summaryrefslogtreecommitdiff
path: root/mm/percpu.c
blob: a0e0c82c1e4cd22324e87a86a5df7301f35b8a83 (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
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
/*
 * mm/percpu.c - percpu memory allocator
 *
 * Copyright (C) 2009		SUSE Linux Products GmbH
 * Copyright (C) 2009		Tejun Heo <tj@kernel.org>
 *
 * Copyright (C) 2017		Facebook Inc.
 * Copyright (C) 2017		Dennis Zhou <dennisszhou@gmail.com>
 *
 * This file is released under the GPLv2 license.
 *
 * The percpu allocator handles both static and dynamic areas.  Percpu
 * areas are allocated in chunks which are divided into units.  There is
 * a 1-to-1 mapping for units to possible cpus.  These units are grouped
 * based on NUMA properties of the machine.
 *
 *  c0                           c1                         c2
 *  -------------------          -------------------        ------------
 * | u0 | u1 | u2 | u3 |        | u0 | u1 | u2 | u3 |      | u0 | u1 | u
 *  -------------------  ......  -------------------  ....  ------------
 *
 * Allocation is done by offsets into a unit's address space.  Ie., an
 * area of 512 bytes at 6k in c1 occupies 512 bytes at 6k in c1:u0,
 * c1:u1, c1:u2, etc.  On NUMA machines, the mapping may be non-linear
 * and even sparse.  Access is handled by configuring percpu base
 * registers according to the cpu to unit mappings and offsetting the
 * base address using pcpu_unit_size.
 *
 * There is special consideration for the first chunk which must handle
 * the static percpu variables in the kernel image as allocation services
 * are not online yet.  In short, the first chunk is structured like so:
 *
 *                  <Static | [Reserved] | Dynamic>
 *
 * The static data is copied from the original section managed by the
 * linker.  The reserved section, if non-zero, primarily manages static
 * percpu variables from kernel modules.  Finally, the dynamic section
 * takes care of normal allocations.
 *
 * The allocator organizes chunks into lists according to free size and
 * tries to allocate from the fullest chunk first.  Each chunk is managed
 * by a bitmap with metadata blocks.  The allocation map is updated on
 * every allocation and free to reflect the current state while the boundary
 * map is only updated on allocation.  Each metadata block contains
 * information to help mitigate the need to iterate over large portions
 * of the bitmap.  The reverse mapping from page to chunk is stored in
 * the page's index.  Lastly, units are lazily backed and grow in unison.
 *
 * There is a unique conversion that goes on here between bytes and bits.
 * Each bit represents a fragment of size PCPU_MIN_ALLOC_SIZE.  The chunk
 * tracks the number of pages it is responsible for in nr_pages.  Helper
 * functions are used to convert from between the bytes, bits, and blocks.
 * All hints are managed in bits unless explicitly stated.
 *
 * To use this allocator, arch code should do the following:
 *
 * - 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
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/bitmap.h>
#include <linux/bootmem.h>
#include <linux/err.h>
#include <linux/lcm.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 <linux/kmemleak.h>

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

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

#include "percpu-internal.h"

/* the slots are sorted by free bytes left, 1-31 bytes share the same slot */
#define PCPU_SLOT_BASE_SHIFT		5

#define PCPU_EMPTY_POP_PAGES_LOW	2
#define PCPU_EMPTY_POP_PAGES_HIGH	4

#ifdef CONFIG_SMP
/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
#ifndef __addr_to_pcpu_ptr
#define __addr_to_pcpu_ptr(addr)					\
	(void __percpu *)((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 __force *)((unsigned long)(ptr) +				\
			 (unsigned long)pcpu_base_addr -		\
			 (unsigned long)__per_cpu_start)
#endif
#else	/* CONFIG_SMP */
/* on UP, it's always identity mapped */
#define __addr_to_pcpu_ptr(addr)	(void __percpu *)(addr)
#define __pcpu_ptr_to_addr(ptr)		(void __force *)(ptr)
#endif	/* CONFIG_SMP */

static int pcpu_unit_pages __ro_after_init;
static int pcpu_unit_size __ro_after_init;
static int pcpu_nr_units __ro_after_init;
static int pcpu_atom_size __ro_after_init;
int pcpu_nr_slots __ro_after_init;
static size_t pcpu_chunk_struct_size __ro_after_init;

/* cpus with the lowest and highest unit addresses */
static unsigned int pcpu_low_unit_cpu __ro_after_init;
static unsigned int pcpu_high_unit_cpu __ro_after_init;

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

static const int *pcpu_unit_map __ro_after_init;		/* cpu -> unit */
const unsigned long *pcpu_unit_offsets __ro_after_init;	/* cpu -> unit offset */

/* group information, used for vm allocation */
static int pcpu_nr_groups __ro_after_init;
static const unsigned long *pcpu_group_offsets __ro_after_init;
static const size_t *pcpu_group_sizes __ro_after_init;

/*
 * 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.
 */
struct pcpu_chunk *pcpu_first_chunk __ro_after_init;

/*
 * Optional reserved chunk.  This chunk reserves part of the first
 * chunk and serves it for reserved allocations.  When the reserved
 * region doesn't exist, the following variable is NULL.
 */
struct pcpu_chunk *pcpu_reserved_chunk __ro_after_init;

DEFINE_SPINLOCK(pcpu_lock);	/* all internal data structures */
static DEFINE_MUTEX(pcpu_alloc_mutex);	/* chunk create/destroy, [de]pop, map ext */

struct list_head *pcpu_slot __ro_after_init; /* chunk list slots */

/* chunks which need their map areas extended, protected by pcpu_lock */
static LIST_HEAD(pcpu_map_extend_chunks);

/*
 * The number of empty populated pages, protected by pcpu_lock.  The
 * reserved chunk doesn't contribute to the count.
 */
int pcpu_nr_empty_pop_pages;

/*
 * Balance work is used to populate or destroy chunks asynchronously.  We
 * try to keep the number of populated free pages between
 * PCPU_EMPTY_POP_PAGES_LOW and HIGH for atomic allocations and at most one
 * empty chunk.
 */
static void pcpu_balance_workfn(struct work_struct *work);
static DECLARE_WORK(pcpu_balance_work, pcpu_balance_workfn);
static bool pcpu_async_enabled __read_mostly;
static bool pcpu_atomic_alloc_failed;

static void pcpu_schedule_balance_work(void)
{
	if (pcpu_async_enabled)
		schedule_work(&pcpu_balance_work);
}

/**
 * pcpu_addr_in_chunk - check if the address is served from this chunk
 * @chunk: chunk of interest
 * @addr: percpu address
 *
 * RETURNS:
 * True if the address is served from this chunk.
 */
static bool pcpu_addr_in_chunk(struct pcpu_chunk *chunk, void *addr)
{
	void *start_addr, *end_addr;

	if (!chunk)
		return false;

	start_addr = chunk->base_addr + chunk->start_offset;
	end_addr = chunk->base_addr + chunk->nr_pages * PAGE_SIZE -
		   chunk->end_offset;

	return addr >= start_addr && addr < end_addr;
}

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_bytes < PCPU_MIN_ALLOC_SIZE || chunk->contig_bits == 0)
		return 0;

	return pcpu_size_to_slot(chunk->free_bytes);
}

/* 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 int __maybe_unused pcpu_page_idx(unsigned int cpu, int page_idx)
{
	return pcpu_unit_map[cpu] * pcpu_unit_pages + page_idx;
}

static unsigned long pcpu_unit_page_offset(unsigned int cpu, int page_idx)
{
	return pcpu_unit_offsets[cpu] + (page_idx << PAGE_SHIFT);
}

static unsigned long pcpu_chunk_addr(struct pcpu_chunk *chunk,
				     unsigned int cpu, int page_idx)
{
	return (unsigned long)chunk->base_addr +
	       pcpu_unit_page_offset(cpu, page_idx);
}

static void pcpu_next_unpop(unsigned long *bitmap, int *rs, int *re, int end)
{
	*rs = find_next_zero_bit(bitmap, end, *rs);
	*re = find_next_bit(bitmap, end, *rs + 1);
}

static void pcpu_next_pop(unsigned long *bitmap, int *rs, int *re, int end)
{
	*rs = find_next_bit(bitmap, end, *rs);
	*re = find_next_zero_bit(bitmap, end, *rs + 1);
}

/*
 * Bitmap region iterators.  Iterates over the bitmap between
 * [@start, @end) in @chunk.  @rs and @re should be integer variables
 * and will be set to start and end index of the current free region.
 */
#define pcpu_for_each_unpop_region(bitmap, rs, re, start, end)		     \
	for ((rs) = (start), pcpu_next_unpop((bitmap), &(rs), &(re), (end)); \
	     (rs) < (re);						     \
	     (rs) = (re) + 1, pcpu_next_unpop((bitmap), &(rs), &(re), (end)))

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

/*
 * The following are helper functions to help access bitmaps and convert
 * between bitmap offsets to address offsets.
 */
static unsigned long *pcpu_index_alloc_map(struct pcpu_chunk *chunk, int index)
{
	return chunk->alloc_map +
	       (index * PCPU_BITMAP_BLOCK_BITS / BITS_PER_LONG);
}

static unsigned long pcpu_off_to_block_index(int off)
{
	return off / PCPU_BITMAP_BLOCK_BITS;
}

static unsigned long pcpu_off_to_block_off(int off)
{
	return off & (PCPU_BITMAP_BLOCK_BITS - 1);
}

static unsigned long pcpu_block_off_to_off(int index, int off)
{
	return index * PCPU_BITMAP_BLOCK_BITS + off;
}

/**
 * pcpu_next_md_free_region - finds the next hint free area
 * @chunk: chunk of interest
 * @bit_off: chunk offset
 * @bits: size of free area
 *
 * Helper function for pcpu_for_each_md_free_region.  It checks
 * block->contig_hint and performs aggregation across blocks to find the
 * next hint.  It modifies bit_off and bits in-place to be consumed in the
 * loop.
 */
static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off,
				     int *bits)
{
	int i = pcpu_off_to_block_index(*bit_off);
	int block_off = pcpu_off_to_block_off(*bit_off);
	struct pcpu_block_md *block;

	*bits = 0;
	for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk);
	     block++, i++) {
		/* handles contig area across blocks */
		if (*bits) {
			*bits += block->left_free;
			if (block->left_free == PCPU_BITMAP_BLOCK_BITS)
				continue;
			return;
		}

