summaryrefslogtreecommitdiffstats
path: root/mm/mm_init.c
blob: dd3a6ed9663faa160796de1d50ce185742998cf8 (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
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
// SPDX-License-Identifier: GPL-2.0-only
/*
 * mm_init.c - Memory initialisation verification and debugging
 *
 * Copyright 2008 IBM Corporation, 2008
 * Author Mel Gorman <mel@csn.ul.ie>
 *
 */
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/kobject.h>
#include <linux/export.h>
#include <linux/memory.h>
#include <linux/notifier.h>
#include <linux/sched.h>
#include <linux/mman.h>
#include <linux/memblock.h>
#include <linux/page-isolation.h>
#include <linux/padata.h>
#include <linux/nmi.h>
#include <linux/buffer_head.h>
#include <linux/kmemleak.h>
#include <linux/kfence.h>
#include <linux/page_ext.h>
#include <linux/pti.h>
#include <linux/pgtable.h>
#include <linux/swap.h>
#include <linux/cma.h>
#include "internal.h"
#include "slab.h"
#include "shuffle.h"

#include <asm/setup.h>

#ifdef CONFIG_DEBUG_MEMORY_INIT
int __meminitdata mminit_loglevel;

/* The zonelists are simply reported, validation is manual. */
void __init mminit_verify_zonelist(void)
{
	int nid;

	if (mminit_loglevel < MMINIT_VERIFY)
		return;

	for_each_online_node(nid) {
		pg_data_t *pgdat = NODE_DATA(nid);
		struct zone *zone;
		struct zoneref *z;
		struct zonelist *zonelist;
		int i, listid, zoneid;

		BUILD_BUG_ON(MAX_ZONELISTS > 2);
		for (i = 0; i < MAX_ZONELISTS * MAX_NR_ZONES; i++) {

			/* Identify the zone and nodelist */
			zoneid = i % MAX_NR_ZONES;
			listid = i / MAX_NR_ZONES;
			zonelist = &pgdat->node_zonelists[listid];
			zone = &pgdat->node_zones[zoneid];
			if (!populated_zone(zone))
				continue;

			/* Print information about the zonelist */
			printk(KERN_DEBUG "mminit::zonelist %s %d:%s = ",
				listid > 0 ? "thisnode" : "general", nid,
				zone->name);

			/* Iterate the zonelist */
			for_each_zone_zonelist(zone, z, zonelist, zoneid)
				pr_cont("%d:%s ", zone_to_nid(zone), zone->name);
			pr_cont("\n");
		}
	}
}

void __init mminit_verify_pageflags_layout(void)
{
	int shift, width;
	unsigned long or_mask, add_mask;

	shift = 8 * sizeof(unsigned long);
	width = shift - SECTIONS_WIDTH - NODES_WIDTH - ZONES_WIDTH
		- LAST_CPUPID_SHIFT - KASAN_TAG_WIDTH - LRU_GEN_WIDTH - LRU_REFS_WIDTH;
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_widths",
		"Section %d Node %d Zone %d Lastcpupid %d Kasantag %d Gen %d Tier %d Flags %d\n",
		SECTIONS_WIDTH,
		NODES_WIDTH,
		ZONES_WIDTH,
		LAST_CPUPID_WIDTH,
		KASAN_TAG_WIDTH,
		LRU_GEN_WIDTH,
		LRU_REFS_WIDTH,
		NR_PAGEFLAGS);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_shifts",
		"Section %d Node %d Zone %d Lastcpupid %d Kasantag %d\n",
		SECTIONS_SHIFT,
		NODES_SHIFT,
		ZONES_SHIFT,
		LAST_CPUPID_SHIFT,
		KASAN_TAG_WIDTH);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_pgshifts",
		"Section %lu Node %lu Zone %lu Lastcpupid %lu Kasantag %lu\n",
		(unsigned long)SECTIONS_PGSHIFT,
		(unsigned long)NODES_PGSHIFT,
		(unsigned long)ZONES_PGSHIFT,
		(unsigned long)LAST_CPUPID_PGSHIFT,
		(unsigned long)KASAN_TAG_PGSHIFT);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodezoneid",
		"Node/Zone ID: %lu -> %lu\n",
		(unsigned long)(ZONEID_PGOFF + ZONEID_SHIFT),
		(unsigned long)ZONEID_PGOFF);
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_usage",
		"location: %d -> %d layout %d -> %d unused %d -> %d page-flags\n",
		shift, width, width, NR_PAGEFLAGS, NR_PAGEFLAGS, 0);
#ifdef NODE_NOT_IN_PAGE_FLAGS
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
		"Node not in page flags");
#endif
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
	mminit_dprintk(MMINIT_TRACE, "pageflags_layout_nodeflags",
		"Last cpupid not in page flags");
#endif

	if (SECTIONS_WIDTH) {
		shift -= SECTIONS_WIDTH;
		BUG_ON(shift != SECTIONS_PGSHIFT);
	}
	if (NODES_WIDTH) {
		shift -= NODES_WIDTH;
		BUG_ON(shift != NODES_PGSHIFT);
	}
	if (ZONES_WIDTH) {
		shift -= ZONES_WIDTH;
		BUG_ON(shift != ZONES_PGSHIFT);
	}

	/* Check for bitmask overlaps */
	or_mask = (ZONES_MASK << ZONES_PGSHIFT) |
			(NODES_MASK << NODES_PGSHIFT) |
			(SECTIONS_MASK << SECTIONS_PGSHIFT);
	add_mask = (ZONES_MASK << ZONES_PGSHIFT) +
			(NODES_MASK << NODES_PGSHIFT) +
			(SECTIONS_MASK << SECTIONS_PGSHIFT);
	BUG_ON(or_mask != add_mask);
}

static __init int set_mminit_loglevel(char *str)
{
	get_option(&str, &mminit_loglevel);
	return 0;
}
early_param("mminit_loglevel", set_mminit_loglevel);
#endif /* CONFIG_DEBUG_MEMORY_INIT */

struct kobject *mm_kobj;
EXPORT_SYMBOL_GPL(mm_kobj);

#ifdef CONFIG_SMP
s32 vm_committed_as_batch = 32;

void mm_compute_batch(int overcommit_policy)
{
	u64 memsized_batch;
	s32 nr = num_present_cpus();
	s32 batch = max_t(s32, nr*2, 32);
	unsigned long ram_pages = totalram_pages();

	/*
	 * For policy OVERCOMMIT_NEVER, set batch size to 0.4% of
	 * (total memory/#cpus), and lift it to 25% for other policies
	 * to easy the possible lock contention for percpu_counter
	 * vm_committed_as, while the max limit is INT_MAX
	 */
	if (overcommit_policy == OVERCOMMIT_NEVER)
		memsized_batch = min_t(u64, ram_pages/nr/256, INT_MAX);
	else
		memsized_batch = min_t(u64, ram_pages/nr/4, INT_MAX);

	vm_committed_as_batch = max_t(s32, memsized_batch, batch);
}

static int __meminit mm_compute_batch_notifier(struct notifier_block *self,
					unsigned long action, void *arg)
{
	switch (action) {
	case MEM_ONLINE:
	case MEM_OFFLINE:
		mm_compute_batch(sysctl_overcommit_memory);
		break;
	default:
		break;
	}
	return NOTIFY_OK;
}

static int __init mm_compute_batch_init(void)
{
	mm_compute_batch(sysctl_overcommit_memory);
	hotplug_memory_notifier(mm_compute_batch_notifier, MM_COMPUTE_BATCH_PRI);
	return 0;
}

__initcall(mm_compute_batch_init);

#endif

static int __init mm_sysfs_init(void)
{
	mm_kobj = kobject_create_and_add("mm", kernel_kobj);
	if (!mm_kobj)
		return -ENOMEM;

	return 0;
}
postcore_initcall(mm_sysfs_init);

static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata;
static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata;
static unsigned long zone_movable_pfn[MAX_NUMNODES] __initdata;

static unsigned long required_kernelcore __initdata;
static unsigned long required_kernelcore_percent __initdata;
static unsigned long required_movablecore __initdata;
static unsigned long required_movablecore_percent __initdata;

static unsigned long nr_kernel_pages __initdata;
static unsigned long nr_all_pages __initdata;
static unsigned long dma_reserve __initdata;

static bool deferred_struct_pages __meminitdata;

static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);

static int __init cmdline_parse_core(char *p, unsigned long *core,
				     unsigned long *percent)
{
	unsigned long long coremem;
	char *endptr;

	if (!p)
		return -EINVAL;

	/* Value may be a percentage of total memory, otherwise bytes */
	coremem = simple_strtoull(p, &endptr, 0);
	if (*endptr == '%') {
		/* Paranoid check for percent values greater than 100 */
		WARN_ON(coremem > 100);

		*percent = coremem;
	} else {
		coremem = memparse(p, &p);
		/* Paranoid check that UL is enough for the coremem value */
		WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX);

		*core = coremem >> PAGE_SHIFT;
		*percent = 0UL;
	}
	return 0;
}

/*
 * kernelcore=size sets the amount of memory for use for allocations that
 * cannot be reclaimed or migrated.
 */
static int __init cmdline_parse_kernelcore(char *p)
{
	/* parse kernelcore=mirror */
	if (parse_option_str(p, "mirror")) {
		mirrored_kernelcore = true;
		return 0;
	}

	return cmdline_parse_core(p, &required_kernelcore,
				  &required_kernelcore_percent);
}
early_param("kernelcore", cmdline_parse_kernelcore);

/*
 * movablecore=size sets the amount of memory for use for allocations that
 * can be reclaimed or migrated.
 */
static int __init cmdline_parse_movablecore(char *p)
{
	return cmdline_parse_core(p, &required_movablecore,
				  &required_movablecore_percent);
}
early_param("movablecore", cmdline_parse_movablecore);

/*
 * early_calculate_totalpages()
 * Sum pages in active regions for movable zone.
 * Populate N_MEMORY for calculating usable_nodes.
 */
static unsigned long __init early_calculate_totalpages(void)
{
	unsigned long totalpages = 0;
	unsigned long start_pfn, end_pfn;
	int i, nid;

	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
		unsigned long pages = end_pfn - start_pfn;

		totalpages += pages;
		if (pages)
			node_set_state(nid, N_MEMORY);
	}
	return totalpages;
}

/*
 * This finds a zone that can be used for ZONE_MOVABLE pages. The
 * assumption is made that zones within a node are ordered in monotonic
 * increasing memory addresses so that the "highest" populated zone is used
 */
static void __init find_usable_zone_for_movable(void)
{
	int zone_index;
	for (zone_index = MAX_NR_ZONES - 1; zone_index >= 0; zone_index--) {
		if (zone_index == ZONE_MOVABLE)
			continue;

		if (arch_zone_highest_possible_pfn[zone_index] >
				arch_zone_lowest_possible_pfn[zone_index])
			break;
	}

