLE |
				SD_BALANCE_FORK |
				SD_BALANCE_EXEC |
				SD_SHARE_CPUPOWER |
				SD_SHARE_PKG_RESOURCES);
		if (nr_node_ids == 1)
			pflags &= ~SD_SERIALIZE;
	}
	if (~cflags & pflags)
		return 0;

	return 1;
}

static void free_rootdomain(struct root_domain *rd)
{
	cpupri_cleanup(&rd->cpupri);

	free_cpumask_var(rd->rto_mask);
	free_cpumask_var(rd->online);
	free_cpumask_var(rd->span);
	kfree(rd);
}

static void rq_attach_root(struct rq *rq, struct root_domain *rd)
{
	struct root_domain *old_rd = NULL;
	unsigned long flags;

	spin_lock_irqsave(&rq->lock, flags);

	if (rq->rd) {
		old_rd = rq->rd;

		if (cpumask_test_cpu(rq->cpu, old_rd->online))
			set_rq_offline(rq);

		cpumask_clear_cpu(rq->cpu, old_rd->span);

		/*
		 * If we dont want to free the old_rt yet then
		 * set old_rd to NULL to skip the freeing later
		 * in this function:
		 */
		if (!atomic_dec_and_test(&old_rd->refcount))
			old_rd = NULL;
	}

	atomic_inc(&rd->refcount);
	rq->rd = rd;

	cpumask_set_cpu(rq->cpu, rd->span);
	if (cpumask_test_cpu(rq->cpu, cpu_online_mask))
		set_rq_online(rq);

	spin_unlock_irqrestore(&rq->lock, flags);

	if (old_rd)
		free_rootdomain(old_rd);
}

static int init_rootdomain(struct root_domain *rd, bool bootmem)
{
	gfp_t gfp = GFP_KERNEL;

	memset(rd, 0, sizeof(*rd));

	if (bootmem)
		gfp = GFP_NOWAIT;

	if (!alloc_cpumask_var(&rd->span, gfp))
		goto out;
	if (!alloc_cpumask_var(&rd->online, gfp))
		goto free_span;
	if (!alloc_cpumask_var(&rd->rto_mask, gfp))
		goto free_online;

	if (cpupri_init(&rd->cpupri, bootmem) != 0)
		goto free_rto_mask;
	return 0;

free_rto_mask:
	free_cpumask_var(rd->rto_mask);
free_online:
	free_cpumask_var(rd->online);
free_span:
	free_cpumask_var(rd->span);
out:
	return -ENOMEM;
}

static void init_defrootdomain(void)
{
	init_rootdomain(&def_root_domain, true);

	atomic_set(&def_root_domain.refcount, 1);
}

static struct root_domain *alloc_rootdomain(void)
{
	struct root_domain *rd;

	rd = kmalloc(sizeof(*rd), GFP_KERNEL);
	if (!rd)
		return NULL;

	if (init_rootdomain(rd, false) != 0) {
		kfree(rd);
		return NULL;
	}

	return rd;
}

/*
 * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
 * hold the hotplug lock.
 */
static void
cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
{
	struct rq *rq = cpu_rq(cpu);
	struct sched_domain *tmp;

	/* Remove the sched domains which do not contribute to scheduling. */
	for (tmp = sd; tmp; ) {
		struct sched_domain *parent = tmp->parent;
		if (!parent)
			break;

		if (sd_parent_degenerate(tmp, parent)) {
			tmp->parent = parent->parent;
			if (parent->parent)
				parent->parent->child = tmp;
		} else
			tmp = tmp->parent;
	}

	if (sd && sd_degenerate(sd)) {
		sd = sd->parent;
		if (sd)
			sd->child = NULL;
	}

	sched_domain_debug(sd, cpu);

	rq_attach_root(rq, rd);
	rcu_assign_pointer(rq->sd, sd);
}

/* cpus with isolated domains */
static cpumask_var_t cpu_isolated_map;

/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
	cpulist_parse(str, cpu_isolated_map);
	return 1;
}

__setup("isolcpus=", isolated_cpu_setup);

/*
 * init_sched_build_groups takes the cpumask we wish to span, and a pointer
 * to a function which identifies what group(along with sched group) a CPU
 * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
 * (due to the fact that we keep track of groups covered with a struct cpumask).
 *
 * init_sched_build_groups will build a circular linked list of the groups
 * covered by the given span, and will set each group's ->cpumask correctly,
 * and ->cpu_power to 0.
 */
static void
init_sched_build_groups(const struct cpumask *span,
			const struct cpumask *cpu_map,
			int (*group_fn)(int cpu, const struct cpumask *cpu_map,
					struct sched_group **sg,
					struct cpumask *tmpmask),
			struct cpumask *covered, struct cpumask *tmpmask)
{
	struct sched_group *first = NULL, *last = NULL;
	int i;

	cpumask_clear(covered);

	for_each_cpu(i, span) {
		struct sched_group *sg;
		int group = group_fn(i, cpu_map, &sg, tmpmask);
		int j;

		if (cpumask_test_cpu(i, covered))
			continue;

		cpumask_clear(sched_group_cpus(sg));
		sg->__cpu_power = 0;

		for_each_cpu(j, span) {
			if (group_fn(j, cpu_map, NULL, tmpmask) != group)
				continue;

			cpumask_set_cpu(j, covered);
			cpumask_set_cpu(j, sched_group_cpus(sg));
		}
		if (!first)
			first = sg;
		if (last)
			last->next = sg;
		last = sg;
	}
	last->next = first;
}

#define SD_NODES_PER_DOMAIN 16

#ifdef CONFIG_NUMA

/**
 * find_next_best_node - find the next node to include in a sched_domain
 * @node: node whose sched_domain we're building
 * @used_nodes: nodes already in the sched_domain
 *
 * Find the next node to include in a given scheduling domain. Simply
 * finds the closest node not already in the @used_nodes map.
 *
 * Should use nodemask_t.
 */
static int find_next_best_node(int node, nodemask_t *used_nodes)
{
	int i, n, val, min_val, best_node = 0;

	min_val = INT_MAX;

	for (i = 0; i < nr_node_ids; i++) {
		/* Start at @node */
		n = (node + i) % nr_node_ids;

		if (!nr_cpus_node(n))
			continue;

		/* Skip already used nodes */
		if (node_isset(n, *used_nodes))
			continue;

		/* Simple min distance search */
		val = node_distance(node, n);

		if (val < min_val) {
			min_val = val;
			best_node = n;
		}
	}

	node_set(best_node, *used_nodes);
	return best_node;
}

/**
 * sched_domain_node_span - get a cpumask for a node's sched_domain
 * @node: node whose cpumask we're constructing
 * @span: resulting cpumask
 *
 * Given a node, construct a good cpumask for its sched_domain to span. It
 * should be one that prevents unnecessary balancing, but also spreads tasks
 * out optimally.
 */
static void sched_domain_node_span(int node, struct cpumask *span)
{
	nodemask_t used_nodes;
	int i;

	cpumask_clear(span);
	nodes_clear(used_nodes);

	cpumask_or(span, span, cpumask_of_node(node));
	node_set(node, used_nodes);

	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
		int next_node = find_next_best_node(node, &used_nodes);

		cpumask_or(span, span, cpumask_of_node(next_node));
	}
}
#endif /* CONFIG_NUMA */

int sched_smt_power_savings = 0, sched_mc_power_savings = 0;

/*
 * The cpus mask in sched_group and sched_domain hangs off the end.
 *
 * ( See the the comments in include/linux/sched.h:struct sched_group
 *   and struct sched_domain. )
 */
struct static_sched_group {
	struct sched_group sg;
	DECLARE_BITMAP(cpus, CONFIG_NR_CPUS);
};

struct static_sched_domain {
	struct sched_domain sd;
	DECLARE_BITMAP(span, CONFIG_NR_CPUS);
};

/*
 * SMT sched-domains:
 */
#ifdef CONFIG_SCHED_SMT
static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);

static int
cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
		 struct sched_group **sg, struct cpumask *unused)
{
	if (sg)
		*sg = &per_cpu(sched_group_cpus, cpu).sg;
	return cpu;
}
#endif /* CONFIG_SCHED_SMT */

/*
 * multi-core sched-domains:
 */
#ifdef CONFIG_SCHED_MC
static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
#endif /* CONFIG_SCHED_MC */

#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
static int
cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
		  struct sched_group **sg, struct cpumask *mask)
{
	int group;

	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
	group = cpumask_first(mask);
	if (sg)
		*sg = &per_cpu(sched_group_core, group).sg;
	return group;
}
#elif defined(CONFIG_SCHED_MC)
static int
cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
		  struct sched_group **sg, struct cpumask *unused)
{
	if (sg)
		*sg = &per_cpu(sched_group_core, cpu).sg;
	return cpu;
}
#endif

static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);

static int
cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
		  struct sched_group **sg, struct cpumask *mask)
{
	int group;
#ifdef CONFIG_SCHED_MC
	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
	group = cpumask_first(mask);
#elif defined(CONFIG_SCHED_SMT)
	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
	group = cpumask_first(mask);
#else
	group = cpu;
#endif
	if (sg)
		*sg = &per_cpu(sched_group_phys, group).sg;
	return group;
}

