aboutsummaryrefslogtreecommitdiff
path: root/mm/percpu.c
blob: bfe6a3afaf45e4be409d8231434447735d40de9c (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
/*
 * linux/mm/percpu.c - percpu memory allocator
 *
 * Copyright (C) 2009		SUSE Linux Products GmbH
 * Copyright (C) 2009		Tejun Heo <tj@kernel.org>
 *
 * This file is released under the GPLv2.
 *
 * This is percpu allocator which can handle both static and dynamic
 * areas.  Percpu areas are allocated in chunks in vmalloc area.  Each
 * chunk is consisted of num_possible_cpus() units and the first chunk
 * is used for static percpu variables in the kernel image (special
 * boot time alloc/init handling necessary as these areas need to be
 * brought up before allocation services are running).  Unit grows as
 * necessary and all units grow or shrink in unison.  When a chunk is
 * filled up, another chunk is allocated.  ie. in vmalloc area
 *
 *  c0                           c1                         c2
 *  -------------------          -------------------        ------------
 * | u0 | u1 | u2 | u3 |        | u0 | u1 | u2 | u3 |      | u0 | u1 | u
 *  -------------------  ......  -------------------  ....  ------------
 *
 * Allocation is done in offset-size areas of single unit space.  Ie,
 * an area of 512 bytes at 6k in c1 occupies 512 bytes at 6k of c1:u0,
 * c1:u1, c1:u2 and c1:u3.  Percpu access can be done by configuring
 * percpu base registers UNIT_SIZE apart.
 *
 * There are usually many small percpu allocations many of them as
 * small as 4 bytes.  The allocator organizes chunks into lists
 * according to free size and tries to allocate from the fullest one.
 * Each chunk keeps the maximum contiguous area size hint which is
 * guaranteed to be eqaul to or larger than the maximum contiguous
 * area in the chunk.  This helps the allocator not to iterate the
 * chunk maps unnecessarily.
 *
 * Allocation state in each chunk is kept using an array of integers
 * on chunk->map.  A positive value in the map represents a free
 * region and negative allocated.  Allocation inside a chunk is done
 * by scanning this map sequentially and serving the first matching
 * entry.  This is mostly copied from the percpu_modalloc() allocator.
 * Chunks are also linked into a rb tree to ease address to chunk
 * mapping during free.
 *
 * To use this allocator, arch code should do the followings.
 *
 * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
 *
 * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
 *   regular address to percpu pointer and back
 *
 * - use pcpu_setup_first_chunk() during percpu area initialization to
 *   setup the first chunk containing the kernel static percpu area
 */

#include <linux/bitmap.h>
#include <linux/bootmem.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/pfn.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>

#include <asm/cacheflush.h>
#include <asm/tlbflush.h>

#define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
#define PCPU_DFL_MAP_ALLOC		16	/* start a map with 16 ents */

struct pcpu_chunk {
	struct list_head	list;		/* linked to pcpu_slot lists */
	struct rb_node		rb_node;	/* key is chunk->vm->addr */
	int			free_size;	/* free bytes in the chunk */
	int			contig_hint;	/* max contiguous size hint */
	struct vm_struct	*vm;		/* mapped vmalloc region */
	int			map_used;	/* # of map entries used */
	int			map_alloc;	/* # of map entries allocated */
	int			*map;		/* allocation map */
	bool			immutable;	/* no [de]population allowed */
	struct page		**page;		/* points to page array */
	struct page		*page_ar[];	/* #cpus * UNIT_PAGES */
};

static int pcpu_unit_pages __read_mostly;
static int pcpu_unit_size __read_mostly;
static int pcpu_chunk_size __read_mostly;
static int pcpu_nr_slots __read_mostly;
static size_t pcpu_chunk_struct_size __read_mostly;

/* the address of the first chunk which starts with the kernel static area */
void *pcpu_base_addr __read_mostly;
EXPORT_SYMBOL_GPL(pcpu_base_addr);

/* optional reserved chunk, only accessible for reserved allocations */
static struct pcpu_chunk *pcpu_reserved_chunk;
/* offset limit of the reserved chunk */
static int pcpu_reserved_chunk_limit;

/*
 * Synchronization rules.
 *
 * There are two locks - pcpu_alloc_mutex and pcpu_lock.  The former
 * protects allocation/reclaim paths, chunks and chunk->page arrays.
 * The latter is a spinlock and protects the index data structures -
 * chunk slots, rbtree, chunks and area maps in chunks.
 *
 * During allocation, pcpu_alloc_mutex is kept locked all the time and
 * pcpu_lock is grabbed and released as necessary.  All actual memory
 * allocations are done using GFP_KERNEL with pcpu_lock released.
 *
 * Free path accesses and alters only the index data structures, so it
 * can be safely called from atomic context.  When memory needs to be
 * returned to the system, free path schedules reclaim_work which
 * grabs both pcpu_alloc_mutex and pcpu_lock, unlinks chunks to be
 * reclaimed, release both locks and frees the chunks.  Note that it's
 * necessary to grab both locks to remove a chunk from circulation as
 * allocation path might be referencing the chunk with only
 * pcpu_alloc_mutex locked.
 */
static DEFINE_MUTEX(pcpu_alloc_mutex);	/* protects whole alloc and reclaim */
static DEFINE_SPINLOCK(pcpu_lock);	/* protects index data structures */

static struct list_head *pcpu_slot __read_mostly; /* chunk list slots */
static struct rb_root pcpu_addr_root = RB_ROOT;	/* chunks by address */