	VM_BUG_ON(zone_index == -1);
	movable_zone = zone_index;
}

/*
 * Find the PFN the Movable zone begins in each node. Kernel memory
 * is spread evenly between nodes as long as the nodes have enough
 * memory. When they don't, some nodes will have more kernelcore than
 * others
 */
static void __init find_zone_movable_pfns_for_nodes(void)
{
	int i, nid;
	unsigned long usable_startpfn;
	unsigned long kernelcore_node, kernelcore_remaining;
	/* save the state before borrow the nodemask */
	nodemask_t saved_node_state = node_states[N_MEMORY];
	unsigned long totalpages = early_calculate_totalpages();
	int usable_nodes = nodes_weight(node_states[N_MEMORY]);
	struct memblock_region *r;

	/* Need to find movable_zone earlier when movable_node is specified. */
	find_usable_zone_for_movable();

	/*
	 * If movable_node is specified, ignore kernelcore and movablecore
	 * options.
	 */
	if (movable_node_is_enabled()) {
		for_each_mem_region(r) {
			if (!memblock_is_hotpluggable(r))
				continue;

			nid = memblock_get_region_node(r);

			usable_startpfn = PFN_DOWN(r->base);
			zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
				min(usable_startpfn, zone_movable_pfn[nid]) :
				usable_startpfn;
		}

		goto out2;
	}

	/*
	 * If kernelcore=mirror is specified, ignore movablecore option
	 */
	if (mirrored_kernelcore) {
		bool mem_below_4gb_not_mirrored = false;

		for_each_mem_region(r) {
			if (memblock_is_mirror(r))
				continue;

			nid = memblock_get_region_node(r);

			usable_startpfn = memblock_region_memory_base_pfn(r);

			if (usable_startpfn < PHYS_PFN(SZ_4G)) {
				mem_below_4gb_not_mirrored = true;
				continue;
			}

			zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
				min(usable_startpfn, zone_movable_pfn[nid]) :
				usable_startpfn;
		}

		if (mem_below_4gb_not_mirrored)
			pr_warn("This configuration results in unmirrored kernel memory.\n");

		goto out2;
	}

	/*
	 * If kernelcore=nn% or movablecore=nn% was specified, calculate the
	 * amount of necessary memory.
	 */
	if (required_kernelcore_percent)
		required_kernelcore = (totalpages * 100 * required_kernelcore_percent) /
				       10000UL;
	if (required_movablecore_percent)
		required_movablecore = (totalpages * 100 * required_movablecore_percent) /
					10000UL;

	/*
	 * If movablecore= was specified, calculate what size of
	 * kernelcore that corresponds so that memory usable for
	 * any allocation type is evenly spread. If both kernelcore
	 * and movablecore are specified, then the value of kernelcore
	 * will be used for required_kernelcore if it's greater than
	 * what movablecore would have allowed.
	 */
	if (required_movablecore) {
		unsigned long corepages;

		/*
		 * Round-up so that ZONE_MOVABLE is at least as large as what
		 * was requested by the user
		 */
		required_movablecore =
			roundup(required_movablecore, MAX_ORDER_NR_PAGES);
		required_movablecore = min(totalpages, required_movablecore);
		corepages = totalpages - required_movablecore;

		required_kernelcore = max(required_kernelcore, corepages);
	}

	/*
	 * If kernelcore was not specified or kernelcore size is larger
	 * than totalpages, there is no ZONE_MOVABLE.
	 */
	if (!required_kernelcore || required_kernelcore >= totalpages)
		goto out;

	/* usable_startpfn is the lowest possible pfn ZONE_MOVABLE can be at */
	usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];

restart:
	/* Spread kernelcore memory as evenly as possible throughout nodes */
	kernelcore_node = required_kernelcore / usable_nodes;
	for_each_node_state(nid, N_MEMORY) {
		unsigned long start_pfn, end_pfn;

		/*
		 * Recalculate kernelcore_node if the division per node
		 * now exceeds what is necessary to satisfy the requested
		 * amount of memory for the kernel
		 */
		if (required_kernelcore < kernelcore_node)
			kernelcore_node = required_kernelcore / usable_nodes;

		/*
		 * As the map is walked, we track how much memory is usable
		 * by the kernel using kernelcore_remaining. When it is
		 * 0, the rest of the node is usable by ZONE_MOVABLE
		 */
		kernelcore_remaining = kernelcore_node;

		/* Go through each range of PFNs within this node */
		for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
			unsigned long size_pages;

			start_pfn = max(start_pfn, zone_movable_pfn[nid]);
			if (start_pfn >= end_pfn)
				continue;

			/* Account for what is only usable for kernelcore */
			if (start_pfn < usable_startpfn) {
				unsigned long kernel_pages;
				kernel_pages = min(end_pfn, usable_startpfn)
								- start_pfn;

				kernelcore_remaining -= min(kernel_pages,
							kernelcore_remaining);
				required_kernelcore -= min(kernel_pages,
							required_kernelcore);

				/* Continue if range is now fully accounted */
				if (end_pfn <= usable_startpfn) {

					/*
					 * Push zone_movable_pfn to the end so
					 * that if we have to rebalance
					 * kernelcore across nodes, we will
					 * not double account here
					 */
					zone_movable_pfn[nid] = end_pfn;
					continue;
				}
				start_pfn = usable_startpfn;
			}

			/*
			 * The usable PFN range for ZONE_MOVABLE is from
			 * start_pfn->end_pfn. Calculate size_pages as the
			 * number of pages used as kernelcore
			 */
			size_pages = end_pfn - start_pfn;
			if (size_pages > kernelcore_remaining)
				size_pages = kernelcore_remaining;
			zone_movable_pfn[nid] = start_pfn + size_pages;

			/*
			 * Some kernelcore has been met, update counts and
			 * break if the kernelcore for this node has been
			 * satisfied
			 */
			required_kernelcore -= min(required_kernelcore,
								size_pages);
			kernelcore_remaining -= size_pages;
			if (!kernelcore_remaining)
				break;
		}
	}

	/*
	 * If there is still required_kernelcore, we do another pass with one
	 * less node in the count. This will push zone_movable_pfn[nid] further
	 * along on the nodes that still have memory until kernelcore is
	 * satisfied
	 */
	usable_nodes--;
	if (usable_nodes && required_kernelcore > usable_nodes)
		goto restart;

out2:
	/* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */
	for (nid = 0; nid < MAX_NUMNODES; nid++) {
		unsigned long start_pfn, end_pfn;

		zone_movable_pfn[nid] =
			roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES);

		get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
		if (zone_movable_pfn[nid] >= end_pfn)
			zone_movable_pfn[nid] = 0;
	}

out:
	/* restore the node_state */
	node_states[N_MEMORY] = saved_node_state;
}

static void __meminit __init_single_page(struct page *page, unsigned long pfn,
				unsigned long zone, int nid)
{
	mm_zero_struct_page(page);
	set_page_links(page, zone, nid, pfn);
	init_page_count(page);
	page_mapcount_reset(page);
	page_cpupid_reset_last(page);
	page_kasan_tag_reset(page);

	INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
	/* The shift won't overflow because ZONE_NORMAL is below 4G. */
	if (!is_highmem_idx(zone))
		set_page_address(page, __va(pfn << PAGE_SHIFT));
#endif
}

#ifdef CONFIG_NUMA
/*
 * During memory init memblocks map pfns to nids. The search is expensive and
 * this caches recent lookups. The implementation of __early_pfn_to_nid
 * treats start/end as pfns.
 */
struct mminit_pfnnid_cache {
	unsigned long last_start;
	unsigned long last_end;
	int last_nid;
};

static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;

/*
 * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
 */
static int __meminit __early_pfn_to_nid(unsigned long pfn,
					struct mminit_pfnnid_cache *state)
{
	unsigned long start_pfn, end_pfn;
	int nid;

	if (state->last_start <= pfn && pfn < state->last_end)
		return state->last_nid;

	nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
	if (nid != NUMA_NO_NODE) {
		state->last_start = start_pfn;
		state->last_end = end_pfn;
		state->last_nid = nid;
	}

	return nid;
}

int __meminit early_pfn_to_nid(unsigned long pfn)
{
	static DEFINE_SPINLOCK(early_pfn_lock);
	int nid;

	spin_lock(&early_pfn_lock);
	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
	if (nid < 0)
		nid = first_online_node;
	spin_unlock(&early_pfn_lock);

	return nid;
}

int hashdist = HASHDIST_DEFAULT;

static int __init set_hashdist(char *str)
{
	if (!str)
		return 0;
	hashdist = simple_strtoul(str, &str, 0);
	return 1;
}
__setup("hashdist=", set_hashdist);

static inline void fixup_hashdist(void)
{
	if (num_node_state(N_MEMORY) == 1)
		hashdist = 0;
}
#else
static inline void fixup_hashdist(void) {}
#endif /* CONFIG_NUMA */

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static inline void pgdat_set_deferred_range(pg_data_t *pgdat)
{
	pgdat->first_deferred_pfn = ULONG_MAX;
}

/* Returns true if the struct page for the pfn is initialised */
static inline bool __meminit early_page_initialised(unsigned long pfn)
{
	int nid = early_pfn_to_nid(pfn);

	if (node_online(nid) && pfn >= NODE_DATA(nid)->first_deferred_pfn)
		return false;

	return true;
}

/*
 * Returns true when the remaining initialisation should be deferred until
 * later in the boot cycle when it can be parallelised.
 */
static bool __meminit
defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
{
	static unsigned long prev_end_pfn, nr_initialised;

	if (early_page_ext_enabled())
		return false;
	/*
	 * prev_end_pfn static that contains the end of previous zone
	 * No need to protect because called very early in boot before smp_init.
	 */
	if (prev_end_pfn != end_pfn) {
		prev_end_pfn = end_pfn;
		nr_initialised = 0;
	}

	/* Always populate low zones for address-constrained allocations */
	if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
		return false;

	if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
		return true;
	/*
	 * We start only with one section of pages, more pages are added as
	 * needed until the rest of deferred pages are initialized.
	 */
	nr_initialised++;
	if ((nr_initialised > PAGES_PER_SECTION) &&
	    (pfn & (PAGES_PER_SECTION - 1)) == 0) {
		NODE_DATA(nid)->first_deferred_pfn = pfn;
		return true;
	}
	return false;
}

static void __meminit init_reserved_page(unsigned long pfn)
{
	pg_data_t *pgdat;
	int nid, zid;

	if (early_page_initialised(pfn))
		return;

	nid = early_pfn_to_nid(pfn);
	pgdat = NODE_DATA(nid);

