summaryrefslogtreecommitdiffstats
path: root/mm/memory_hotplug.c
blob: 39528831e788c67ee18ff22f22f9c3b1472e9bb7 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  linux/mm/memory_hotplug.c
 *
 *  Copyright (C)
 */

#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/writeback.h>
#include <linux/slab.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/memory.h>
#include <linux/memremap.h>
#include <linux/memory_hotplug.h>
#include <linux/vmalloc.h>
#include <linux/ioport.h>
#include <linux/delay.h>
#include <linux/migrate.h>
#include <linux/page-isolation.h>
#include <linux/pfn.h>
#include <linux/suspend.h>
#include <linux/mm_inline.h>
#include <linux/firmware-map.h>
#include <linux/stop_machine.h>
#include <linux/hugetlb.h>
#include <linux/memblock.h>
#include <linux/compaction.h>
#include <linux/rmap.h>
#include <linux/module.h>

#include <asm/tlbflush.h>

#include "internal.h"
#include "shuffle.h"

enum {
	MEMMAP_ON_MEMORY_DISABLE = 0,
	MEMMAP_ON_MEMORY_ENABLE,
	MEMMAP_ON_MEMORY_FORCE,
};

static int memmap_mode __read_mostly = MEMMAP_ON_MEMORY_DISABLE;

static inline unsigned long memory_block_memmap_size(void)
{
	return PHYS_PFN(memory_block_size_bytes()) * sizeof(struct page);
}

static inline unsigned long memory_block_memmap_on_memory_pages(void)
{
	unsigned long nr_pages = PFN_UP(memory_block_memmap_size());

	/*
	 * In "forced" memmap_on_memory mode, we add extra pages to align the
	 * vmemmap size to cover full pageblocks. That way, we can add memory
	 * even if the vmemmap size is not properly aligned, however, we might waste
	 * memory.
	 */
	if (memmap_mode == MEMMAP_ON_MEMORY_FORCE)
		return pageblock_align(nr_pages);
	return nr_pages;
}

#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
/*
 * memory_hotplug.memmap_on_memory parameter
 */
static int set_memmap_mode(const char *val, const struct kernel_param *kp)
{
	int ret, mode;
	bool enabled;

	if (sysfs_streq(val, "force") ||  sysfs_streq(val, "FORCE")) {
		mode = MEMMAP_ON_MEMORY_FORCE;
	} else {
		ret = kstrtobool(val, &enabled);
		if (ret < 0)
			return ret;
		if (enabled)
			mode = MEMMAP_ON_MEMORY_ENABLE;
		else
			mode = MEMMAP_ON_MEMORY_DISABLE;
	}
	*((int *)kp->arg) = mode;
	if (mode == MEMMAP_ON_MEMORY_FORCE) {
		unsigned long memmap_pages = memory_block_memmap_on_memory_pages();

		pr_info_once("Memory hotplug will waste %ld pages in each memory block\n",
			     memmap_pages - PFN_UP(memory_block_memmap_size()));
	}
	return 0;
}

static int get_memmap_mode(char *buffer, const struct kernel_param *kp)
{
	if (*((int *)kp->arg) == MEMMAP_ON_MEMORY_FORCE)
		return sprintf(buffer,  "force\n");
	return param_get_bool(buffer, kp);
}

static const struct kernel_param_ops memmap_mode_ops = {
	.set = set_memmap_mode,
	.get = get_memmap_mode,
};
module_param_cb(memmap_on_memory, &memmap_mode_ops, &memmap_mode, 0444);
MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug\n"
		 "With value \"force\" it could result in memory wastage due "
		 "to memmap size limitations (Y/N/force)");

static inline bool mhp_memmap_on_memory(void)
{
	return memmap_mode != MEMMAP_ON_MEMORY_DISABLE;
}
#else
static inline bool mhp_memmap_on_memory(void)
{
	return false;
}
#endif

enum {
	ONLINE_POLICY_CONTIG_ZONES = 0,
	ONLINE_POLICY_AUTO_MOVABLE,
};

static const char * const online_policy_to_str[] = {
	[ONLINE_POLICY_CONTIG_ZONES] = "contig-zones",
	[ONLINE_POLICY_AUTO_MOVABLE] = "auto-movable",
};

static int set_online_policy(const char *val, const struct kernel_param *kp)
{
	int ret = sysfs_match_string(online_policy_to_str, val);

	if (ret < 0)
		return ret;
	*((int *)kp->arg) = ret;
	return 0;
}

static int get_online_policy(char *buffer, const struct kernel_param *kp)
{
	return sprintf(buffer, "%s\n", online_policy_to_str[*((int *)kp->arg)]);
}