/* reclaim work to release fully free chunks, scheduled from free path */
static void pcpu_reclaim(struct work_struct *work);
static DECLARE_WORK(pcpu_reclaim_work, pcpu_reclaim);

static int __pcpu_size_to_slot(int size)
{
	int highbit = fls(size);	/* size is in bytes */
	return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1);
}

static int pcpu_size_to_slot(int size)
{
	if (size == pcpu_unit_size)
		return pcpu_nr_slots - 1;
	return __pcpu_size_to_slot(size);
}

static int pcpu_chunk_slot(const struct pcpu_chunk *chunk)
{
	if (chunk->free_size < sizeof(int) || chunk->contig_hint < sizeof(int))
		return 0;

	return pcpu_size_to_slot(chunk->free_size);
}

static int pcpu_page_idx(unsigned int cpu, int page_idx)
{
	return cpu * pcpu_unit_pages + page_idx;
}

static struct page **pcpu_chunk_pagep(struct pcpu_chunk *chunk,
				      unsigned int cpu, int page_idx)
{
	return &chunk->page[pcpu_page_idx(cpu, page_idx)];
}

static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk,
				     unsigned int cpu, int page_idx)
{
	return (unsigned long)chunk->vm->addr +
		(pcpu_page_idx(cpu, page_idx) << PAGE_SHIFT);
}

static bool pcpu_chunk_page_occupied(struct pcpu_chunk *chunk,
				     int page_idx)
{
	return *pcpu_chunk_pagep(chunk, 0, page_idx) != NULL;
}

/**
 * pcpu_mem_alloc - allocate memory
 * @size: bytes to allocate
 *
 * Allocate @size bytes.  If @size is smaller than PAGE_SIZE,
 * kzalloc() is used; otherwise, vmalloc() is used.  The returned
 * memory is always zeroed.
 *
 * CONTEXT:
 * Does GFP_KERNEL allocation.
 *
 * RETURNS:
 * Pointer to the allocated area on success, NULL on failure.
 */
static void *pcpu_mem_alloc(size_t size)
{
	if (size <= PAGE_SIZE)
		return kzalloc(size, GFP_KERNEL);
	else {
		void *ptr = vmalloc(size);
		if (ptr)
			memset(ptr, 0, size);
		return ptr;
	}
}

/**
 * pcpu_mem_free - free memory
 * @ptr: memory to free
 * @size: size of the area
 *
 * Free @ptr.  @ptr should have been allocated using pcpu_mem_alloc().
 */
static void pcpu_mem_free(void *ptr, size_t size)
{
	if (size <= PAGE_SIZE)
		kfree(ptr);
	else
		vfree(ptr);
}

/**
 * pcpu_chunk_relocate - put chunk in the appropriate chunk slot
 * @chunk: chunk of interest
 * @oslot: the previous slot it was on
 *
 * This function is called after an allocation or free changed @chunk.
 * New slot according to the changed state is determined and @chunk is
 * moved to the slot.  Note that the reserved chunk is never put on
 * chunk slots.
 *
 * CONTEXT:
 * pcpu_lock.
 */
static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot)
{
	int nslot = pcpu_chunk_slot(chunk);

	if (chunk != pcpu_reserved_chunk && oslot != nslot) {
		if (oslot < nslot)
			list_move(&chunk->list, &pcpu_slot[nslot]);
		else
			list_move_tail(&chunk->list, &pcpu_slot[nslot]);
	}
}

static struct rb_node **pcpu_chunk_rb_search(void *addr,
					     struct rb_node **parentp)
{
	struct rb_node **p = &pcpu_addr_root.rb_node;
	struct rb_node *parent = NULL;
	struct pcpu_chunk *chunk;

	while (*p) {
		parent = *p;
		chunk = rb_entry(parent, struct pcpu_chunk, rb_node);

		if (addr < chunk->vm->addr)
			p = &(*p)->rb_left;
		else if (addr > chunk->vm->addr)
			p = &(*p)->rb_right;
		else
			break;
	}

	if (parentp)
		*parentp = parent;
	return p;
}

/**
 * pcpu_chunk_addr_search - search for chunk containing specified address
 * @addr: address to search for
 *
 * Look for chunk which might contain @addr.  More specifically, it
 * searchs for the chunk with the highest start address which isn't
 * beyond @addr.
 *
 * CONTEXT:
 * pcpu_lock.
 *
 * RETURNS:
 * The address of the found chunk.
 */
static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
{
	struct rb_node *n, *parent;
	struct pcpu_chunk *chunk;