		/*
		 * This checks three things.  First is there a contig_hint to
		 * check.  Second, have we checked this hint before by
		 * comparing the block_off.  Third, is this the same as the
		 * right contig hint.  In the last case, it spills over into
		 * the next block and should be handled by the contig area
		 * across blocks code.
		 */
		*bits = block->contig_hint;
		if (*bits && block->contig_hint_start >= block_off &&
		    *bits + block->contig_hint_start < PCPU_BITMAP_BLOCK_BITS) {
			*bit_off = pcpu_block_off_to_off(i,
					block->contig_hint_start);
			return;
		}
		/* reset to satisfy the second predicate above */
		block_off = 0;

		*bits = block->right_free;
		*bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free;
	}
}

/**
 * pcpu_next_fit_region - finds fit areas for a given allocation request
 * @chunk: chunk of interest
 * @alloc_bits: size of allocation
 * @align: alignment of area (max PAGE_SIZE)
 * @bit_off: chunk offset
 * @bits: size of free area
 *
 * Finds the next free region that is viable for use with a given size and
 * alignment.  This only returns if there is a valid area to be used for this
 * allocation.  block->first_free is returned if the allocation request fits
 * within the block to see if the request can be fulfilled prior to the contig
 * hint.
 */
static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits,
				 int align, int *bit_off, int *bits)
{
	int i = pcpu_off_to_block_index(*bit_off);
	int block_off = pcpu_off_to_block_off(*bit_off);
	struct pcpu_block_md *block;

	*bits = 0;
	for (block = chunk->md_blocks + i; i < pcpu_chunk_nr_blocks(chunk);
	     block++, i++) {
		/* handles contig area across blocks */
		if (*bits) {
			*bits += block->left_free;
			if (*bits >= alloc_bits)
				return;
			if (block->left_free == PCPU_BITMAP_BLOCK_BITS)
				continue;
		}

		/* check block->contig_hint */
		*bits = ALIGN(block->contig_hint_start, align) -
			block->contig_hint_start;
		/*
		 * This uses the block offset to determine if this has been
		 * checked in the prior iteration.
		 */
		if (block->contig_hint &&
		    block->contig_hint_start >= block_off &&
		    block->contig_hint >= *bits + alloc_bits) {
			*bits += alloc_bits + block->contig_hint_start -
				 block->first_free;
			*bit_off = pcpu_block_off_to_off(i, block->first_free);
			return;
		}
		/* reset to satisfy the second predicate above */
		block_off = 0;

		*bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free,
				 align);
		*bits = PCPU_BITMAP_BLOCK_BITS - *bit_off;
		*bit_off = pcpu_block_off_to_off(i, *bit_off);
		if (*bits >= alloc_bits)
			return;
	}

	/* no valid offsets were found - fail condition */
	*bit_off = pcpu_chunk_map_bits(chunk);
}

/*
 * Metadata free area iterators.  These perform aggregation of free areas
 * based on the metadata blocks and return the offset @bit_off and size in
 * bits of the free area @bits.  pcpu_for_each_fit_region only returns when
 * a fit is found for the allocation request.
 */
#define pcpu_for_each_md_free_region(chunk, bit_off, bits)		\
	for (pcpu_next_md_free_region((chunk), &(bit_off), &(bits));	\
	     (bit_off) < pcpu_chunk_map_bits((chunk));			\
	     (bit_off) += (bits) + 1,					\
	     pcpu_next_md_free_region((chunk), &(bit_off), &(bits)))

#define pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits)     \
	for (pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \
				  &(bits));				      \
	     (bit_off) < pcpu_chunk_map_bits((chunk));			      \
	     (bit_off) += (bits),					      \
	     pcpu_next_fit_region((chunk), (alloc_bits), (align), &(bit_off), \
				  &(bits)))

/**
 * pcpu_mem_zalloc - allocate memory
 * @size: bytes to allocate
 *
 * Allocate @size bytes.  If @size is smaller than PAGE_SIZE,
 * kzalloc() is used; otherwise, vzalloc() 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_zalloc(size_t size)
{
	if (WARN_ON_ONCE(!slab_is_available()))
		return NULL;

	if (size <= PAGE_SIZE)
		return kzalloc(size, GFP_KERNEL);
	else
		return vzalloc(size);
}

/**
 * pcpu_mem_free - free memory
 * @ptr: memory to free
 *
 * Free @ptr.  @ptr should have been allocated using pcpu_mem_zalloc().
 */
static void pcpu_mem_free(void *ptr)
{
	kvfree(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_cnt_pop_pages- counts populated backing pages in range
 * @chunk: chunk of interest
 * @bit_off: start offset
 * @bits: size of area to check
 *
 * Calculates the number of populated pages in the region
 * [page_start, page_end).  This keeps track of how many empty populated
 * pages are available and decide if async work should be scheduled.
 *
 * RETURNS:
 * The nr of populated pages.
 */
static inline int pcpu_cnt_pop_pages(struct pcpu_chunk *chunk, int bit_off,
				     int bits)
{
	int page_start = PFN_UP(bit_off * PCPU_MIN_ALLOC_SIZE);
	int page_end = PFN_DOWN((bit_off + bits) * PCPU_MIN_ALLOC_SIZE);

	if (page_start >= page_end)
		return 0;

	/*
	 * bitmap_weight counts the number of bits set in a bitmap up to
	 * the specified number of bits.  This is counting the populated
	 * pages up to page_end and then subtracting the populated pages
	 * up to page_start to count the populated pages in
	 * [page_start, page_end).
	 */
	return bitmap_weight(chunk->populated, page_end) -
	       bitmap_weight(chunk->populated, page_start);
}

/**
 * pcpu_chunk_update - updates the chunk metadata given a free area
 * @chunk: chunk of interest
 * @bit_off: chunk offset
 * @bits: size of free area
 *
 * This updates the chunk's contig hint and starting offset given a free area.
 * Choose the best starting offset if the contig hint is equal.
 */
static void pcpu_chunk_update(struct pcpu_chunk *chunk, int bit_off, int bits)
{
	if (bits > chunk->contig_bits) {
		chunk->contig_bits_start = bit_off;
		chunk->contig_bits = bits;
	} else if (bits == chunk->contig_bits && chunk->contig_bits_start &&
		   (!bit_off ||
		    __ffs(bit_off) > __ffs(chunk->contig_bits_start))) {
		/* use the start with the best alignment */
		chunk->contig_bits_start = bit_off;
	}
}

/**
 * pcpu_chunk_refresh_hint - updates metadata about a chunk
 * @chunk: chunk of interest
 *
 * Iterates over the metadata blocks to find the largest contig area.
 * It also counts the populated pages and uses the delta to update the
 * global count.
 *
 * Updates:
 *      chunk->contig_bits
 *      chunk->contig_bits_start
 *      nr_empty_pop_pages (chunk and global)
 */
static void pcpu_chunk_refresh_hint(struct pcpu_chunk *chunk)
{
	int bit_off, bits, nr_empty_pop_pages;

	/* clear metadata */
	chunk->contig_bits = 0;

	bit_off = chunk->first_bit;
	bits = nr_empty_pop_pages = 0;
	pcpu_for_each_md_free_region(chunk, bit_off, bits) {
		pcpu_chunk_update(chunk, bit_off, bits);

		nr_empty_pop_pages += pcpu_cnt_pop_pages(chunk, bit_off, bits);
	}

	/*
	 * Keep track of nr_empty_pop_pages.
	 *
	 * The chunk maintains the previous number of free pages it held,
	 * so the delta is used to update the global counter.  The reserved
	 * chunk is not part of the free page count as they are populated
	 * at init and are special to serving reserved allocations.
	 */
	if (chunk != pcpu_reserved_chunk)
		pcpu_nr_empty_pop_pages +=
			(nr_empty_pop_pages - chunk->nr_empty_pop_pages);

	chunk->nr_empty_pop_pages = nr_empty_pop_pages;
}

/**
 * pcpu_block_update - updates a block given a free area
 * @block: block of interest
 * @start: start offset in block
 * @end: end offset in block
 *
 * Updates a block given a known free area.  The region [start, end) is
 * expected to be the entirety of the free area within a block.  Chooses
 * the best starting offset if the contig hints are equal.
 */
static void pcpu_block_update(struct pcpu_block_md *block, int start, int end)
{
	int contig = end - start;

	block->first_free = min(block->first_free, start);
	if (start == 0)
		block->left_free = contig;

	if (end == PCPU_BITMAP_BLOCK_BITS)
		block->right_free = contig;

	if (contig > block->contig_hint) {
		block->contig_hint_start = start;
		block->contig_hint = contig;
	} else if (block->contig_hint_start && contig == block->contig_hint &&
		   (!start || __ffs(start) > __ffs(block->contig_hint_start))) {
		/* use the start with the best alignment */
		block->contig_hint_start = start;
	}
}

/**
 * pcpu_block_refresh_hint
 * @chunk: chunk of interest
 * @index: index of the metadata block
 *
 * Scans over the block beginning at first_free and updates the block
 * metadata accordingly.
 */
static void pcpu_block_refresh_hint(struct pcpu_chunk *chunk, int index)
{
	struct pcpu_block_md *block = chunk->md_blocks + index;
	unsigned long *alloc_map = pcpu_index_alloc_map(chunk, index);
	int rs, re;	/* region start, region end */

	/* clear hints */
	block->contig_hint = 0;
	block->left_free = block->right_free = 0;

	/* iterate over free areas and update the contig hints */
	pcpu_for_each_unpop_region(alloc_map, rs, re, block->first_free,
				   PCPU_BITMAP_BLOCK_BITS) {
		pcpu_block_update(block, rs, re);
	}
}

/**
 * pcpu_block_update_hint_alloc - update hint on allocation path
 * @chunk: chunk of interest
 * @bit_off: chunk offset
 * @bits: size of request
 *
 * Updates metadata for the allocation path.  The metadata only has to be
 * refreshed by a full scan iff the chunk's contig hint is broken.  Block level
 * scans are required if the block's contig hint is broken.
 */
static void pcpu_block_update_hint_alloc(struct pcpu_chunk *chunk, int bit_off,
					 int bits)
{
	struct pcpu_block_md *s_block, *e_block, *block;
	int s_index, e_index;	/* block indexes of the freed allocation */
	int s_off, e_off;	/* block offsets of the freed allocation */