/*
 * memory_hotplug.online_policy: configure online behavior when onlining without
 * specifying a zone (MMOP_ONLINE)
 *
 * "contig-zones": keep zone contiguous
 * "auto-movable": online memory to ZONE_MOVABLE if the configuration
 *                 (auto_movable_ratio, auto_movable_numa_aware) allows for it
 */
static int online_policy __read_mostly = ONLINE_POLICY_CONTIG_ZONES;
static const struct kernel_param_ops online_policy_ops = {
	.set = set_online_policy,
	.get = get_online_policy,
};
module_param_cb(online_policy, &online_policy_ops, &online_policy, 0644);
MODULE_PARM_DESC(online_policy,
		"Set the online policy (\"contig-zones\", \"auto-movable\") "
		"Default: \"contig-zones\"");

/*
 * memory_hotplug.auto_movable_ratio: specify maximum MOVABLE:KERNEL ratio
 *
 * The ratio represent an upper limit and the kernel might decide to not
 * online some memory to ZONE_MOVABLE -- e.g., because hotplugged KERNEL memory
 * doesn't allow for more MOVABLE memory.
 */
static unsigned int auto_movable_ratio __read_mostly = 301;
module_param(auto_movable_ratio, uint, 0644);
MODULE_PARM_DESC(auto_movable_ratio,
		"Set the maximum ratio of MOVABLE:KERNEL memory in the system "
		"in percent for \"auto-movable\" online policy. Default: 301");

/*
 * memory_hotplug.auto_movable_numa_aware: consider numa node stats
 */
#ifdef CONFIG_NUMA
static bool auto_movable_numa_aware __read_mostly = true;
module_param(auto_movable_numa_aware, bool, 0644);
MODULE_PARM_DESC(auto_movable_numa_aware,
		"Consider numa node stats in addition to global stats in "
		"\"auto-movable\" online policy. Default: true");
#endif /* CONFIG_NUMA */

/*
 * online_page_callback contains pointer to current page onlining function.
 * Initially it is generic_online_page(). If it is required it could be
 * changed by calling set_online_page_callback() for callback registration
 * and restore_online_page_callback() for generic callback restore.
 */

static online_page_callback_t online_page_callback = generic_online_page;
static DEFINE_MUTEX(online_page_callback_lock);

DEFINE_STATIC_PERCPU_RWSEM(mem_hotplug_lock);

void get_online_mems(void)
{
	percpu_down_read(&mem_hotplug_lock);
}

void put_online_mems(void)
{
	percpu_up_read(&mem_hotplug_lock);
}

bool movable_node_enabled = false;

#ifndef CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE
int mhp_default_online_type = MMOP_OFFLINE;
#else
int mhp_default_online_type = MMOP_ONLINE;
#endif

static int __init setup_memhp_default_state(char *str)
{
	const int online_type = mhp_online_type_from_str(str);

	if (online_type >= 0)
		mhp_default_online_type = online_type;

	return 1;
}
__setup("memhp_default_state=", setup_memhp_default_state);

void mem_hotplug_begin(void)
{
	cpus_read_lock();
	percpu_down_write(&mem_hotplug_lock);
}

void mem_hotplug_done(void)
{
	percpu_up_write(&mem_hotplug_lock);
	cpus_read_unlock();
}

u64 max_mem_size = U64_MAX;

/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size,
						 const char *resource_name)
{
	struct resource *res;
	unsigned long flags =  IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;

	if (strcmp(resource_name, "System RAM"))
		flags |= IORESOURCE_SYSRAM_DRIVER_MANAGED;

	if (!mhp_range_allowed(start, size, true))
		return ERR_PTR(-E2BIG);

	/*
	 * Make sure value parsed from 'mem=' only restricts memory adding
	 * while booting, so that memory hotplug won't be impacted. Please
	 * refer to document of 'mem=' in kernel-parameters.txt for more
	 * details.
	 */
	if (start + size > max_mem_size && system_state < SYSTEM_RUNNING)
		return ERR_PTR(-E2BIG);