	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
		struct zone *zone = &pgdat->node_zones[zid];

		if (zone_spans_pfn(zone, pfn))
			break;
	}
	__init_single_page(pfn_to_page(pfn), pfn, zid, nid);
}
#else
static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {}

static inline bool early_page_initialised(unsigned long pfn)
{
	return true;
}

static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn)
{
	return false;
}

static inline void init_reserved_page(unsigned long pfn)
{
}
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */

/*
 * Initialised pages do not have PageReserved set. This function is
 * called for each range allocated by the bootmem allocator and
 * marks the pages PageReserved. The remaining valid pages are later
 * sent to the buddy page allocator.
 */
void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
{
	unsigned long start_pfn = PFN_DOWN(start);
	unsigned long end_pfn = PFN_UP(end);

	for (; start_pfn < end_pfn; start_pfn++) {
		if (pfn_valid(start_pfn)) {
			struct page *page = pfn_to_page(start_pfn);

			init_reserved_page(start_pfn);

			/* Avoid false-positive PageTail() */
			INIT_LIST_HEAD(&page->lru);

			/*
			 * no need for atomic set_bit because the struct
			 * page is not visible yet so nobody should
			 * access it yet.
			 */
			__SetPageReserved(page);
		}
	}
}

/* If zone is ZONE_MOVABLE but memory is mirrored, it is an overlapped init */
static bool __meminit
overlap_memmap_init(unsigned long zone, unsigned long *pfn)
{
	static struct memblock_region *r;

	if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
		if (!r || *pfn >= memblock_region_memory_end_pfn(r)) {
			for_each_mem_region(r) {
				if (*pfn < memblock_region_memory_end_pfn(r))
					break;
			}
		}
		if (*pfn >= memblock_region_memory_base_pfn(r) &&
		    memblock_is_mirror(r)) {
			*pfn = memblock_region_memory_end_pfn(r);
			return true;
		}
	}
	return false;
}

/*
 * Only struct pages that correspond to ranges defined by memblock.memory
 * are zeroed and initialized by going through __init_single_page() during
 * memmap_init_zone_range().
 *
 * But, there could be struct pages that correspond to holes in
 * memblock.memory. This can happen because of the following reasons:
 * - physical memory bank size is not necessarily the exact multiple of the
 *   arbitrary section size
 * - early reserved memory may not be listed in memblock.memory
 * - memory layouts defined with memmap= kernel parameter may not align
 *   nicely with memmap sections
 *
 * Explicitly initialize those struct pages so that:
 * - PG_Reserved is set
 * - zone and node links point to zone and node that span the page if the
 *   hole is in the middle of a zone
 * - zone and node links point to adjacent zone/node if the hole falls on
 *   the zone boundary; the pages in such holes will be prepended to the
 *   zone/node above the hole except for the trailing pages in the last
 *   section that will be appended to the zone/node below.
 */
static void __init init_unavailable_range(unsigned long spfn,
					  unsigned long epfn,
					  int zone, int node)
{
	unsigned long pfn;
	u64 pgcnt = 0;

	for (pfn = spfn; pfn < epfn; pfn++) {
		if (!pfn_valid(pageblock_start_pfn(pfn))) {
			pfn = pageblock_end_pfn(pfn) - 1;
			continue;
		}
		__init_single_page(pfn_to_page(pfn), pfn, zone, node);
		__SetPageReserved(pfn_to_page(pfn));
		pgcnt++;
	}

	if (pgcnt)
		pr_info("On node %d, zone %s: %lld pages in unavailable ranges",
			node, zone_names[zone], pgcnt);
}

/*
 * Initially all pages are reserved - free ones are freed
 * up by memblock_free_all() once the early boot process is
 * done. Non-atomic initialization, single-pass.
 *
 * All aligned pageblocks are initialized to the specified migratetype
 * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
 * zone stats (e.g., nr_isolate_pageblock) are touched.
 */
void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone,
		unsigned long start_pfn, unsigned long zone_end_pfn,
		enum meminit_context context,
		struct vmem_altmap *altmap, int migratetype)
{
	unsigned long pfn, end_pfn = start_pfn + size;
	struct page *page;

	if (highest_memmap_pfn < end_pfn - 1)
		highest_memmap_pfn = end_pfn - 1;

#ifdef CONFIG_ZONE_DEVICE
	/*
	 * Honor reservation requested by the driver for this ZONE_DEVICE
	 * memory. We limit the total number of pages to initialize to just
	 * those that might contain the memory mapping. We will defer the
	 * ZONE_DEVICE page initialization until after we have released
	 * the hotplug lock.
	 */
	if (zone == ZONE_DEVICE) {
		if (!altmap)
			return;

		if (start_pfn == altmap->base_pfn)
			start_pfn += altmap->reserve;
		end_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
	}
#endif

	for (pfn = start_pfn; pfn < end_pfn; ) {
		/*
		 * There can be holes in boot-time mem_map[]s handed to this
		 * function.  They do not exist on hotplugged memory.
		 */
		if (context == MEMINIT_EARLY) {
			if (overlap_memmap_init(zone, &pfn))
				continue;
			if (defer_init(nid, pfn, zone_end_pfn)) {
				deferred_struct_pages = true;
				break;
			}
		}

		page = pfn_to_page(pfn);
		__init_single_page(page, pfn, zone, nid);
		if (context == MEMINIT_HOTPLUG)
			__SetPageReserved(page);

		/*
		 * Usually, we want to mark the pageblock MIGRATE_MOVABLE,
		 * such that unmovable allocations won't be scattered all
		 * over the place during system boot.
		 */
		if (pageblock_aligned(pfn)) {
			set_pageblock_migratetype(page, migratetype);
			cond_resched();
		}
		pfn++;
	}
}

static void __init memmap_init_zone_range(struct zone *zone,
					  unsigned long start_pfn,
					  unsigned long end_pfn,
					  unsigned long *hole_pfn)
{
	unsigned long zone_start_pfn = zone->zone_start_pfn;
	unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages;
	int nid = zone_to_nid(zone), zone_id = zone_idx(zone);

	start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn);
	end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn);

	if (start_pfn >= end_pfn)
		return;

	memmap_init_range(end_pfn - start_pfn, nid, zone_id, start_pfn,
			  zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);

	if (*hole_pfn < start_pfn)
		init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid);

	*hole_pfn = end_pfn;
}

static void __init memmap_init(void)
{
	unsigned long start_pfn, end_pfn;
	unsigned long hole_pfn = 0;
	int i, j, zone_id = 0, nid;

	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
		struct pglist_data *node = NODE_DATA(nid);

		for (j = 0; j < MAX_NR_ZONES; j++) {
			struct zone *zone = node->node_zones + j;

			if (!populated_zone(zone))
				continue;

			memmap_init_zone_range(zone, start_pfn, end_pfn,
					       &hole_pfn);
			zone_id = j;
		}
	}

#ifdef CONFIG_SPARSEMEM
	/*
	 * Initialize the memory map for hole in the range [memory_end,
	 * section_end].
	 * Append the pages in this hole to the highest zone in the last
	 * node.
	 * The call to init_unavailable_range() is outside the ifdef to
	 * silence the compiler warining about zone_id set but not used;
	 * for FLATMEM it is a nop anyway
	 */
	end_pfn = round_up(end_pfn, PAGES_PER_SECTION);
	if (hole_pfn < end_pfn)
#endif
		init_unavailable_range(hole_pfn, end_pfn, zone_id, nid);
}

#ifdef CONFIG_ZONE_DEVICE
static void __ref __init_zone_device_page(struct page *page, unsigned long pfn,
					  unsigned long zone_idx, int nid,
					  struct dev_pagemap *pgmap)
{

	__init_single_page(page, pfn, zone_idx, nid);

	/*
	 * Mark page reserved as it will need to wait for onlining
	 * phase for it to be fully associated with a zone.
	 *
	 * We can use the non-atomic __set_bit operation for setting
	 * the flag as we are still initializing the pages.
	 */
	__SetPageReserved(page);

	/*
	 * ZONE_DEVICE pages union ->lru with a ->pgmap back pointer
	 * and zone_device_data.  It is a bug if a ZONE_DEVICE page is
	 * ever freed or placed on a driver-private list.
	 */
	page->pgmap = pgmap;
	page->zone_device_data = NULL;

	/*
	 * Mark the block movable so that blocks are reserved for
	 * movable at startup. This will force kernel allocations
	 * to reserve their blocks rather than leaking throughout
	 * the address space during boot when many long-lived
	 * kernel allocations are made.
	 *
	 * Please note that MEMINIT_HOTPLUG path doesn't clear memmap
	 * because this is done early in section_activate()
	 */
	if (pageblock_aligned(pfn)) {
		set_pageblock_migratetype(page, MIGRATE_MOVABLE);
		cond_resched();
	}

	/*
	 * ZONE_DEVICE pages are released directly to the driver page allocator
	 * which will set the page count to 1 when allocating the page.
	 */
	if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
	    pgmap->type == MEMORY_DEVICE_COHERENT)
		set_page_count(page, 0);
}

/*
 * With compound page geometry and when struct pages are stored in ram most
 * tail pages are reused. Consequently, the amount of unique struct pages to
 * initialize is a lot smaller that the total amount of struct pages being
 * mapped. This is a paired / mild layering violation with explicit knowledge
 * of how the sparse_vmemmap internals handle compound pages in the lack
 * of an altmap. See vmemmap_populate_compound_pages().
 */
static inline unsigned long compound_nr_pages(struct vmem_altmap *altmap,
					      unsigned long nr_pages)
{
	return is_power_of_2(sizeof(struct page)) &&
		!altmap ? 2 * (PAGE_SIZE / sizeof(struct page)) : nr_pages;
}

static void __ref memmap_init_compound(struct page *head,
				       unsigned long head_pfn,
				       unsigned long zone_idx, int nid,
				       struct dev_pagemap *pgmap,
				       unsigned long nr_pages)
{
	unsigned long pfn, end_pfn = head_pfn + nr_pages;
	unsigned int order = pgmap->vmemmap_shift;

	__SetPageHead(head);
	for (pfn = head_pfn + 1; pfn < end_pfn; pfn++) {
		struct page *page = pfn_to_page(pfn);

		__init_zone_device_page(page, pfn, zone_idx, nid, pgmap);
		prep_compound_tail(head, pfn - head_pfn);
		set_page_count(page, 0);