	/*
	 * Calculate per block offsets.
	 * The calculation uses an inclusive range, but the resulting offsets
	 * are [start, end).  e_index always points to the last block in the
	 * range.
	 */
	s_index = pcpu_off_to_block_index(bit_off);
	e_index = pcpu_off_to_block_index(bit_off + bits - 1);
	s_off = pcpu_off_to_block_off(bit_off);
	e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1;

	s_block = chunk->md_blocks + s_index;
	e_block = chunk->md_blocks + e_index;

	/*
	 * Update s_block.
	 * block->first_free must be updated if the allocation takes its place.
	 * If the allocation breaks the contig_hint, a scan is required to
	 * restore this hint.
	 */
	if (s_off == s_block->first_free)
		s_block->first_free = find_next_zero_bit(
					pcpu_index_alloc_map(chunk, s_index),
					PCPU_BITMAP_BLOCK_BITS,
					s_off + bits);

	if (s_off >= s_block->contig_hint_start &&
	    s_off < s_block->contig_hint_start + s_block->contig_hint) {
		/* block contig hint is broken - scan to fix it */
		pcpu_block_refresh_hint(chunk, s_index);
	} else {
		/* update left and right contig manually */
		s_block->left_free = min(s_block->left_free, s_off);
		if (s_index == e_index)
			s_block->right_free = min_t(int, s_block->right_free,
					PCPU_BITMAP_BLOCK_BITS - e_off);
		else
			s_block->right_free = 0;
	}

	/*
	 * Update e_block.
	 */
	if (s_index != e_index) {
		/*
		 * When the allocation is across blocks, the end is along
		 * the left part of the e_block.
		 */
		e_block->first_free = find_next_zero_bit(
				pcpu_index_alloc_map(chunk, e_index),
				PCPU_BITMAP_BLOCK_BITS, e_off);

		if (e_off == PCPU_BITMAP_BLOCK_BITS) {
			/* reset the block */
			e_block++;
		} else {
			if (e_off > e_block->contig_hint_start) {
				/* contig hint is broken - scan to fix it */
				pcpu_block_refresh_hint(chunk, e_index);
			} else {
				e_block->left_free = 0;
				e_block->right_free =
					min_t(int, e_block->right_free,
					      PCPU_BITMAP_BLOCK_BITS - e_off);
			}
		}

		/* update in-between md_blocks */
		for (block = s_block + 1; block < e_block; block++) {
			block->contig_hint = 0;
			block->left_free = 0;
			block->right_free = 0;
		}
	}

	/*
	 * The only time a full chunk scan is required is if the chunk
	 * contig hint is broken.  Otherwise, it means a smaller space
	 * was used and therefore the chunk contig hint is still correct.
	 */
	if (bit_off >= chunk->contig_bits_start  &&
	    bit_off < chunk->contig_bits_start + chunk->contig_bits)
		pcpu_chunk_refresh_hint(chunk);
}

/**
 * pcpu_block_update_hint_free - updates the block hints on the free path
 * @chunk: chunk of interest
 * @bit_off: chunk offset
 * @bits: size of request
 *
 * Updates metadata for the allocation path.  This avoids a blind block
 * refresh by making use of the block contig hints.  If this fails, it scans
 * forward and backward to determine the extent of the free area.  This is
 * capped at the boundary of blocks.
 *
 * A chunk update is triggered if a page becomes free, a block becomes free,
 * or the free spans across blocks.  This tradeoff is to minimize iterating
 * over the block metadata to update chunk->contig_bits.  chunk->contig_bits
 * may be off by up to a page, but it will never be more than the available
 * space.  If the contig hint is contained in one block, it will be accurate.
 */
static void pcpu_block_update_hint_free(struct pcpu_chunk *chunk, int bit_off,
					int bits)
{
	struct pcpu_block_md *s_block, *e_block, *block;
	int s_index, e_index;	/* block indexes of the freed allocation */
	int s_off, e_off;	/* block offsets of the freed allocation */
	int start, end;		/* start and end of the whole free area */

	/*
	 * Calculate per block offsets.
	 * The calculation uses an inclusive range, but the resulting offsets
	 * are [start, end).  e_index always points to the last block in the
	 * range.
	 */
	s_index = pcpu_off_to_block_index(bit_off);
	e_index = pcpu_off_to_block_index(bit_off + bits - 1);
	s_off = pcpu_off_to_block_off(bit_off);
	e_off = pcpu_off_to_block_off(bit_off + bits - 1) + 1;

	s_block = chunk->md_blocks + s_index;
	e_block = chunk->md_blocks + e_index;

	/*
	 * Check if the freed area aligns with the block->contig_hint.
	 * If it does, then the scan to find the beginning/end of the
	 * larger free area can be avoided.
	 *
	 * start and end refer to beginning and end of the free area
	 * within each their respective blocks.  This is not necessarily
	 * the entire free area as it may span blocks past the beginning
	 * or end of the block.
	 */
	start = s_off;
	if (s_off == s_block->contig_hint + s_block->contig_hint_start) {
		start = s_block->contig_hint_start;
	} else {
		/*
		 * Scan backwards to find the extent of the free area.
		 * find_last_bit returns the starting bit, so if the start bit
		 * is returned, that means there was no last bit and the
		 * remainder of the chunk is free.
		 */
		int l_bit = find_last_bit(pcpu_index_alloc_map(chunk, s_index),
					  start);
		start = (start == l_bit) ? 0 : l_bit + 1;
	}

	end = e_off;
	if (e_off == e_block->contig_hint_start)
		end = e_block->contig_hint_start + e_block->contig_hint;
	else
		end = find_next_bit(pcpu_index_alloc_map(chunk, e_index),
				    PCPU_BITMAP_BLOCK_BITS, end);

	/* update s_block */
	e_off = (s_index == e_index) ? end : PCPU_BITMAP_BLOCK_BITS;
	pcpu_block_update(s_block, start, e_off);

	/* freeing in the same block */
	if (s_index != e_index) {
		/* update e_block */
		pcpu_block_update(e_block, 0, end);

		/* reset md_blocks in the middle */
		for (block = s_block + 1; block < e_block; block++) {
			block->first_free = 0;
			block->contig_hint_start = 0;
			block->contig_hint = PCPU_BITMAP_BLOCK_BITS;
			block->left_free = PCPU_BITMAP_BLOCK_BITS;
			block->right_free = PCPU_BITMAP_BLOCK_BITS;
		}
	}

	/*
	 * Refresh chunk metadata when the free makes a page free, a block
	 * free, or spans across blocks.  The contig hint may be off by up to
	 * a page, but if the hint is contained in a block, it will be accurate
	 * with the else condition below.
	 */
	if ((ALIGN_DOWN(end, min(PCPU_BITS_PER_PAGE, PCPU_BITMAP_BLOCK_BITS)) >
	     ALIGN(start, min(PCPU_BITS_PER_PAGE, PCPU_BITMAP_BLOCK_BITS))) ||
	    s_index != e_index)
		pcpu_chunk_refresh_hint(chunk);
	else
		pcpu_chunk_update(chunk, pcpu_block_off_to_off(s_index, start),
				  s_block->contig_hint);
}

/**
 * pcpu_is_populated - determines if the region is populated
 * @chunk: chunk of interest
 * @bit_off: chunk offset
 * @bits: size of area
 * @next_off: return value for the next offset to start searching
 *
 * For atomic allocations, check if the backing pages are populated.
 *
 * RETURNS:
 * Bool if the backing pages are populated.
 * next_index is to skip over unpopulated blocks in pcpu_find_block_fit.
 */
static bool pcpu_is_populated(struct pcpu_chunk *chunk, int bit_off, int bits,
			      int *next_off)
{
	int page_start, page_end, rs, re;

	page_start = PFN_DOWN(bit_off * PCPU_MIN_ALLOC_SIZE);
	page_end = PFN_UP((bit_off + bits) * PCPU_MIN_ALLOC_SIZE);

	rs = page_start;
	pcpu_next_unpop(chunk->populated, &rs, &re, page_end);
	if (rs >= page_end)
		return true;

	*next_off = re * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE;
	return false;
}

/**
 * pcpu_find_block_fit - finds the block index to start searching
 * @chunk: chunk of interest
 * @alloc_bits: size of request in allocation units
 * @align: alignment of area (max PAGE_SIZE bytes)
 * @pop_only: use populated regions only
 *
 * Given a chunk and an allocation spec, find the offset to begin searching
 * for a free region.  This iterates over the bitmap metadata blocks to
 * find an offset that will be guaranteed to fit the requirements.  It is
 * not quite first fit as if the allocation does not fit in the contig hint
 * of a block or chunk, it is skipped.  This errs on the side of caution
 * to prevent excess iteration.  Poor alignment can cause the allocator to
 * skip over blocks and chunks that have valid free areas.
 *
 * RETURNS:
 * The offset in the bitmap to begin searching.
 * -1 if no offset is found.
 */
static int pcpu_find_block_fit(struct pcpu_chunk *chunk, int alloc_bits,
			       size_t align, bool pop_only)
{
	int bit_off, bits, next_off;

	/*
	 * Check to see if the allocation can fit in the chunk's contig hint.
	 * This is an optimization to prevent scanning by assuming if it
	 * cannot fit in the global hint, there is memory pressure and creating
	 * a new chunk would happen soon.
	 */
	bit_off = ALIGN(chunk->contig_bits_start, align) -
		  chunk->contig_bits_start;
	if (bit_off + alloc_bits > chunk->contig_bits)
		return -1;

	bit_off = chunk->first_bit;
	bits = 0;
	pcpu_for_each_fit_region(chunk, alloc_bits, align, bit_off, bits) {
		if (!pop_only || pcpu_is_populated(chunk, bit_off, bits,
						   &next_off))
			break;

		bit_off = next_off;
		bits = 0;
	}

	if (bit_off == pcpu_chunk_map_bits(chunk))
		return -1;

	return bit_off;
}

/**
 * pcpu_alloc_area - allocates an area from a pcpu_chunk
 * @chunk: chunk of interest
 * @alloc_bits: size of request in allocation units
 * @align: alignment of area (max PAGE_SIZE)
 * @start: bit_off to start searching
 *
 * This function takes in a @start offset to begin searching to fit an
 * allocation of @alloc_bits with alignment @align.  It needs to scan
 * the allocation map because if it fits within the block's contig hint,
 * @start will be block->first_free. This is an attempt to fill the
 * allocation prior to breaking the contig hint.  The allocation and
 * boundary maps are updated accordingly if it confirms a valid
 * free area.
 *
 * RETURNS:
 * Allocated addr offset in @chunk on success.
 * -1 if no matching area is found.
 */
static int pcpu_alloc_area(struct pcpu_chunk *chunk, int alloc_bits,
			   size_t align, int start)
{
	size_t align_mask = (align) ? (align - 1) : 0;
	int bit_off, end, oslot;

	lockdep_assert_held(&pcpu_lock);

	oslot = pcpu_chunk_slot(chunk);