	/*
	 * Request ownership of the new memory range.  This might be
	 * a child of an existing resource that was present but
	 * not marked as busy.
	 */
	res = __request_region(&iomem_resource, start, size,
			       resource_name, flags);

	if (!res) {
		pr_debug("Unable to reserve System RAM region: %016llx->%016llx\n",
				start, start + size);
		return ERR_PTR(-EEXIST);
	}
	return res;
}

static void release_memory_resource(struct resource *res)
{
	if (!res)
		return;
	release_resource(res);
	kfree(res);
}

static int check_pfn_span(unsigned long pfn, unsigned long nr_pages)
{
	/*
	 * Disallow all operations smaller than a sub-section and only
	 * allow operations smaller than a section for
	 * SPARSEMEM_VMEMMAP. Note that check_hotplug_memory_range()
	 * enforces a larger memory_block_size_bytes() granularity for
	 * memory that will be marked online, so this check should only
	 * fire for direct arch_{add,remove}_memory() users outside of
	 * add_memory_resource().
	 */
	unsigned long min_align;

	if (IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP))
		min_align = PAGES_PER_SUBSECTION;
	else
		min_align = PAGES_PER_SECTION;
	if (!IS_ALIGNED(pfn | nr_pages, min_align))
		return -EINVAL;
	return 0;
}

/*
 * Return page for the valid pfn only if the page is online. All pfn
 * walkers which rely on the fully initialized page->flags and others
 * should use this rather than pfn_valid && pfn_to_page
 */
struct page *pfn_to_online_page(unsigned long pfn)
{
	unsigned long nr = pfn_to_section_nr(pfn);
	struct dev_pagemap *pgmap;
	struct mem_section *ms;

	if (nr >= NR_MEM_SECTIONS)
		return NULL;

	ms = __nr_to_section(nr);
	if (!online_section(ms))
		return NULL;

	/*
	 * Save some code text when online_section() +
	 * pfn_section_valid() are sufficient.
	 */
	if (IS_ENABLED(CONFIG_HAVE_ARCH_PFN_VALID) && !pfn_valid(pfn))
		return NULL;

	if (!pfn_section_valid(ms, pfn))
		return NULL;

	if (!online_device_section(ms))
		return pfn_to_page(pfn);

	/*
	 * Slowpath: when ZONE_DEVICE collides with
	 * ZONE_{NORMAL,MOVABLE} within the same section some pfns in
	 * the section may be 'offline' but 'valid'. Only
	 * get_dev_pagemap() can determine sub-section online status.
	 */
	pgmap = get_dev_pagemap(pfn, NULL);
	put_dev_pagemap(pgmap);

	/* The presence of a pgmap indicates ZONE_DEVICE offline pfn */
	if (pgmap)
		return NULL;

	return pfn_to_page(pfn);
}
EXPORT_SYMBOL_GPL(pfn_to_online_page);

int __ref __add_pages(int nid, unsigned long pfn, unsigned long nr_pages,
		struct mhp_params *params)
{
	const unsigned long end_pfn = pfn + nr_pages;
	unsigned long cur_nr_pages;
	int err;
	struct vmem_altmap *altmap = params->altmap;

	if (WARN_ON_ONCE(!pgprot_val(params->pgprot)))
		return -EINVAL;

	VM_BUG_ON(!mhp_range_allowed(PFN_PHYS(pfn), nr_pages * PAGE_SIZE, false));

	if (altmap) {
		/*
		 * Validate altmap is within bounds of the total request
		 */
		if (altmap->base_pfn != pfn
				|| vmem_altmap_offset(altmap) > nr_pages) {
			pr_warn_once("memory add fail, invalid altmap\n");
			return -EINVAL;
		}
		altmap->alloc = 0;
	}

	if (check_pfn_span(pfn, nr_pages)) {
		WARN(1, "Misaligned %s start: %#lx end: %#lx\n", __func__, pfn, pfn + nr_pages - 1);
		return -EINVAL;
	}

	for (; pfn < end_pfn; pfn += cur_nr_pages) {
		/* Select all remaining pages up to the next section boundary */
		cur_nr_pages = min(end_pfn - pfn,
				   SECTION_ALIGN_UP(pfn + 1) - pfn);
		err = sparse_add_section(nid, pfn, cur_nr_pages, altmap,
					 params->pgmap);
		if (err)
			break;
		cond_resched();
	}
	vmemmap_populate_print_last();
	return err;
}