		/*
		 * The first tail page stores important compound page info.
		 * Call prep_compound_head() after the first tail page has
		 * been initialized, to not have the data overwritten.
		 */
		if (pfn == head_pfn + 1)
			prep_compound_head(head, order);
	}
}

void __ref memmap_init_zone_device(struct zone *zone,
				   unsigned long start_pfn,
				   unsigned long nr_pages,
				   struct dev_pagemap *pgmap)
{
	unsigned long pfn, end_pfn = start_pfn + nr_pages;
	struct pglist_data *pgdat = zone->zone_pgdat;
	struct vmem_altmap *altmap = pgmap_altmap(pgmap);
	unsigned int pfns_per_compound = pgmap_vmemmap_nr(pgmap);
	unsigned long zone_idx = zone_idx(zone);
	unsigned long start = jiffies;
	int nid = pgdat->node_id;

	if (WARN_ON_ONCE(!pgmap || zone_idx != ZONE_DEVICE))
		return;

	/*
	 * The call to memmap_init should have already taken care
	 * of the pages reserved for the memmap, so we can just jump to
	 * the end of that region and start processing the device pages.
	 */
	if (altmap) {
		start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
		nr_pages = end_pfn - start_pfn;
	}

	for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) {
		struct page *page = pfn_to_page(pfn);

		__init_zone_device_page(page, pfn, zone_idx, nid, pgmap);

		if (pfns_per_compound == 1)
			continue;

		memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
				     compound_nr_pages(altmap, pfns_per_compound));
	}

	pr_debug("%s initialised %lu pages in %ums\n", __func__,
		nr_pages, jiffies_to_msecs(jiffies - start));
}
#endif

/*
 * The zone ranges provided by the architecture do not include ZONE_MOVABLE
 * because it is sized independent of architecture. Unlike the other zones,
 * the starting point for ZONE_MOVABLE is not fixed. It may be different
 * in each node depending on the size of each node and how evenly kernelcore
 * is distributed. This helper function adjusts the zone ranges
 * provided by the architecture for a given node by using the end of the
 * highest usable zone for ZONE_MOVABLE. This preserves the assumption that
 * zones within a node are in order of monotonic increases memory addresses
 */
static void __init adjust_zone_range_for_zone_movable(int nid,
					unsigned long zone_type,
					unsigned long node_start_pfn,
					unsigned long node_end_pfn,
					unsigned long *zone_start_pfn,
					unsigned long *zone_end_pfn)
{
	/* Only adjust if ZONE_MOVABLE is on this node */
	if (zone_movable_pfn[nid]) {
		/* Size ZONE_MOVABLE */
		if (zone_type == ZONE_MOVABLE) {
			*zone_start_pfn = zone_movable_pfn[nid];
			*zone_end_pfn = min(node_end_pfn,
				arch_zone_highest_possible_pfn[movable_zone]);

		/* Adjust for ZONE_MOVABLE starting within this range */
		} else if (!mirrored_kernelcore &&
			*zone_start_pfn < zone_movable_pfn[nid] &&
			*zone_end_pfn > zone_movable_pfn[nid]) {
			*zone_end_pfn = zone_movable_pfn[nid];

		/* Check if this whole range is within ZONE_MOVABLE */
		} else if (*zone_start_pfn >= zone_movable_pfn[nid])
			*zone_start_pfn = *zone_end_pfn;
	}
}

/*
 * Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
 * then all holes in the requested range will be accounted for.
 */
unsigned long __init __absent_pages_in_range(int nid,
				unsigned long range_start_pfn,
				unsigned long range_end_pfn)
{
	unsigned long nr_absent = range_end_pfn - range_start_pfn;
	unsigned long start_pfn, end_pfn;
	int i;

	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
		start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn);
		end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn);
		nr_absent -= end_pfn - start_pfn;
	}
	return nr_absent;
}

/**
 * absent_pages_in_range - Return number of page frames in holes within a range
 * @start_pfn: The start PFN to start searching for holes
 * @end_pfn: The end PFN to stop searching for holes
 *
 * Return: the number of pages frames in memory holes within a range.
 */
unsigned long __init absent_pages_in_range(unsigned long start_pfn,
							unsigned long end_pfn)
{
	return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn);
}

/* Return the number of page frames in holes in a zone on a node */
static unsigned long __init zone_absent_pages_in_node(int nid,
					unsigned long zone_type,
					unsigned long node_start_pfn,
					unsigned long node_end_pfn)
{
	unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
	unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
	unsigned long zone_start_pfn, zone_end_pfn;
	unsigned long nr_absent;

	/* When hotadd a new node from cpu_up(), the node should be empty */
	if (!node_start_pfn && !node_end_pfn)
		return 0;

	zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
	zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);

	adjust_zone_range_for_zone_movable(nid, zone_type,
			node_start_pfn, node_end_pfn,
			&zone_start_pfn, &zone_end_pfn);
	nr_absent = __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);

	/*
	 * ZONE_MOVABLE handling.
	 * Treat pages to be ZONE_MOVABLE in ZONE_NORMAL as absent pages
	 * and vice versa.
	 */
	if (mirrored_kernelcore && zone_movable_pfn[nid]) {
		unsigned long start_pfn, end_pfn;
		struct memblock_region *r;

		for_each_mem_region(r) {
			start_pfn = clamp(memblock_region_memory_base_pfn(r),
					  zone_start_pfn, zone_end_pfn);
			end_pfn = clamp(memblock_region_memory_end_pfn(r),
					zone_start_pfn, zone_end_pfn);

			if (zone_type == ZONE_MOVABLE &&
			    memblock_is_mirror(r))
				nr_absent += end_pfn - start_pfn;

			if (zone_type == ZONE_NORMAL &&
			    !memblock_is_mirror(r))
				nr_absent += end_pfn - start_pfn;
		}
	}

	return nr_absent;
}

/*
 * Return the number of pages a zone spans in a node, including holes
 * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node()
 */
static unsigned long __init zone_spanned_pages_in_node(int nid,
					unsigned long zone_type,
					unsigned long node_start_pfn,
					unsigned long node_end_pfn,
					unsigned long *zone_start_pfn,
					unsigned long *zone_end_pfn)
{
	unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
	unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
	/* When hotadd a new node from cpu_up(), the node should be empty */
	if (!node_start_pfn && !node_end_pfn)
		return 0;

	/* Get the start and end of the zone */
	*zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
	*zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
	adjust_zone_range_for_zone_movable(nid, zone_type,
				node_start_pfn, node_end_pfn,
				zone_start_pfn, zone_end_pfn);

	/* Check that this node has pages within the zone's required range */
	if (*zone_end_pfn < node_start_pfn || *zone_start_pfn > node_end_pfn)
		return 0;

	/* Move the zone boundaries inside the node if necessary */
	*zone_end_pfn = min(*zone_end_pfn, node_end_pfn);
	*zone_start_pfn = max(*zone_start_pfn, node_start_pfn);

	/* Return the spanned pages */
	return *zone_end_pfn - *zone_start_pfn;
}

static void __init calculate_node_totalpages(struct pglist_data *pgdat,
						unsigned long node_start_pfn,
						unsigned long node_end_pfn)
{
	unsigned long realtotalpages = 0, totalpages = 0;
	enum zone_type i;

	for (i = 0; i < MAX_NR_ZONES; i++) {
		struct zone *zone = pgdat->node_zones + i;
		unsigned long zone_start_pfn, zone_end_pfn;
		unsigned long spanned, absent;
		unsigned long size, real_size;

		spanned = zone_spanned_pages_in_node(pgdat->node_id, i,
						     node_start_pfn,
						     node_end_pfn,
						     &zone_start_pfn,
						     &zone_end_pfn);
		absent = zone_absent_pages_in_node(pgdat->node_id, i,
						   node_start_pfn,
						   node_end_pfn);

		size = spanned;
		real_size = size - absent;

		if (size)
			zone->zone_start_pfn = zone_start_pfn;
		else
			zone->zone_start_pfn = 0;
		zone->spanned_pages = size;
		zone->present_pages = real_size;
#if defined(CONFIG_MEMORY_HOTPLUG)
		zone->present_early_pages = real_size;
#endif

		totalpages += size;
		realtotalpages += real_size;
	}

	pgdat->node_spanned_pages = totalpages;
	pgdat->node_present_pages = realtotalpages;
	pr_debug("On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
}

static unsigned long __init calc_memmap_size(unsigned long spanned_pages,
						unsigned long present_pages)
{
	unsigned long pages = spanned_pages;

	/*
	 * Provide a more accurate estimation if there are holes within
	 * the zone and SPARSEMEM is in use. If there are holes within the
	 * zone, each populated memory region may cost us one or two extra
	 * memmap pages due to alignment because memmap pages for each
	 * populated regions may not be naturally aligned on page boundary.
	 * So the (present_pages >> 4) heuristic is a tradeoff for that.
	 */
	if (spanned_pages > present_pages + (present_pages >> 4) &&
	    IS_ENABLED(CONFIG_SPARSEMEM))
		pages = present_pages;

	return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT;
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void pgdat_init_split_queue(struct pglist_data *pgdat)
{
	struct deferred_split *ds_queue = &pgdat->deferred_split_queue;

	spin_lock_init(&ds_queue->split_queue_lock);
	INIT_LIST_HEAD(&ds_queue->split_queue);
	ds_queue->split_queue_len = 0;
}
#else
static void pgdat_init_split_queue(struct pglist_data *pgdat) {}
#endif

#ifdef CONFIG_COMPACTION
static void pgdat_init_kcompactd(struct pglist_data *pgdat)
{
	init_waitqueue_head(&pgdat->kcompactd_wait);
}
#else
static void pgdat_init_kcompactd(struct pglist_data *pgdat) {}
#endif

static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
{
	int i;

	pgdat_resize_init(pgdat);
	pgdat_kswapd_lock_init(pgdat);

	pgdat_init_split_queue(pgdat);
	pgdat_init_kcompactd(pgdat);

	init_waitqueue_head(&pgdat->kswapd_wait);
	init_waitqueue_head(&pgdat->pfmemalloc_wait);

	for (i = 0; i < NR_VMSCAN_THROTTLE; i++)
		init_waitqueue_head(&pgdat->reclaim_wait[i]);

	pgdat_page_ext_init(pgdat);
	lruvec_init(&pgdat->__lruvec);
}

static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid,
							unsigned long remaining_pages)
{
	atomic_long_set(&zone->managed_pages, remaining_pages);
	zone_set_nid(zone, nid);
	zone->name = zone_names[idx];
	zone->zone_pgdat = NODE_DATA(nid);
	spin_lock_init(&zone->lock);
	zone_seqlock_init(zone);
	zone_pcp_init(zone);
}

static void __meminit zone_init_free_lists(struct zone *zone)
{
	unsigned int order, t;
	for_each_migratetype_order(order, t) {
		INIT_LIST_HEAD(&zone->free_area[order].free_list[t]);
		zone->free_area[order].nr_free = 0;
	}
}

void __meminit init_currently_empty_zone(struct zone *zone,
					unsigned long zone_start_pfn,
					unsigned long size)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int zone_idx = zone_idx(zone) + 1;

	if (zone_idx > pgdat->nr_zones)
		pgdat->nr_zones = zone_idx;