	/* is it in the reserved chunk? */
	if (pcpu_reserved_chunk) {
		void *start = pcpu_reserved_chunk->vm->addr;

		if (addr >= start && addr < start + pcpu_reserved_chunk_limit)
			return pcpu_reserved_chunk;
	}

	/* nah... search the regular ones */
	n = *pcpu_chunk_rb_search(addr, &parent);
	if (!n) {
		/* no exactly matching chunk, the parent is the closest */
		n = parent;
		BUG_ON(!n);
	}
	chunk = rb_entry(n, struct pcpu_chunk, rb_node);

	if (addr < chunk->vm->addr) {
		/* the parent was the next one, look for the previous one */
		n = rb_prev(n);
		BUG_ON(!n);
		chunk = rb_entry(n, struct pcpu_chunk, rb_node);
	}

	return chunk;
}

/**
 * pcpu_chunk_addr_insert - insert chunk into address rb tree
 * @new: chunk to insert
 *
 * Insert @new into address rb tree.
 *
 * CONTEXT:
 * pcpu_lock.
 */
static void pcpu_chunk_addr_insert(struct pcpu_chunk *new)
{
	struct rb_node **p, *parent;

	p = pcpu_chunk_rb_search(new->vm->addr, &parent);
	BUG_ON(*p);
	rb_link_node(&new->rb_node, parent, p);
	rb_insert_color(&new->rb_node, &pcpu_addr_root);
}

/**
 * pcpu_extend_area_map - extend area map for allocation
 * @chunk: target chunk
 *
 * Extend area map of @chunk so that it can accomodate an allocation.
 * A single allocation can split an area into three areas, so this
 * function makes sure that @chunk->map has at least two extra slots.
 *
 * CONTEXT:
 * pcpu_alloc_mutex, pcpu_lock.  pcpu_lock is released and reacquired
 * if area map is extended.
 *
 * RETURNS:
 * 0 if noop, 1 if successfully extended, -errno on failure.
 */
static int pcpu_extend_area_map(struct pcpu_chunk *chunk)
{
	int new_alloc;
	int *new;
	size_t size;

	/* has enough? */
	if (chunk->map_alloc >= chunk->map_used + 2)
		return 0;

	spin_unlock_irq(&pcpu_lock);

	new_alloc = PCPU_DFL_MAP_ALLOC;
	while (new_alloc < chunk->map_used + 2)
		new_alloc *= 2;

	new = pcpu_mem_alloc(new_alloc * sizeof(new[0]));
	if (!new) {
		spin_lock_irq(&pcpu_lock);
		return -ENOMEM;
	}

	/*
	 * Acquire pcpu_lock and switch to new area map.  Only free
	 * could have happened inbetween, so map_used couldn't have
	 * grown.
	 */
	spin_lock_irq(&pcpu_lock);
	BUG_ON(new_alloc < chunk->map_used + 2);

	size = chunk->map_alloc * sizeof(chunk->map[0]);
	memcpy(new, chunk->map, size);

	/*
	 * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is
	 * one of the first chunks and still using static map.
	 */
	if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC)
		pcpu_mem_free(chunk->map, size);

	chunk->map_alloc = new_alloc;
	chunk->map = new;
	return 0;
}

/**
 * pcpu_split_block - split a map block
 * @chunk: chunk of interest
 * @i: index of map block to split
 * @head: head size in bytes (can be 0)
 * @tail: tail size in bytes (can be 0)
 *
 * Split the @i'th map block into two or three blocks.  If @head is
 * non-zero, @head bytes block is inserted before block @i moving it
 * to @i+1 and reducing its size by @head bytes.
 *
 * If @tail is non-zero, the target block, which can be @i or @i+1
 * depending on @head, is reduced by @tail bytes and @tail byte block
 * is inserted after the target block.
 *
 * @chunk->map must have enough free slots to accomodate the split.
 *
 * CONTEXT:
 * pcpu_lock.
 */
static void pcpu_split_block(struct pcpu_chunk *chunk, int i,
			     int head, int tail)
{
	int nr_extra = !!head + !!tail;

	BUG_ON(chunk->map_alloc < chunk->map_used + nr_extra);

	/* insert new subblocks */
	memmove(&chunk->map[i + nr_extra], &chunk->map[i],
		sizeof(chunk->map[0]) * (chunk->map_used - i));
	chunk->map_used += nr_extra;

	if (head) {
		chunk->map[i + 1] = chunk->map[i] - head;
		chunk->map[i++] = head;
	}
	if (tail) {
		chunk->map[i++] -= tail;
		chunk->map[i] = tail;
	}
}