/* find the smallest valid pfn in the range [start_pfn, end_pfn) */
static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
				     unsigned long start_pfn,
				     unsigned long end_pfn)
{
	for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) {
		if (unlikely(!pfn_to_online_page(start_pfn)))
			continue;

		if (unlikely(pfn_to_nid(start_pfn) != nid))
			continue;

		if (zone != page_zone(pfn_to_page(start_pfn)))
			continue;

		return start_pfn;
	}

	return 0;
}

/* find the biggest valid pfn in the range [start_pfn, end_pfn). */
static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
				    unsigned long start_pfn,
				    unsigned long end_pfn)
{
	unsigned long pfn;

	/* pfn is the end pfn of a memory section. */
	pfn = end_pfn - 1;
	for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) {
		if (unlikely(!pfn_to_online_page(pfn)))
			continue;

		if (unlikely(pfn_to_nid(pfn) != nid))
			continue;

		if (zone != page_zone(pfn_to_page(pfn)))
			continue;

		return pfn;
	}

	return 0;
}

static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
			     unsigned long end_pfn)
{
	unsigned long pfn;
	int nid = zone_to_nid(zone);

	if (zone->zone_start_pfn == start_pfn) {
		/*
		 * If the section is smallest section in the zone, it need
		 * shrink zone->zone_start_pfn and zone->zone_spanned_pages.
		 * In this case, we find second smallest valid mem_section
		 * for shrinking zone.
		 */
		pfn = find_smallest_section_pfn(nid, zone, end_pfn,
						zone_end_pfn(zone));
		if (pfn) {
			zone->spanned_pages = zone_end_pfn(zone) - pfn;
			zone->zone_start_pfn = pfn;
		} else {
			zone->zone_start_pfn = 0;
			zone->spanned_pages = 0;
		}
	} else if (zone_end_pfn(zone) == end_pfn) {
		/*
		 * If the section is biggest section in the zone, it need
		 * shrink zone->spanned_pages.
		 * In this case, we find second biggest valid mem_section for
		 * shrinking zone.
		 */
		pfn = find_biggest_section_pfn(nid, zone, zone->zone_start_pfn,
					       start_pfn);
		if (pfn)
			zone->spanned_pages = pfn - zone->zone_start_pfn + 1;
		else {
			zone->zone_start_pfn = 0;
			zone->spanned_pages = 0;
		}
	}
}

static void update_pgdat_span(struct pglist_data *pgdat)
{
	unsigned long node_start_pfn = 0, node_end_pfn = 0;
	struct zone *zone;

	for (zone = pgdat->node_zones;
	     zone < pgdat->node_zones + MAX_NR_ZONES; zone++) {
		unsigned long end_pfn = zone_end_pfn(zone);

		/* No need to lock the zones, they can't change. */
		if (!zone->spanned_pages)
			continue;
		if (!node_end_pfn) {
			node_start_pfn = zone->zone_start_pfn;
			node_end_pfn = end_pfn;
			continue;
		}

		if (end_pfn > node_end_pfn)
			node_end_pfn = end_pfn;
		if (zone->zone_start_pfn < node_start_pfn)
			node_start_pfn = zone->zone_start_pfn;
	}

	pgdat->node_start_pfn = node_start_pfn;
	pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
}

void __ref remove_pfn_range_from_zone(struct zone *zone,
				      unsigned long start_pfn,
				      unsigned long nr_pages)
{
	const unsigned long end_pfn = start_pfn + nr_pages;
	struct pglist_data *pgdat = zone->zone_pgdat;
	unsigned long pfn, cur_nr_pages;

	/* Poison struct pages because they are now uninitialized again. */
	for (pfn = start_pfn; pfn < end_pfn; pfn += cur_nr_pages) {
		cond_resched();

		/* Select all remaining pages up to the next section boundary */
		cur_nr_pages =
			min(end_pfn - pfn, SECTION_ALIGN_UP(pfn + 1) - pfn);
		page_init_poison(pfn_to_page(pfn),
				 sizeof(struct page) * cur_nr_pages);
	}

	/*
	 * Zone shrinking code cannot properly deal with ZONE_DEVICE. So
	 * we will not try to shrink the zones - which is okay as
	 * set_zone_contiguous() cannot deal with ZONE_DEVICE either way.
	 */
	if (zone_is_zone_device(zone))
		return;

	clear_zone_contiguous(zone);