	zone->zone_start_pfn = zone_start_pfn;

	mminit_dprintk(MMINIT_TRACE, "memmap_init",
			"Initialising map node %d zone %lu pfns %lu -> %lu\n",
			pgdat->node_id,
			(unsigned long)zone_idx(zone),
			zone_start_pfn, (zone_start_pfn + size));

	zone_init_free_lists(zone);
	zone->initialized = 1;
}

#ifndef CONFIG_SPARSEMEM
/*
 * Calculate the size of the zone->blockflags rounded to an unsigned long
 * Start by making sure zonesize is a multiple of pageblock_order by rounding
 * up. Then use 1 NR_PAGEBLOCK_BITS worth of bits per pageblock, finally
 * round what is now in bits to nearest long in bits, then return it in
 * bytes.
 */
static unsigned long __init usemap_size(unsigned long zone_start_pfn, unsigned long zonesize)
{
	unsigned long usemapsize;

	zonesize += zone_start_pfn & (pageblock_nr_pages-1);
	usemapsize = roundup(zonesize, pageblock_nr_pages);
	usemapsize = usemapsize >> pageblock_order;
	usemapsize *= NR_PAGEBLOCK_BITS;
	usemapsize = roundup(usemapsize, 8 * sizeof(unsigned long));

	return usemapsize / 8;
}

static void __ref setup_usemap(struct zone *zone)
{
	unsigned long usemapsize = usemap_size(zone->zone_start_pfn,
					       zone->spanned_pages);
	zone->pageblock_flags = NULL;
	if (usemapsize) {
		zone->pageblock_flags =
			memblock_alloc_node(usemapsize, SMP_CACHE_BYTES,
					    zone_to_nid(zone));
		if (!zone->pageblock_flags)
			panic("Failed to allocate %ld bytes for zone %s pageblock flags on node %d\n",
			      usemapsize, zone->name, zone_to_nid(zone));
	}
}
#else
static inline void setup_usemap(struct zone *zone) {}
#endif /* CONFIG_SPARSEMEM */

#ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE

/* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
void __init set_pageblock_order(void)
{
	unsigned int order = MAX_ORDER;

	/* Check that pageblock_nr_pages has not already been setup */
	if (pageblock_order)
		return;

	/* Don't let pageblocks exceed the maximum allocation granularity. */
	if (HPAGE_SHIFT > PAGE_SHIFT && HUGETLB_PAGE_ORDER < order)
		order = HUGETLB_PAGE_ORDER;

	/*
	 * Assume the largest contiguous order of interest is a huge page.
	 * This value may be variable depending on boot parameters on IA64 and
	 * powerpc.
	 */
	pageblock_order = order;
}
#else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */

/*
 * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order()
 * is unused as pageblock_order is set at compile-time. See
 * include/linux/pageblock-flags.h for the values of pageblock_order based on
 * the kernel config
 */
void __init set_pageblock_order(void)
{
}

#endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */

/*
 * Set up the zone data structures
 * - init pgdat internals
 * - init all zones belonging to this node
 *
 * NOTE: this function is only called during memory hotplug
 */
#ifdef CONFIG_MEMORY_HOTPLUG
void __ref free_area_init_core_hotplug(struct pglist_data *pgdat)
{
	int nid = pgdat->node_id;
	enum zone_type z;
	int cpu;

	pgdat_init_internals(pgdat);

	if (pgdat->per_cpu_nodestats == &boot_nodestats)
		pgdat->per_cpu_nodestats = alloc_percpu(struct per_cpu_nodestat);

	/*
	 * Reset the nr_zones, order and highest_zoneidx before reuse.
	 * Note that kswapd will init kswapd_highest_zoneidx properly
	 * when it starts in the near future.
	 */
	pgdat->nr_zones = 0;
	pgdat->kswapd_order = 0;
	pgdat->kswapd_highest_zoneidx = 0;
	pgdat->node_start_pfn = 0;
	for_each_online_cpu(cpu) {
		struct per_cpu_nodestat *p;

		p = per_cpu_ptr(pgdat->per_cpu_nodestats, cpu);
		memset(p, 0, sizeof(*p));
	}

	for (z = 0; z < MAX_NR_ZONES; z++)
		zone_init_internals(&pgdat->node_zones[z], z, nid, 0);
}
#endif

/*
 * Set up the zone data structures:
 *   - mark all pages reserved
 *   - mark all memory queues empty
 *   - clear the memory bitmaps
 *
 * NOTE: pgdat should get zeroed by caller.
 * NOTE: this function is only called during early init.
 */
static void __init free_area_init_core(struct pglist_data *pgdat)
{
	enum zone_type j;
	int nid = pgdat->node_id;

	pgdat_init_internals(pgdat);
	pgdat->per_cpu_nodestats = &boot_nodestats;

	for (j = 0; j < MAX_NR_ZONES; j++) {
		struct zone *zone = pgdat->node_zones + j;
		unsigned long size, freesize, memmap_pages;

		size = zone->spanned_pages;
		freesize = zone->present_pages;

		/*
		 * Adjust freesize so that it accounts for how much memory
		 * is used by this zone for memmap. This affects the watermark
		 * and per-cpu initialisations
		 */
		memmap_pages = calc_memmap_size(size, freesize);
		if (!is_highmem_idx(j)) {
			if (freesize >= memmap_pages) {
				freesize -= memmap_pages;
				if (memmap_pages)
					pr_debug("  %s zone: %lu pages used for memmap\n",
						 zone_names[j], memmap_pages);
			} else
				pr_warn("  %s zone: %lu memmap pages exceeds freesize %lu\n",
					zone_names[j], memmap_pages, freesize);
		}

		/* Account for reserved pages */
		if (j == 0 && freesize > dma_reserve) {
			freesize -= dma_reserve;
			pr_debug("  %s zone: %lu pages reserved\n", zone_names[0], dma_reserve);
		}

		if (!is_highmem_idx(j))
			nr_kernel_pages += freesize;
		/* Charge for highmem memmap if there are enough kernel pages */
		else if (nr_kernel_pages > memmap_pages * 2)
			nr_kernel_pages -= memmap_pages;
		nr_all_pages += freesize;

		/*
		 * Set an approximate value for lowmem here, it will be adjusted
		 * when the bootmem allocator frees pages into the buddy system.
		 * And all highmem pages will be managed by the buddy system.
		 */
		zone_init_internals(zone, j, nid, freesize);

		if (!size)
			continue;

		set_pageblock_order();
		setup_usemap(zone);
		init_currently_empty_zone(zone, zone->zone_start_pfn, size);
	}
}

void __init *memmap_alloc(phys_addr_t size, phys_addr_t align,
			  phys_addr_t min_addr, int nid, bool exact_nid)
{
	void *ptr;

	if (exact_nid)
		ptr = memblock_alloc_exact_nid_raw(size, align, min_addr,
						   MEMBLOCK_ALLOC_ACCESSIBLE,
						   nid);
	else
		ptr = memblock_alloc_try_nid_raw(size, align, min_addr,
						 MEMBLOCK_ALLOC_ACCESSIBLE,
						 nid);

	if (ptr && size > 0)
		page_init_poison(ptr, size);

	return ptr;
}

#ifdef CONFIG_FLATMEM
static void __init alloc_node_mem_map(struct pglist_data *pgdat)
{
	unsigned long __maybe_unused start = 0;
	unsigned long __maybe_unused offset = 0;

	/* Skip empty nodes */
	if (!pgdat->node_spanned_pages)
		return;

	start = pgdat->node_start_pfn & ~(MAX_ORDER_NR_PAGES - 1);
	offset = pgdat->node_start_pfn - start;
	/* ia64 gets its own node_mem_map, before this, without bootmem */
	if (!pgdat->node_mem_map) {
		unsigned long size, end;
		struct page *map;

		/*
		 * The zone's endpoints aren't required to be MAX_ORDER
		 * aligned but the node_mem_map endpoints must be in order
		 * for the buddy allocator to function correctly.
		 */
		end = pgdat_end_pfn(pgdat);
		end = ALIGN(end, MAX_ORDER_NR_PAGES);
		size =  (end - start) * sizeof(struct page);
		map = memmap_alloc(size, SMP_CACHE_BYTES, MEMBLOCK_LOW_LIMIT,
				   pgdat->node_id, false);
		if (!map)
			panic("Failed to allocate %ld bytes for node %d memory map\n",
			      size, pgdat->node_id);
		pgdat->node_mem_map = map + offset;
	}
	pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n",
				__func__, pgdat->node_id, (unsigned long)pgdat,
				(unsigned long)pgdat->node_mem_map);
#ifndef CONFIG_NUMA
	/*
	 * With no DISCONTIG, the global mem_map is just set as node 0's
	 */
	if (pgdat == NODE_DATA(0)) {
		mem_map = NODE_DATA(0)->node_mem_map;
		if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
			mem_map -= offset;
	}
#endif
}
#else
static inline void alloc_node_mem_map(struct pglist_data *pgdat) { }
#endif /* CONFIG_FLATMEM */

/**
 * get_pfn_range_for_nid - Return the start and end page frames for a node
 * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
 * @start_pfn: Passed by reference. On return, it will have the node start_pfn.
 * @end_pfn: Passed by reference. On return, it will have the node end_pfn.
 *
 * It returns the start and end page frame of a node based on information
 * provided by memblock_set_node(). If called for a node
 * with no available memory, a warning is printed and the start and end
 * PFNs will be 0.
 */
void __init get_pfn_range_for_nid(unsigned int nid,
			unsigned long *start_pfn, unsigned long *end_pfn)
{
	unsigned long this_start_pfn, this_end_pfn;
	int i;

	*start_pfn = -1UL;
	*end_pfn = 0;

	for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) {
		*start_pfn = min(*start_pfn, this_start_pfn);
		*end_pfn = max(*end_pfn, this_end_pfn);
	}

	if (*start_pfn == -1UL)
		*start_pfn = 0;
}

static void __init free_area_init_node(int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);
	unsigned long start_pfn = 0;
	unsigned long end_pfn = 0;

	/* pg_data_t should be reset to zero when it's allocated */
	WARN_ON(pgdat->nr_zones || pgdat->kswapd_highest_zoneidx);

	get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);

	pgdat->node_id = nid;
	pgdat->node_start_pfn = start_pfn;
	pgdat->per_cpu_nodestats = NULL;

	if (start_pfn != end_pfn) {
		pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
			(u64)start_pfn << PAGE_SHIFT,
			end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0);
	} else {
		pr_info("Initmem setup node %d as memoryless\n", nid);
	}

	calculate_node_totalpages(pgdat, start_pfn, end_pfn);

	alloc_node_mem_map(pgdat);
	pgdat_set_deferred_range(pgdat);

	free_area_init_core(pgdat);
	lru_gen_init_pgdat(pgdat);
}

/* Any regular or high memory on that node ? */
static void check_for_memory(pg_data_t *pgdat, int nid)
{
	enum zone_type zone_type;

	for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) {
		struct zone *zone = &pgdat->node_zones[zone_type];
		if (populated_zone(zone)) {
			if (IS_ENABLED(CONFIG_HIGHMEM))
				node_set_state(nid, N_HIGH_MEMORY);
			if (zone_type <= ZONE_NORMAL)
				node_set_state(nid, N_NORMAL_MEMORY);
			break;
		}
	}
}