/**
 * pcpu_alloc_area - allocate area from a pcpu_chunk
 * @chunk: chunk of interest
 * @size: wanted size in bytes
 * @align: wanted align
 *
 * Try to allocate @size bytes area aligned at @align from @chunk.
 * Note that this function only allocates the offset.  It doesn't
 * populate or map the area.
 *
 * @chunk->map must have at least two free slots.
 *
 * CONTEXT:
 * pcpu_lock.
 *
 * RETURNS:
 * Allocated offset in @chunk on success, -1 if no matching area is
 * found.
 */
static int pcpu_alloc_area(struct pcpu_chunk *chunk, int size, int align)
{
	int oslot = pcpu_chunk_slot(chunk);
	int max_contig = 0;
	int i, off;

	for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++])) {
		bool is_last = i + 1 == chunk->map_used;
		int head, tail;

		/* extra for alignment requirement */
		head = ALIGN(off, align) - off;
		BUG_ON(i == 0 && head != 0);

		if (chunk->map[i] < 0)
			continue;
		if (chunk->map[i] < head + size) {
			max_contig = max(chunk->map[i], max_contig);
			continue;
		}

		/*
		 * If head is small or the previous block is free,
		 * merge'em.  Note that 'small' is defined as smaller
		 * than sizeof(int), which is very small but isn't too
		 * uncommon for percpu allocations.
		 */
		if (head && (head < sizeof(int) || chunk->map[i - 1] > 0)) {
			if (chunk->map[i - 1] > 0)
				chunk->map[i - 1] += head;
			else {
				chunk->map[i - 1] -= head;
				chunk->free_size -= head;
			}
			chunk->map[i] -= head;
			off += head;
			head = 0;
		}

		/* if tail is small, just keep it around */
		tail = chunk->map[i] - head - size;
		if (tail < sizeof(int))
			tail = 0;

		/* split if warranted */
		if (head || tail) {
			pcpu_split_block(chunk, i, head, tail);
			if (head) {
				i++;
				off += head;
				max_contig = max(chunk->map[i - 1], max_contig);
			}
			if (tail)
				max_contig = max(chunk->map[i + 1], max_contig);
		}

		/* update hint and mark allocated */
		if (is_last)
			chunk->contig_hint = max_contig; /* fully scanned */
		else
			chunk->contig_hint = max(chunk->contig_hint,
						 max_contig);

		chunk->free_size -= chunk->map[i];
		chunk->map[i] = -chunk->map[i];

		pcpu_chunk_relocate(chunk, oslot);
		return off;
	}

	chunk->contig_hint = max_contig;	/* fully scanned */
	pcpu_chunk_relocate(chunk, oslot);

	/* tell the upper layer that this chunk has no matching area */
	return -1;
}

/**
 * pcpu_free_area - free area to a pcpu_chunk
 * @chunk: chunk of interest
 * @freeme: offset of area to free
 *
 * Free area starting from @freeme to @chunk.  Note that this function
 * only modifies the allocation map.  It doesn't depopulate or unmap
 * the area.
 *
 * CONTEXT:
 * pcpu_lock.
 */
static void pcpu_free_area(struct pcpu_chunk *chunk, int freeme)
{
	int oslot = pcpu_chunk_slot(chunk);
	int i, off;

	for (i = 0, off = 0; i < chunk->map_used; off += abs(chunk->map[i++]))
		if (off == freeme)
			break;
	BUG_ON(off != freeme);
	BUG_ON(chunk->map[i] > 0);

	chunk->map[i] = -chunk->map[i];
	chunk->free_size += chunk->map[i];

	/* merge with previous? */
	if (i > 0 && chunk->map[i - 1] >= 0) {
		chunk->map[i - 1] += chunk->map[i];
		chunk->map_used--;
		memmove(&chunk->map[i], &chunk->map[i + 1],
			(chunk->map_used - i) * sizeof(chunk->map[0]));
		i--;
	}
	/* merge with next? */
	if (i + 1 < chunk->map_used && chunk->map[i + 1] >= 0) {
		chunk->map[i] += chunk->map[i + 1];
		chunk->map_used--;
		memmove(&chunk->map[i + 1], &chunk->map[i + 2],
			(chunk->map_used - (i + 1)) * sizeof(chunk->map[0]));
	}

	chunk->contig_hint = max(chunk->map[i], chunk->contig_hint);
	pcpu_chunk_relocate(chunk, oslot);
}

/**
 * pcpu_unmap - unmap pages out of a pcpu_chunk
 * @chunk: chunk of interest
 * @page_start: page index of the first page to unmap
 * @page_end: page index of the last page to unmap + 1
 * @flush: whether to flush cache and tlb or not
 *
 * For each cpu, unmap pages [@page_start,@page_end) out of @chunk.
 * If @flush is true, vcache is flushed before unmapping and tlb
 * after.
 */
static void pcpu_unmap(struct pcpu_chunk *chunk, int page_start, int page_end,
		       bool flush)
{
	unsigned int last = num_possible_cpus() - 1;
	unsigned int cpu;

	/* unmap must not be done on immutable chunk */
	WARN_ON(chunk->immutable);