#ifdef CONFIG_NUMA
/*
 * The init_sched_build_groups can't handle what we want to do with node
 * groups, so roll our own. Now each node has its own list of groups which
 * gets dynamically allocated.
 */
static DEFINE_PER_CPU(struct static_sched_domain, node_domains);
static struct sched_group ***sched_group_nodes_bycpu;

static DEFINE_PER_CPU(struct static_sched_domain, allnodes_domains);
static DEFINE_PER_CPU(struct static_sched_group, sched_group_allnodes);

static int cpu_to_allnodes_group(int cpu, const struct cpumask *cpu_map,
				 struct sched_group **sg,
				 struct cpumask *nodemask)
{
	int group;

	cpumask_and(nodemask, cpumask_of_node(cpu_to_node(cpu)), cpu_map);
	group = cpumask_first(nodemask);

	if (sg)
		*sg = &per_cpu(sched_group_allnodes, group).sg;
	return group;
}

static void init_numa_sched_groups_power(struct sched_group *group_head)
{
	struct sched_group *sg = group_head;
	int j;

	if (!sg)
		return;
	do {
		for_each_cpu(j, sched_group_cpus(sg)) {
			struct sched_domain *sd;

			sd = &per_cpu(phys_domains, j).sd;
			if (j != group_first_cpu(sd->groups)) {
				/*
				 * Only add "power" once for each
				 * physical package.
				 */
				continue;
			}

			sg_inc_cpu_power(sg, sd->groups->__cpu_power);
		}
		sg = sg->next;
	} while (sg != group_head);
}
#endif /* CONFIG_NUMA */

#ifdef CONFIG_NUMA
/* Free memory allocated for various sched_group structures */
static void free_sched_groups(const struct cpumask *cpu_map,
			      struct cpumask *nodemask)
{
	int cpu, i;

	for_each_cpu(cpu, cpu_map) {
		struct sched_group **sched_group_nodes
			= sched_group_nodes_bycpu[cpu];

		if (!sched_group_nodes)
			continue;

		for (i = 0; i < nr_node_ids; i++) {
			struct sched_group *oldsg, *sg = sched_group_nodes[i];

			cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
			if (cpumask_empty(nodemask))
				continue;

			if (sg == NULL)
				continue;
			sg = sg->next;
next_sg:
			oldsg = sg;
			sg = sg->next;
			kfree(oldsg);
			if (oldsg != sched_group_nodes[i])
				goto next_sg;
		}
		kfree(sched_group_nodes);
		sched_group_nodes_bycpu[cpu] = NULL;
	}
}
#else /* !CONFIG_NUMA */
static void free_sched_groups(const struct cpumask *cpu_map,
			      struct cpumask *nodemask)
{
}
#endif /* CONFIG_NUMA */

/*
 * Initialize sched groups cpu_power.
 *
 * cpu_power indicates the capacity of sched group, which is used while
 * distributing the load between different sched groups in a sched domain.
 * Typically cpu_power for all the groups in a sched domain will be same unless
 * there are asymmetries in the topology. If there are asymmetries, group
 * having more cpu_power will pickup more load compared to the group having
 * less cpu_power.
 *
 * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents
 * the maximum number of tasks a group can handle in the presence of other idle
 * or lightly loaded groups in the same sched domain.
 */
static void init_sched_groups_power(int cpu, struct sched_domain *sd)
{
	struct sched_domain *child;
	struct sched_group *group;

	WARN_ON(!sd || !sd->groups);

	if (cpu != group_first_cpu(sd->groups))
		return;

	child = sd->child;

	sd->groups->__cpu_power = 0;

	/*
	 * For perf policy, if the groups in child domain share resources
	 * (for example cores sharing some portions of the cache hierarchy
	 * or SMT), then set this domain groups cpu_power such that each group
	 * can handle only one task, when there are other idle groups in the
	 * same sched domain.
	 */
	if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) &&
		       (child->flags &
			(SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) {
		sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE);
		return;
	}

	/*
	 * add cpu_power of each child group to this groups cpu_power
	 */
	group = child->groups;
	do {
		sg_inc_cpu_power(sd->groups, group->__cpu_power);
		group = group->next;
	} while (group != child->groups);
}

/*
 * Initializers for schedule domains
 * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
 */

#ifdef CONFIG_SCHED_DEBUG
# define SD_INIT_NAME(sd, type)		sd->name = #type
#else
# define SD_INIT_NAME(sd, type)		do { } while (0)
#endif

#define	SD_INIT(sd, type)	sd_init_##type(sd)

#define SD_INIT_FUNC(type)	\
static noinline void sd_init_##type(struct sched_domain *sd)	\
{								\
	memset(sd, 0, sizeof(*sd));				\
	*sd = SD_##type##_INIT;					\
	sd->level = SD_LV_##type;				\
	SD_INIT_NAME(sd, type);					\
}

SD_INIT_FUNC(CPU)
#ifdef CONFIG_NUMA
 SD_INIT_FUNC(ALLNODES)
 SD_INIT_FUNC(NODE)
#endif
#ifdef CONFIG_SCHED_SMT
 SD_INIT_FUNC(SIBLING)
#endif
#ifdef CONFIG_SCHED_MC
 SD_INIT_FUNC(MC)
#endif

static int default_relax_domain_level = -1;

static int __init setup_relax_domain_level(char *str)
{
	unsigned long val;

	val = simple_strtoul(str, NULL, 0);
	if (val < SD_LV_MAX)
		default_relax_domain_level = val;

	return 1;
}
__setup("relax_domain_level=", setup_relax_domain_level);

static void set_domain_attribute(struct sched_domain *sd,
				 struct sched_domain_attr *attr)
{
	int request;

	if (!attr || attr->relax_domain_level < 0) {
		if (default_relax_domain_level < 0)
			return;
		else
			request = default_relax_domain_level;
	} else
		request = attr->relax_domain_level;
	if (request < sd->level) {
		/* turn off idle balance on this domain */
		sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE);
	} else {
		/* turn on idle balance on this domain */
		sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE);
	}
}

/*
 * Build sched domains for a given set of cpus and attach the sched domains
 * to the individual cpus
 */
static int __build_sched_domains(const struct cpumask *cpu_map,
				 struct sched_domain_attr *attr)
{
	int i, err = -ENOMEM;
	struct root_domain *rd;
	cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered,
		tmpmask;
#ifdef CONFIG_NUMA
	cpumask_var_t domainspan, covered, notcovered;
	struct sched_group **sched_group_nodes = NULL;
	int sd_allnodes = 0;

	if (!alloc_cpumask_var(&domainspan, GFP_KERNEL))
		goto out;
	if (!alloc_cpumask_var(&covered, GFP_KERNEL))
		goto free_domainspan;
	if (!alloc_cpumask_var(&notcovered, GFP_KERNEL))
		goto free_covered;
#endif

	if (!alloc_cpumask_var(&nodemask, GFP_KERNEL))
		goto free_notcovered;
	if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL))
		goto free_nodemask;
	if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL))
		goto free_this_sibling_map;
	if (!alloc_cpumask_var(&send_covered, GFP_KERNEL))
		goto free_this_core_map;
	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
		goto free_send_covered;

#ifdef CONFIG_NUMA
	/*
	 * Allocate the per-node list of sched groups
	 */
	sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *),
				    GFP_KERNEL);
	if (!sched_group_nodes) {
		printk(KERN_WARNING "Can not alloc sched group node list\n");
		goto free_tmpmask;
	}
#endif

	rd = alloc_rootdomain();
	if (!rd) {
		printk(KERN_WARNING "Cannot alloc root domain\n");
		goto free_sched_groups;
	}

#ifdef CONFIG_NUMA
	sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes;
#endif

	/*
	 * Set up domains for cpus specified by the cpu_map.
	 */
	for_each_cpu(i, cpu_map) {
		struct sched_domain *sd = NULL, *p;

		cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);

#ifdef CONFIG_NUMA
		if (cpumask_weight(cpu_map) >
				SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) {
			sd = &per_cpu(allnodes_domains, i).sd;
			SD_INIT(sd, ALLNODES);
			set_domain_attribute(sd, attr);
			cpumask_copy(sched_domain_span(sd), cpu_map);
			cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
			p = sd;
			sd_allnodes = 1;
		} else
			p = NULL;

		sd = &per_cpu(node_domains, i).sd;
		SD_INIT(sd, NODE);
		set_domain_attribute(sd, attr);
		sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd));
		sd->parent = p;
		if (p)
			p->child = sd;
		cpumask_and(sched_domain_span(sd),
			    sched_domain_span(sd), cpu_map);
#endif

		p = sd;
		sd = &per_cpu(phys_domains, i).sd;
		SD_INIT(sd, CPU);
		set_domain_attribute(sd, attr);
		cpumask_copy(sched_domain_span(sd), nodemask);
		sd->parent = p;
		if (p)
			p->child = sd;
		cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask);

#ifdef CONFIG_SCHED_MC
		p = sd;
		sd = &per_cpu(core_domains, i).sd;
		SD_INIT(sd, MC);
		set_domain_attribute(sd, attr);
		cpumask_and(sched_domain_span(sd), cpu_map,
						   cpu_coregroup_mask(i));
		sd->parent = p;
		p->child = sd;
		cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
#endif