#if MAX_NUMNODES > 1
/*
 * Figure out the number of possible node ids.
 */
void __init setup_nr_node_ids(void)
{
	unsigned int highest;

	highest = find_last_bit(node_possible_map.bits, MAX_NUMNODES);
	nr_node_ids = highest + 1;
}
#endif

static void __init free_area_init_memoryless_node(int nid)
{
	free_area_init_node(nid);
}

/*
 * Some architectures, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For
 * such cases we allow max_zone_pfn sorted in the descending order
 */
bool __weak arch_has_descending_max_zone_pfns(void)
{
	return false;
}

/**
 * free_area_init - Initialise all pg_data_t and zone data
 * @max_zone_pfn: an array of max PFNs for each zone
 *
 * This will call free_area_init_node() for each active node in the system.
 * Using the page ranges provided by memblock_set_node(), the size of each
 * zone in each node and their holes is calculated. If the maximum PFN
 * between two adjacent zones match, it is assumed that the zone is empty.
 * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed
 * that arch_max_dma32_pfn has no pages. It is also assumed that a zone
 * starts where the previous one ended. For example, ZONE_DMA32 starts
 * at arch_max_dma_pfn.
 */
void __init free_area_init(unsigned long *max_zone_pfn)
{
	unsigned long start_pfn, end_pfn;
	int i, nid, zone;
	bool descending;

	/* Record where the zone boundaries are */
	memset(arch_zone_lowest_possible_pfn, 0,
				sizeof(arch_zone_lowest_possible_pfn));
	memset(arch_zone_highest_possible_pfn, 0,
				sizeof(arch_zone_highest_possible_pfn));

	start_pfn = PHYS_PFN(memblock_start_of_DRAM());
	descending = arch_has_descending_max_zone_pfns();

	for (i = 0; i < MAX_NR_ZONES; i++) {
		if (descending)
			zone = MAX_NR_ZONES - i - 1;
		else
			zone = i;

		if (zone == ZONE_MOVABLE)
			continue;

		end_pfn = max(max_zone_pfn[zone], start_pfn);
		arch_zone_lowest_possible_pfn[zone] = start_pfn;
		arch_zone_highest_possible_pfn[zone] = end_pfn;

		start_pfn = end_pfn;
	}

	/* Find the PFNs that ZONE_MOVABLE begins at in each node */
	memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn));
	find_zone_movable_pfns_for_nodes();

	/* Print out the zone ranges */
	pr_info("Zone ranges:\n");
	for (i = 0; i < MAX_NR_ZONES; i++) {
		if (i == ZONE_MOVABLE)
			continue;
		pr_info("  %-8s ", zone_names[i]);
		if (arch_zone_lowest_possible_pfn[i] ==
				arch_zone_highest_possible_pfn[i])
			pr_cont("empty\n");
		else
			pr_cont("[mem %#018Lx-%#018Lx]\n",
				(u64)arch_zone_lowest_possible_pfn[i]
					<< PAGE_SHIFT,
				((u64)arch_zone_highest_possible_pfn[i]
					<< PAGE_SHIFT) - 1);
	}

	/* Print out the PFNs ZONE_MOVABLE begins at in each node */
	pr_info("Movable zone start for each node\n");
	for (i = 0; i < MAX_NUMNODES; i++) {
		if (zone_movable_pfn[i])
			pr_info("  Node %d: %#018Lx\n", i,
			       (u64)zone_movable_pfn[i] << PAGE_SHIFT);
	}

	/*
	 * Print out the early node map, and initialize the
	 * subsection-map relative to active online memory ranges to
	 * enable future "sub-section" extensions of the memory map.
	 */
	pr_info("Early memory node ranges\n");
	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
		pr_info("  node %3d: [mem %#018Lx-%#018Lx]\n", nid,
			(u64)start_pfn << PAGE_SHIFT,
			((u64)end_pfn << PAGE_SHIFT) - 1);
		subsection_map_init(start_pfn, end_pfn - start_pfn);
	}

	/* Initialise every node */
	mminit_verify_pageflags_layout();
	setup_nr_node_ids();
	for_each_node(nid) {
		pg_data_t *pgdat;

		if (!node_online(nid)) {
			pr_info("Initializing node %d as memoryless\n", nid);

			/* Allocator not initialized yet */
			pgdat = arch_alloc_nodedata(nid);
			if (!pgdat)
				panic("Cannot allocate %zuB for node %d.\n",
				       sizeof(*pgdat), nid);
			arch_refresh_nodedata(nid, pgdat);
			free_area_init_memoryless_node(nid);

			/*
			 * We do not want to confuse userspace by sysfs
			 * files/directories for node without any memory
			 * attached to it, so this node is not marked as
			 * N_MEMORY and not marked online so that no sysfs
			 * hierarchy will be created via register_one_node for
			 * it. The pgdat will get fully initialized by
			 * hotadd_init_pgdat() when memory is hotplugged into
			 * this node.
			 */
			continue;
		}

		pgdat = NODE_DATA(nid);
		free_area_init_node(nid);

		/* Any memory on that node */
		if (pgdat->node_present_pages)
			node_set_state(nid, N_MEMORY);
		check_for_memory(pgdat, nid);
	}

	memmap_init();

	/* disable hash distribution for systems with a single node */
	fixup_hashdist();
}

/**
 * node_map_pfn_alignment - determine the maximum internode alignment
 *
 * This function should be called after node map is populated and sorted.
 * It calculates the maximum power of two alignment which can distinguish
 * all the nodes.
 *
 * For example, if all nodes are 1GiB and aligned to 1GiB, the return value
 * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)).  If the
 * nodes are shifted by 256MiB, 256MiB.  Note that if only the last node is
 * shifted, 1GiB is enough and this function will indicate so.
 *
 * This is used to test whether pfn -> nid mapping of the chosen memory
 * model has fine enough granularity to avoid incorrect mapping for the
 * populated node map.
 *
 * Return: the determined alignment in pfn's.  0 if there is no alignment
 * requirement (single node).
 */
unsigned long __init node_map_pfn_alignment(void)
{
	unsigned long accl_mask = 0, last_end = 0;
	unsigned long start, end, mask;
	int last_nid = NUMA_NO_NODE;
	int i, nid;

	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) {
		if (!start || last_nid < 0 || last_nid == nid) {
			last_nid = nid;
			last_end = end;
			continue;
		}

		/*
		 * Start with a mask granular enough to pin-point to the
		 * start pfn and tick off bits one-by-one until it becomes
		 * too coarse to separate the current node from the last.
		 */
		mask = ~((1 << __ffs(start)) - 1);
		while (mask && last_end <= (start & (mask << 1)))
			mask <<= 1;

		/* accumulate all internode masks */
		accl_mask |= mask;
	}

	/* convert mask to number of pages */
	return ~accl_mask + 1;
}

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __init deferred_free_range(unsigned long pfn,
				       unsigned long nr_pages)
{
	struct page *page;
	unsigned long i;

	if (!nr_pages)
		return;

	page = pfn_to_page(pfn);

	/* Free a large naturally-aligned chunk if possible */
	if (nr_pages == MAX_ORDER_NR_PAGES && IS_MAX_ORDER_ALIGNED(pfn)) {
		for (i = 0; i < nr_pages; i += pageblock_nr_pages)
			set_pageblock_migratetype(page + i, MIGRATE_MOVABLE);
		__free_pages_core(page, MAX_ORDER);
		return;
	}

	for (i = 0; i < nr_pages; i++, page++, pfn++) {
		if (pageblock_aligned(pfn))
			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
		__free_pages_core(page, 0);
	}
}

/* Completion tracking for deferred_init_memmap() threads */
static atomic_t pgdat_init_n_undone __initdata;
static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);

static inline void __init pgdat_init_report_one_done(void)
{
	if (atomic_dec_and_test(&pgdat_init_n_undone))
		complete(&pgdat_init_all_done_comp);
}

/*
 * Returns true if page needs to be initialized or freed to buddy allocator.
 *
 * We check if a current MAX_ORDER block is valid by only checking the validity
 * of the head pfn.
 */
static inline bool __init deferred_pfn_valid(unsigned long pfn)
{
	if (IS_MAX_ORDER_ALIGNED(pfn) && !pfn_valid(pfn))
		return false;
	return true;
}

/*
 * Free pages to buddy allocator. Try to free aligned pages in
 * MAX_ORDER_NR_PAGES sizes.
 */
static void __init deferred_free_pages(unsigned long pfn,
				       unsigned long end_pfn)
{
	unsigned long nr_free = 0;

	for (; pfn < end_pfn; pfn++) {
		if (!deferred_pfn_valid(pfn)) {
			deferred_free_range(pfn - nr_free, nr_free);
			nr_free = 0;
		} else if (IS_MAX_ORDER_ALIGNED(pfn)) {
			deferred_free_range(pfn - nr_free, nr_free);
			nr_free = 1;
		} else {
			nr_free++;
		}
	}
	/* Free the last block of pages to allocator */
	deferred_free_range(pfn - nr_free, nr_free);
}

/*
 * Initialize struct pages.  We minimize pfn page lookups and scheduler checks
 * by performing it only once every MAX_ORDER_NR_PAGES.
 * Return number of pages initialized.
 */
static unsigned long  __init deferred_init_pages(struct zone *zone,
						 unsigned long pfn,
						 unsigned long end_pfn)
{
	int nid = zone_to_nid(zone);
	unsigned long nr_pages = 0;
	int zid = zone_idx(zone);
	struct page *page = NULL;

	for (; pfn < end_pfn; pfn++) {
		if (!deferred_pfn_valid(pfn)) {
			page = NULL;
			continue;
		} else if (!page || IS_MAX_ORDER_ALIGNED(pfn)) {
			page = pfn_to_page(pfn);
		} else {
			page++;
		}
		__init_single_page(page, pfn, zid, nid);
		nr_pages++;
	}
	return (nr_pages);
}

/*
 * This function is meant to pre-load the iterator for the zone init.
 * Specifically it walks through the ranges until we are caught up to the
 * first_init_pfn value and exits there. If we never encounter the value we
 * return false indicating there are no valid ranges left.
 */
static bool __init
deferred_init_mem_pfn_range_in_zone(u64 *i, struct zone *zone,
				    unsigned long *spfn, unsigned long *epfn,
				    unsigned long first_init_pfn)
{
	u64 j;