	/*
	 * Each flushing trial can be very expensive, issue flush on
	 * the whole region at once rather than doing it for each cpu.
	 * This could be an overkill but is more scalable.
	 */
	if (flush)
		flush_cache_vunmap(pcpu_chunk_addr(chunk, 0, page_start),
				   pcpu_chunk_addr(chunk, last, page_end));

	for_each_possible_cpu(cpu)
		unmap_kernel_range_noflush(
				pcpu_chunk_addr(chunk, cpu, page_start),
				(page_end - page_start) << PAGE_SHIFT);

	/* ditto as flush_cache_vunmap() */
	if (flush)
		flush_tlb_kernel_range(pcpu_chunk_addr(chunk, 0, page_start),
				       pcpu_chunk_addr(chunk, last, page_end));
}

/**
 * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk
 * @chunk: chunk to depopulate
 * @off: offset to the area to depopulate
 * @size: size of the area to depopulate in bytes
 * @flush: whether to flush cache and tlb or not
 *
 * For each cpu, depopulate and unmap pages [@page_start,@page_end)
 * from @chunk.  If @flush is true, vcache is flushed before unmapping
 * and tlb after.
 *
 * CONTEXT:
 * pcpu_alloc_mutex.
 */
static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size,
				  bool flush)
{
	int page_start = PFN_DOWN(off);
	int page_end = PFN_UP(off + size);
	int unmap_start = -1;
	int uninitialized_var(unmap_end);
	unsigned int cpu;
	int i;

	for (i = page_start; i < page_end; i++) {
		for_each_possible_cpu(cpu) {
			struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i);

			if (!*pagep)
				continue;

			__free_page(*pagep);

			/*
			 * If it's partial depopulation, it might get
			 * populated or depopulated again.  Mark the
			 * page gone.
			 */
			*pagep = NULL;

			unmap_start = unmap_start < 0 ? i : unmap_start;
			unmap_end = i + 1;
		}
	}

	if (unmap_start >= 0)
		pcpu_unmap(chunk, unmap_start, unmap_end, flush);
}

/**
 * pcpu_map - map pages into a pcpu_chunk
 * @chunk: chunk of interest
 * @page_start: page index of the first page to map
 * @page_end: page index of the last page to map + 1
 *
 * For each cpu, map pages [@page_start,@page_end) into @chunk.
 * vcache is flushed afterwards.
 */
static int pcpu_map(struct pcpu_chunk *chunk, int page_start, int page_end)
{
	unsigned int last = num_possible_cpus() - 1;
	unsigned int cpu;
	int err;

	/* map must not be done on immutable chunk */
	WARN_ON(chunk->immutable);

	for_each_possible_cpu(cpu) {
		err = map_kernel_range_noflush(
				pcpu_chunk_addr(chunk, cpu, page_start),
				(page_end - page_start) << PAGE_SHIFT,
				PAGE_KERNEL,
				pcpu_chunk_pagep(chunk, cpu, page_start));
		if (err < 0)
			return err;
	}

	/* flush at once, please read comments in pcpu_unmap() */
	flush_cache_vmap(pcpu_chunk_addr(chunk, 0, page_start),
			 pcpu_chunk_addr(chunk, last, page_end));
	return 0;
}

/**
 * pcpu_populate_chunk - populate and map an area of a pcpu_chunk
 * @chunk: chunk of interest
 * @off: offset to the area to populate
 * @size: size of the area to populate in bytes
 *
 * For each cpu, populate and map pages [@page_start,@page_end) into
 * @chunk.  The area is cleared on return.
 *
 * CONTEXT:
 * pcpu_alloc_mutex, does GFP_KERNEL allocation.
 */
static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
{
	const gfp_t alloc_mask = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
	int page_start = PFN_DOWN(off);
	int page_end = PFN_UP(off + size);
	int map_start = -1;
	int uninitialized_var(map_end);
	unsigned int cpu;
	int i;

	for (i = page_start; i < page_end; i++) {
		if (pcpu_chunk_page_occupied(chunk, i)) {
			if (map_start >= 0) {
				if (pcpu_map(chunk, map_start, map_end))
					goto err;
				map_start = -1;
			}
			continue;
		}

		map_start = map_start < 0 ? i : map_start;
		map_end = i + 1;

		for_each_possible_cpu(cpu) {
			struct page **pagep = pcpu_chunk_pagep(chunk, cpu, i);

			*pagep = alloc_pages_node(cpu_to_node(cpu),
						  alloc_mask, 0);
			if (!*pagep)
				goto err;
		}
	}

	if (map_start >= 0 && pcpu_map(chunk, map_start, map_end))
		goto err;

	for_each_possible_cpu(cpu)
		memset(chunk->vm->addr + cpu * pcpu_unit_size + off, 0,
		       size);

	return 0;
err:
	/* likely under heavy memory pressure, give memory back */
	pcpu_depopulate_chunk(chunk, off, size, true);
	return -ENOMEM;
}

static void free_pcpu_chunk(struct pcpu_chunk *chunk)
{
	if (!chunk)
		return;
	if (chunk->vm)
		free_vm_area(chunk->vm);
	pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0]));
	kfree(chunk);
}

static struct pcpu_chunk *alloc_pcpu_chunk(void)
{
	struct pcpu_chunk *chunk;

	chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL);
	if (!chunk)
		return NULL;

	chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
	chunk->map_alloc = PCPU_DFL_MAP_ALLOC;
	chunk->map[chunk->map_used++] = pcpu_unit_size;
	chunk->page = chunk->page_ar;

	chunk->vm = get_vm_area(pcpu_chunk_size, GFP_KERNEL);
	if (!chunk->vm) {
		free_pcpu_chunk(chunk);
		return NULL;
	}