	/*
	 * Search to find a fit.
	 */
	end = start + alloc_bits + PCPU_BITMAP_BLOCK_BITS;
	bit_off = bitmap_find_next_zero_area(chunk->alloc_map, end, start,
					     alloc_bits, align_mask);
	if (bit_off >= end)
		return -1;

	/* update alloc map */
	bitmap_set(chunk->alloc_map, bit_off, alloc_bits);

	/* update boundary map */
	set_bit(bit_off, chunk->bound_map);
	bitmap_clear(chunk->bound_map, bit_off + 1, alloc_bits - 1);
	set_bit(bit_off + alloc_bits, chunk->bound_map);

	chunk->free_bytes -= alloc_bits * PCPU_MIN_ALLOC_SIZE;

	/* update first free bit */
	if (bit_off == chunk->first_bit)
		chunk->first_bit = find_next_zero_bit(
					chunk->alloc_map,
					pcpu_chunk_map_bits(chunk),
					bit_off + alloc_bits);

	pcpu_block_update_hint_alloc(chunk, bit_off, alloc_bits);

	pcpu_chunk_relocate(chunk, oslot);

	return bit_off * PCPU_MIN_ALLOC_SIZE;
}

/**
 * pcpu_free_area - frees the corresponding offset
 * @chunk: chunk of interest
 * @off: addr offset into chunk
 *
 * This function determines the size of an allocation to free using
 * the boundary bitmap and clears the allocation map.
 */
static void pcpu_free_area(struct pcpu_chunk *chunk, int off)
{
	int bit_off, bits, end, oslot;

	lockdep_assert_held(&pcpu_lock);
	pcpu_stats_area_dealloc(chunk);

	oslot = pcpu_chunk_slot(chunk);

	bit_off = off / PCPU_MIN_ALLOC_SIZE;

	/* find end index */
	end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk),
			    bit_off + 1);
	bits = end - bit_off;
	bitmap_clear(chunk->alloc_map, bit_off, bits);

	/* update metadata */
	chunk->free_bytes += bits * PCPU_MIN_ALLOC_SIZE;

	/* update first free bit */
	chunk->first_bit = min(chunk->first_bit, bit_off);

	pcpu_block_update_hint_free(chunk, bit_off, bits);

	pcpu_chunk_relocate(chunk, oslot);
}

static void pcpu_init_md_blocks(struct pcpu_chunk *chunk)
{
	struct pcpu_block_md *md_block;

	for (md_block = chunk->md_blocks;
	     md_block != chunk->md_blocks + pcpu_chunk_nr_blocks(chunk);
	     md_block++) {
		md_block->contig_hint = PCPU_BITMAP_BLOCK_BITS;
		md_block->left_free = PCPU_BITMAP_BLOCK_BITS;
		md_block->right_free = PCPU_BITMAP_BLOCK_BITS;
	}
}

/**
 * pcpu_alloc_first_chunk - creates chunks that serve the first chunk
 * @tmp_addr: the start of the region served
 * @map_size: size of the region served
 *
 * This is responsible for creating the chunks that serve the first chunk.  The
 * base_addr is page aligned down of @tmp_addr while the region end is page
 * aligned up.  Offsets are kept track of to determine the region served. All
 * this is done to appease the bitmap allocator in avoiding partial blocks.
 *
 * RETURNS:
 * Chunk serving the region at @tmp_addr of @map_size.
 */
static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
							 int map_size)
{
	struct pcpu_chunk *chunk;
	unsigned long aligned_addr, lcm_align;
	int start_offset, offset_bits, region_size, region_bits;

	/* region calculations */
	aligned_addr = tmp_addr & PAGE_MASK;

	start_offset = tmp_addr - aligned_addr;

	/*
	 * Align the end of the region with the LCM of PAGE_SIZE and
	 * PCPU_BITMAP_BLOCK_SIZE.  One of these constants is a multiple of
	 * the other.
	 */
	lcm_align = lcm(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE);
	region_size = ALIGN(start_offset + map_size, lcm_align);

	/* allocate chunk */
	chunk = memblock_virt_alloc(sizeof(struct pcpu_chunk) +
				    BITS_TO_LONGS(region_size >> PAGE_SHIFT),
				    0);

	INIT_LIST_HEAD(&chunk->list);

	chunk->base_addr = (void *)aligned_addr;
	chunk->start_offset = start_offset;
	chunk->end_offset = region_size - chunk->start_offset - map_size;

	chunk->nr_pages = region_size >> PAGE_SHIFT;
	region_bits = pcpu_chunk_map_bits(chunk);

	chunk->alloc_map = memblock_virt_alloc(BITS_TO_LONGS(region_bits) *
					       sizeof(chunk->alloc_map[0]), 0);
	chunk->bound_map = memblock_virt_alloc(BITS_TO_LONGS(region_bits + 1) *
					       sizeof(chunk->bound_map[0]), 0);
	chunk->md_blocks = memblock_virt_alloc(pcpu_chunk_nr_blocks(chunk) *
					       sizeof(chunk->md_blocks[0]), 0);
	pcpu_init_md_blocks(chunk);

	/* manage populated page bitmap */
	chunk->immutable = true;
	bitmap_fill(chunk->populated, chunk->nr_pages);
	chunk->nr_populated = chunk->nr_pages;
	chunk->nr_empty_pop_pages =
		pcpu_cnt_pop_pages(chunk, start_offset / PCPU_MIN_ALLOC_SIZE,
				   map_size / PCPU_MIN_ALLOC_SIZE);

	chunk->contig_bits = map_size / PCPU_MIN_ALLOC_SIZE;
	chunk->free_bytes = map_size;

	if (chunk->start_offset) {
		/* hide the beginning of the bitmap */
		offset_bits = chunk->start_offset / PCPU_MIN_ALLOC_SIZE;
		bitmap_set(chunk->alloc_map, 0, offset_bits);
		set_bit(0, chunk->bound_map);
		set_bit(offset_bits, chunk->bound_map);

		chunk->first_bit = offset_bits;

		pcpu_block_update_hint_alloc(chunk, 0, offset_bits);
	}

	if (chunk->end_offset) {
		/* hide the end of the bitmap */
		offset_bits = chunk->end_offset / PCPU_MIN_ALLOC_SIZE;
		bitmap_set(chunk->alloc_map,
			   pcpu_chunk_map_bits(chunk) - offset_bits,
			   offset_bits);
		set_bit((start_offset + map_size) / PCPU_MIN_ALLOC_SIZE,
			chunk->bound_map);
		set_bit(region_bits, chunk->bound_map);

		pcpu_block_update_hint_alloc(chunk, pcpu_chunk_map_bits(chunk)
					     - offset_bits, offset_bits);
	}

	return chunk;
}

static struct pcpu_chunk *pcpu_alloc_chunk(void)
{
	struct pcpu_chunk *chunk;
	int region_bits;

	chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
	if (!chunk)
		return NULL;

	INIT_LIST_HEAD(&chunk->list);
	chunk->nr_pages = pcpu_unit_pages;
	region_bits = pcpu_chunk_map_bits(chunk);

	chunk->alloc_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits) *
					   sizeof(chunk->alloc_map[0]));
	if (!chunk->alloc_map)
		goto alloc_map_fail;

	chunk->bound_map = pcpu_mem_zalloc(BITS_TO_LONGS(region_bits + 1) *
					   sizeof(chunk->bound_map[0]));
	if (!chunk->bound_map)
		goto bound_map_fail;

	chunk->md_blocks = pcpu_mem_zalloc(pcpu_chunk_nr_blocks(chunk) *
					   sizeof(chunk->md_blocks[0]));
	if (!chunk->md_blocks)
		goto md_blocks_fail;

	pcpu_init_md_blocks(chunk);

	/* init metadata */
	chunk->contig_bits = region_bits;
	chunk->free_bytes = chunk->nr_pages * PAGE_SIZE;

	return chunk;

md_blocks_fail:
	pcpu_mem_free(chunk->bound_map);
bound_map_fail:
	pcpu_mem_free(chunk->alloc_map);
alloc_map_fail:
	pcpu_mem_free(chunk);

	return NULL;
}

static void pcpu_free_chunk(struct pcpu_chunk *chunk)
{
	if (!chunk)
		return;
	pcpu_mem_free(chunk->bound_map);
	pcpu_mem_free(chunk->alloc_map);
	pcpu_mem_free(chunk);
}

/**
 * pcpu_chunk_populated - post-population bookkeeping
 * @chunk: pcpu_chunk which got populated
 * @page_start: the start page
 * @page_end: the end page
 * @for_alloc: if this is to populate for allocation
 *
 * Pages in [@page_start,@page_end) have been populated to @chunk.  Update
 * the bookkeeping information accordingly.  Must be called after each
 * successful population.
 *
 * If this is @for_alloc, do not increment pcpu_nr_empty_pop_pages because it
 * is to serve an allocation in that area.
 */
static void pcpu_chunk_populated(struct pcpu_chunk *chunk, int page_start,
				 int page_end, bool for_alloc)
{
	int nr = page_end - page_start;

	lockdep_assert_held(&pcpu_lock);

	bitmap_set(chunk->populated, page_start, nr);
	chunk->nr_populated += nr;

	if (!for_alloc) {
		chunk->nr_empty_pop_pages += nr;
		pcpu_nr_empty_pop_pages += nr;
	}
}

/**
 * pcpu_chunk_depopulated - post-depopulation bookkeeping
 * @chunk: pcpu_chunk which got depopulated
 * @page_start: the start page
 * @page_end: the end page
 *
 * Pages in [@page_start,@page_end) have been depopulated from @chunk.
 * Update the bookkeeping information accordingly.  Must be called after
 * each successful depopulation.
 */
static void pcpu_chunk_depopulated(struct pcpu_chunk *chunk,
				   int page_start, int page_end)
{
	int nr = page_end - page_start;

	lockdep_assert_held(&pcpu_lock);

	bitmap_clear(chunk->populated, page_start, nr);
	chunk->nr_populated -= nr;
	chunk->nr_empty_pop_pages -= nr;
	pcpu_nr_empty_pop_pages -= nr;
}