	/*
	 * Start out by walking through the ranges in this zone that have
	 * already been initialized. We don't need to do anything with them
	 * so we just need to flush them out of the system.
	 */
	for_each_free_mem_pfn_range_in_zone(j, zone, spfn, epfn) {
		if (*epfn <= first_init_pfn)
			continue;
		if (*spfn < first_init_pfn)
			*spfn = first_init_pfn;
		*i = j;
		return true;
	}

	return false;
}

/*
 * Initialize and free pages. We do it in two loops: first we initialize
 * struct page, then free to buddy allocator, because while we are
 * freeing pages we can access pages that are ahead (computing buddy
 * page in __free_one_page()).
 *
 * In order to try and keep some memory in the cache we have the loop
 * broken along max page order boundaries. This way we will not cause
 * any issues with the buddy page computation.
 */
static unsigned long __init
deferred_init_maxorder(u64 *i, struct zone *zone, unsigned long *start_pfn,
		       unsigned long *end_pfn)
{
	unsigned long mo_pfn = ALIGN(*start_pfn + 1, MAX_ORDER_NR_PAGES);
	unsigned long spfn = *start_pfn, epfn = *end_pfn;
	unsigned long nr_pages = 0;
	u64 j = *i;

	/* First we loop through and initialize the page values */
	for_each_free_mem_pfn_range_in_zone_from(j, zone, start_pfn, end_pfn) {
		unsigned long t;

		if (mo_pfn <= *start_pfn)
			break;

		t = min(mo_pfn, *end_pfn);
		nr_pages += deferred_init_pages(zone, *start_pfn, t);

		if (mo_pfn < *end_pfn) {
			*start_pfn = mo_pfn;
			break;
		}
	}

	/* Reset values and now loop through freeing pages as needed */
	swap(j, *i);

	for_each_free_mem_pfn_range_in_zone_from(j, zone, &spfn, &epfn) {
		unsigned long t;

		if (mo_pfn <= spfn)
			break;

		t = min(mo_pfn, epfn);
		deferred_free_pages(spfn, t);

		if (mo_pfn <= epfn)
			break;
	}

	return nr_pages;
}

static void __init
deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
			   void *arg)
{
	unsigned long spfn, epfn;
	struct zone *zone = arg;
	u64 i;

	deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn);

	/*
	 * Initialize and free pages in MAX_ORDER sized increments so that we
	 * can avoid introducing any issues with the buddy allocator.
	 */
	while (spfn < end_pfn) {
		deferred_init_maxorder(&i, zone, &spfn, &epfn);
		cond_resched();
	}
}

/* An arch may override for more concurrency. */
__weak int __init
deferred_page_init_max_threads(const struct cpumask *node_cpumask)
{
	return 1;
}

/* Initialise remaining memory on a node */
static int __init deferred_init_memmap(void *data)
{
	pg_data_t *pgdat = data;
	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
	unsigned long spfn = 0, epfn = 0;
	unsigned long first_init_pfn, flags;
	unsigned long start = jiffies;
	struct zone *zone;
	int zid, max_threads;
	u64 i;

	/* Bind memory initialisation thread to a local node if possible */
	if (!cpumask_empty(cpumask))
		set_cpus_allowed_ptr(current, cpumask);

	pgdat_resize_lock(pgdat, &flags);
	first_init_pfn = pgdat->first_deferred_pfn;
	if (first_init_pfn == ULONG_MAX) {
		pgdat_resize_unlock(pgdat, &flags);
		pgdat_init_report_one_done();
		return 0;
	}

	/* Sanity check boundaries */
	BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn);
	BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
	pgdat->first_deferred_pfn = ULONG_MAX;

	/*
	 * Once we unlock here, the zone cannot be grown anymore, thus if an
	 * interrupt thread must allocate this early in boot, zone must be
	 * pre-grown prior to start of deferred page initialization.
	 */
	pgdat_resize_unlock(pgdat, &flags);

	/* Only the highest zone is deferred so find it */
	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
		zone = pgdat->node_zones + zid;
		if (first_init_pfn < zone_end_pfn(zone))
			break;
	}

	/* If the zone is empty somebody else may have cleared out the zone */
	if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
						 first_init_pfn))
		goto zone_empty;

	max_threads = deferred_page_init_max_threads(cpumask);

	while (spfn < epfn) {
		unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION);
		struct padata_mt_job job = {
			.thread_fn   = deferred_init_memmap_chunk,
			.fn_arg      = zone,
			.start       = spfn,
			.size        = epfn_align - spfn,
			.align       = PAGES_PER_SECTION,
			.min_chunk   = PAGES_PER_SECTION,
			.max_threads = max_threads,
		};

		padata_do_multithreaded(&job);
		deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
						    epfn_align);
	}
zone_empty:
	/* Sanity check that the next zone really is unpopulated */
	WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));

	pr_info("node %d deferred pages initialised in %ums\n",
		pgdat->node_id, jiffies_to_msecs(jiffies - start));

	pgdat_init_report_one_done();
	return 0;
}

/*
 * If this zone has deferred pages, try to grow it by initializing enough
 * deferred pages to satisfy the allocation specified by order, rounded up to
 * the nearest PAGES_PER_SECTION boundary.  So we're adding memory in increments
 * of SECTION_SIZE bytes by initializing struct pages in increments of
 * PAGES_PER_SECTION * sizeof(struct page) bytes.
 *
 * Return true when zone was grown, otherwise return false. We return true even
 * when we grow less than requested, to let the caller decide if there are
 * enough pages to satisfy the allocation.
 *
 * Note: We use noinline because this function is needed only during boot, and
 * it is called from a __ref function _deferred_grow_zone. This way we are
 * making sure that it is not inlined into permanent text section.
 */
bool __init deferred_grow_zone(struct zone *zone, unsigned int order)
{
	unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION);
	pg_data_t *pgdat = zone->zone_pgdat;
	unsigned long first_deferred_pfn = pgdat->first_deferred_pfn;
	unsigned long spfn, epfn, flags;
	unsigned long nr_pages = 0;
	u64 i;

	/* Only the last zone may have deferred pages */
	if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat))
		return false;

	pgdat_resize_lock(pgdat, &flags);

	/*
	 * If someone grew this zone while we were waiting for spinlock, return
	 * true, as there might be enough pages already.
	 */
	if (first_deferred_pfn != pgdat->first_deferred_pfn) {
		pgdat_resize_unlock(pgdat, &flags);
		return true;
	}

	/* If the zone is empty somebody else may have cleared out the zone */
	if (!deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
						 first_deferred_pfn)) {
		pgdat->first_deferred_pfn = ULONG_MAX;
		pgdat_resize_unlock(pgdat, &flags);
		/* Retry only once. */
		return first_deferred_pfn != ULONG_MAX;
	}

	/*
	 * Initialize and free pages in MAX_ORDER sized increments so
	 * that we can avoid introducing any issues with the buddy
	 * allocator.
	 */
	while (spfn < epfn) {
		/* update our first deferred PFN for this section */
		first_deferred_pfn = spfn;

		nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
		touch_nmi_watchdog();

		/* We should only stop along section boundaries */
		if ((first_deferred_pfn ^ spfn) < PAGES_PER_SECTION)
			continue;

		/* If our quota has been met we can stop here */
		if (nr_pages >= nr_pages_needed)
			break;
	}

	pgdat->first_deferred_pfn = spfn;
	pgdat_resize_unlock(pgdat, &flags);

	return nr_pages > 0;
}

#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */

#ifdef CONFIG_CMA
void __init init_cma_reserved_pageblock(struct page *page)
{
	unsigned i = pageblock_nr_pages;
	struct page *p = page;

	do {
		__ClearPageReserved(p);
		set_page_count(p, 0);
	} while (++p, --i);

	set_pageblock_migratetype(page, MIGRATE_CMA);
	set_page_refcounted(page);
	__free_pages(page, pageblock_order);

	adjust_managed_page_count(page, pageblock_nr_pages);
	page_zone(page)->cma_pages += pageblock_nr_pages;
}
#endif

void __init page_alloc_init_late(void)
{
	struct zone *zone;
	int nid;

#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT

	/* There will be num_node_state(N_MEMORY) threads */
	atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
	for_each_node_state(nid, N_MEMORY) {
		kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
	}

	/* Block until all are initialised */
	wait_for_completion(&pgdat_init_all_done_comp);

	/*
	 * We initialized the rest of the deferred pages.  Permanently disable
	 * on-demand struct page initialization.
	 */
	static_branch_disable(&deferred_pages);

	/* Reinit limits that are based on free pages after the kernel is up */
	files_maxfiles_init();
#endif

	buffer_init();

	/* Discard memblock private memory */
	memblock_discard();

	for_each_node_state(nid, N_MEMORY)
		shuffle_free_memory(NODE_DATA(nid));

	for_each_populated_zone(zone)
		set_zone_contiguous(zone);

	/* Initialize page ext after all struct pages are initialized. */
	if (deferred_struct_pages)
		page_ext_init();
}

#ifndef __HAVE_ARCH_RESERVED_KERNEL_PAGES
/*
 * Returns the number of pages that arch has reserved but
 * is not known to alloc_large_system_hash().
 */
static unsigned long __init arch_reserved_kernel_pages(void)
{
	return 0;
}
#endif

/*
 * Adaptive scale is meant to reduce sizes of hash tables on large memory
 * machines. As memory size is increased the scale is also increased but at
 * slower pace.  Starting from ADAPT_SCALE_BASE (64G), every time memory
 * quadruples the scale is increased by one, which means the size of hash table
 * only doubles, instead of quadrupling as well.
 * Because 32-bit systems cannot have large physical memory, where this scaling
 * makes sense, it is disabled on such platforms.
 */
#if __BITS_PER_LONG > 32
#define ADAPT_SCALE_BASE	(64ul << 30)
#define ADAPT_SCALE_SHIFT	2
#define ADAPT_SCALE_NPAGES	(ADAPT_SCALE_BASE >> PAGE_SHIFT)
#endif

/*
 * allocate a large system hash table from bootmem
 * - it is assumed that the hash table must contain an exact power-of-2
 *   quantity of entries
 * - limit is the number of hash buckets, not the total allocation size
 */
void *__init alloc_large_system_hash(const char *tablename,
				     unsigned long bucketsize,
				     unsigned long numentries,
				     int scale,
				     int flags,
				     unsigned int *_hash_shift,
				     unsigned int *_hash_mask,
				     unsigned long low_limit,
				     unsigned long high_limit)
{
	unsigned long long max = high_limit;
	unsigned long log2qty, size;
	void *table;
	gfp_t gfp_flags;
	bool virt;
	bool huge;