	INIT_LIST_HEAD(&chunk->list);
	chunk->free_size = pcpu_unit_size;
	chunk->contig_hint = pcpu_unit_size;

	return chunk;
}

/**
 * pcpu_alloc - the percpu allocator
 * @size: size of area to allocate in bytes
 * @align: alignment of area (max PAGE_SIZE)
 * @reserved: allocate from the reserved chunk if available
 *
 * Allocate percpu area of @size bytes aligned at @align.
 *
 * CONTEXT:
 * Does GFP_KERNEL allocation.
 *
 * RETURNS:
 * Percpu pointer to the allocated area on success, NULL on failure.
 */
static void *pcpu_alloc(size_t size, size_t align, bool reserved)
{
	struct pcpu_chunk *chunk;
	int slot, off;

	if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE)) {
		WARN(true, "illegal size (%zu) or align (%zu) for "
		     "percpu allocation\n", size, align);
		return NULL;
	}

	mutex_lock(&pcpu_alloc_mutex);
	spin_lock_irq(&pcpu_lock);

	/* serve reserved allocations from the reserved chunk if available */
	if (reserved && pcpu_reserved_chunk) {
		chunk = pcpu_reserved_chunk;
		if (size > chunk->contig_hint ||
		    pcpu_extend_area_map(chunk) < 0)
			goto fail_unlock;
		off = pcpu_alloc_area(chunk, size, align);
		if (off >= 0)
			goto area_found;
		goto fail_unlock;
	}

restart:
	/* search through normal chunks */
	for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) {
		list_for_each_entry(chunk, &pcpu_slot[slot], list) {
			if (size > chunk->contig_hint)
				continue;

			switch (pcpu_extend_area_map(chunk)) {
			case 0:
				break;
			case 1:
				goto restart;	/* pcpu_lock dropped, restart */
			default:
				goto fail_unlock;
			}

			off = pcpu_alloc_area(chunk, size, align);
			if (off >= 0)
				goto area_found;
		}
	}

	/* hmmm... no space left, create a new chunk */
	spin_unlock_irq(&pcpu_lock);

	chunk = alloc_pcpu_chunk();
	if (!chunk)
		goto fail_unlock_mutex;

	spin_lock_irq(&pcpu_lock);
	pcpu_chunk_relocate(chunk, -1);
	pcpu_chunk_addr_insert(chunk);
	goto restart;

area_found:
	spin_unlock_irq(&pcpu_lock);

	/* populate, map and clear the area */
	if (pcpu_populate_chunk(chunk, off, size)) {
		spin_lock_irq(&pcpu_lock);
		pcpu_free_area(chunk, off);
		goto fail_unlock;
	}

	mutex_unlock(&pcpu_alloc_mutex);

	return __addr_to_pcpu_ptr(chunk->vm->addr + off);

fail_unlock:
	spin_unlock_irq(&pcpu_lock);
fail_unlock_mutex:
	mutex_unlock(&pcpu_alloc_mutex);
	return NULL;
}

/**
 * __alloc_percpu - allocate dynamic percpu area
 * @size: size of area to allocate in bytes
 * @align: alignment of area (max PAGE_SIZE)
 *
 * Allocate percpu area of @size bytes aligned at @align.  Might
 * sleep.  Might trigger writeouts.
 *
 * CONTEXT:
 * Does GFP_KERNEL allocation.
 *
 * RETURNS:
 * Percpu pointer to the allocated area on success, NULL on failure.
 */
void *__alloc_percpu(size_t size, size_t align)
{
	return pcpu_alloc(size, align, false);
}
EXPORT_SYMBOL_GPL(__alloc_percpu);

/**
 * __alloc_reserved_percpu - allocate reserved percpu area
 * @size: size of area to allocate in bytes
 * @align: alignment of area (max PAGE_SIZE)
 *
 * Allocate percpu area of @size bytes aligned at @align from reserved
 * percpu area if arch has set it up; otherwise, allocation is served
 * from the same dynamic area.  Might sleep.  Might trigger writeouts.
 *
 * CONTEXT:
 * Does GFP_KERNEL allocation.
 *
 * RETURNS:
 * Percpu pointer to the allocated area on success, NULL on failure.
 */
void *__alloc_reserved_percpu(size_t size, size_t align)
{
	return pcpu_alloc(size, align, true);
}