#ifdef CONFIG_SCHED_SMT
		p = sd;
		sd = &per_cpu(cpu_domains, i).sd;
		SD_INIT(sd, SIBLING);
		set_domain_attribute(sd, attr);
		cpumask_and(sched_domain_span(sd),
			    topology_thread_cpumask(i), cpu_map);
		sd->parent = p;
		p->child = sd;
		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
#endif
	}

#ifdef CONFIG_SCHED_SMT
	/* Set up CPU (sibling) groups */
	for_each_cpu(i, cpu_map) {
		cpumask_and(this_sibling_map,
			    topology_thread_cpumask(i), cpu_map);
		if (i != cpumask_first(this_sibling_map))
			continue;

		init_sched_build_groups(this_sibling_map, cpu_map,
					&cpu_to_cpu_group,
					send_covered, tmpmask);
	}
#endif

#ifdef CONFIG_SCHED_MC
	/* Set up multi-core groups */
	for_each_cpu(i, cpu_map) {
		cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map);
		if (i != cpumask_first(this_core_map))
			continue;

		init_sched_build_groups(this_core_map, cpu_map,
					&cpu_to_core_group,
					send_covered, tmpmask);
	}
#endif

	/* Set up physical groups */
	for (i = 0; i < nr_node_ids; i++) {
		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
		if (cpumask_empty(nodemask))
			continue;

		init_sched_build_groups(nodemask, cpu_map,
					&cpu_to_phys_group,
					send_covered, tmpmask);
	}

#ifdef CONFIG_NUMA
	/* Set up node groups */
	if (sd_allnodes) {
		init_sched_build_groups(cpu_map, cpu_map,
					&cpu_to_allnodes_group,
					send_covered, tmpmask);
	}

	for (i = 0; i < nr_node_ids; i++) {
		/* Set up node groups */
		struct sched_group *sg, *prev;
		int j;

		cpumask_clear(covered);
		cpumask_and(nodemask, cpumask_of_node(i), cpu_map);
		if (cpumask_empty(nodemask)) {
			sched_group_nodes[i] = NULL;
			continue;
		}

		sched_domain_node_span(i, domainspan);
		cpumask_and(domainspan, domainspan, cpu_map);

		sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(),
				  GFP_KERNEL, i);
		if (!sg) {
			printk(KERN_WARNING "Can not alloc domain group for "
				"node %d\n", i);
			goto error;
		}
		sched_group_nodes[i] = sg;
		for_each_cpu(j, nodemask) {
			struct sched_domain *sd;

			sd = &per_cpu(node_domains, j).sd;
			sd->groups = sg;
		}
		sg->__cpu_power = 0;
		cpumask_copy(sched_group_cpus(sg), nodemask);
		sg->next = sg;
		cpumask_or(covered, covered, nodemask);
		prev = sg;

		for (j = 0; j < nr_node_ids; j++) {
			int n = (i + j) % nr_node_ids;

			cpumask_complement(notcovered, covered);
			cpumask_and(tmpmask, notcovered, cpu_map);
			cpumask_and(tmpmask, tmpmask, domainspan);
			if (cpumask_empty(tmpmask))
				break;

			cpumask_and(tmpmask, tmpmask, cpumask_of_node(n));
			if (cpumask_empty(tmpmask))
				continue;

			sg = kmalloc_node(sizeof(struct sched_group) +
					  cpumask_size(),
					  GFP_KERNEL, i);
			if (!sg) {
				printk(KERN_WARNING
				"Can not alloc domain group for node %d\n", j);
				goto error;
			}
			sg->__cpu_power = 0;
			cpumask_copy(sched_group_cpus(sg), tmpmask);
			sg->next = prev->next;
			cpumask_or(covered, covered, tmpmask);
			prev->next = sg;
			prev = sg;
		}
	}
#endif

	/* Calculate CPU power for physical packages and nodes */
#ifdef CONFIG_SCHED_SMT
	for_each_cpu(i, cpu_map) {
		struct sched_domain *sd = &per_cpu(cpu_domains, i).sd;

		init_sched_groups_power(i, sd);
	}
#endif
#ifdef CONFIG_SCHED_MC
	for_each_cpu(i, cpu_map) {
		struct sched_domain *sd = &per_cpu(core_domains, i).sd;

		init_sched_groups_power(i, sd);
	}
#endif

	for_each_cpu(i, cpu_map) {
		struct sched_domain *sd = &per_cpu(phys_domains, i).sd;

		init_sched_groups_power(i, sd);
	}

#ifdef CONFIG_NUMA
	for (i = 0; i < nr_node_ids; i++)
		init_numa_sched_groups_power(sched_group_nodes[i]);

	if (sd_allnodes) {
		struct sched_group *sg;

		cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg,
								tmpmask);
		init_numa_sched_groups_power(sg);
	}
#endif

	/* Attach the domains */
	for_each_cpu(i, cpu_map) {
		struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
		sd = &per_cpu(cpu_domains, i).sd;
#elif defined(CONFIG_SCHED_MC)
		sd = &per_cpu(core_domains, i).sd;
#else
		sd = &per_cpu(phys_domains, i).sd;
#endif
		cpu_attach_domain(sd, rd, i);
	}

	err = 0;

free_tmpmask:
	free_cpumask_var(tmpmask);
free_send_covered:
	free_cpumask_var(send_covered);
free_this_core_map:
	free_cpumask_var(this_core_map);
free_this_sibling_map:
	free_cpumask_var(this_sibling_map);
free_nodemask:
	free_cpumask_var(nodemask);
free_notcovered:
#ifdef CONFIG_NUMA
	free_cpumask_var(notcovered);
free_covered:
	free_cpumask_var(covered);
free_domainspan:
	free_cpumask_var(domainspan);
out:
#endif
	return err;

free_sched_groups:
#ifdef CONFIG_NUMA
	kfree(sched_group_nodes);
#endif
	goto free_tmpmask;

#ifdef CONFIG_NUMA
error:
	free_sched_groups(cpu_map, tmpmask);
	free_rootdomain(rd);
	goto free_tmpmask;
#endif
}

static int build_sched_domains(const struct cpumask *cpu_map)
{
	return __build_sched_domains(cpu_map, NULL);
}

static struct cpumask *doms_cur;	/* current sched domains */
static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
static struct sched_domain_attr *dattr_cur;
				/* attribues of custom domains in 'doms_cur' */

/*
 * Special case: If a kmalloc of a doms_cur partition (array of
 * cpumask) fails, then fallback to a single sched domain,
 * as determined by the single cpumask fallback_doms.
 */
static cpumask_var_t fallback_doms;

/*
 * arch_update_cpu_topology lets virtualized architectures update the
 * cpu core maps. It is supposed to return 1 if the topology changed
 * or 0 if it stayed the same.
 */
int __attribute__((weak)) arch_update_cpu_topology(void)
{
	return 0;
}

/*
 * Set up scheduler domains and groups. Callers must hold the hotplug lock.
 * For now this just excludes isolated cpus, but could be used to
 * exclude other special cases in the future.
 */
static int arch_init_sched_domains(const struct cpumask *cpu_map)
{
	int err;

	arch_update_cpu_topology();
	ndoms_cur = 1;
	doms_cur = kmalloc(cpumask_size(), GFP_KERNEL);
	if (!doms_cur)
		doms_cur = fallback_doms;
	cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map);
	dattr_cur = NULL;
	err = build_sched_domains(doms_cur);
	register_sched_domain_sysctl();

	return err;
}

static void arch_destroy_sched_domains(const struct cpumask *cpu_map,
				       struct cpumask *tmpmask)
{
	free_sched_groups(cpu_map, tmpmask);
}

/*
 * Detach sched domains from a group of cpus specified in cpu_map
 * These cpus will now be attached to the NULL domain
 */
static void detach_destroy_domains(const struct cpumask *cpu_map)
{
	/* Save because hotplug lock held. */
	static DECLARE_BITMAP(tmpmask, CONFIG_NR_CPUS);
	int i;

	for_each_cpu(i, cpu_map)
		cpu_attach_domain(NULL, &def_root_domain, i);
	synchronize_sched();
	arch_destroy_sched_domains(cpu_map, to_cpumask(tmpmask));
}

/* handle null as "default" */
static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
			struct sched_domain_attr *new, int idx_new)
{
	struct sched_domain_attr tmp;

	/* fast path */
	if (!new && !cur)
		return 1;

	tmp = SD_ATTR_INIT;
	return !memcmp(cur ? (cur + idx_cur) : &tmp,
			new ? (new + idx_new) : &tmp,
			sizeof(struct sched_domain_attr));
}

/*
 * Partition sched domains as specified by the 'ndoms_new'
 * cpumasks in the array doms_new[] of cpumasks. This compares
 * doms_new[] to the current sched domain partitioning, doms_cur[].
 * It destroys each deleted domain and builds each new domain.
 *
 * 'doms_new' is an array of cpumask's of length 'ndoms_new'.
 * The masks don't intersect (don't overlap.) We should setup one
 * sched domain for each mask. CPUs not in any of the cpumasks will
 * not be load balanced. If the same cpumask appears both in the
 * current 'doms_cur' domains and in the new 'doms_new', we can leave
 * it as it is.
 *
 * The passed in 'doms_new' should be kmalloc'd. This routine takes
 * ownership of it and will kfree it when done with it. If the caller
 * failed the kmalloc call, then it can pass in doms_new == NULL &&
 * ndoms_new == 1, and partition_sched_domains() will fallback to
 * the single partition 'fallback_doms', it also forces the domains
 * to be rebuilt.
 *
 * If doms_new == NULL it will be replaced with cpu_online_mask.
 * ndoms_new == 0 is a special case for destroying existing domains,
 * and it will not create the default domain.
 *
 * Call with hotplug lock held
 */
/* FIXME: Change to struct cpumask *doms_new[] */
void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
			     struct sched_domain_attr *dattr_new)
{
	int i, j, n;
	int new_topology;

	mutex_lock(&sched_domains_mutex);