/*
 * Chunk management implementation.
 *
 * To allow different implementations, chunk alloc/free and
 * [de]population are implemented in a separate file which is pulled
 * into this file and compiled together.  The following functions
 * should be implemented.
 *
 * pcpu_populate_chunk		- populate the specified range of a chunk
 * pcpu_depopulate_chunk	- depopulate the specified range of a chunk
 * pcpu_create_chunk		- create a new chunk
 * pcpu_destroy_chunk		- destroy a chunk, always preceded by full depop
 * pcpu_addr_to_page		- translate address to physical address
 * pcpu_verify_alloc_info	- check alloc_info is acceptable during init
 */
static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size);
static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int off, int size);
static struct pcpu_chunk *pcpu_create_chunk(void);
static void pcpu_destroy_chunk(struct pcpu_chunk *chunk);
static struct page *pcpu_addr_to_page(void *addr);
static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai);

#ifdef CONFIG_NEED_PER_CPU_KM
#include "percpu-km.c"
#else
#include "percpu-vm.c"
#endif

/**
 * pcpu_chunk_addr_search - determine chunk containing specified address
 * @addr: address for which the chunk needs to be determined.
 *
 * This is an internal function that handles all but static allocations.
 * Static percpu address values should never be passed into the allocator.
 *
 * RETURNS:
 * The address of the found chunk.
 */
static struct pcpu_chunk *pcpu_chunk_addr_search(void *addr)
{
	/* is it in the dynamic region (first chunk)? */
	if (pcpu_addr_in_chunk(pcpu_first_chunk, addr))
		return pcpu_first_chunk;

	/* is it in the reserved region? */
	if (pcpu_addr_in_chunk(pcpu_reserved_chunk, addr))
		return pcpu_reserved_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_offsets[raw_smp_processor_id()];
	return pcpu_get_page_chunk(pcpu_addr_to_page(addr));
}

/**
 * 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
 * @gfp: allocation flags
 *
 * Allocate percpu area of @size bytes aligned at @align.  If @gfp doesn't
 * contain %GFP_KERNEL, the allocation is atomic. If @gfp has __GFP_NOWARN
 * then no warning will be triggered on invalid or failed allocation
 * requests.
 *
 * RETURNS:
 * Percpu pointer to the allocated area on success, NULL on failure.
 */
static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved,
				 gfp_t gfp)
{
	bool is_atomic = (gfp & GFP_KERNEL) != GFP_KERNEL;
	bool do_warn = !(gfp & __GFP_NOWARN);
	static int warn_limit = 10;
	struct pcpu_chunk *chunk;
	const char *err;
	int slot, off, cpu, ret;
	unsigned long flags;
	void __percpu *ptr;
	size_t bits, bit_align;

	/*
	 * There is now a minimum allocation size of PCPU_MIN_ALLOC_SIZE,
	 * therefore alignment must be a minimum of that many bytes.
	 * An allocation may have internal fragmentation from rounding up
	 * of up to PCPU_MIN_ALLOC_SIZE - 1 bytes.
	 */
	if (unlikely(align < PCPU_MIN_ALLOC_SIZE))
		align = PCPU_MIN_ALLOC_SIZE;

	size = ALIGN(size, PCPU_MIN_ALLOC_SIZE);
	bits = size >> PCPU_MIN_ALLOC_SHIFT;
	bit_align = align >> PCPU_MIN_ALLOC_SHIFT;

	if (unlikely(!size || size > PCPU_MIN_UNIT_SIZE || align > PAGE_SIZE ||
		     !is_power_of_2(align))) {
		WARN(do_warn, "illegal size (%zu) or align (%zu) for percpu allocation\n",
		     size, align);
		return NULL;
	}

	if (!is_atomic)
		mutex_lock(&pcpu_alloc_mutex);

	spin_lock_irqsave(&pcpu_lock, flags);

	/* serve reserved allocations from the reserved chunk if available */
	if (reserved && pcpu_reserved_chunk) {
		chunk = pcpu_reserved_chunk;

		off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic);
		if (off < 0) {
			err = "alloc from reserved chunk failed";
			goto fail_unlock;
		}

		off = pcpu_alloc_area(chunk, bits, bit_align, off);
		if (off >= 0)
			goto area_found;

		err = "alloc from reserved chunk failed";
		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) {
			off = pcpu_find_block_fit(chunk, bits, bit_align,
						  is_atomic);
			if (off < 0)
				continue;

			off = pcpu_alloc_area(chunk, bits, bit_align, off);
			if (off >= 0)
				goto area_found;

		}
	}

	spin_unlock_irqrestore(&pcpu_lock, flags);

	/*
	 * No space left.  Create a new chunk.  We don't want multiple
	 * tasks to create chunks simultaneously.  Serialize and create iff
	 * there's still no empty chunk after grabbing the mutex.
	 */
	if (is_atomic) {
		err = "atomic alloc failed, no space left";
		goto fail;
	}

	if (list_empty(&pcpu_slot[pcpu_nr_slots - 1])) {
		chunk = pcpu_create_chunk();
		if (!chunk) {
			err = "failed to allocate new chunk";
			goto fail;
		}

		spin_lock_irqsave(&pcpu_lock, flags);
		pcpu_chunk_relocate(chunk, -1);
	} else {
		spin_lock_irqsave(&pcpu_lock, flags);
	}

	goto restart;

area_found:
	pcpu_stats_area_alloc(chunk, size);
	spin_unlock_irqrestore(&pcpu_lock, flags);

	/* populate if not all pages are already there */
	if (!is_atomic) {
		int page_start, page_end, rs, re;

		page_start = PFN_DOWN(off);
		page_end = PFN_UP(off + size);

		pcpu_for_each_unpop_region(chunk->populated, rs, re,
					   page_start, page_end) {
			WARN_ON(chunk->immutable);

			ret = pcpu_populate_chunk(chunk, rs, re);

			spin_lock_irqsave(&pcpu_lock, flags);
			if (ret) {
				pcpu_free_area(chunk, off);
				err = "failed to populate";
				goto fail_unlock;
			}
			pcpu_chunk_populated(chunk, rs, re, true);
			spin_unlock_irqrestore(&pcpu_lock, flags);
		}

		mutex_unlock(&pcpu_alloc_mutex);
	}

	if (pcpu_nr_empty_pop_pages < PCPU_EMPTY_POP_PAGES_LOW)
		pcpu_schedule_balance_work();

	/* clear the areas and return address relative to base address */
	for_each_possible_cpu(cpu)
		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);

	ptr = __addr_to_pcpu_ptr(chunk->base_addr + off);
	kmemleak_alloc_percpu(ptr, size, gfp);

	trace_percpu_alloc_percpu(reserved, is_atomic, size, align,
			chunk->base_addr, off, ptr);

	return ptr;

fail_unlock:
	spin_unlock_irqrestore(&pcpu_lock, flags);
fail:
	trace_percpu_alloc_percpu_fail(reserved, is_atomic, size, align);

	if (!is_atomic && do_warn && warn_limit) {
		pr_warn("allocation failed, size=%zu align=%zu atomic=%d, %s\n",
			size, align, is_atomic, err);
		dump_stack();
		if (!--warn_limit)
			pr_info("limit reached, disable warning\n");
	}
	if (is_atomic) {
		/* see the flag handling in pcpu_blance_workfn() */
		pcpu_atomic_alloc_failed = true;
		pcpu_schedule_balance_work();
	} else {
		mutex_unlock(&pcpu_alloc_mutex);
	}
	return NULL;
}

/**
 * __alloc_percpu_gfp - allocate dynamic percpu area
 * @size: size of area to allocate in bytes
 * @align: alignment of area (max PAGE_SIZE)
 * @gfp: allocation flags
 *
 * Allocate zero-filled percpu area of @size bytes aligned at @align.  If
 * @gfp doesn't contain %GFP_KERNEL, the allocation doesn't block and can
 * be called from any context but is a lot more likely to fail. If @gfp
 * has __GFP_NOWARN then no warning will be triggered on invalid or failed
 * allocation requests.
 *
 * RETURNS:
 * Percpu pointer to the allocated area on success, NULL on failure.
 */
void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp)
{
	return pcpu_alloc(size, align, false, gfp);
}
EXPORT_SYMBOL_GPL(__alloc_percpu_gfp);

/**
 * __alloc_percpu - allocate dynamic percpu area
 * @size: size of area to allocate in bytes
 * @align: alignment of area (max PAGE_SIZE)
 *
 * Equivalent to __alloc_percpu_gfp(size, align, %GFP_KERNEL).
 */
void __percpu *__alloc_percpu(size_t size, size_t align)
{
	return pcpu_alloc(size, align, false, GFP_KERNEL);
}
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 zero-filled 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 __percpu *__alloc_reserved_percpu(size_t size, size_t align)
{
	return pcpu_alloc(size, align, true, GFP_KERNEL);
}

/**
 * pcpu_balance_workfn - manage the amount of free chunks and populated pages
 * @work: unused
 *
 * Reclaim all fully free chunks except for the first one.
 */
static void pcpu_balance_workfn(struct work_struct *work)
{
	LIST_HEAD(to_free);
	struct list_head *free_head = &pcpu_slot[pcpu_nr_slots - 1];
	struct pcpu_chunk *chunk, *next;
	int slot, nr_to_pop, ret;

	/*
	 * There's no reason to keep around multiple unused chunks and VM
	 * areas can be scarce.  Destroy all free chunks except for one.
	 */
	mutex_lock(&pcpu_alloc_mutex);
	spin_lock_irq(&pcpu_lock);

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

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

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

	spin_unlock_irq(&pcpu_lock);

	list_for_each_entry_safe(chunk, next, &to_free, list) {
		int rs, re;

		pcpu_for_each_pop_region(chunk->populated, rs, re, 0,
					 chunk->nr_pages) {
			pcpu_depopulate_chunk(chunk, rs, re);
			spin_lock_irq(&pcpu_lock);
			pcpu_chunk_depopulated(chunk, rs, re);
			spin_unlock_irq(&pcpu_lock);
		}
		pcpu_destroy_chunk(chunk);
	}