/**
 * pcpu_reclaim - reclaim fully free chunks, workqueue function
 * @work: unused
 *
 * Reclaim all fully free chunks except for the first one.
 *
 * CONTEXT:
 * workqueue context.
 */
static void pcpu_reclaim(struct work_struct *work)
{
	LIST_HEAD(todo);
	struct list_head *head = &pcpu_slot[pcpu_nr_slots - 1];
	struct pcpu_chunk *chunk, *next;

	mutex_lock(&pcpu_alloc_mutex);
	spin_lock_irq(&pcpu_lock);

	list_for_each_entry_safe(chunk, next, head, list) {
		WARN_ON(chunk->immutable);

		/* spare the first one */
		if (chunk == list_first_entry(head, struct pcpu_chunk, list))
			continue;

		rb_erase(&chunk->rb_node, &pcpu_addr_root);
		list_move(&chunk->list, &todo);
	}

	spin_unlock_irq(&pcpu_lock);
	mutex_unlock(&pcpu_alloc_mutex);

	list_for_each_entry_safe(chunk, next, &todo, list) {
		pcpu_depopulate_chunk(chunk, 0, pcpu_unit_size, false);
		free_pcpu_chunk(chunk);
	}
}

/**
 * free_percpu - free percpu area
 * @ptr: pointer to area to free
 *
 * Free percpu area @ptr.
 *
 * CONTEXT:
 * Can be called from atomic context.
 */
void free_percpu(void *ptr)
{
	void *addr = __pcpu_ptr_to_addr(ptr);
	struct pcpu_chunk *chunk;
	unsigned long flags;
	int off;

	if (!ptr)
		return;

	spin_lock_irqsave(&pcpu_lock, flags);

	chunk = pcpu_chunk_addr_search(addr);
	off = addr - chunk->vm->addr;

	pcpu_free_area(chunk, off);

	/* if there are more than one fully free chunks, wake up grim reaper */
	if (chunk->free_size == pcpu_unit_size) {
		struct pcpu_chunk *pos;

		list_for_each_entry(pos, &pcpu_slot[pcpu_nr_slots - 1], list)
			if (pos != chunk) {
				schedule_work(&pcpu_reclaim_work);
				break;
			}
	}

	spin_unlock_irqrestore(&pcpu_lock, flags);
}
EXPORT_SYMBOL_GPL(free_percpu);

/**
 * pcpu_setup_first_chunk - initialize the first percpu chunk
 * @get_page_fn: callback to fetch page pointer
 * @static_size: the size of static percpu area in bytes
 * @reserved_size: the size of reserved percpu area in bytes
 * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto
 * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
 * @base_addr: mapped address, NULL for auto
 * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary
 *
 * Initialize the first percpu chunk which contains the kernel static
 * perpcu area.  This function is to be called from arch percpu area
 * setup path.  The first two parameters are mandatory.  The rest are
 * optional.
 *
 * @get_page_fn() should return pointer to percpu page given cpu
 * number and page number.  It should at least return enough pages to
 * cover the static area.  The returned pages for static area should
 * have been initialized with valid data.  If @unit_size is specified,
 * it can also return pages after the static area.  NULL return
 * indicates end of pages for the cpu.  Note that @get_page_fn() must
 * return the same number of pages for all cpus.
 *
 * @reserved_size, if non-zero, specifies the amount of bytes to
 * reserve after the static area in the first chunk.  This reserves
 * the first chunk such that it's available only through reserved
 * percpu allocation.  This is primarily used to serve module percpu
 * static areas on architectures where the addressing model has
 * limited offset range for symbol relocations to guarantee module
 * percpu symbols fall inside the relocatable range.
 *
 * @unit_size, if non-negative, specifies unit size and must be
 * aligned to PAGE_SIZE and equal to or larger than @static_size +
 * @reserved_size + @dyn_size.
 *
 * @dyn_size, if non-negative, limits the number of bytes available
 * for dynamic allocation in the first chunk.  Specifying non-negative
 * value make percpu leave alone the area beyond @static_size +
 * @reserved_size + @dyn_size.
 *
 * Non-null @base_addr means that the caller already allocated virtual
 * region for the first chunk and mapped it.  percpu must not mess
 * with the chunk.  Note that @base_addr with 0 @unit_size or non-NULL
 * @populate_pte_fn doesn't make any sense.
 *
 * @populate_pte_fn is used to populate the pagetable.  NULL means the
 * caller already populated the pagetable.
 *
 * If the first chunk ends up with both reserved and dynamic areas, it
 * is served by two chunks - one to serve the core static and reserved
 * areas and the other for the dynamic area.  They share the same vm
 * and page map but uses different area allocation map to stay away
 * from each other.  The latter chunk is circulated in the chunk slots
 * and available for dynamic allocation like any other chunks.
 *
 * RETURNS:
 * The determined pcpu_unit_size which can be used to initialize
 * percpu access.
 */
size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
				     size_t static_size, size_t reserved_size,
				     ssize_t unit_size, ssize_t dyn_size,
				     void *base_addr,
				     pcpu_populate_pte_fn_t populate_pte_fn)
{
	static struct vm_struct first_vm;
	static int smap[2], dmap[2];
	struct pcpu_chunk *schunk, *dchunk = NULL;
	unsigned int cpu;
	int nr_pages;
	int err, i;

