summaryrefslogtreecommitdiffstats
path: root/mm/percpu.c
blob: e2ac58a39bb2369b67445ec5a95acab681e91ba6 (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
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
/*
 * 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 boot-time determined number of 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.  On UMA, units corresponds directly to
 * cpus.  On NUMA, the mapping can be non-linear and even sparse.
 * Percpu access can be done by configuring percpu base registers
 * according to cpu to unit mapping and pcpu_unit_size.
 *
 * There are usually many small percpu allocations many of them being
 * 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 can be determined from the address using the index field
 * in the page struct. The index field contains a pointer to the chunk.
 *
 * To use this allocator, arch code should do the followings.
 *
 * - drop CONFIG_HAVE_LEGACY_PER_CPU_AREA
 *
 * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
 *   regular address to percpu pointer and back if they need to be
 *   different from the default
 *
 * - 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/log2.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/pfn.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>

#include <asm/cacheflush.h>
#include <asm/sections.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 */

/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
#ifndef __addr_to_pcpu_ptr
#define __addr_to_pcpu_ptr(addr)					\
	(void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr	\
		 + (unsigned long)__per_cpu_start)
#endif
#ifndef __pcpu_ptr_to_addr
#define __pcpu_ptr_to_addr(ptr)						\
	(void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr	\
		 - (unsigned long)__per_cpu_start)
#endif

struct pcpu_chunk {
	struct list_head	list;		/* linked to pcpu_slot lists */
	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 */
	unsigned long		populated[];	/* populated bitmap */
};

static int pcpu_unit_pages __read_mostly;
static int pcpu_unit_size __read_mostly;
static int pcpu_nr_units __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;

/* cpus with the lowest and highest unit numbers */
static unsigned int pcpu_first_unit_cpu __read_mostly;
static unsigned int pcpu_last_unit_cpu __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);

/* cpu -> unit map */
const int *pcpu_unit_map __read_mostly;

/*
 * The first chunk which always exists.  Note that unlike other
 * chunks, this one can be allocated and mapped in several different
 * ways and thus often doesn't live in the vmalloc area.
 */
static struct pcpu_chunk *pcpu_first_chunk;

/*
 * Optional reserved chunk.  This chunk reserves part of the first
 * chunk and serves it for reserved allocations.  The amount of
 * reserved offset is in pcpu_reserved_chunk_limit.  When reserved
 * area doesn't exist, the following variables contain NULL and 0
 * respectively.
 */
static struct pcpu_chunk *pcpu_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, populated bitmap and
 * vmalloc mapping.  The latter is a spinlock and protects the index
 * data structures - chunk slots, 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 */

/* 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 pcpu_unit_map[cpu] * pcpu_unit_pages + 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 struct page *pcpu_chunk_page(struct pcpu_chunk *chunk,
				    unsigned int cpu, int page_idx)
{
	/* must not be used on pre-mapped chunk */
	WARN_ON(chunk->immutable);

	return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx));
}

/* set the pointer to a chunk in a page struct */
static void pcpu_set_page_chunk(struct page *page, struct pcpu_chunk *pcpu)
{
	page->index = (unsigned long)pcpu;
}

/* obtain pointer to a chunk from a page struct */
static struct pcpu_chunk *pcpu_get_page_chunk(struct page *page)
{
	return (struct pcpu_chunk *)page->index;
}

static void pcpu_next_unpop(struct pcpu_chunk *chunk, int *rs, int *re, int end)
{
	*rs = find_next_zero_bit(chunk->populated, end, *rs);
	*re = find_next_bit(chunk->populated, end, *rs + 1);
}

static void pcpu_next_pop(struct pcpu_chunk *chunk, int *rs, int *re, int end)
{
	*rs = find_next_bit(chunk->populated, end, *rs);
	*re = find_next_zero_bit(chunk->populated, end, *rs + 1);
}

/*
 * (Un)populated page region iterators.  Iterate over (un)populated
 * page regions betwen @start and @end in @chunk.  @rs and @re should
 * be integer variables and will be set to start and end page index of
 * the current region.
 */
#define pcpu_for_each_unpop_region(chunk, rs, re, start, end)		    \
	for ((rs) = (start), pcpu_next_unpop((chunk), &(rs), &(re), (end)); \
	     (rs) < (re);						    \
	     (rs) = (re) + 1, pcpu_next_unpop((chunk), &(rs), &(re), (end)))

#define pcpu_for_each_pop_region(chunk, rs, re, start, end)		    \
	for ((rs) = (start), pcpu_next_pop((chunk), &(rs), &(re), (end));   \
	     (rs) < (re);						    \
	     (rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end)))

/**
 * 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]);
	}
}

/**
 * pcpu_chunk_addr_search - determine chunk containing specified address
 * @addr: address for which the chunk needs to be determined.
 *
 * RETURNS:
 * The address of the found chunk.
 */
static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
{
	void *first_start = pcpu_first_chunk->vm->addr;

	/* is it in the first chunk? */
	if (addr >= first_start && addr < first_start + pcpu_unit_size) {
		/* is it in the reserved area? */
		if (addr < first_start + pcpu_reserved_chunk_limit)
			return pcpu_reserved_chunk;
		return pcpu_first_chunk;
	}