	/*
	 * Ensure there are certain number of free populated pages for
	 * atomic allocs.  Fill up from the most packed so that atomic
	 * allocs don't increase fragmentation.  If atomic allocation
	 * failed previously, always populate the maximum amount.  This
	 * should prevent atomic allocs larger than PAGE_SIZE from keeping
	 * failing indefinitely; however, large atomic allocs are not
	 * something we support properly and can be highly unreliable and
	 * inefficient.
	 */
retry_pop:
	if (pcpu_atomic_alloc_failed) {
		nr_to_pop = PCPU_EMPTY_POP_PAGES_HIGH;
		/* best effort anyway, don't worry about synchronization */
		pcpu_atomic_alloc_failed = false;
	} else {
		nr_to_pop = clamp(PCPU_EMPTY_POP_PAGES_HIGH -
				  pcpu_nr_empty_pop_pages,
				  0, PCPU_EMPTY_POP_PAGES_HIGH);
	}

	for (slot = pcpu_size_to_slot(PAGE_SIZE); slot < pcpu_nr_slots; slot++) {
		int nr_unpop = 0, rs, re;

		if (!nr_to_pop)
			break;

		spin_lock_irq(&pcpu_lock);
		list_for_each_entry(chunk, &pcpu_slot[slot], list) {
			nr_unpop = chunk->nr_pages - chunk->nr_populated;
			if (nr_unpop)
				break;
		}
		spin_unlock_irq(&pcpu_lock);

		if (!nr_unpop)
			continue;

		/* @chunk can't go away while pcpu_alloc_mutex is held */
		pcpu_for_each_unpop_region(chunk->populated, rs, re, 0,
					   chunk->nr_pages) {
			int nr = min(re - rs, nr_to_pop);

			ret = pcpu_populate_chunk(chunk, rs, rs + nr);
			if (!ret) {
				nr_to_pop -= nr;
				spin_lock_irq(&pcpu_lock);
				pcpu_chunk_populated(chunk, rs, rs + nr, false);
				spin_unlock_irq(&pcpu_lock);
			} else {
				nr_to_pop = 0;
			}

			if (!nr_to_pop)
				break;
		}
	}

	if (nr_to_pop) {
		/* ran out of chunks to populate, create a new one and retry */
		chunk = pcpu_create_chunk();
		if (chunk) {
			spin_lock_irq(&pcpu_lock);
			pcpu_chunk_relocate(chunk, -1);
			spin_unlock_irq(&pcpu_lock);
			goto retry_pop;
		}
	}

	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 __percpu *ptr)
{
	void *addr;
	struct pcpu_chunk *chunk;
	unsigned long flags;
	int off;

	if (!ptr)
		return;

	kmemleak_free_percpu(ptr);

	addr = __pcpu_ptr_to_addr(ptr);

	spin_lock_irqsave(&pcpu_lock, flags);

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

	pcpu_free_area(chunk, off);

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

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

	trace_percpu_free_percpu(chunk->base_addr, off, ptr);

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

bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr)
{
#ifdef CONFIG_SMP
	const size_t static_size = __per_cpu_end - __per_cpu_start;
	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
	unsigned int cpu;

	for_each_possible_cpu(cpu) {
		void *start = per_cpu_ptr(base, cpu);
		void *va = (void *)addr;

		if (va >= start && va < start + static_size) {
			if (can_addr) {
				*can_addr = (unsigned long) (va - start);
				*can_addr += (unsigned long)
					per_cpu_ptr(base, get_boot_cpu_id());
			}
			return true;
		}
	}
#endif
	/* on UP, can't distinguish from other static vars, always false */
	return false;
}

/**
 * is_kernel_percpu_address - test whether address is from static percpu area
 * @addr: address to test
 *
 * Test whether @addr belongs to in-kernel static percpu area.  Module
 * static percpu areas are not considered.  For those, use
 * is_module_percpu_address().
 *
 * RETURNS:
 * %true if @addr is from in-kernel static percpu area, %false otherwise.
 */
bool is_kernel_percpu_address(unsigned long addr)
{
	return __is_kernel_percpu_address(addr, NULL);
}

/**
 * per_cpu_ptr_to_phys - convert translated percpu address to physical address
 * @addr: the address to be converted to physical address
 *
 * Given @addr which is dereferenceable address obtained via one of
 * percpu access macros, this function translates it into its physical
 * address.  The caller is responsible for ensuring @addr stays valid
 * until this function finishes.
 *
 * percpu allocator has special setup for the first chunk, which currently
 * supports either embedding in linear address space or vmalloc mapping,
 * and, from the second one, the backing allocator (currently either vm or
 * km) provides translation.
 *
 * The addr can be translated simply without checking if it falls into the
 * first chunk. But the current code reflects better how percpu allocator
 * actually works, and the verification can discover both bugs in percpu
 * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current
 * code.
 *
 * RETURNS:
 * The physical address for @addr.
 */
phys_addr_t per_cpu_ptr_to_phys(void *addr)
{
	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
	bool in_first_chunk = false;
	unsigned long first_low, first_high;
	unsigned int cpu;

	/*
	 * The following test on unit_low/high isn't strictly
	 * necessary but will speed up lookups of addresses which
	 * aren't in the first chunk.
	 *
	 * The address check is against full chunk sizes.  pcpu_base_addr
	 * points to the beginning of the first chunk including the
	 * static region.  Assumes good intent as the first chunk may
	 * not be full (ie. < pcpu_unit_pages in size).
	 */
	first_low = (unsigned long)pcpu_base_addr +
		    pcpu_unit_page_offset(pcpu_low_unit_cpu, 0);
	first_high = (unsigned long)pcpu_base_addr +
		     pcpu_unit_page_offset(pcpu_high_unit_cpu, pcpu_unit_pages);
	if ((unsigned long)addr >= first_low &&
	    (unsigned long)addr < first_high) {
		for_each_possible_cpu(cpu) {
			void *start = per_cpu_ptr(base, cpu);

			if (addr >= start && addr < start + pcpu_unit_size) {
				in_first_chunk = true;
				break;
			}
		}
	}

	if (in_first_chunk) {
		if (!is_vmalloc_addr(addr))
			return __pa(addr);
		else
			return page_to_phys(vmalloc_to_page(addr)) +
			       offset_in_page(addr);
	} else
		return page_to_phys(pcpu_addr_to_page(addr)) +
		       offset_in_page(addr);
}

/**
 * pcpu_alloc_alloc_info - allocate percpu allocation info
 * @nr_groups: the number of groups
 * @nr_units: the number of units
 *
 * Allocate ai which is large enough for @nr_groups groups containing
 * @nr_units units.  The returned ai's groups[0].cpu_map points to the
 * cpu_map array which is long enough for @nr_units and filled with
 * NR_CPUS.  It's the caller's responsibility to initialize cpu_map
 * pointer of other groups.
 *
 * RETURNS:
 * Pointer to the allocated pcpu_alloc_info on success, NULL on
 * failure.
 */
struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
						      int nr_units)
{
	struct pcpu_alloc_info *ai;
	size_t base_size, ai_size;
	void *ptr;
	int unit;

	base_size = ALIGN(sizeof(*ai) + nr_groups * sizeof(ai->groups[0]),
			  __alignof__(ai->groups[0].cpu_map[0]));
	ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]);

	ptr = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), 0);
	if (!ptr)
		return NULL;
	ai = ptr;
	ptr += base_size;

	ai->groups[0].cpu_map = ptr;

	for (unit = 0; unit < nr_units; unit++)
		ai->groups[0].cpu_map[unit] = NR_CPUS;

	ai->nr_groups = nr_groups;
	ai->__ai_size = PFN_ALIGN(ai_size);

	return ai;
}

/**
 * pcpu_free_alloc_info - free percpu allocation info
 * @ai: pcpu_alloc_info to free
 *
 * Free @ai which was allocated by pcpu_alloc_alloc_info().
 */
void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
{
	memblock_free_early(__pa(ai), ai->__ai_size);
}

/**
 * pcpu_dump_alloc_info - print out information about pcpu_alloc_info
 * @lvl: loglevel
 * @ai: allocation info to dump
 *
 * Print out information about @ai using loglevel @lvl.
 */
static void pcpu_dump_alloc_info(const char *lvl,
				 const struct pcpu_alloc_info *ai)
{
	int group_width = 1, cpu_width = 1, width;
	char empty_str[] = "--------";
	int alloc = 0, alloc_end = 0;
	int group, v;
	int upa, apl;	/* units per alloc, allocs per line */

	v = ai->nr_groups;
	while (v /= 10)
		group_width++;

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

	upa = ai->alloc_size / ai->unit_size;
	width = upa * (cpu_width + 1) + group_width + 3;
	apl = rounddown_pow_of_two(max(60 / width, 1));

	printk("%spcpu-alloc: s%zu r%zu d%zu u%zu alloc=%zu*%zu",
	       lvl, ai->static_size, ai->reserved_size, ai->dyn_size,
	       ai->unit_size, ai->alloc_size / ai->atom_size, ai->atom_size);

	for (group = 0; group < ai->nr_groups; group++) {
		const struct pcpu_group_info *gi = &ai->groups[group];
		int unit = 0, unit_end = 0;

		BUG_ON(gi->nr_units % upa);
		for (alloc_end += gi->nr_units / upa;
		     alloc < alloc_end; alloc++) {
			if (!(alloc % apl)) {
				pr_cont("\n");
				printk("%spcpu-alloc: ", lvl);
			}
			pr_cont("[%0*d] ", group_width, group);

			for (unit_end += upa; unit < unit_end; unit++)
				if (gi->cpu_map[unit] != NR_CPUS)
					pr_cont("%0*d ",
						cpu_width, gi->cpu_map[unit]);
				else
					pr_cont("%s ", empty_str);
		}
	}
	pr_cont("\n");
}