	/* always unregister in case we don't destroy any domains */
	unregister_sched_domain_sysctl();

	/* Let architecture update cpu core mappings. */
	new_topology = arch_update_cpu_topology();

	n = doms_new ? ndoms_new : 0;

	/* Destroy deleted domains */
	for (i = 0; i < ndoms_cur; i++) {
		for (j = 0; j < n && !new_topology; j++) {
			if (cpumask_equal(&doms_cur[i], &doms_new[j])
			    && dattrs_equal(dattr_cur, i, dattr_new, j))
				goto match1;
		}
		/* no match - a current sched domain not in new doms_new[] */
		detach_destroy_domains(doms_cur + i);
match1:
		;
	}

	if (doms_new == NULL) {
		ndoms_cur = 0;
		doms_new = fallback_doms;
		cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map);
		WARN_ON_ONCE(dattr_new);
	}

	/* Build new domains */
	for (i = 0; i < ndoms_new; i++) {
		for (j = 0; j < ndoms_cur && !new_topology; j++) {
			if (cpumask_equal(&doms_new[i], &doms_cur[j])
			    && dattrs_equal(dattr_new, i, dattr_cur, j))
				goto match2;
		}
		/* no match - add a new doms_new */
		__build_sched_domains(doms_new + i,
					dattr_new ? dattr_new + i : NULL);
match2:
		;
	}

	/* Remember the new sched domains */
	if (doms_cur != fallback_doms)
		kfree(doms_cur);
	kfree(dattr_cur);	/* kfree(NULL) is safe */
	doms_cur = doms_new;
	dattr_cur = dattr_new;
	ndoms_cur = ndoms_new;

	register_sched_domain_sysctl();

	mutex_unlock(&sched_domains_mutex);
}

#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
static void arch_reinit_sched_domains(void)
{
	get_online_cpus();

	/* Destroy domains first to force the rebuild */
	partition_sched_domains(0, NULL, NULL);

	rebuild_sched_domains();
	put_online_cpus();
}

static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
{
	unsigned int level = 0;

	if (sscanf(buf, "%u", &level) != 1)
		return -EINVAL;

	/*
	 * level is always be positive so don't check for
	 * level < POWERSAVINGS_BALANCE_NONE which is 0
	 * What happens on 0 or 1 byte write,
	 * need to check for count as well?
	 */

	if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS)
		return -EINVAL;

	if (smt)
		sched_smt_power_savings = level;
	else
		sched_mc_power_savings = level;

	arch_reinit_sched_domains();

	return count;
}

#ifdef CONFIG_SCHED_MC
static ssize_t sched_mc_power_savings_show(struct sysdev_class *class,
					   char *page)
{
	return sprintf(page, "%u\n", sched_mc_power_savings);
}
static ssize_t sched_mc_power_savings_store(struct sysdev_class *class,
					    const char *buf, size_t count)
{
	return sched_power_savings_store(buf, count, 0);
}
static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644,
			 sched_mc_power_savings_show,
			 sched_mc_power_savings_store);
#endif

#ifdef CONFIG_SCHED_SMT
static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev,
					    char *page)
{
	return sprintf(page, "%u\n", sched_smt_power_savings);
}
static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev,
					     const char *buf, size_t count)
{
	return sched_power_savings_store(buf, count, 1);
}
static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644,
		   sched_smt_power_savings_show,
		   sched_smt_power_savings_store);
#endif

int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls)
{
	int err = 0;

#ifdef CONFIG_SCHED_SMT
	if (smt_capable())
		err = sysfs_create_file(&cls->kset.kobj,
					&attr_sched_smt_power_savings.attr);
#endif
#ifdef CONFIG_SCHED_MC
	if (!err && mc_capable())
		err = sysfs_create_file(&cls->kset.kobj,
					&attr_sched_mc_power_savings.attr);
#endif
	return err;
}
#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */

#ifndef CONFIG_CPUSETS
/*
 * Add online and remove offline CPUs from the scheduler domains.
 * When cpusets are enabled they take over this function.
 */
static int update_sched_domains(struct notifier_block *nfb,
				unsigned long action, void *hcpu)
{
	switch (action) {
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		partition_sched_domains(1, NULL, NULL);
		return NOTIFY_OK;

	default:
		return NOTIFY_DONE;
	}
}
#endif

static int update_runtime(struct notifier_block *nfb,
				unsigned long action, void *hcpu)
{
	int cpu = (int)(long)hcpu;

	switch (action) {
	case CPU_DOWN_PREPARE:
	case CPU_DOWN_PREPARE_FROZEN:
		disable_runtime(cpu_rq(cpu));
		return NOTIFY_OK;

	case CPU_DOWN_FAILED:
	case CPU_DOWN_FAILED_FROZEN:
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		enable_runtime(cpu_rq(cpu));
		return NOTIFY_OK;

	default:
		return NOTIFY_DONE;
	}
}

void __init sched_init_smp(void)
{
	cpumask_var_t non_isolated_cpus;

	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);

#if defined(CONFIG_NUMA)
	sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **),
								GFP_KERNEL);
	BUG_ON(sched_group_nodes_bycpu == NULL);
#endif
	get_online_cpus();
	mutex_lock(&sched_domains_mutex);
	arch_init_sched_domains(cpu_online_mask);
	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
	if (cpumask_empty(non_isolated_cpus))
		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
	mutex_unlock(&sched_domains_mutex);
	put_online_cpus();

#ifndef CONFIG_CPUSETS
	/* XXX: Theoretical race here - CPU may be hotplugged now */
	hotcpu_notifier(update_sched_domains, 0);
#endif

	/* RT runtime code needs to handle some hotplug events */
	hotcpu_notifier(update_runtime, 0);

	init_hrtick();

	/* Move init over to a non-isolated CPU */
	if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
		BUG();
	sched_init_granularity();
	free_cpumask_var(non_isolated_cpus);

	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
	init_sched_rt_class();
}
#else
void __init sched_init_smp(void)
{
	sched_init_granularity();
}
#endif /* CONFIG_SMP */

const_debug unsigned int sysctl_timer_migration = 1;

int in_sched_functions(unsigned long addr)
{
	return in_lock_functions(addr) ||
		(addr >= (unsigned long)__sched_text_start
		&& addr < (unsigned long)__sched_text_end);
}

static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq)
{
	cfs_rq->tasks_timeline = RB_ROOT;
	INIT_LIST_HEAD(&cfs_rq->tasks);
#ifdef CONFIG_FAIR_GROUP_SCHED
	cfs_rq->rq = rq;
#endif
	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
}

static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq)
{
	struct rt_prio_array *array;
	int i;

	array = &rt_rq->active;
	for (i = 0; i < MAX_RT_PRIO; i++) {
		INIT_LIST_HEAD(array->queue + i);
		__clear_bit(i, array->bitmap);
	}
	/* delimiter for bitsearch: */
	__set_bit(MAX_RT_PRIO, array->bitmap);

#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
	rt_rq->highest_prio.curr = MAX_RT_PRIO;
#ifdef CONFIG_SMP
	rt_rq->highest_prio.next = MAX_RT_PRIO;
#endif
#endif
#ifdef CONFIG_SMP
	rt_rq->rt_nr_migratory = 0;
	rt_rq->overloaded = 0;
	plist_head_init(&rq->rt.pushable_tasks, &rq->lock);
#endif

	rt_rq->rt_time = 0;
	rt_rq->rt_throttled = 0;
	rt_rq->rt_runtime = 0;
	spin_lock_init(&rt_rq->rt_runtime_lock);

#ifdef CONFIG_RT_GROUP_SCHED
	rt_rq->rt_nr_boosted = 0;
	rt_rq->rq = rq;
#endif
}

#ifdef CONFIG_FAIR_GROUP_SCHED
static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
				struct sched_entity *se, int cpu, int add,
				struct sched_entity *parent)
{
	struct rq *rq = cpu_rq(cpu);
	tg->cfs_rq[cpu] = cfs_rq;
	init_cfs_rq(cfs_rq, rq);
	cfs_rq->tg = tg;
	if (add)
		list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);

	tg->se[cpu] = se;
	/* se could be NULL for init_task_group */
	if (!se)
		return;

	if (!parent)
		se->cfs_rq = &rq->cfs;
	else
		se->cfs_rq = parent->my_q;

	se->my_q = cfs_rq;
	se->load.weight = tg->shares;
	se->load.inv_weight = 0;
	se->parent = parent;
}
#endif