	/* santiy checks */
	BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC ||
		     ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
	BUG_ON(!static_size);
	if (unit_size >= 0) {
		BUG_ON(unit_size < static_size + reserved_size +
				   (dyn_size >= 0 ? dyn_size : 0));
		BUG_ON(unit_size & ~PAGE_MASK);
	} else {
		BUG_ON(dyn_size >= 0);
		BUG_ON(base_addr);
	}
	BUG_ON(base_addr && populate_pte_fn);

	if (unit_size >= 0)
		pcpu_unit_pages = unit_size >> PAGE_SHIFT;
	else
		pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT,
					PFN_UP(static_size + reserved_size));

	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
	pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size;
	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk)
		+ num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *);

	if (dyn_size < 0)
		dyn_size = pcpu_unit_size - static_size - reserved_size;

	/*
	 * Allocate chunk slots.  The additional last slot is for
	 * empty chunks.
	 */
	pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
	pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0]));
	for (i = 0; i < pcpu_nr_slots; i++)
		INIT_LIST_HEAD(&pcpu_slot[i]);

	/*
	 * Initialize static chunk.  If reserved_size is zero, the
	 * static chunk covers static area + dynamic allocation area
	 * in the first chunk.  If reserved_size is not zero, it
	 * covers static area + reserved area (mostly used for module
	 * static percpu allocation).
	 */
	schunk = alloc_bootmem(pcpu_chunk_struct_size);
	INIT_LIST_HEAD(&schunk->list);
	schunk->vm = &first_vm;
	schunk->map = smap;
	schunk->map_alloc = ARRAY_SIZE(smap);
	schunk->page = schunk->page_ar;

	if (reserved_size) {
		schunk->free_size = reserved_size;
		pcpu_reserved_chunk = schunk;	/* not for dynamic alloc */
	} else {
		schunk->free_size = dyn_size;
		dyn_size = 0;			/* dynamic area covered */
	}
	schunk->contig_hint = schunk->free_size;

	schunk->map[schunk->map_used++] = -static_size;
	if (schunk->free_size)
		schunk->map[schunk->map_used++] = schunk->free_size;

	pcpu_reserved_chunk_limit = static_size + schunk->free_size;

	/* init dynamic chunk if necessary */
	if (dyn_size) {
		dchunk = alloc_bootmem(sizeof(struct pcpu_chunk));
		INIT_LIST_HEAD(&dchunk->list);
		dchunk->vm = &first_vm;
		dchunk->map = dmap;
		dchunk->map_alloc = ARRAY_SIZE(dmap);
		dchunk->page = schunk->page_ar;	/* share page map with schunk */

		dchunk->contig_hint = dchunk->free_size = dyn_size;
		dchunk->map[dchunk->map_used++] = -pcpu_reserved_chunk_limit;
		dchunk->map[dchunk->map_used++] = dchunk->free_size;
	}

	/* allocate vm address */
	first_vm.flags = VM_ALLOC;
	first_vm.size = pcpu_chunk_size;

	if (!base_addr)
		vm_area_register_early(&first_vm, PAGE_SIZE);
	else {
		/*
		 * Pages already mapped.  No need to remap into
		 * vmalloc area.  In this case the first chunks can't
		 * be mapped or unmapped by percpu and are marked
		 * immutable.
		 */
		first_vm.addr = base_addr;
		schunk->immutable = true;
		if (dchunk)
			dchunk->immutable = true;
	}

	/* assign pages */
	nr_pages = -1;
	for_each_possible_cpu(cpu) {
		for (i = 0; i < pcpu_unit_pages; i++) {
			struct page *page = get_page_fn(cpu, i);

			if (!page)
				break;
			*pcpu_chunk_pagep(schunk, cpu, i) = page;
		}

		BUG_ON(i < PFN_UP(static_size));

		if (nr_pages < 0)
			nr_pages = i;
		else
			BUG_ON(nr_pages != i);
	}

	/* map them */
	if (populate_pte_fn) {
		for_each_possible_cpu(cpu)
			for (i = 0; i < nr_pages; i++)
				populate_pte_fn(pcpu_chunk_addr(schunk,
								cpu, i));

		err = pcpu_map(schunk, 0, nr_pages);
		if (err)
			panic("failed to setup static percpu area, err=%d\n",
			      err);
	}

	/* link the first chunk in */
	if (!dchunk) {
		pcpu_chunk_relocate(schunk, -1);
		pcpu_chunk_addr_insert(schunk);
	} else {
		pcpu_chunk_relocate(dchunk, -1);
		pcpu_chunk_addr_insert(dchunk);
	}

	/* we're done */
	pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0);
	return pcpu_unit_size;
}