/**
 * pcpu_setup_first_chunk - initialize the first percpu chunk
 * @ai: pcpu_alloc_info describing how to percpu area is shaped
 * @base_addr: mapped address
 *
 * Initialize the first percpu chunk which contains the kernel static
 * perpcu area.  This function is to be called from arch percpu area
 * setup path.
 *
 * @ai contains all information necessary to initialize the first
 * chunk and prime the dynamic percpu allocator.
 *
 * @ai->static_size is the size of static percpu area.
 *
 * @ai->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.
 *
 * @ai->dyn_size determines the number of bytes available for dynamic
 * allocation in the first chunk.  The area between @ai->static_size +
 * @ai->reserved_size + @ai->dyn_size and @ai->unit_size is unused.
 *
 * @ai->unit_size specifies unit size and must be aligned to PAGE_SIZE
 * and equal to or larger than @ai->static_size + @ai->reserved_size +
 * @ai->dyn_size.
 *
 * @ai->atom_size is the allocation atom size and used as alignment
 * for vm areas.
 *
 * @ai->alloc_size is the allocation size and always multiple of
 * @ai->atom_size.  This is larger than @ai->atom_size if
 * @ai->unit_size is larger than @ai->atom_size.
 *
 * @ai->nr_groups and @ai->groups describe virtual memory layout of
 * percpu areas.  Units which should be colocated are put into the
 * same group.  Dynamic VM areas will be allocated according to these
 * groupings.  If @ai->nr_groups is zero, a single group containing
 * all units is assumed.
 *
 * The caller should have mapped the first chunk at @base_addr and
 * copied static data to each unit.
 *
 * The first chunk will always contain a static and a dynamic region.
 * However, the static region is not managed by any chunk.  If the first
 * chunk also contains a reserved region, it is served by two chunks -
 * one for the reserved region and one for the dynamic region.  They
 * share the same vm, but use offset regions in the area allocation map.
 * The chunk serving the dynamic region is circulated in the chunk slots
 * and available for dynamic allocation like any other chunk.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
				  void *base_addr)
{
	size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
	size_t static_size, dyn_size;
	struct pcpu_chunk *chunk;
	unsigned long *group_offsets;
	size_t *group_sizes;
	unsigned long *unit_off;
	unsigned int cpu;
	int *unit_map;
	int group, unit, i;
	int map_size;
	unsigned long tmp_addr;

#define PCPU_SETUP_BUG_ON(cond)	do {					\
	if (unlikely(cond)) {						\
		pr_emerg("failed to initialize, %s\n", #cond);		\
		pr_emerg("cpu_possible_mask=%*pb\n",			\
			 cpumask_pr_args(cpu_possible_mask));		\
		pcpu_dump_alloc_info(KERN_EMERG, ai);			\
		BUG();							\
	}								\
} while (0)

	/* sanity checks */
	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
#ifdef CONFIG_SMP
	PCPU_SETUP_BUG_ON(!ai->static_size);
	PCPU_SETUP_BUG_ON(offset_in_page(__per_cpu_start));
#endif
	PCPU_SETUP_BUG_ON(!base_addr);
	PCPU_SETUP_BUG_ON(offset_in_page(base_addr));
	PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
	PCPU_SETUP_BUG_ON(offset_in_page(ai->unit_size));
	PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
	PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->unit_size, PCPU_BITMAP_BLOCK_SIZE));
	PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE);
	PCPU_SETUP_BUG_ON(!ai->dyn_size);
	PCPU_SETUP_BUG_ON(!IS_ALIGNED(ai->reserved_size, PCPU_MIN_ALLOC_SIZE));
	PCPU_SETUP_BUG_ON(!(IS_ALIGNED(PCPU_BITMAP_BLOCK_SIZE, PAGE_SIZE) ||
			    IS_ALIGNED(PAGE_SIZE, PCPU_BITMAP_BLOCK_SIZE)));
	PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);

	/* process group information and build config tables accordingly */
	group_offsets = memblock_virt_alloc(ai->nr_groups *
					     sizeof(group_offsets[0]), 0);
	group_sizes = memblock_virt_alloc(ai->nr_groups *
					   sizeof(group_sizes[0]), 0);
	unit_map = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0);
	unit_off = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0);

	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
		unit_map[cpu] = UINT_MAX;

	pcpu_low_unit_cpu = NR_CPUS;
	pcpu_high_unit_cpu = NR_CPUS;

	for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
		const struct pcpu_group_info *gi = &ai->groups[group];

		group_offsets[group] = gi->base_offset;
		group_sizes[group] = gi->nr_units * ai->unit_size;

		for (i = 0; i < gi->nr_units; i++) {
			cpu = gi->cpu_map[i];
			if (cpu == NR_CPUS)
				continue;

			PCPU_SETUP_BUG_ON(cpu >= nr_cpu_ids);
			PCPU_SETUP_BUG_ON(!cpu_possible(cpu));
			PCPU_SETUP_BUG_ON(unit_map[cpu] != UINT_MAX);

			unit_map[cpu] = unit + i;
			unit_off[cpu] = gi->base_offset + i * ai->unit_size;

			/* determine low/high unit_cpu */
			if (pcpu_low_unit_cpu == NR_CPUS ||
			    unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
				pcpu_low_unit_cpu = cpu;
			if (pcpu_high_unit_cpu == NR_CPUS ||
			    unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
				pcpu_high_unit_cpu = cpu;
		}
	}
	pcpu_nr_units = unit;

	for_each_possible_cpu(cpu)
		PCPU_SETUP_BUG_ON(unit_map[cpu] == UINT_MAX);

	/* we're done parsing the input, undefine BUG macro and dump config */
#undef PCPU_SETUP_BUG_ON
	pcpu_dump_alloc_info(KERN_DEBUG, ai);

	pcpu_nr_groups = ai->nr_groups;
	pcpu_group_offsets = group_offsets;
	pcpu_group_sizes = group_sizes;
	pcpu_unit_map = unit_map;
	pcpu_unit_offsets = unit_off;

	/* determine basic parameters */
	pcpu_unit_pages = ai->unit_size >> PAGE_SHIFT;
	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
	pcpu_atom_size = ai->atom_size;
	pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
		BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long);

	pcpu_stats_save_ai(ai);

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

	/*
	 * The end of the static region needs to be aligned with the
	 * minimum allocation size as this offsets the reserved and
	 * dynamic region.  The first chunk ends page aligned by
	 * expanding the dynamic region, therefore the dynamic region
	 * can be shrunk to compensate while still staying above the
	 * configured sizes.
	 */
	static_size = ALIGN(ai->static_size, PCPU_MIN_ALLOC_SIZE);
	dyn_size = ai->dyn_size - (static_size - ai->static_size);

	/*
	 * Initialize first chunk.
	 * If the reserved_size is non-zero, this initializes the reserved
	 * chunk.  If the reserved_size is zero, the reserved chunk is NULL
	 * and the dynamic region is initialized here.  The first chunk,
	 * pcpu_first_chunk, will always point to the chunk that serves
	 * the dynamic region.
	 */
	tmp_addr = (unsigned long)base_addr + static_size;
	map_size = ai->reserved_size ?: dyn_size;
	chunk = pcpu_alloc_first_chunk(tmp_addr, map_size);

	/* init dynamic chunk if necessary */
	if (ai->reserved_size) {
		pcpu_reserved_chunk = chunk;

		tmp_addr = (unsigned long)base_addr + static_size +
			   ai->reserved_size;
		map_size = dyn_size;
		chunk = pcpu_alloc_first_chunk(tmp_addr, map_size);
	}

	/* link the first chunk in */
	pcpu_first_chunk = chunk;
	pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages;
	pcpu_chunk_relocate(pcpu_first_chunk, -1);

	pcpu_stats_chunk_alloc();
	trace_percpu_create_chunk(base_addr);

	/* we're done */
	pcpu_base_addr = base_addr;
	return 0;
}

#ifdef CONFIG_SMP

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

enum pcpu_fc pcpu_chosen_fc __initdata = PCPU_FC_AUTO;

static int __init percpu_alloc_setup(char *str)
{
	if (!str)
		return -EINVAL;

	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
	else
		pr_warn("unknown allocator %s specified\n", str);

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

/*
 * pcpu_embed_first_chunk() is used by the generic percpu setup.
 * Build it if needed by the arch config or the generic setup is going
 * to be used.
 */
#if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
	!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
#define BUILD_EMBED_FIRST_CHUNK
#endif

/* build pcpu_page_first_chunk() iff needed by the arch config */
#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
#define BUILD_PAGE_FIRST_CHUNK
#endif

/* pcpu_build_alloc_info() is used by both embed and page first chunk */
#if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK)
/**
 * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_size: minimum free size for dynamic allocation in bytes
 * @atom_size: allocation atom size
 * @cpu_distance_fn: callback to determine distance between cpus, optional
 *
 * This function determines grouping of units, their mappings to cpus
 * and other parameters considering needed percpu size, allocation
 * atom size and distances between CPUs.
 *
 * Groups are always multiples of atom size and CPUs which are of
 * LOCAL_DISTANCE both ways are grouped together and share space for
 * units in the same group.  The returned configuration is guaranteed
 * to have CPUs on different nodes on different groups and >=75% usage
 * of allocated virtual address space.
 *
 * RETURNS:
 * On success, pointer to the new allocation_info is returned.  On
 * failure, ERR_PTR value is returned.
 */
static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
				size_t reserved_size, size_t dyn_size,
				size_t atom_size,
				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 nr_groups = 1, nr_units = 0;
	size_t size_sum, min_unit_size, alloc_size;
	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
	int last_allocs, group, unit;
	unsigned int cpu, tcpu;
	struct pcpu_alloc_info *ai;
	unsigned int *cpu_map;

	/* this function may be called multiple times */
	memset(group_map, 0, sizeof(group_map));
	memset(group_cnt, 0, sizeof(group_cnt));

	/* calculate size_sum and ensure dyn_size is enough for early alloc */
	size_sum = PFN_ALIGN(static_size + reserved_size +
			    max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
	dyn_size = size_sum - static_size - reserved_size;

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

	/* determine the maximum # of units that can fit in an allocation */
	alloc_size = roundup(min_unit_size, atom_size);
	upa = alloc_size / min_unit_size;
	while (alloc_size % upa || (offset_in_page(alloc_size / upa)))
		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_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
				group++;
				nr_groups = max(nr_groups, group + 1);
				goto next_group;
			}
		}
		group_map[cpu] = group;
		group_cnt[group]++;
	}

	/*
	 * Wasted space is caused by a ratio imbalance of upa to group_cnt.
	 * Expand the unit_size until we use >= 75% of the units allocated.
	 * Related to atom_size, which could be much larger than the unit_size.
	 */
	last_allocs = INT_MAX;
	for (upa = max_upa; upa; upa--) {
		int allocs = 0, wasted = 0;

		if (alloc_size % upa || (offset_in_page(alloc_size / upa)))
			continue;

		for (group = 0; group < nr_groups; 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 1/3.  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;
	}
	upa = best_upa;