#ifdef CONFIG_RT_GROUP_SCHED
static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
		struct sched_rt_entity *rt_se, int cpu, int add,
		struct sched_rt_entity *parent)
{
	struct rq *rq = cpu_rq(cpu);

	tg->rt_rq[cpu] = rt_rq;
	init_rt_rq(rt_rq, rq);
	rt_rq->tg = tg;
	rt_rq->rt_se = rt_se;
	rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime;
	if (add)
		list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list);

	tg->rt_se[cpu] = rt_se;
	if (!rt_se)
		return;

	if (!parent)
		rt_se->rt_rq = &rq->rt;
	else
		rt_se->rt_rq = parent->my_q;

	rt_se->my_q = rt_rq;
	rt_se->parent = parent;
	INIT_LIST_HEAD(&rt_se->run_list);
}
#endif

void __init sched_init(void)
{
	int i, j;
	unsigned long alloc_size = 0, ptr;

#ifdef CONFIG_FAIR_GROUP_SCHED
	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
#ifdef CONFIG_RT_GROUP_SCHED
	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
#endif
#ifdef CONFIG_USER_SCHED
	alloc_size *= 2;
#endif
#ifdef CONFIG_CPUMASK_OFFSTACK
	alloc_size += num_possible_cpus() * cpumask_size();
#endif
	/*
	 * As sched_init() is called before page_alloc is setup,
	 * we use alloc_bootmem().
	 */
	if (alloc_size) {
		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);

#ifdef CONFIG_FAIR_GROUP_SCHED
		init_task_group.se = (struct sched_entity **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);

		init_task_group.cfs_rq = (struct cfs_rq **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);

#ifdef CONFIG_USER_SCHED
		root_task_group.se = (struct sched_entity **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);

		root_task_group.cfs_rq = (struct cfs_rq **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);
#endif /* CONFIG_USER_SCHED */
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
		init_task_group.rt_se = (struct sched_rt_entity **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);

		init_task_group.rt_rq = (struct rt_rq **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);

#ifdef CONFIG_USER_SCHED
		root_task_group.rt_se = (struct sched_rt_entity **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);

		root_task_group.rt_rq = (struct rt_rq **)ptr;
		ptr += nr_cpu_ids * sizeof(void **);
#endif /* CONFIG_USER_SCHED */
#endif /* CONFIG_RT_GROUP_SCHED */
#ifdef CONFIG_CPUMASK_OFFSTACK
		for_each_possible_cpu(i) {
			per_cpu(load_balance_tmpmask, i) = (void *)ptr;
			ptr += cpumask_size();
		}
#endif /* CONFIG_CPUMASK_OFFSTACK */
	}

#ifdef CONFIG_SMP
	init_defrootdomain();
#endif

	init_rt_bandwidth(&def_rt_bandwidth,
			global_rt_period(), global_rt_runtime());

#ifdef CONFIG_RT_GROUP_SCHED
	init_rt_bandwidth(&init_task_group.rt_bandwidth,
			global_rt_period(), global_rt_runtime());
#ifdef CONFIG_USER_SCHED
	init_rt_bandwidth(&root_task_group.rt_bandwidth,
			global_rt_period(), RUNTIME_INF);
#endif /* CONFIG_USER_SCHED */
#endif /* CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_GROUP_SCHED
	list_add(&init_task_group.list, &task_groups);
	INIT_LIST_HEAD(&init_task_group.children);

#ifdef CONFIG_USER_SCHED
	INIT_LIST_HEAD(&root_task_group.children);
	init_task_group.parent = &root_task_group;
	list_add(&init_task_group.siblings, &root_task_group.children);
#endif /* CONFIG_USER_SCHED */
#endif /* CONFIG_GROUP_SCHED */

	for_each_possible_cpu(i) {
		struct rq *rq;

		rq = cpu_rq(i);
		spin_lock_init(&rq->lock);
		rq->nr_running = 0;
		rq->calc_load_active = 0;
		rq->calc_load_update = jiffies + LOAD_FREQ;
		init_cfs_rq(&rq->cfs, rq);
		init_rt_rq(&rq->rt, rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
		init_task_group.shares = init_task_group_load;
		INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
#ifdef CONFIG_CGROUP_SCHED
		/*
		 * How much cpu bandwidth does init_task_group get?
		 *
		 * In case of task-groups formed thr' the cgroup filesystem, it
		 * gets 100% of the cpu resources in the system. This overall
		 * system cpu resource is divided among the tasks of
		 * init_task_group and its child task-groups in a fair manner,
		 * based on each entity's (task or task-group's) weight
		 * (se->load.weight).
		 *
		 * In other words, if init_task_group has 10 tasks of weight
		 * 1024) and two child groups A0 and A1 (of weight 1024 each),
		 * then A0's share of the cpu resource is:
		 *
		 *	A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33%
		 *
		 * We achieve this by letting init_task_group's tasks sit
		 * directly in rq->cfs (i.e init_task_group->se[] = NULL).
		 */
		init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL);
#elif defined CONFIG_USER_SCHED
		root_task_group.shares = NICE_0_LOAD;
		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, 0, NULL);
		/*
		 * In case of task-groups formed thr' the user id of tasks,
		 * init_task_group represents tasks belonging to root user.
		 * Hence it forms a sibling of all subsequent groups formed.
		 * In this case, init_task_group gets only a fraction of overall
		 * system cpu resource, based on the weight assigned to root
		 * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished
		 * by letting tasks of init_task_group sit in a separate cfs_rq
		 * (init_cfs_rq) and having one entity represent this group of
		 * tasks in rq->cfs (i.e init_task_group->se[] != NULL).
		 */
		init_tg_cfs_entry(&init_task_group,
				&per_cpu(init_cfs_rq, i),
				&per_cpu(init_sched_entity, i), i, 1,
				root_task_group.se[i]);

#endif
#endif /* CONFIG_FAIR_GROUP_SCHED */

		rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
#ifdef CONFIG_RT_GROUP_SCHED
		INIT_LIST_HEAD(&rq->leaf_rt_rq_list);
#ifdef CONFIG_CGROUP_SCHED
		init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL);
#elif defined CONFIG_USER_SCHED
		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
		init_tg_rt_entry(&init_task_group,
				&per_cpu(init_rt_rq, i),
				&per_cpu(init_sched_rt_entity, i), i, 1,
				root_task_group.rt_se[i]);
#endif
#endif

		for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
			rq->cpu_load[j] = 0;
#ifdef CONFIG_SMP
		rq->sd = NULL;
		rq->rd = NULL;
		rq->active_balance = 0;
		rq->next_balance = jiffies;
		rq->push_cpu = 0;
		rq->cpu = i;
		rq->online = 0;
		rq->migration_thread = NULL;
		INIT_LIST_HEAD(&rq->migration_queue);
		rq_attach_root(rq, &def_root_domain);
#endif
		init_rq_hrtick(rq);
		atomic_set(&rq->nr_iowait, 0);
	}

	set_load_weight(&init_task);

#ifdef CONFIG_PREEMPT_NOTIFIERS
	INIT_HLIST_HEAD(&init_task.preempt_notifiers);
#endif

#ifdef CONFIG_SMP
	open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
#endif

#ifdef CONFIG_RT_MUTEXES
	plist_head_init(&init_task.pi_waiters, &init_task.pi_lock);
#endif

	/*
	 * The boot idle thread does lazy MMU switching as well:
	 */
	atomic_inc(&init_mm.mm_count);
	enter_lazy_tlb(&init_mm, current);

	/*
	 * Make us the idle thread. Technically, schedule() should not be
	 * called from this thread, however somewhere below it might be,
	 * but because we are the idle thread, we just pick up running again
	 * when this runqueue becomes "idle".
	 */
	init_idle(current, smp_processor_id());

	calc_load_update = jiffies + LOAD_FREQ;

	/*
	 * During early bootup we pretend to be a normal task:
	 */
	current->sched_class = &fair_sched_class;

	/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
	alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ
	alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
	alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
#endif
	alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
#endif /* SMP */

	perf_counter_init();

	scheduler_running = 1;
}

#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
void __might_sleep(char *file, int line)
{
#ifdef in_atomic
	static unsigned long prev_jiffy;	/* ratelimiting */

	if ((!in_atomic() && !irqs_disabled()) ||
		    system_state != SYSTEM_RUNNING || oops_in_progress)
		return;
	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
		return;
	prev_jiffy = jiffies;

	printk(KERN_ERR
		"BUG: sleeping function called from invalid context at %s:%d\n",
			file, line);
	printk(KERN_ERR
		"in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
			in_atomic(), irqs_disabled(),
			current->pid, current->comm);

	debug_show_held_locks(current);
	if (irqs_disabled())
		print_irqtrace_events(current);
	dump_stack();
#endif
}
EXPORT_SYMBOL(__might_sleep);
#endif