	/*
	 * The address is relative to unit0 which might be unused and
	 * thus unmapped.  Offset the address to the unit space of the
	 * current processor before looking it up in the vmalloc
	 * space.  Note that any possible cpu id can be used here, so
	 * there's no need to worry about preemption or cpu hotplug.
	 */
	addr += pcpu_unit_map[smp_processor_id()] * pcpu_unit_size;
	return pcpu_get_page_chunk(vmalloc_to_page(addr));
}

/**
 * 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_get_pages_and_bitmap - get temp pages array and bitmap
 * @chunk: chunk of interest
 * @bitmapp: output parameter for bitmap
 * @may_alloc: may allocate the array
 *
 * Returns pointer to array of pointers to struct page and bitmap,
 * both of which can be indexed with pcpu_page_idx().  The returned
 * array is cleared to zero and *@bitmapp is copied from
 * @chunk->populated.  Note that there is only one array and bitmap
 * and access exclusion is the caller's responsibility.
 *
 * CONTEXT:
 * pcpu_alloc_mutex and does GFP_KERNEL allocation if @may_alloc.
 * Otherwise, don't care.
 *
 * RETURNS:
 * Pointer to temp pages array on success, NULL on failure.
 */
static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
					       unsigned long **bitmapp,
					       bool may_alloc)
{
	static struct page **pages;
	static unsigned long *bitmap;
	size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]);
	size_t bitmap_size = BITS_TO_LONGS(pcpu_unit_pages) *
			     sizeof(unsigned long);

	if (!pages || !bitmap) {
		if (may_alloc && !pages)
			pages = pcpu_mem_alloc(pages_size);
		if (may_alloc && !bitmap)
			bitmap = pcpu_mem_alloc(bitmap_size);
		if (!pages || !bitmap)
			return NULL;
	}

	memset(pages, 0, pages_size);
	bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages);

	*bitmapp = bitmap;
	return pages;
}

/**
 * pcpu_free_pages - free pages which were allocated for @chunk
 * @chunk: chunk pages were allocated for
 * @pages: array of pages to be freed, indexed by pcpu_page_idx()
 * @populated: populated bitmap
 * @page_start: page index of the first page to be freed
 * @page_end: page index of the last page to be freed + 1
 *
 * Free pages [@page_start and @page_end) in @pages for all units.
 * The pages were allocated for @chunk.
 */
static void pcpu_free_pages(struct pcpu_chunk *chunk,
			    struct page **pages, unsigned long *populated,
			    int page_start, int page_end)
{
	unsigned int cpu;
	int i;

	for_each_possible_cpu(cpu) {
		for (i = page_start; i < page_end; i++) {
			struct page *page = pages[pcpu_page_idx(cpu, i)];

			if (page)
				__free_page(page);
		}
	}
}

/**
 * pcpu_alloc_pages - allocates pages for @chunk
 * @chunk: target chunk
 * @pages: array to put the allocated pages into, indexed by pcpu_page_idx()
 * @populated: populated bitmap
 * @page_start: page index of the first page to be allocated
 * @page_end: page index of the last page to be allocated + 1
 *
 * Allocate pages [@page_start,@page_end) into @pages for all units.
 * The allocation is for @chunk.  Percpu core doesn't care about the
 * content of @pages and will pass it verbatim to pcpu_map_pages().
 */
static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
			    struct page **pages, unsigned long *populated,
			    int page_start, int page_end)
{
	const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
	unsigned int cpu;
	int i;

	for_each_possible_cpu(cpu) {
		for (i = page_start; i < page_end; i++) {
			struct page **pagep = &pages[pcpu_page_idx(cpu, i)];

			*pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0);
			if (!*pagep) {
				pcpu_free_pages(chunk, pages, populated,
						page_start, page_end);
				return -ENOMEM;
			}
		}
	}
	return 0;
}

/**
 * pcpu_pre_unmap_flush - flush cache prior to unmapping
 * @chunk: chunk the regions to be flushed belongs to
 * @page_start: page index of the first page to be flushed
 * @page_end: page index of the last page to be flushed + 1
 *
 * Pages in [@page_start,@page_end) of @chunk are about to be
 * unmapped.  Flush cache.  As 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.
 */
static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
				 int page_start, int page_end)
{
	flush_cache_vunmap(
		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
}

static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
{
	unmap_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT);
}

/**
 * pcpu_unmap_pages - unmap pages out of a pcpu_chunk
 * @chunk: chunk of interest
 * @pages: pages array which can be used to pass information to free
 * @populated: populated bitmap
 * @page_start: page index of the first page to unmap
 * @page_end: page index of the last page to unmap + 1
 *
 * For each cpu, unmap pages [@page_start,@page_end) out of @chunk.
 * Corresponding elements in @pages were cleared by the caller and can
 * be used to carry information to pcpu_free_pages() which will be
 * called after all unmaps are finished.  The caller should call
 * proper pre/post flush functions.
 */
static void pcpu_unmap_pages(struct pcpu_chunk *chunk,
			     struct page **pages, unsigned long *populated,
			     int page_start, int page_end)
{
	unsigned int cpu;
	int i;