	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
	update_pgdat_span(pgdat);

	set_zone_contiguous(zone);
}

/**
 * __remove_pages() - remove sections of pages
 * @pfn: starting pageframe (must be aligned to start of a section)
 * @nr_pages: number of pages to remove (must be multiple of section size)
 * @altmap: alternative device page map or %NULL if default memmap is used
 *
 * Generic helper function to remove section mappings and sysfs entries
 * for the section of the memory we are removing. Caller needs to make
 * sure that pages are marked reserved and zones are adjust properly by
 * calling offline_pages().
 */
void __remove_pages(unsigned long pfn, unsigned long nr_pages,
		    struct vmem_altmap *altmap)
{
	const unsigned long end_pfn = pfn + nr_pages;
	unsigned long cur_nr_pages;

	if (check_pfn_span(pfn, nr_pages)) {
		WARN(1, "Misaligned %s start: %#lx end: %#lx\n", __func__, pfn, pfn + nr_pages - 1);
		return;
	}

	for (; pfn < end_pfn; pfn += cur_nr_pages) {
		cond_resched();
		/* Select all remaining pages up to the next section boundary */
		cur_nr_pages = min(end_pfn - pfn,
				   SECTION_ALIGN_UP(pfn + 1) - pfn);
		sparse_remove_section(pfn, cur_nr_pages, altmap);
	}
}

int set_online_page_callback(online_page_callback_t callback)
{
	int rc = -EINVAL;

	get_online_mems();
	mutex_lock(&online_page_callback_lock);

	if (online_page_callback == generic_online_page) {
		online_page_callback = callback;
		rc = 0;
	}

	mutex_unlock(&online_page_callback_lock);
	put_online_mems();

	return rc;
}
EXPORT_SYMBOL_GPL(set_online_page_callback);

int restore_online_page_callback(online_page_callback_t callback)
{
	int rc = -EINVAL;

	get_online_mems();
	mutex_lock(&online_page_callback_lock);

	if (online_page_callback == callback) {
		online_page_callback = generic_online_page;
		rc = 0;
	}

	mutex_unlock(&online_page_callback_lock);
	put_online_mems();

	return rc;
}
EXPORT_SYMBOL_GPL(restore_online_page_callback);

void generic_online_page(struct page *page, unsigned int order)
{
	/*
	 * Freeing the page with debug_pagealloc enabled will try to unmap it,
	 * so we should map it first. This is better than introducing a special
	 * case in page freeing fast path.
	 */
	debug_pagealloc_map_pages(page, 1 << order);
	__free_pages_core(page, order);
	totalram_pages_add(1UL << order);
}
EXPORT_SYMBOL_GPL(generic_online_page);

static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages)
{
	const unsigned long end_pfn = start_pfn + nr_pages;
	unsigned long pfn;

	/*
	 * Online the pages in MAX_ORDER aligned chunks. The callback might
	 * decide to not expose all pages to the buddy (e.g., expose them
	 * later). We account all pages as being online and belonging to this
	 * zone ("present").
	 * When using memmap_on_memory, the range might not be aligned to
	 * MAX_ORDER_NR_PAGES - 1, but pageblock aligned. __ffs() will detect
	 * this and the first chunk to online will be pageblock_nr_pages.
	 */
	for (pfn = start_pfn; pfn < end_pfn;) {
		int order;

		/*
		 * Free to online pages in the largest chunks alignment allows.
		 *
		 * __ffs() behaviour is undefined for 0. start == 0 is
		 * MAX_ORDER-aligned, Set order to MAX_ORDER for the case.
		 */
		if (pfn)
			order = min_t(int, MAX_ORDER, __ffs(pfn));
		else
			order = MAX_ORDER;

		(*online_page_callback)(pfn_to_page(pfn), order);
		pfn += (1UL << order);
	}

	/* mark all involved sections as online */
	online_mem_sections(start_pfn, end_pfn);
}