#ifdef CONFIG_MAGIC_SYSRQ
static void normalize_task(struct rq *rq, struct task_struct *p)
{
	int on_rq;

	update_rq_clock(rq);
	on_rq = p->se.on_rq;
	if (on_rq)
		deactivate_task(rq, p, 0);
	__setscheduler(rq, p, SCHED_NORMAL, 0);
	if (on_rq) {
		activate_task(rq, p, 0);
		resched_task(rq->curr);
	}
}

void normalize_rt_tasks(void)
{
	struct task_struct *g, *p;
	unsigned long flags;
	struct rq *rq;

	read_lock_irqsave(&tasklist_lock, flags);
	do_each_thread(g, p) {
		/*
		 * Only normalize user tasks:
		 */
		if (!p->mm)
			continue;

		p->se.exec_start		= 0;
#ifdef CONFIG_SCHEDSTATS
		p->se.wait_start		= 0;
		p->se.sleep_start		= 0;
		p->se.block_start		= 0;
#endif

		if (!rt_task(p)) {
			/*
			 * Renice negative nice level userspace
			 * tasks back to 0:
			 */
			if (TASK_NICE(p) < 0 && p->mm)
				set_user_nice(p, 0);
			continue;
		}

		spin_lock(&p->pi_lock);
		rq = __task_rq_lock(p);

		normalize_task(rq, p);

		__task_rq_unlock(rq);
		spin_unlock(&p->pi_lock);
	} while_each_thread(g, p);

	read_unlock_irqrestore(&tasklist_lock, flags);
}

#endif /* CONFIG_MAGIC_SYSRQ */

#ifdef CONFIG_IA64
/*
 * These functions are only useful for the IA64 MCA handling.
 *
 * They can only be called when the whole system has been
 * stopped - every CPU needs to be quiescent, and no scheduling
 * activity can take place. Using them for anything else would
 * be a serious bug, and as a result, they aren't even visible
 * under any other configuration.
 */

/**
 * curr_task - return the current task for a given cpu.
 * @cpu: the processor in question.
 *
 * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
 */
struct task_struct *curr_task(int cpu)
{
	return cpu_curr(cpu);
}

/**
 * set_curr_task - set the current task for a given cpu.
 * @cpu: the processor in question.
 * @p: the task pointer to set.
 *
 * Description: This function must only be used when non-maskable interrupts
 * are serviced on a separate stack. It allows the architecture to switch the
 * notion of the current task on a cpu in a non-blocking manner. This function
 * must be called with all CPU's synchronized, and interrupts disabled, the
 * and caller must save the original value of the current task (see
 * curr_task() above) and restore that value before reenabling interrupts and
 * re-starting the system.
 *
 * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
 */
void set_curr_task(int cpu, struct task_struct *p)
{
	cpu_curr(cpu) = p;
}

#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
static void free_fair_sched_group(struct task_group *tg)
{
	int i;

	for_each_possible_cpu(i) {
		if (tg->cfs_rq)
			kfree(tg->cfs_rq[i]);
		if (tg->se)
			kfree(tg->se[i]);
	}

	kfree(tg->cfs_rq);
	kfree(tg->se);
}

static
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
	struct cfs_rq *cfs_rq;
	struct sched_entity *se;
	struct rq *rq;
	int i;

	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->cfs_rq)
		goto err;
	tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->se)
		goto err;

	tg->shares = NICE_0_LOAD;

	for_each_possible_cpu(i) {
		rq = cpu_rq(i);

		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
				      GFP_KERNEL, cpu_to_node(i));
		if (!cfs_rq)
			goto err;

		se = kzalloc_node(sizeof(struct sched_entity),
				  GFP_KERNEL, cpu_to_node(i));
		if (!se)
			goto err;

		init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
	}

	return 1;

 err:
	return 0;
}

static inline void register_fair_sched_group(struct task_group *tg, int cpu)
{
	list_add_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list,
			&cpu_rq(cpu)->leaf_cfs_rq_list);
}

static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
{
	list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list);
}
#else /* !CONFG_FAIR_GROUP_SCHED */
static inline void free_fair_sched_group(struct task_group *tg)
{
}

static inline
int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
{
	return 1;
}

static inline void register_fair_sched_group(struct task_group *tg, int cpu)
{
}

static inline void unregister_fair_sched_group(struct task_group *tg, int cpu)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */

#ifdef CONFIG_RT_GROUP_SCHED
static void free_rt_sched_group(struct task_group *tg)
{
	int i;

	destroy_rt_bandwidth(&tg->rt_bandwidth);

	for_each_possible_cpu(i) {
		if (tg->rt_rq)
			kfree(tg->rt_rq[i]);
		if (tg->rt_se)
			kfree(tg->rt_se[i]);
	}

	kfree(tg->rt_rq);
	kfree(tg->rt_se);
}

static
int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
	struct rt_rq *rt_rq;
	struct sched_rt_entity *rt_se;
	struct rq *rq;
	int i;

	tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->rt_rq)
		goto err;
	tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL);
	if (!tg->rt_se)
		goto err;

	init_rt_bandwidth(&tg->rt_bandwidth,
			ktime_to_ns(def_rt_bandwidth.rt_period), 0);

	for_each_possible_cpu(i) {
		rq = cpu_rq(i);

		rt_rq = kzalloc_node(sizeof(struct rt_rq),
				     GFP_KERNEL, cpu_to_node(i));
		if (!rt_rq)
			goto err;

		rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
				     GFP_KERNEL, cpu_to_node(i));
		if (!rt_se)
			goto err;

		init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
	}

	return 1;

 err:
	return 0;
}

static inline void register_rt_sched_group(struct task_group *tg, int cpu)
{
	list_add_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list,
			&cpu_rq(cpu)->leaf_rt_rq_list);
}

static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
{
	list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list);
}
#else /* !CONFIG_RT_GROUP_SCHED */
static inline void free_rt_sched_group(struct task_group *tg)
{
}

static inline
int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent)
{
	return 1;
}

static inline void register_rt_sched_group(struct task_group *tg, int cpu)
{
}

static inline void unregister_rt_sched_group(struct task_group *tg, int cpu)
{
}
#endif /* CONFIG_RT_GROUP_SCHED */

#ifdef CONFIG_GROUP_SCHED
static void free_sched_group(struct task_group *tg)
{
	free_fair_sched_group(tg);
	free_rt_sched_group(tg);
	kfree(tg);
}

/* allocate runqueue etc for a new task group */
struct task_group *sched_create_group(struct task_group *parent)
{
	struct task_group *tg;
	unsigned long flags;
	int i;

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

	if (!alloc_fair_sched_group(tg, parent))
		goto err;

	if (!alloc_rt_sched_group(tg, parent))
		goto err;

	spin_lock_irqsave(&task_group_lock, flags);
	for_each_possible_cpu(i) {
		register_fair_sched_group(tg, i);
		register_rt_sched_group(tg, i);
	}
	list_add_rcu(&tg->list, &task_groups);

	WARN_ON(!parent); /* root should already exist */

	tg->parent = parent;
	INIT_LIST_HEAD(&tg->children);
	list_add_rcu(&tg->siblings, &parent->children);
	spin_unlock_irqrestore(&task_group_lock, flags);

	return tg;

err:
	free_sched_group(tg);
	return ERR_PTR(-ENOMEM);
}

/* rcu callback to free various structures associated with a task group */
static void free_sched_group_rcu(struct rcu_head *rhp)
{
	/* now it should be safe to free those cfs_rqs */
	free_sched_group(container_of(rhp, struct task_group, rcu));
}

/* Destroy runqueue etc associated with a task group */
void sched_destroy_group(struct task_group *tg)
{
	unsigned long flags;
	int i;

	spin_lock_irqsave(&task_group_lock, flags);
	for_each_possible_cpu(i) {
		unregister_fair_sched_group(tg, i);
		unregister_rt_sched_group(tg, i);
	}
	list_del_rcu(&tg->list);
	list_del_rcu(&tg->siblings);
	spin_unlock_irqrestore(&task_group_lock, flags);

	/* wait for possible concurrent references to cfs_rqs complete */
	call_rcu(&tg->rcu, free_sched_group_rcu);
}

/* change task's runqueue when it moves between groups.
 *	The caller of this function should have put the task in its new group
 *	by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
 *	reflect its new group.
 */
void sched_move_task(struct task_struct *tsk)
{
	int on_rq, running;
	unsigned long flags;
	struct rq *rq;

	rq = task_rq_lock(tsk, &flags);

	update_rq_clock(rq);

	running = task_current(rq, tsk);
	on_rq = tsk->se.on_rq;

	if (on_rq)
		dequeue_task(rq, tsk, 0);
	if (unlikely(running))
		tsk->sched_class->put_prev_task(rq, tsk);

	set_task_rq(tsk, task_cpu(tsk));

#ifdef CONFIG_FAIR_GROUP_SCHED
	if (tsk->sched_class->moved_group)
		tsk->sched_class->moved_group(tsk);
#endif

	if (unlikely(running))
		tsk->sched_class->set_curr_task(rq);
	if (on_rq)
		enqueue_task(rq, tsk, 0);

	task_rq_unlock(rq, &flags);
}
#endif /* CONFIG_GROUP_SCHED */

#ifdef CONFIG_FAIR_GROUP_SCHED
static void __set_se_shares(struct sched_entity *se, unsigned long shares)
{
	struct cfs_rq *cfs_rq = se->cfs_rq;
	int on_rq;

	on_rq = se->on_rq;
	if (on_rq)
		dequeue_entity(cfs_rq, se, 0);

	se->load.weight = shares;
	se->load.inv_weight = 0;

	if (on_rq)
		enqueue_entity(cfs_rq, se, 0);
}

static void set_se_shares(struct sched_entity *se, unsigned long shares)
{
	struct cfs_rq *cfs_rq = se->cfs_rq;
	struct rq *rq = cfs_rq->rq;
	unsigned long flags;

	spin_lock_irqsave(&rq->lock, flags);
	__set_se_shares(se, shares);
	spin_unlock_irqrestore(&rq->lock, flags);
}

static DEFINE_MUTEX(shares_mutex);

int sched_group_set_shares(struct task_group *tg, unsigned long shares)
{
	int i;
	unsigned long flags;