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

			page = pcpu_chunk_page(chunk, cpu, i);
			WARN_ON(!page);
			pages[pcpu_page_idx(cpu, i)] = page;
		}
		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start),
				   page_end - page_start);
	}

	for (i = page_start; i < page_end; i++)
		__clear_bit(i, populated);
}

/**
 * pcpu_post_unmap_tlb_flush - flush TLB after unmapping
 * @chunk: pcpu_chunk the regions to be flushed belong to
 * @page_start: page index of the first page to be flushed
 * @page_end: page index of the last page to be flushed + 1
 *
 * Pages [@page_start,@page_end) of @chunk have been unmapped.  Flush
 * TLB for the regions.  This can be skipped if the area is to be
 * returned to vmalloc as vmalloc will handle TLB flushing lazily.
 *
 * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
 * for the whole region.
 */
static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
				      int page_start, int page_end)
{
	flush_tlb_kernel_range(
		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
}

static int __pcpu_map_pages(unsigned long addr, struct page **pages,
			    int nr_pages)
{
	return map_kernel_range_noflush(addr, nr_pages << PAGE_SHIFT,
					PAGE_KERNEL, pages);
}

/**
 * pcpu_map_pages - map pages into a pcpu_chunk
 * @chunk: chunk of interest
 * @pages: pages array containing pages to be mapped
 * @populated: populated bitmap
 * @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.  The
 * caller is responsible for calling pcpu_post_map_flush() after all
 * mappings are complete.
 *
 * This function is responsible for setting corresponding bits in
 * @chunk->populated bitmap and whatever is necessary for reverse
 * lookup (addr -> chunk).
 */
static int pcpu_map_pages(struct pcpu_chunk *chunk,
			  struct page **pages, unsigned long *populated,
			  int page_start, int page_end)
{
	unsigned int cpu, tcpu;
	int i, err;

	for_each_possible_cpu(cpu) {
		err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start),
				       &pages[pcpu_page_idx(cpu, page_start)],
				       page_end - page_start);
		if (err < 0)
			goto err;
	}

	/* mapping successful, link chunk and mark populated */
	for (i = page_start; i < page_end; i++) {
		for_each_possible_cpu(cpu)
			pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)],
					    chunk);
		__set_bit(i, populated);
	}

	return 0;

err:
	for_each_possible_cpu(tcpu) {
		if (tcpu == cpu)
			break;
		__pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start),
				   page_end - page_start);
	}
	return err;
}

/**
 * pcpu_post_map_flush - flush cache after mapping
 * @chunk: pcpu_chunk the regions to be flushed belong to
 * @page_start: page index of the first page to be flushed
 * @page_end: page index of the last page to be flushed + 1
 *
 * Pages [@page_start,@page_end) of @chunk have been mapped.  Flush
 * cache.
 *
 * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once
 * for the whole region.
 */
static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
				int page_start, int page_end)
{
	flush_cache_vmap(
		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, 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)
{
	int page_start = PFN_DOWN(off);
	int page_end = PFN_UP(off + size);
	struct page **pages;
	unsigned long *populated;
	int rs, re;

	/* quick path, check whether it's empty already */
	pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
		if (rs == page_start && re == page_end)
			return;
		break;
	}

	/* immutable chunks can't be depopulated */
	WARN_ON(chunk->immutable);

	/*
	 * If control reaches here, there must have been at least one
	 * successful population attempt so the temp pages array must
	 * be available now.
	 */
	pages = pcpu_get_pages_and_bitmap(chunk, &populated, false);
	BUG_ON(!pages);

	/* unmap and free */
	pcpu_pre_unmap_flush(chunk, page_start, page_end);

	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
		pcpu_unmap_pages(chunk, pages, populated, rs, re);

	/* no need to flush tlb, vmalloc will handle it lazily */

	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end)
		pcpu_free_pages(chunk, pages, populated, rs, re);

	/* commit new bitmap */
	bitmap_copy(chunk->populated, populated, pcpu_unit_pages);
}

/**
 * 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)
{
	int page_start = PFN_DOWN(off);
	int page_end = PFN_UP(off + size);
	int free_end = page_start, unmap_end = page_start;
	struct page **pages;
	unsigned long *populated;
	unsigned int cpu;
	int rs, re, rc;

	/* quick path, check whether all pages are already there */
	pcpu_for_each_pop_region(chunk, rs, re, page_start, page_end) {
		if (rs == page_start && re == page_end)
			goto clear;
		break;
	}

	/* need to allocate and map pages, this chunk can't be immutable */
	WARN_ON(chunk->immutable);

	pages = pcpu_get_pages_and_bitmap(chunk, &populated, true);
	if (!pages)
		return -ENOMEM;

	/* alloc and map */
	pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
		rc = pcpu_alloc_pages(chunk, pages, populated, rs, re);
		if (rc)
			goto err_free;
		free_end = re;
	}

	pcpu_for_each_unpop_region(chunk, rs, re, page_start, page_end) {
		rc = pcpu_map_pages(chunk, pages, populated, rs, re);
		if (rc)
			goto err_unmap;
		unmap_end = re;
	}
	pcpu_post_map_flush(chunk, page_start, page_end);

	/* commit new bitmap */
	bitmap_copy(chunk->populated, populated, pcpu_unit_pages);
clear:
	for_each_possible_cpu(cpu)
		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
	return 0;

err_unmap:
	pcpu_pre_unmap_flush(chunk, page_start, unmap_end);
	pcpu_for_each_unpop_region(chunk, rs, re, page_start, unmap_end)
		pcpu_unmap_pages(chunk, pages, populated, rs, re);
	pcpu_post_unmap_tlb_flush(chunk, page_start, unmap_end);
err_free:
	pcpu_for_each_unpop_region(chunk, rs, re, page_start, free_end)
		pcpu_free_pages(chunk, pages, populated, rs, re);
	return rc;
}