/* check which state of node_states will be changed when online memory */
static void node_states_check_changes_online(unsigned long nr_pages,
	struct zone *zone, struct memory_notify *arg)
{
	int nid = zone_to_nid(zone);

	arg->status_change_nid = NUMA_NO_NODE;
	arg->status_change_nid_normal = NUMA_NO_NODE;

	if (!node_state(nid, N_MEMORY))
		arg->status_change_nid = nid;
	if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY))
		arg->status_change_nid_normal = nid;
}

static void node_states_set_node(int node, struct memory_notify *arg)
{
	if (arg->status_change_nid_normal >= 0)
		node_set_state(node, N_NORMAL_MEMORY);

	if (arg->status_change_nid >= 0)
		node_set_state(node, N_MEMORY);
}

static void __meminit resize_zone_range(struct zone *zone, unsigned long start_pfn,
		unsigned long nr_pages)
{
	unsigned long old_end_pfn = zone_end_pfn(zone);

	if (zone_is_empty(zone) || start_pfn < zone->zone_start_pfn)
		zone->zone_start_pfn = start_pfn;

	zone->spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - zone->zone_start_pfn;
}

static void __meminit resize_pgdat_range(struct pglist_data *pgdat, unsigned long start_pfn,
                                     unsigned long nr_pages)
{
	unsigned long old_end_pfn = pgdat_end_pfn(pgdat);

	if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn)
		pgdat->node_start_pfn = start_pfn;

	pgdat->node_spanned_pages = max(start_pfn + nr_pages, old_end_pfn) - pgdat->node_start_pfn;

}

#ifdef CONFIG_ZONE_DEVICE
static void section_taint_zone_device(unsigned long pfn)
{
	struct mem_section *ms = __pfn_to_section(pfn);

	ms->section_mem_map |= SECTION_TAINT_ZONE_DEVICE;
}
#else
static inline void section_taint_zone_device(unsigned long pfn)
{
}
#endif

/*
 * Associate the pfn range with the given zone, initializing the memmaps
 * and resizing the pgdat/zone data to span the added pages. After this
 * call, all affected pages are PG_reserved.
 *
 * 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 __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
				  unsigned long nr_pages,
				  struct vmem_altmap *altmap, int migratetype)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	int nid = pgdat->node_id;

	clear_zone_contiguous(zone);

	if (zone_is_empty(zone))
		init_currently_empty_zone(zone, start_pfn, nr_pages);
	resize_zone_range(zone, start_pfn, nr_pages);
	resize_pgdat_range(pgdat, start_pfn, nr_pages);

	/*
	 * Subsection population requires care in pfn_to_online_page().
	 * Set the taint to enable the slow path detection of
	 * ZONE_DEVICE pages in an otherwise  ZONE_{NORMAL,MOVABLE}
	 * section.
	 */
	if (zone_is_zone_device(zone)) {
		if (!IS_ALIGNED(start_pfn, PAGES_PER_SECTION))
			section_taint_zone_device(start_pfn);
		if (!IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION))
			section_taint_zone_device(start_pfn + nr_pages);
	}

	/*
	 * TODO now we have a visible range of pages which are not associated
	 * with their zone properly. Not nice but set_pfnblock_flags_mask
	 * expects the zone spans the pfn range. All the pages in the range
	 * are reserved so nobody should be touching them so we should be safe
	 */
	memmap_init_range(nr_pages, nid, zone_idx(zone), start_pfn, 0,
			 MEMINIT_HOTPLUG, altmap, migratetype);

	set_zone_contiguous(zone);
}

struct auto_movable_stats {
	unsigned long kernel_early_pages;
	unsigned long movable_pages;
};

static void auto_movable_stats_account_zone(struct auto_movable_stats *stats,
					    struct zone *zone)
{
	if (zone_idx(zone) == ZONE_MOVABLE) {
		stats->movable_pages += zone->present_pages;
	} else {
		stats->kernel_early_pages += zone->present_early_pages;
#ifdef CONFIG_CMA
		/*
		 * CMA pages (never on hotplugged memory) behave like
		 * ZONE_MOVABLE.
		 */
		stats->movable_pages += zone->cma_pages;
		stats->kernel_early_pages -= zone->cma_pages;
#endif /* CONFIG_CMA */
	}
}
struct auto_movable_group_stats {
	unsigned long movable_pages;
	unsigned long req_kernel_early_pages;
};

static int auto_movable_stats_account_group(struct memory_group *group,
					   void *arg)
{
	const int ratio = READ_ONCE(auto_movable_ratio);
	struct auto_movable_group_stats *stats = arg;
	long pages;