	/*
	 * We can't change the weight of the root cgroup.
	 */
	if (!tg->se[0])
		return -EINVAL;

	if (shares < MIN_SHARES)
		shares = MIN_SHARES;
	else if (shares > MAX_SHARES)
		shares = MAX_SHARES;

	mutex_lock(&shares_mutex);
	if (tg->shares == shares)
		goto done;

	spin_lock_irqsave(&task_group_lock, flags);
	for_each_possible_cpu(i)
		unregister_fair_sched_group(tg, i);
	list_del_rcu(&tg->siblings);
	spin_unlock_irqrestore(&task_group_lock, flags);

	/* wait for any ongoing reference to this group to finish */
	synchronize_sched();

	/*
	 * Now we are free to modify the group's share on each cpu
	 * w/o tripping rebalance_share or load_balance_fair.
	 */
	tg->shares = shares;
	for_each_possible_cpu(i) {
		/*
		 * force a rebalance
		 */
		cfs_rq_set_shares(tg->cfs_rq[i], 0);
		set_se_shares(tg->se[i], shares);
	}

	/*
	 * Enable load balance activity on this group, by inserting it back on
	 * each cpu's rq->leaf_cfs_rq_list.
	 */
	spin_lock_irqsave(&task_group_lock, flags);
	for_each_possible_cpu(i)
		register_fair_sched_group(tg, i);
	list_add_rcu(&tg->siblings, &tg->parent->children);
	spin_unlock_irqrestore(&task_group_lock, flags);
done:
	mutex_unlock(&shares_mutex);
	return 0;
}

unsigned long sched_group_shares(struct task_group *tg)
{
	return tg->shares;
}
#endif

#ifdef CONFIG_RT_GROUP_SCHED
/*
 * Ensure that the real time constraints are schedulable.
 */
static DEFINE_MUTEX(rt_constraints_mutex);

static unsigned long to_ratio(u64 period, u64 runtime)
{
	if (runtime == RUNTIME_INF)
		return 1ULL << 20;

	return div64_u64(runtime << 20, period);
}

/* Must be called with tasklist_lock held */
static inline int tg_has_rt_tasks(struct task_group *tg)
{
	struct task_struct *g, *p;

	do_each_thread(g, p) {
		if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg)
			return 1;
	} while_each_thread(g, p);

	return 0;
}

struct rt_schedulable_data {
	struct task_group *tg;
	u64 rt_period;
	u64 rt_runtime;
};

static int tg_schedulable(struct task_group *tg, void *data)
{
	struct rt_schedulable_data *d = data;
	struct task_group *child;
	unsigned long total, sum = 0;
	u64 period, runtime;

	period = ktime_to_ns(tg->rt_bandwidth.rt_period);
	runtime = tg->rt_bandwidth.rt_runtime;

	if (tg == d->tg) {
		period = d->rt_period;
		runtime = d->rt_runtime;
	}

#ifdef CONFIG_USER_SCHED
	if (tg == &root_task_group) {
		period = global_rt_period();
		runtime = global_rt_runtime();
	}
#endif

	/*
	 * Cannot have more runtime than the period.
	 */
	if (runtime > period && runtime != RUNTIME_INF)
		return -EINVAL;

	/*
	 * Ensure we don't starve existing RT tasks.
	 */
	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
		return -EBUSY;

	total = to_ratio(period, runtime);

	/*
	 * Nobody can have more than the global setting allows.
	 */
	if (total > to_ratio(global_rt_period(), global_rt_runtime()))
		return -EINVAL;

	/*
	 * The sum of our children's runtime should not exceed our own.
	 */
	list_for_each_entry_rcu(child, &tg->children, siblings) {
		period = ktime_to_ns(child->rt_bandwidth.rt_period);
		runtime = child->rt_bandwidth.rt_runtime;

		if (child == d->tg) {
			period = d->rt_period;
			runtime = d->rt_runtime;
		}

		sum += to_ratio(period, runtime);
	}

	if (sum > total)
		return -EINVAL;

	return 0;
}

static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
{
	struct rt_schedulable_data data = {
		.tg = tg,
		.rt_period = period,
		.rt_runtime = runtime,
	};

	return walk_tg_tree(tg_schedulable, tg_nop, &data);
}

static int tg_set_bandwidth(struct task_group *tg,
		u64 rt_period, u64 rt_runtime)
{
	int i, err = 0;

	mutex_lock(&rt_constraints_mutex);
	read_lock(&tasklist_lock);
	err = __rt_schedulable(tg, rt_period, rt_runtime);
	if (err)
		goto unlock;

	spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
	tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
	tg->rt_bandwidth.rt_runtime = rt_runtime;

	for_each_possible_cpu(i) {
		struct rt_rq *rt_rq = tg->rt_rq[i];

		spin_lock(&rt_rq->rt_runtime_lock);
		rt_rq->rt_runtime = rt_runtime;
		spin_unlock(&rt_rq->rt_runtime_lock);
	}
	spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
 unlock:
	read_unlock(&tasklist_lock);
	mutex_unlock(&rt_constraints_mutex);

	return err;
}

int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
{
	u64 rt_runtime, rt_period;

	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
	if (rt_runtime_us < 0)
		rt_runtime = RUNTIME_INF;

	return tg_set_bandwidth(tg, rt_period, rt_runtime);
}

long sched_group_rt_runtime(struct task_group *tg)
{
	u64 rt_runtime_us;

	if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
		return -1;

	rt_runtime_us = tg->rt_bandwidth.rt_runtime;
	do_div(rt_runtime_us, NSEC_PER_USEC);
	return rt_runtime_us;
}

int sched_group_set_rt_period(struct task_group *tg, long rt_period_us)
{
	u64 rt_runtime, rt_period;

	rt_period = (u64)rt_period_us * NSEC_PER_USEC;
	rt_runtime = tg->rt_bandwidth.rt_runtime;

	if (rt_period == 0)
		return -EINVAL;

	return tg_set_bandwidth(tg, rt_period, rt_runtime);
}

long sched_group_rt_period(struct task_group *tg)
{
	u64 rt_period_us;

	rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
	do_div(rt_period_us, NSEC_PER_USEC);
	return rt_period_us;
}

static int sched_rt_global_constraints(void)
{
	u64 runtime, period;
	int ret = 0;

	if (sysctl_sched_rt_period <= 0)
		return -EINVAL;

	runtime = global_rt_runtime();
	period = global_rt_period();

	/*
	 * Sanity check on the sysctl variables.
	 */
	if (runtime > period && runtime != RUNTIME_INF)
		return -EINVAL;

	mutex_lock(&rt_constraints_mutex);
	read_lock(&tasklist_lock);
	ret = __rt_schedulable(NULL, 0, 0);
	read_unlock(&tasklist_lock);
	mutex_unlock(&rt_constraints_mutex);

	return ret;
}

int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
{
	/* Don't accept realtime tasks when there is no way for them to run */
	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
		return 0;

	return 1;
}

#else /* !CONFIG_RT_GROUP_SCHED */
static int sched_rt_global_constraints(void)
{
	unsigned long flags;
	int i;

	if (sysctl_sched_rt_period <= 0)
		return -EINVAL;

	/*
	 * There's always some RT tasks in the root group
	 * -- migration, kstopmachine etc..
	 */
	if (sysctl_sched_rt_runtime == 0)
		return -EBUSY;

	spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
	for_each_possible_cpu(i) {
		struct rt_rq *rt_rq = &cpu_rq(i)->rt;

		spin_lock(&rt_rq->rt_runtime_lock);
		rt_rq->rt_runtime = global_rt_runtime();
		spin_unlock(&rt_rq->rt_runtime_lock);
	}
	spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);

	return 0;
}
#endif /* CONFIG_RT_GROUP_SCHED */

int sched_rt_handler(struct ctl_table *table, int write,
		struct file *filp, void __user *buffer, size_t *lenp,
		loff_t *ppos)
{
	int ret;
	int old_period, old_runtime;
	static DEFINE_MUTEX(mutex);

	mutex_lock(&mutex);
	old_period = sysctl_sched_rt_period;
	old_runtime = sysctl_sched_rt_runtime;

	ret = proc_dointvec(table, write, filp, buffer, lenp, ppos);

	if (!ret && write) {
		ret = sched_rt_global_constraints();
		if (ret) {
			sysctl_sched_rt_period = old_period;
			sysctl_sched_rt_runtime = old_runtime;
		} else {
			def_rt_bandwidth.rt_runtime = global_rt_runtime();
			def_rt_bandwidth.rt_period =
				ns_to_ktime(global_rt_period());
		}
	}
	mutex_unlock(&mutex);

	return ret;
}

#ifdef CONFIG_CGROUP_SCHED

/* return corresponding task_group object of a cgroup */
static inline struct task_group *cgroup_tg(struct cgroup *cgrp)
{
	return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id),
			    struct task_group, css);
}

static struct cgroup_subsys_state *
cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	struct task_group *tg, *parent;

	if (!cgrp->parent) {
		/* This is early initialization for the top cgroup */
		return &init_task_group.css;
	}

	parent = cgroup_tg(cgrp->parent);
	tg = sched_create_group(parent);
	if (IS_ERR(tg))
		return ERR_PTR(-ENOMEM);

	return &tg->css;
}

static void
cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	struct task_group *tg = cgroup_tg(cgrp);

	sched_destroy_group(tg);
}

static int
cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
		      struct task_struct *tsk)
{
#ifdef CONFIG_RT_GROUP_SCHED
	if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk))
		return -EINVAL;
#else
	/* We don't support RT-tasks being in separate groups */
	if (tsk->sched_class != &fair_sched_class)
		return -EINVAL;
#endif

	return 0;
}

static void
cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
			struct cgroup *old_cont, struct task_struct *tsk)
{
	sched_move_task(tsk);
}