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->vm = get_vm_area(pcpu_chunk_size, VM_ALLOC);
	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);
	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 address relative to unit0 */
	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;

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

	spin_unlock_irq(&pcpu_lock);

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

	mutex_unlock(&pcpu_alloc_mutex);
}

/**
 * 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
 * @static_size: the size of static percpu area in bytes
 * @reserved_size: the size of reserved percpu area in bytes, 0 for none
 * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
 * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE
 * @base_addr: mapped address
 * @unit_map: cpu -> unit map, NULL for sequential mapping
 *
 * Initialize the first percpu chunk which contains the kernel static
 * perpcu area.  This function is to be called from arch percpu area
 * setup path.
 *
 * @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.
 *
 * @dyn_size, if non-negative, determines the number of bytes
 * available for dynamic allocation in the first chunk.  Specifying
 * non-negative value makes percpu leave alone the area beyond
 * @static_size + @reserved_size + @dyn_size.
 *
 * @unit_size specifies unit size and must be aligned to PAGE_SIZE and
 * equal to or larger than @static_size + @reserved_size + if
 * non-negative, @dyn_size.
 *
 * The caller should have mapped the first chunk at @base_addr and
 * copied static data to each unit.
 *
 * 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(size_t static_size, size_t reserved_size,
				     ssize_t dyn_size, size_t unit_size,
				     void *base_addr, const int *unit_map)
{
	static struct vm_struct first_vm;
	static int smap[2], dmap[2];
	size_t size_sum = static_size + reserved_size +
			  (dyn_size >= 0 ? dyn_size : 0);
	struct pcpu_chunk *schunk, *dchunk = NULL;
	unsigned int cpu, tcpu;
	int i;

	/* sanity checks */
	BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC ||
		     ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
	BUG_ON(!static_size);
	BUG_ON(!base_addr);
	BUG_ON(unit_size < size_sum);
	BUG_ON(unit_size & ~PAGE_MASK);
	BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE);

	/* determine number of units and verify and initialize pcpu_unit_map */
	if (unit_map) {
		int first_unit = INT_MAX, last_unit = INT_MIN;

		for_each_possible_cpu(cpu) {
			int unit = unit_map[cpu];

			BUG_ON(unit < 0);
			for_each_possible_cpu(tcpu) {
				if (tcpu == cpu)
					break;
				/* the mapping should be one-to-one */
				BUG_ON(unit_map[tcpu] == unit);
			}

			if (unit < first_unit) {
				pcpu_first_unit_cpu = cpu;
				first_unit = unit;
			}
			if (unit > last_unit) {
				pcpu_last_unit_cpu = cpu;
				last_unit = unit;
			}
		}
		pcpu_nr_units = last_unit + 1;
		pcpu_unit_map = unit_map;
	} else {
		int *identity_map;

		/* #units == #cpus, identity mapped */
		identity_map = alloc_bootmem(nr_cpu_ids *
					     sizeof(identity_map[0]));

		for_each_possible_cpu(cpu)
			identity_map[cpu] = cpu;

		pcpu_first_unit_cpu = 0;
		pcpu_last_unit_cpu = pcpu_nr_units - 1;
		pcpu_nr_units = nr_cpu_ids;
		pcpu_unit_map = identity_map;
	}

	/* determine basic parameters */
	pcpu_unit_pages = unit_size >> PAGE_SHIFT;
	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
	pcpu_chunk_size = pcpu_nr_units * pcpu_unit_size;
	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
		BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);

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

	first_vm.flags = VM_ALLOC;
	first_vm.size = pcpu_chunk_size;
	first_vm.addr = base_addr;

	/*
	 * 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->immutable = true;
	bitmap_fill(schunk->populated, pcpu_unit_pages);

	if (reserved_size) {
		schunk->free_size = reserved_size;
		pcpu_reserved_chunk = schunk;
		pcpu_reserved_chunk_limit = static_size + reserved_size;
	} 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;

	/* init dynamic chunk if necessary */
	if (dyn_size) {
		dchunk = alloc_bootmem(pcpu_chunk_struct_size);
		INIT_LIST_HEAD(&dchunk->list);
		dchunk->vm = &first_vm;
		dchunk->map = dmap;
		dchunk->map_alloc = ARRAY_SIZE(dmap);
		dchunk->immutable = true;
		bitmap_fill(dchunk->populated, pcpu_unit_pages);

		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;
	}

	/* link the first chunk in */
	pcpu_first_chunk = dchunk ?: schunk;
	pcpu_chunk_relocate(pcpu_first_chunk, -1);