	/* allow the kernel cmdline to have a say */
	if (!numentries) {
		/* round applicable memory size up to nearest megabyte */
		numentries = nr_kernel_pages;
		numentries -= arch_reserved_kernel_pages();

		/* It isn't necessary when PAGE_SIZE >= 1MB */
		if (PAGE_SIZE < SZ_1M)
			numentries = round_up(numentries, SZ_1M / PAGE_SIZE);

#if __BITS_PER_LONG > 32
		if (!high_limit) {
			unsigned long adapt;

			for (adapt = ADAPT_SCALE_NPAGES; adapt < numentries;
			     adapt <<= ADAPT_SCALE_SHIFT)
				scale++;
		}
#endif

		/* limit to 1 bucket per 2^scale bytes of low memory */
		if (scale > PAGE_SHIFT)
			numentries >>= (scale - PAGE_SHIFT);
		else
			numentries <<= (PAGE_SHIFT - scale);

		/* Make sure we've got at least a 0-order allocation.. */
		if (unlikely(flags & HASH_SMALL)) {
			/* Makes no sense without HASH_EARLY */
			WARN_ON(!(flags & HASH_EARLY));
			if (!(numentries >> *_hash_shift)) {
				numentries = 1UL << *_hash_shift;
				BUG_ON(!numentries);
			}
		} else if (unlikely((numentries * bucketsize) < PAGE_SIZE))
			numentries = PAGE_SIZE / bucketsize;
	}
	numentries = roundup_pow_of_two(numentries);

	/* limit allocation size to 1/16 total memory by default */
	if (max == 0) {
		max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4;
		do_div(max, bucketsize);
	}
	max = min(max, 0x80000000ULL);

	if (numentries < low_limit)
		numentries = low_limit;
	if (numentries > max)
		numentries = max;

	log2qty = ilog2(numentries);

	gfp_flags = (flags & HASH_ZERO) ? GFP_ATOMIC | __GFP_ZERO : GFP_ATOMIC;
	do {
		virt = false;
		size = bucketsize << log2qty;
		if (flags & HASH_EARLY) {
			if (flags & HASH_ZERO)
				table = memblock_alloc(size, SMP_CACHE_BYTES);
			else
				table = memblock_alloc_raw(size,
							   SMP_CACHE_BYTES);
		} else if (get_order(size) > MAX_ORDER || hashdist) {
			table = vmalloc_huge(size, gfp_flags);
			virt = true;
			if (table)
				huge = is_vm_area_hugepages(table);
		} else {
			/*
			 * If bucketsize is not a power-of-two, we may free
			 * some pages at the end of hash table which
			 * alloc_pages_exact() automatically does
			 */
			table = alloc_pages_exact(size, gfp_flags);
			kmemleak_alloc(table, size, 1, gfp_flags);
		}
	} while (!table && size > PAGE_SIZE && --log2qty);

	if (!table)
		panic("Failed to allocate %s hash table\n", tablename);

	pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n",
		tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size,
		virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear");

	if (_hash_shift)
		*_hash_shift = log2qty;
	if (_hash_mask)
		*_hash_mask = (1 << log2qty) - 1;

	return table;
}

/**
 * set_dma_reserve - set the specified number of pages reserved in the first zone
 * @new_dma_reserve: The number of pages to mark reserved
 *
 * The per-cpu batchsize and zone watermarks are determined by managed_pages.
 * In the DMA zone, a significant percentage may be consumed by kernel image
 * and other unfreeable allocations which can skew the watermarks badly. This
 * function may optionally be used to account for unfreeable pages in the
 * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and
 * smaller per-cpu batchsize.
 */
void __init set_dma_reserve(unsigned long new_dma_reserve)
{
	dma_reserve = new_dma_reserve;
}

void __init memblock_free_pages(struct page *page, unsigned long pfn,
							unsigned int order)
{
	if (!early_page_initialised(pfn))
		return;
	if (!kmsan_memblock_free_pages(page, order)) {
		/* KMSAN will take care of these pages. */
		return;
	}
	__free_pages_core(page, order);
}

static bool _init_on_alloc_enabled_early __read_mostly
				= IS_ENABLED(CONFIG_INIT_ON_ALLOC_DEFAULT_ON);
static int __init early_init_on_alloc(char *buf)
{

	return kstrtobool(buf, &_init_on_alloc_enabled_early);
}
early_param("init_on_alloc", early_init_on_alloc);

static bool _init_on_free_enabled_early __read_mostly
				= IS_ENABLED(CONFIG_INIT_ON_FREE_DEFAULT_ON);
static int __init early_init_on_free(char *buf)
{
	return kstrtobool(buf, &_init_on_free_enabled_early);
}
early_param("init_on_free", early_init_on_free);

DEFINE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled);

/*
 * Enable static keys related to various memory debugging and hardening options.
 * Some override others, and depend on early params that are evaluated in the
 * order of appearance. So we need to first gather the full picture of what was
 * enabled, and then make decisions.
 */
static void __init mem_debugging_and_hardening_init(void)
{
	bool page_poisoning_requested = false;
	bool want_check_pages = false;

#ifdef CONFIG_PAGE_POISONING
	/*
	 * Page poisoning is debug page alloc for some arches. If
	 * either of those options are enabled, enable poisoning.
	 */
	if (page_poisoning_enabled() ||
	     (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) &&
	      debug_pagealloc_enabled())) {
		static_branch_enable(&_page_poisoning_enabled);
		page_poisoning_requested = true;
		want_check_pages = true;
	}
#endif

	if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) &&
	    page_poisoning_requested) {
		pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
			"will take precedence over init_on_alloc and init_on_free\n");
		_init_on_alloc_enabled_early = false;
		_init_on_free_enabled_early = false;
	}

	if (_init_on_alloc_enabled_early) {
		want_check_pages = true;
		static_branch_enable(&init_on_alloc);
	} else {
		static_branch_disable(&init_on_alloc);
	}

	if (_init_on_free_enabled_early) {
		want_check_pages = true;
		static_branch_enable(&init_on_free);
	} else {
		static_branch_disable(&init_on_free);
	}

	if (IS_ENABLED(CONFIG_KMSAN) &&
	    (_init_on_alloc_enabled_early || _init_on_free_enabled_early))
		pr_info("mem auto-init: please make sure init_on_alloc and init_on_free are disabled when running KMSAN\n");

#ifdef CONFIG_DEBUG_PAGEALLOC
	if (debug_pagealloc_enabled()) {
		want_check_pages = true;
		static_branch_enable(&_debug_pagealloc_enabled);

		if (debug_guardpage_minorder())
			static_branch_enable(&_debug_guardpage_enabled);
	}
#endif

	/*
	 * Any page debugging or hardening option also enables sanity checking
	 * of struct pages being allocated or freed. With CONFIG_DEBUG_VM it's
	 * enabled already.
	 */
	if (!IS_ENABLED(CONFIG_DEBUG_VM) && want_check_pages)
		static_branch_enable(&check_pages_enabled);
}

/* Report memory auto-initialization states for this boot. */
static void __init report_meminit(void)
{
	const char *stack;

	if (IS_ENABLED(CONFIG_INIT_STACK_ALL_PATTERN))
		stack = "all(pattern)";
	else if (IS_ENABLED(CONFIG_INIT_STACK_ALL_ZERO))
		stack = "all(zero)";
	else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL))
		stack = "byref_all(zero)";
	else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF))
		stack = "byref(zero)";
	else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_USER))
		stack = "__user(zero)";
	else
		stack = "off";

	pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n",
		stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off",
		want_init_on_free() ? "on" : "off");
	if (want_init_on_free())
		pr_info("mem auto-init: clearing system memory may take some time...\n");
}

static void __init mem_init_print_info(void)
{
	unsigned long physpages, codesize, datasize, rosize, bss_size;
	unsigned long init_code_size, init_data_size;

	physpages = get_num_physpages();
	codesize = _etext - _stext;
	datasize = _edata - _sdata;
	rosize = __end_rodata - __start_rodata;
	bss_size = __bss_stop - __bss_start;
	init_data_size = __init_end - __init_begin;
	init_code_size = _einittext - _sinittext;

	/*
	 * Detect special cases and adjust section sizes accordingly:
	 * 1) .init.* may be embedded into .data sections
	 * 2) .init.text.* may be out of [__init_begin, __init_end],
	 *    please refer to arch/tile/kernel/vmlinux.lds.S.
	 * 3) .rodata.* may be embedded into .text or .data sections.
	 */
#define adj_init_size(start, end, size, pos, adj) \
	do { \
		if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \
			size -= adj; \
	} while (0)

	adj_init_size(__init_begin, __init_end, init_data_size,
		     _sinittext, init_code_size);
	adj_init_size(_stext, _etext, codesize, _sinittext, init_code_size);
	adj_init_size(_sdata, _edata, datasize, __init_begin, init_data_size);
	adj_init_size(_stext, _etext, codesize, __start_rodata, rosize);
	adj_init_size(_sdata, _edata, datasize, __start_rodata, rosize);

#undef	adj_init_size

	pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved"
#ifdef	CONFIG_HIGHMEM
		", %luK highmem"
#endif
		")\n",
		K(nr_free_pages()), K(physpages),
		codesize / SZ_1K, datasize / SZ_1K, rosize / SZ_1K,
		(init_data_size + init_code_size) / SZ_1K, bss_size / SZ_1K,
		K(physpages - totalram_pages() - totalcma_pages),
		K(totalcma_pages)
#ifdef	CONFIG_HIGHMEM
		, K(totalhigh_pages())
#endif
		);
}

/*
 * Set up kernel memory allocators
 */
void __init mm_core_init(void)
{
	/* Initializations relying on SMP setup */
	build_all_zonelists(NULL);
	page_alloc_init_cpuhp();

	/*
	 * page_ext requires contiguous pages,
	 * bigger than MAX_ORDER unless SPARSEMEM.
	 */
	page_ext_init_flatmem();
	mem_debugging_and_hardening_init();
	kfence_alloc_pool();
	report_meminit();
	kmsan_init_shadow();
	stack_depot_early_init();
	mem_init();
	mem_init_print_info();
	kmem_cache_init();
	/*
	 * page_owner must be initialized after buddy is ready, and also after
	 * slab is ready so that stack_depot_init() works properly
	 */
	page_ext_init_flatmem_late();
	kmemleak_init();
	ptlock_cache_init();
	pgtable_cache_init();
	debug_objects_mem_init();
	vmalloc_init();
	/* If no deferred init page_ext now, as vmap is fully initialized */
	if (!deferred_struct_pages)
		page_ext_init();
	/* Should be run before the first non-init thread is created */
	init_espfix_bsp();
	/* Should be run after espfix64 is set up. */
	pti_init();
	kmsan_init_runtime();
	mm_cache_init();
}