#ifdef CONFIG_FAIR_GROUP_SCHED
static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype,
				u64 shareval)
{
	return sched_group_set_shares(cgroup_tg(cgrp), shareval);
}

static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft)
{
	struct task_group *tg = cgroup_tg(cgrp);

	return (u64) tg->shares;
}
#endif /* CONFIG_FAIR_GROUP_SCHED */

#ifdef CONFIG_RT_GROUP_SCHED
static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft,
				s64 val)
{
	return sched_group_set_rt_runtime(cgroup_tg(cgrp), val);
}

static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft)
{
	return sched_group_rt_runtime(cgroup_tg(cgrp));
}

static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype,
		u64 rt_period_us)
{
	return sched_group_set_rt_period(cgroup_tg(cgrp), rt_period_us);
}

static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft)
{
	return sched_group_rt_period(cgroup_tg(cgrp));
}
#endif /* CONFIG_RT_GROUP_SCHED */

static struct cftype cpu_files[] = {
#ifdef CONFIG_FAIR_GROUP_SCHED
	{
		.name = "shares",
		.read_u64 = cpu_shares_read_u64,
		.write_u64 = cpu_shares_write_u64,
	},
#endif
#ifdef CONFIG_RT_GROUP_SCHED
	{
		.name = "rt_runtime_us",
		.read_s64 = cpu_rt_runtime_read,
		.write_s64 = cpu_rt_runtime_write,
	},
	{
		.name = "rt_period_us",
		.read_u64 = cpu_rt_period_read_uint,
		.write_u64 = cpu_rt_period_write_uint,
	},
#endif
};

static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
{
	return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files));
}

struct cgroup_subsys cpu_cgroup_subsys = {
	.name		= "cpu",
	.create		= cpu_cgroup_create,
	.destroy	= cpu_cgroup_destroy,
	.can_attach	= cpu_cgroup_can_attach,
	.attach		= cpu_cgroup_attach,
	.populate	= cpu_cgroup_populate,
	.subsys_id	= cpu_cgroup_subsys_id,
	.early_init	= 1,
};

#endif	/* CONFIG_CGROUP_SCHED */

#ifdef CONFIG_CGROUP_CPUACCT

/*
 * CPU accounting code for task groups.
 *
 * Based on the work by Paul Menage (menage@google.com) and Balbir Singh
 * (balbir@in.ibm.com).
 */

/* track cpu usage of a group of tasks and its child groups */
struct cpuacct {
	struct cgroup_subsys_state css;
	/* cpuusage holds pointer to a u64-type object on every cpu */
	u64 *cpuusage;
	struct percpu_counter cpustat[CPUACCT_STAT_NSTATS];
	struct cpuacct *parent;
};

struct cgroup_subsys cpuacct_subsys;

/* return cpu accounting group corresponding to this container */
static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
{
	return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id),
			    struct cpuacct, css);
}

/* return cpu accounting group to which this task belongs */
static inline struct cpuacct *task_ca(struct task_struct *tsk)
{
	return container_of(task_subsys_state(tsk, cpuacct_subsys_id),
			    struct cpuacct, css);
}

/* create a new cpu accounting group */
static struct cgroup_subsys_state *cpuacct_create(
	struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
	int i;

	if (!ca)
		goto out;

	ca->cpuusage = alloc_percpu(u64);
	if (!ca->cpuusage)
		goto out_free_ca;

	for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
		if (percpu_counter_init(&ca->cpustat[i], 0))
			goto out_free_counters;

	if (cgrp->parent)
		ca->parent = cgroup_ca(cgrp->parent);

	return &ca->css;

out_free_counters:
	while (--i >= 0)
		percpu_counter_destroy(&ca->cpustat[i]);
	free_percpu(ca->cpuusage);
out_free_ca:
	kfree(ca);
out:
	return ERR_PTR(-ENOMEM);
}

/* destroy an existing cpu accounting group */
static void
cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	struct cpuacct *ca = cgroup_ca(cgrp);
	int i;

	for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
		percpu_counter_destroy(&ca->cpustat[i]);
	free_percpu(ca->cpuusage);
	kfree(ca);
}

static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu)
{
	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
	u64 data;

#ifndef CONFIG_64BIT
	/*
	 * Take rq->lock to make 64-bit read safe on 32-bit platforms.
	 */
	spin_lock_irq(&cpu_rq(cpu)->lock);
	data = *cpuusage;
	spin_unlock_irq(&cpu_rq(cpu)->lock);
#else
	data = *cpuusage;
#endif

	return data;
}

static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
{
	u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);

#ifndef CONFIG_64BIT
	/*
	 * Take rq->lock to make 64-bit write safe on 32-bit platforms.
	 */
	spin_lock_irq(&cpu_rq(cpu)->lock);
	*cpuusage = val;
	spin_unlock_irq(&cpu_rq(cpu)->lock);
#else
	*cpuusage = val;
#endif
}

/* return total cpu usage (in nanoseconds) of a group */
static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft)
{
	struct cpuacct *ca = cgroup_ca(cgrp);
	u64 totalcpuusage = 0;
	int i;

	for_each_present_cpu(i)
		totalcpuusage += cpuacct_cpuusage_read(ca, i);

	return totalcpuusage;
}

static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype,
								u64 reset)
{
	struct cpuacct *ca = cgroup_ca(cgrp);
	int err = 0;
	int i;

	if (reset) {
		err = -EINVAL;
		goto out;
	}

	for_each_present_cpu(i)
		cpuacct_cpuusage_write(ca, i, 0);

out:
	return err;
}

static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft,
				   struct seq_file *m)
{
	struct cpuacct *ca = cgroup_ca(cgroup);
	u64 percpu;
	int i;

	for_each_present_cpu(i) {
		percpu = cpuacct_cpuusage_read(ca, i);
		seq_printf(m, "%llu ", (unsigned long long) percpu);
	}
	seq_printf(m, "\n");
	return 0;
}

static const char *cpuacct_stat_desc[] = {
	[CPUACCT_STAT_USER] = "user",
	[CPUACCT_STAT_SYSTEM] = "system",
};

static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
		struct cgroup_map_cb *cb)
{
	struct cpuacct *ca = cgroup_ca(cgrp);
	int i;

	for (i = 0; i < CPUACCT_STAT_NSTATS; i++) {
		s64 val = percpu_counter_read(&ca->cpustat[i]);
		val = cputime64_to_clock_t(val);
		cb->fill(cb, cpuacct_stat_desc[i], val);
	}
	return 0;
}

static struct cftype files[] = {
	{
		.name = "usage",
		.read_u64 = cpuusage_read,
		.write_u64 = cpuusage_write,
	},
	{
		.name = "usage_percpu",
		.read_seq_string = cpuacct_percpu_seq_read,
	},
	{
		.name = "stat",
		.read_map = cpuacct_stats_show,
	},
};

static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
	return cgroup_add_files(cgrp, ss, files, ARRAY_SIZE(files));
}

/*
 * charge this task's execution time to its accounting group.
 *
 * called with rq->lock held.
 */
static void cpuacct_charge(struct task_struct *tsk, u64 cputime)
{
	struct cpuacct *ca;
	int cpu;

	if (unlikely(!cpuacct_subsys.active))
		return;

	cpu = task_cpu(tsk);

	rcu_read_lock();

	ca = task_ca(tsk);

	for (; ca; ca = ca->parent) {
		u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
		*cpuusage += cputime;
	}

	rcu_read_unlock();
}

/*
 * Charge the system/user time to the task's accounting group.
 */
static void cpuacct_update_stats(struct task_struct *tsk,
		enum cpuacct_stat_index idx, cputime_t val)
{
	struct cpuacct *ca;

	if (unlikely(!cpuacct_subsys.active))
		return;

	rcu_read_lock();
	ca = task_ca(tsk);

	do {
		percpu_counter_add(&ca->cpustat[idx], val);
		ca = ca->parent;
	} while (ca);
	rcu_read_unlock();
}

struct cgroup_subsys cpuacct_subsys = {
	.name = "cpuacct",
	.create = cpuacct_create,
	.destroy = cpuacct_destroy,
	.populate = cpuacct_populate,
	.subsys_id = cpuacct_subsys_id,
};
#endif	/* CONFIG_CGROUP_CPUACCT */