	/* we're done */
	pcpu_base_addr = schunk->vm->addr;
	return pcpu_unit_size;
}

const char *pcpu_fc_names[PCPU_FC_NR] __initdata = {
	[PCPU_FC_AUTO]	= "auto",
	[PCPU_FC_EMBED]	= "embed",
	[PCPU_FC_PAGE]	= "page",
	[PCPU_FC_LPAGE]	= "lpage",
};

enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO;

static int __init percpu_alloc_setup(char *str)
{
	if (0)
		/* nada */;
#ifdef CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK
	else if (!strcmp(str, "embed"))
		pcpu_chosen_fc = PCPU_FC_EMBED;
#endif
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
	else if (!strcmp(str, "page"))
		pcpu_chosen_fc = PCPU_FC_PAGE;
#endif
#ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK
	else if (!strcmp(str, "lpage"))
		pcpu_chosen_fc = PCPU_FC_LPAGE;
#endif
	else
		pr_warning("PERCPU: unknown allocator %s specified\n", str);

	return 0;
}
early_param("percpu_alloc", percpu_alloc_setup);

static inline size_t pcpu_calc_fc_sizes(size_t static_size,
					size_t reserved_size,
					ssize_t *dyn_sizep)
{
	size_t size_sum;

	size_sum = PFN_ALIGN(static_size + reserved_size +
			     (*dyn_sizep >= 0 ? *dyn_sizep : 0));
	if (*dyn_sizep != 0)
		*dyn_sizep = size_sum - static_size - reserved_size;

	return size_sum;
}

#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
	!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
/**
 * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
 *
 * This is a helper to ease setting up embedded first percpu chunk and
 * can be called where pcpu_setup_first_chunk() is expected.
 *
 * If this function is used to setup the first chunk, it is allocated
 * as a contiguous area using bootmem allocator and used as-is without
 * being mapped into vmalloc area.  This enables the first chunk to
 * piggy back on the linear physical mapping which often uses larger
 * page size.
 *
 * When @dyn_size is positive, dynamic area might be larger than
 * specified to fill page alignment.  When @dyn_size is auto,
 * @dyn_size is just big enough to fill page alignment after static
 * and reserved areas.
 *
 * If the needed size is smaller than the minimum or specified unit
 * size, the leftover is returned to the bootmem allocator.
 *
 * RETURNS:
 * The determined pcpu_unit_size which can be used to initialize
 * percpu access on success, -errno on failure.
 */
ssize_t __init pcpu_embed_first_chunk(size_t reserved_size, ssize_t dyn_size)
{
	const size_t static_size = __per_cpu_end - __per_cpu_start;
	size_t size_sum, unit_size, chunk_size;
	void *base;
	unsigned int cpu;

	/* determine parameters and allocate */
	size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, &dyn_size);

	unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
	chunk_size = unit_size * nr_cpu_ids;

	base = __alloc_bootmem_nopanic(chunk_size, PAGE_SIZE,
				       __pa(MAX_DMA_ADDRESS));
	if (!base) {
		pr_warning("PERCPU: failed to allocate %zu bytes for "
			   "embedding\n", chunk_size);
		return -ENOMEM;
	}

	/* return the leftover and copy */
	for (cpu = 0; cpu < nr_cpu_ids; cpu++) {
		void *ptr = base + cpu * unit_size;

		if (cpu_possible(cpu)) {
			free_bootmem(__pa(ptr + size_sum),
				     unit_size - size_sum);
			memcpy(ptr, __per_cpu_load, static_size);
		} else
			free_bootmem(__pa(ptr), unit_size);
	}

	/* we're ready, commit */
	pr_info("PERCPU: Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
		PFN_DOWN(size_sum), base, static_size, reserved_size, dyn_size,
		unit_size);

	return pcpu_setup_first_chunk(static_size, reserved_size, dyn_size,
				      unit_size, base, NULL);
}
#endif /* CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK ||
	  !CONFIG_HAVE_SETUP_PER_CPU_AREA */

#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
/**
 * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
 * @reserved_size: the size of reserved percpu area in bytes
 * @alloc_fn: function to allocate percpu page, always called with PAGE_SIZE
 * @free_fn: funtion to free percpu page, always called with PAGE_SIZE
 * @populate_pte_fn: function to populate pte
 *
 * This is a helper to ease setting up page-remapped first percpu
 * chunk and can be called where pcpu_setup_first_chunk() is expected.
 *
 * This is the basic allocator.  Static percpu area is allocated
 * page-by-page into vmalloc area.
 *
 * RETURNS:
 * The determined pcpu_unit_size which can be used to initialize
 * percpu access on success, -errno on failure.
 */
ssize_t __init pcpu_page_first_chunk(size_t reserved_size,
				     pcpu_fc_alloc_fn_t alloc_fn,
				     pcpu_fc_free_fn_t free_fn,
				     pcpu_fc_populate_pte_fn_t populate_pte_fn)
{
	static struct vm_struct vm;
	const size_t static_size = __per_cpu_end - __per_cpu_start;
	char psize_str[16];
	int unit_pages;
	size_t pages_size;
	struct page **pages;
	unsigned int cpu;
	int i, j;
	ssize_t ret;

	snprintf(psize_str, sizeof(psize_str), "%luK", PAGE_SIZE >> 10);

	unit_pages = PFN_UP(max_t(size_t, static_size + reserved_size,
				  PCPU_MIN_UNIT_SIZE));

	/* unaligned allocations can't be freed, round up to page size */
	pages_size = PFN_ALIGN(unit_pages * nr_cpu_ids * sizeof(pages[0]));
	pages = alloc_bootmem(pages_size);

	/* allocate pages */
	j = 0;
	for_each_possible_cpu(cpu)
		for (i = 0; i < unit_pages; i++) {
			void *ptr;

			ptr = alloc_fn(cpu, PAGE_SIZE);
			if (!ptr) {
				pr_warning("PERCPU: failed to allocate %s page "
					   "for cpu%u\n", psize_str, cpu);
				goto enomem;
			}
			pages[j++] = virt_to_page(ptr);
		}