	/* allocate and fill alloc_info */
	for (group = 0; group < nr_groups; group++)
		nr_units += roundup(group_cnt[group], upa);

	ai = pcpu_alloc_alloc_info(nr_groups, nr_units);
	if (!ai)
		return ERR_PTR(-ENOMEM);
	cpu_map = ai->groups[0].cpu_map;

	for (group = 0; group < nr_groups; group++) {
		ai->groups[group].cpu_map = cpu_map;
		cpu_map += roundup(group_cnt[group], upa);
	}

	ai->static_size = static_size;
	ai->reserved_size = reserved_size;
	ai->dyn_size = dyn_size;
	ai->unit_size = alloc_size / upa;
	ai->atom_size = atom_size;
	ai->alloc_size = alloc_size;

	for (group = 0, unit = 0; group_cnt[group]; group++) {
		struct pcpu_group_info *gi = &ai->groups[group];

		/*
		 * Initialize base_offset as if all groups are located
		 * back-to-back.  The caller should update this to
		 * reflect actual allocation.
		 */
		gi->base_offset = unit * ai->unit_size;

		for_each_possible_cpu(cpu)
			if (group_map[cpu] == group)
				gi->cpu_map[gi->nr_units++] = cpu;
		gi->nr_units = roundup(gi->nr_units, upa);
		unit += gi->nr_units;
	}
	BUG_ON(unit != nr_units);

	return ai;
}
#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */

#if defined(BUILD_EMBED_FIRST_CHUNK)
/**
 * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
 * @reserved_size: the size of reserved percpu area in bytes
 * @dyn_size: minimum free size for dynamic allocation in bytes
 * @atom_size: allocation atom size
 * @cpu_distance_fn: callback to determine distance between cpus, optional
 * @alloc_fn: function to allocate percpu page
 * @free_fn: function to free percpu page
 *
 * 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
 * by calling @alloc_fn and used as-is without being mapped into
 * vmalloc area.  Allocations are always whole multiples of @atom_size
 * aligned to @atom_size.
 *
 * This enables the first chunk to piggy back on the linear physical
 * mapping which often uses larger page size.  Please note that this
 * can result in very sparse cpu->unit mapping on NUMA machines thus
 * requiring large vmalloc address space.  Don't use this allocator if
 * vmalloc space is not orders of magnitude larger than distances
 * between node memory addresses (ie. 32bit NUMA machines).
 *
 * @dyn_size specifies the minimum dynamic area size.
 *
 * If the needed size is smaller than the minimum or specified unit
 * size, the leftover is returned using @free_fn.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
				  size_t atom_size,
				  pcpu_fc_cpu_distance_fn_t cpu_distance_fn,
				  pcpu_fc_alloc_fn_t alloc_fn,
				  pcpu_fc_free_fn_t free_fn)
{
	void *base = (void *)ULONG_MAX;
	void **areas = NULL;
	struct pcpu_alloc_info *ai;
	size_t size_sum, areas_size;
	unsigned long max_distance;
	int group, i, highest_group, rc;

	ai = pcpu_build_alloc_info(reserved_size, dyn_size, atom_size,
				   cpu_distance_fn);
	if (IS_ERR(ai))
		return PTR_ERR(ai);

	size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
	areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *));

	areas = memblock_virt_alloc_nopanic(areas_size, 0);
	if (!areas) {
		rc = -ENOMEM;
		goto out_free;
	}

	/* allocate, copy and determine base address & max_distance */
	highest_group = 0;
	for (group = 0; group < ai->nr_groups; group++) {
		struct pcpu_group_info *gi = &ai->groups[group];
		unsigned int cpu = NR_CPUS;
		void *ptr;

		for (i = 0; i < gi->nr_units && cpu == NR_CPUS; i++)
			cpu = gi->cpu_map[i];
		BUG_ON(cpu == NR_CPUS);

		/* allocate space for the whole group */
		ptr = alloc_fn(cpu, gi->nr_units * ai->unit_size, atom_size);
		if (!ptr) {
			rc = -ENOMEM;
			goto out_free_areas;
		}
		/* kmemleak tracks the percpu allocations separately */
		kmemleak_free(ptr);
		areas[group] = ptr;

		base = min(ptr, base);
		if (ptr > areas[highest_group])
			highest_group = group;
	}
	max_distance = areas[highest_group] - base;
	max_distance += ai->unit_size * ai->groups[highest_group].nr_units;

	/* warn if maximum distance is further than 75% of vmalloc space */
	if (max_distance > VMALLOC_TOTAL * 3 / 4) {
		pr_warn("max_distance=0x%lx too large for vmalloc space 0x%lx\n",
				max_distance, VMALLOC_TOTAL);
#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
		/* and fail if we have fallback */
		rc = -EINVAL;
		goto out_free_areas;
#endif
	}

	/*
	 * Copy data and free unused parts.  This should happen after all
	 * allocations are complete; otherwise, we may end up with
	 * overlapping groups.
	 */
	for (group = 0; group < ai->nr_groups; group++) {
		struct pcpu_group_info *gi = &ai->groups[group];
		void *ptr = areas[group];

		for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
			if (gi->cpu_map[i] == NR_CPUS) {
				/* unused unit, free whole */
				free_fn(ptr, ai->unit_size);
				continue;
			}
			/* copy and return the unused part */
			memcpy(ptr, __per_cpu_load, ai->static_size);
			free_fn(ptr + size_sum, ai->unit_size - size_sum);
		}
	}

	/* base address is now known, determine group base offsets */
	for (group = 0; group < ai->nr_groups; group++) {
		ai->groups[group].base_offset = areas[group] - base;
	}

	pr_info("Embedded %zu pages/cpu @%p s%zu r%zu d%zu u%zu\n",
		PFN_DOWN(size_sum), base, ai->static_size, ai->reserved_size,
		ai->dyn_size, ai->unit_size);

	rc = pcpu_setup_first_chunk(ai, base);
	goto out_free;

out_free_areas:
	for (group = 0; group < ai->nr_groups; group++)
		if (areas[group])
			free_fn(areas[group],
				ai->groups[group].nr_units * ai->unit_size);
out_free:
	pcpu_free_alloc_info(ai);
	if (areas)
		memblock_free_early(__pa(areas), areas_size);
	return rc;
}
#endif /* BUILD_EMBED_FIRST_CHUNK */

#ifdef BUILD_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: function 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:
 * 0 on success, -errno on failure.
 */
int __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;
	struct pcpu_alloc_info *ai;
	char psize_str[16];
	int unit_pages;
	size_t pages_size;
	struct page **pages;
	int unit, i, j, rc;
	int upa;
	int nr_g0_units;

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

	ai = pcpu_build_alloc_info(reserved_size, 0, PAGE_SIZE, NULL);
	if (IS_ERR(ai))
		return PTR_ERR(ai);
	BUG_ON(ai->nr_groups != 1);
	upa = ai->alloc_size/ai->unit_size;
	nr_g0_units = roundup(num_possible_cpus(), upa);
	if (unlikely(WARN_ON(ai->groups[0].nr_units != nr_g0_units))) {
		pcpu_free_alloc_info(ai);
		return -EINVAL;
	}

	unit_pages = ai->unit_size >> PAGE_SHIFT;

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

	/* allocate pages */
	j = 0;
	for (unit = 0; unit < num_possible_cpus(); unit++) {
		unsigned int cpu = ai->groups[0].cpu_map[unit];
		for (i = 0; i < unit_pages; i++) {
			void *ptr;

			ptr = alloc_fn(cpu, PAGE_SIZE, PAGE_SIZE);
			if (!ptr) {
				pr_warn("failed to allocate %s page for cpu%u\n",
						psize_str, cpu);
				goto enomem;
			}
			/* kmemleak tracks the percpu allocations separately */
			kmemleak_free(ptr);
			pages[j++] = virt_to_page(ptr);
		}
	}

	/* allocate vm area, map the pages and copy static data */
	vm.flags = VM_ALLOC;
	vm.size = num_possible_cpus() * ai->unit_size;
	vm_area_register_early(&vm, PAGE_SIZE);

	for (unit = 0; unit < num_possible_cpus(); unit++) {
		unsigned long unit_addr =
			(unsigned long)vm.addr + unit * ai->unit_size;

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

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

		/*
		 * 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, ai->static_size);
	}

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

	rc = pcpu_setup_first_chunk(ai, vm.addr);
	goto out_free_ar;

enomem:
	while (--j >= 0)
		free_fn(page_address(pages[j]), PAGE_SIZE);
	rc = -ENOMEM;
out_free_ar:
	memblock_free_early(__pa(pages), pages_size);
	pcpu_free_alloc_info(ai);
	return rc;
}
#endif /* BUILD_PAGE_FIRST_CHUNK */

#ifndef	CONFIG_HAVE_SETUP_PER_CPU_AREA
/*
 * Generic SMP 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.
 */
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);

static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size,
				       size_t align)
{
	return  memblock_virt_alloc_from_nopanic(
			size, align, __pa(MAX_DMA_ADDRESS));
}

static void __init pcpu_dfl_fc_free(void *ptr, size_t size)
{
	memblock_free_early(__pa(ptr), size);
}

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

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

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

#else	/* CONFIG_SMP */

/*
 * UP percpu area setup.
 *
 * UP always uses km-based percpu allocator with identity mapping.
 * Static percpu variables are indistinguishable from the usual static
 * variables and don't require any special preparation.
 */
void __init setup_per_cpu_areas(void)
{
	const size_t unit_size =
		roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE,
					 PERCPU_DYNAMIC_RESERVE));
	struct pcpu_alloc_info *ai;
	void *fc;

	ai = pcpu_alloc_alloc_info(1, 1);
	fc = memblock_virt_alloc_from_nopanic(unit_size,
					      PAGE_SIZE,
					      __pa(MAX_DMA_ADDRESS));
	if (!ai || !fc)
		panic("Failed to allocate memory for percpu areas.");
	/* kmemleak tracks the percpu allocations separately */
	kmemleak_free(fc);

	ai->dyn_size = unit_size;
	ai->unit_size = unit_size;
	ai->atom_size = unit_size;
	ai->alloc_size = unit_size;
	ai->groups[0].nr_units = 1;
	ai->groups[0].cpu_map[0] = 0;

	if (pcpu_setup_first_chunk(ai, fc) < 0)
		panic("Failed to initialize percpu areas.");
}

#endif	/* CONFIG_SMP */

/*
 * Percpu allocator is initialized early during boot when neither slab or
 * workqueue is available.  Plug async management until everything is up
 * and running.
 */
static int __init percpu_enable_async(void)
{
	pcpu_async_enabled = true;
	return 0;
}
subsys_initcall(percpu_enable_async);