	/* allocate vm area, map the pages and copy static data */
	vm.flags = VM_ALLOC;
	vm.size = nr_cpu_ids * unit_pages << PAGE_SHIFT;
	vm_area_register_early(&vm, PAGE_SIZE);

	for_each_possible_cpu(cpu) {
		unsigned long unit_addr = (unsigned long)vm.addr +
			(cpu * unit_pages << PAGE_SHIFT);

		for (i = 0; i < unit_pages; i++)
			populate_pte_fn(unit_addr + (i << PAGE_SHIFT));

		/* pte already populated, the following shouldn't fail */
		ret = __pcpu_map_pages(unit_addr, &pages[cpu * unit_pages],
				       unit_pages);
		if (ret < 0)
			panic("failed to map percpu area, err=%zd\n", ret);

		/*
		 * FIXME: Archs with virtual cache should flush local
		 * cache for the linear mapping here - something
		 * equivalent to flush_cache_vmap() on the local cpu.
		 * flush_cache_vmap() can't be used as most supporting
		 * data structures are not set up yet.
		 */

		/* copy static data */
		memcpy((void *)unit_addr, __per_cpu_load, static_size);
	}

	/* we're ready, commit */
	pr_info("PERCPU: %d %s pages/cpu @%p s%zu r%zu\n",
		unit_pages, psize_str, vm.addr, static_size, reserved_size);

	ret = pcpu_setup_first_chunk(static_size, reserved_size, -1,
				     unit_pages << PAGE_SHIFT, vm.addr, NULL);
	goto out_free_ar;

enomem:
	while (--j >= 0)
		free_fn(page_address(pages[j]), PAGE_SIZE);
	ret = -ENOMEM;
out_free_ar:
	free_bootmem(__pa(pages), pages_size);
	return ret;
}
#endif /* CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK */

#ifdef CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK
/**
 * pcpu_lpage_build_unit_map - build unit_map for large page remapping
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_sizep: in/out parameter for dynamic size, -1 for auto
 * @unit_sizep: out parameter for unit size
 * @unit_map: unit_map to be filled
 * @cpu_distance_fn: callback to determine distance between cpus
 *
 * This function builds cpu -> unit map and determine other parameters
 * considering needed percpu size, large page size and distances
 * between CPUs in NUMA.
 *
 * CPUs which are of LOCAL_DISTANCE both ways are grouped together and
 * may share units in the same large page.  The returned configuration
 * is guaranteed to have CPUs on different nodes on different large
 * pages and >=75% usage of allocated virtual address space.
 *
 * RETURNS:
 * On success, fills in @unit_map, sets *@dyn_sizep, *@unit_sizep and
 * returns the number of units to be allocated.  -errno on failure.
 */
int __init pcpu_lpage_build_unit_map(size_t reserved_size, ssize_t *dyn_sizep,
				     size_t *unit_sizep, size_t lpage_size,
				     int *unit_map,
				     pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
{
	static int group_map[NR_CPUS] __initdata;
	static int group_cnt[NR_CPUS] __initdata;
	const size_t static_size = __per_cpu_end - __per_cpu_start;
	int group_cnt_max = 0;
	size_t size_sum, min_unit_size, alloc_size;
	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
	int last_allocs;
	unsigned int cpu, tcpu;
	int group, unit;

	/*
	 * Determine min_unit_size, alloc_size and max_upa such that
	 * alloc_size is multiple of lpage_size and is the smallest
	 * which can accomodate 4k aligned segments which are equal to
	 * or larger than min_unit_size.
	 */
	size_sum = pcpu_calc_fc_sizes(static_size, reserved_size, dyn_sizep);
	min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);

	alloc_size = roundup(min_unit_size, lpage_size);
	upa = alloc_size / min_unit_size;
	while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
		upa--;
	max_upa = upa;

	/* group cpus according to their proximity */
	for_each_possible_cpu(cpu) {
		group = 0;
	next_group:
		for_each_possible_cpu(tcpu) {
			if (cpu == tcpu)
				break;
			if (group_map[tcpu] == group &&
			    (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
				group++;
				goto next_group;
			}
		}
		group_map[cpu] = group;
		group_cnt[group]++;
		group_cnt_max = max(group_cnt_max, group_cnt[group]);
	}

	/*
	 * Expand unit size until address space usage goes over 75%
	 * and then as much as possible without using more address
	 * space.
	 */
	last_allocs = INT_MAX;
	for (upa = max_upa; upa; upa--) {
		int allocs = 0, wasted = 0;

		if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
			continue;

		for (group = 0; group_cnt[group]; group++) {
			int this_allocs = DIV_ROUND_UP(group_cnt[group], upa);
			allocs += this_allocs;
			wasted += this_allocs * upa - group_cnt[group];
		}

		/*
		 * Don't accept if wastage is over 25%.  The
		 * greater-than comparison ensures upa==1 always
		 * passes the following check.
		 */
		if (wasted > num_possible_cpus() / 3)
			continue;

		/* and then don't consume more memory */
		if (allocs > last_allocs)
			break;
		last_allocs = allocs;
		best_upa = upa;
	}
	*unit_sizep = alloc_size / best_upa;

	/* assign units to cpus accordingly */
	unit = 0;
	for (group = 0; group_cnt[group]; group++) {
		for_each_possible_cpu(cpu)
			if (group_map[cpu] == group)
				unit_map[cpu] = unit++;
		unit = roundup(unit, best_upa);
	}

	return unit;	/* unit contains aligned number of units */
}

struct pcpul_ent {
	void		*ptr;
	void		*map_addr;
};

static size_t pcpul_size;
static size_t pcpul_lpage_size;
static int pcpul_nr_lpages;
static struct pcpul_ent *pcpul_map;

static bool __init pcpul_unit_to_cpu(int unit, const int *unit_map,
				     unsigned int *cpup)
{
	unsigned int cpu;

	for_each_possible_cpu(cpu)
		if (unit_map[cpu] == unit) {
			if (cpup)
				*cpup = cpu;
			return true;
		}

	return false;
}

static void __init pcpul_lpage_dump_cfg(const char *lvl, size_t static_size,
					size_t reserved_size, size_t dyn_size,
					size_t unit_size, size_t lpage_size,
					const int *unit_map, int nr_units)
{
	int width = 1, v = nr_units;
	char empty_str[] = "--------";
	int upl, lpl;	/* units per lpage, lpage per line */
	unsigned int cpu;
	int lpage, unit;

	while (v /= 10)
		width++;
	empty_str[min_t(int, width, sizeof(empty_str) - 1)] = '\0';

	upl = max_t(int, lpage_size / unit_size, 1);
	lpl = rounddown_pow_of_two(max_t(int, 60 / (upl * (width + 1) + 2), 1));

	printk("%spcpu-lpage: sta/res/dyn=%zu/%zu/%zu unit=%zu lpage=%zu", lvl,
	       static_size, reserved_size, dyn_size, unit_size, lpage_size);

	for (lpage = 0, unit = 0; unit < nr_units; unit++) {
		if (!(unit % upl)) {
			if (!(lpage++ % lpl)) {
				printk("\n");
				printk("%spcpu-lpage: ", lvl);
			} else
				printk("| ");
		}
		if (pcpul_unit_to_cpu(unit, unit_map, &cpu))
			printk("%0*d ", width, cpu);
		else
			printk("%s ", empty_str);
	}
	printk("\n");
}

/**
 * pcpu_lpage_first_chunk - remap the first percpu chunk using large page
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_size: free size for dynamic allocation in bytes
 * @unit_size: unit size in bytes
 * @lpage_size: the size of a large page
 * @unit_map: cpu -> unit mapping
 * @nr_units: the number of units
 * @alloc_fn: function to allocate percpu lpage, always called with lpage_size
 * @free_fn: function to free percpu memory, @size <= lpage_size
 * @map_fn: function to map percpu lpage, always called with lpage_size
 *
 * This allocator uses large page to build and map the first chunk.
 * Unlike other helpers, the caller should always specify @dyn_size
 * and @unit_size.  These parameters along with @unit_map and
 * @nr_units can be determined using pcpu_lpage_build_unit_map().
 * This two stage initialization is to allow arch code to evaluate the
 * parameters before committing to it.
 *
 * Large pages are allocated as directed by @unit_map and other
 * parameters and mapped to vmalloc space.  Unused holes are returned
 * to the page allocator.  Note that these holes end up being actively
 * mapped twice - once to the physical mapping and to the vmalloc area
 * for the first percpu chunk.  Depending on architecture, this might
 * cause problem when changing page attributes of the returned area.
 * These double mapped areas can be detected using
 * pcpu_lpage_remapped().
 *
 * RETURNS:
 * The determined pcpu_unit_size which can be used to initialize
 * percpu access on success, -errno on failure.
 */
ssize_t __init pcpu_lpage_first_chunk(size_t reserved_size, size_t dyn_size,
				      size_t unit_size, size_t lpage_size,
				      const int *unit_map, int nr_units,
				      pcpu_fc_alloc_fn_t alloc_fn,
				      pcpu_fc_free_fn_t free_fn,
				      pcpu_fc_map_fn_t map_fn)
{
	static struct vm_struct vm;
	const size_t static_size = __per_cpu_end - __per_cpu_start;
	size_t chunk_size = unit_size * nr_units;
	size_t map_size;
	unsigned int cpu;
	ssize_t ret;
	int i, j, unit;

	pcpul_lpage_dump_cfg(KERN_DEBUG, static_size, reserved_size, dyn_size,
			     unit_size, lpage_size, unit_map, nr_units);

	BUG_ON(chunk_size % lpage_size);

	pcpul_size = static_size + reserved_size + dyn_size;
	pcpul_lpage_size = lpage_size;
	pcpul_nr_lpages = chunk_size / lpage_size;

	/* allocate pointer array and alloc large pages */
	map_size = pcpul_nr_lpages * sizeof(pcpul_map[0]);
	pcpul_map = alloc_bootmem(map_size);

	/* allocate all pages */
	for (i = 0; i < pcpul_nr_lpages; i++) {
		size_t offset = i * lpage_size;
		int first_unit = offset / unit_size;
		int last_unit = (offset + lpage_size - 1) / unit_size;
		void *ptr;

		/* find out which cpu is mapped to this unit */
		for (unit = first_unit; unit <= last_unit; unit++)
			if (pcpul_unit_to_cpu(unit, unit_map, &cpu))
				goto found;
		continue;
	found:
		ptr = alloc_fn(cpu, lpage_size);
		if (!ptr) {
			pr_warning("PERCPU: failed to allocate large page "
				   "for cpu%u\n", cpu);
			goto enomem;
		}

		pcpul_map[i].ptr = ptr;
	}

	/* return unused holes */
	for (unit = 0; unit < nr_units; unit++) {
		size_t start = unit * unit_size;
		size_t end = start + unit_size;
		size_t off, next;

		/* don't free used part of occupied unit */
		if (pcpul_unit_to_cpu(unit, unit_map, NULL))
			start += pcpul_size;

		/* unit can span more than one page, punch the holes */
		for (off = start; off < end; off = next) {
			void *ptr = pcpul_map[off / lpage_size].ptr;
			next = min(roundup(off + 1, lpage_size), end);
			if (ptr)
				free_fn(ptr + off % lpage_size, next - off);
		}
	}

	/* allocate address, map and copy */
	vm.flags = VM_ALLOC;
	vm.size = chunk_size;
	vm_area_register_early(&vm, unit_size);

	for (i = 0; i < pcpul_nr_lpages; i++) {
		if (!pcpul_map[i].ptr)
			continue;
		pcpul_map[i].map_addr = vm.addr + i * lpage_size;
		map_fn(pcpul_map[i].ptr, lpage_size, pcpul_map[i].map_addr);
	}

	for_each_possible_cpu(cpu)
		memcpy(vm.addr + unit_map[cpu] * unit_size, __per_cpu_load,
		       static_size);

	/* we're ready, commit */
	pr_info("PERCPU: large pages @%p s%zu r%zu d%zu u%zu\n",
		vm.addr, static_size, reserved_size, dyn_size, unit_size);

	ret = pcpu_setup_first_chunk(static_size, reserved_size, dyn_size,
				     unit_size, vm.addr, unit_map);

	/*
	 * Sort pcpul_map array for pcpu_lpage_remapped().  Unmapped
	 * lpages are pushed to the end and trimmed.
	 */
	for (i = 0; i < pcpul_nr_lpages - 1; i++)
		for (j = i + 1; j < pcpul_nr_lpages; j++) {
			struct pcpul_ent tmp;

			if (!pcpul_map[j].ptr)
				continue;
			if (pcpul_map[i].ptr &&
			    pcpul_map[i].ptr < pcpul_map[j].ptr)
				continue;

			tmp = pcpul_map[i];
			pcpul_map[i] = pcpul_map[j];
			pcpul_map[j] = tmp;
		}

	while (pcpul_nr_lpages && !pcpul_map[pcpul_nr_lpages - 1].ptr)
		pcpul_nr_lpages--;

	return ret;

enomem:
	for (i = 0; i < pcpul_nr_lpages; i++)
		if (pcpul_map[i].ptr)
			free_fn(pcpul_map[i].ptr, lpage_size);
	free_bootmem(__pa(pcpul_map), map_size);
	return -ENOMEM;
}

/**
 * pcpu_lpage_remapped - determine whether a kaddr is in pcpul recycled area
 * @kaddr: the kernel address in question
 *
 * Determine whether @kaddr falls in the pcpul recycled area.  This is
 * used by pageattr to detect VM aliases and break up the pcpu large
 * page mapping such that the same physical page is not mapped under
 * different attributes.
 *
 * The recycled area is always at the tail of a partially used large
 * page.
 *
 * RETURNS:
 * Address of corresponding remapped pcpu address if match is found;
 * otherwise, NULL.
 */
void *pcpu_lpage_remapped(void *kaddr)
{
	unsigned long lpage_mask = pcpul_lpage_size - 1;
	void *lpage_addr = (void *)((unsigned long)kaddr & ~lpage_mask);
	unsigned long offset = (unsigned long)kaddr & lpage_mask;
	int left = 0, right = pcpul_nr_lpages - 1;
	int pos;

	/* pcpul in use at all? */
	if (!pcpul_map)
		return NULL;

	/* okay, perform binary search */
	while (left <= right) {
		pos = (left + right) / 2;

		if (pcpul_map[pos].ptr < lpage_addr)
			left = pos + 1;
		else if (pcpul_map[pos].ptr > lpage_addr)
			right = pos - 1;
		else
			return pcpul_map[pos].map_addr + offset;
	}

	return NULL;
}
#endif /* CONFIG_NEED_PER_CPU_LPAGE_FIRST_CHUNK */

/*
 * Generic percpu area setup.
 *
 * The embedding helper is used because its behavior closely resembles
 * the original non-dynamic generic percpu area setup.  This is
 * important because many archs have addressing restrictions and might
 * fail if the percpu area is located far away from the previous
 * location.  As an added bonus, in non-NUMA cases, embedding is
 * generally a good idea TLB-wise because percpu area can piggy back
 * on the physical linear memory mapping which uses large page
 * mappings on applicable archs.
 */
#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);

void __init setup_per_cpu_areas(void)
{
	ssize_t unit_size;
	unsigned long delta;
	unsigned int cpu;

	/*
	 * Always reserve area for module percpu variables.  That's
	 * what the legacy allocator did.
	 */
	unit_size = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
					   PERCPU_DYNAMIC_RESERVE);
	if (unit_size < 0)
		panic("Failed to initialized percpu areas.");

	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
	for_each_possible_cpu(cpu)
		__per_cpu_offset[cpu] = delta + cpu * unit_size;
}
#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
OpenPOWER on IntegriCloud