	/*
	 * We don't support modifying the config while the auto-movable online
	 * policy is already enabled. Just avoid the division by zero below.
	 */
	if (!ratio)
		return 0;

	/*
	 * Calculate how many early kernel pages this group requires to
	 * satisfy the configured zone ratio.
	 */
	pages = group->present_movable_pages * 100 / ratio;
	pages -= group->present_kernel_pages;

	if (pages > 0)
		stats->req_kernel_early_pages += pages;
	stats->movable_pages += group->present_movable_pages;
	return 0;
}

static bool auto_movable_can_online_movable(int nid, struct memory_group *group,
					    unsigned long nr_pages)
{
	unsigned long kernel_early_pages, movable_pages;
	struct auto_movable_group_stats group_stats = {};
	struct auto_movable_stats stats = {};
	pg_data_t *pgdat = NODE_DATA(nid);
	struct zone *zone;
	int i;

	/* Walk all relevant zones and collect MOVABLE vs. KERNEL stats. */
	if (nid == NUMA_NO_NODE) {
		/* TODO: cache values */
		for_each_populated_zone(zone)
			auto_movable_stats_account_zone(&stats, zone);
	} else {
		for (i = 0; i < MAX_NR_ZONES; i++) {
			zone = pgdat->node_zones + i;
			if (populated_zone(zone))
				auto_movable_stats_account_zone(&stats, zone);
		}
	}

	kernel_early_pages = stats.kernel_early_pages;
	movable_pages = stats.movable_pages;

	/*
	 * Kernel memory inside dynamic memory group allows for more MOVABLE
	 * memory within the same group. Remove the effect of all but the
	 * current group from the stats.
	 */
	walk_dynamic_memory_groups(nid, auto_movable_stats_account_group,
				   group, &group_stats);
	if (kernel_early_pages <= group_stats.req_kernel_early_pages)
		return false;
	kernel_early_pages -= group_stats.req_kernel_early_pages;
	movable_pages -= group_stats.movable_pages;

	if (group && group->is_dynamic)
		kernel_early_pages += group->present_kernel_pages;

	/*
	 * Test if we could online the given number of pages to ZONE_MOVABLE
	 * and still stay in the configured ratio.
	 */
	movable_pages += nr_pages;
	return movable_pages <= (auto_movable_ratio * kernel_early_pages) / 100;
}

/*
 * Returns a default kernel memory zone for the given pfn range.
 * If no kernel zone covers this pfn range it will automatically go
 * to the ZONE_NORMAL.
 */
static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn,
		unsigned long nr_pages)
{
	struct pglist_data *pgdat = NODE_DATA(nid);
	int zid;

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

		if (zone_intersects(zone, start_pfn, nr_pages))
			return zone;
	}

	return &pgdat->node_zones[ZONE_NORMAL];
}

/*
 * Determine to which zone to online memory dynamically based on user
 * configuration and system stats. We care about the following ratio:
 *
 *   MOVABLE : KERNEL
 *
 * Whereby MOVABLE is memory in ZONE_MOVABLE and KERNEL is memory in
 * one of the kernel zones. CMA pages inside one of the kernel zones really
 * behaves like ZONE_MOVABLE, so we treat them accordingly.
 *
 * We don't allow for hotplugged memory in a KERNEL zone to increase the
 * amount of MOVABLE memory we can have, so we end up with:
 *
 *   MOVABLE : KERNEL_EARLY
 *
 * Whereby KERNEL_EARLY is memory in one of the kernel zones, available sinze
 * boot. We base our calculation on KERNEL_EARLY internally, because:
 *
 * a) Hotplugged memory in one of the kernel zones can sometimes still get
 *    hotunplugged, especially when hot(un)plugging individual memory blocks.
 *    There is no coordination across memory devices, therefore "automatic"
 *    hotunplugging, as implemented in hypervisors, could result in zone
 *    imbalances.
 * b) Early/boot memory in one of the kernel zones can usually not get
 *    hotunplugged again (e.g., no firmware interface to unplug, fragmented
 *    with unmovable allocations). While there are corner cases where it might
 *    still work, it is barely relevant in practice.
 *
 * Exceptions are dynamic memory groups, which allow for more MOVABLE
 * memory within the same memory group -- because in that case, there is
 * coordination within the single memory device managed by a single driver.
 *
 * We rely on "present pages" instead of "managed pages", as the latter is
 * highly unreliable and dynamic in virtualized environments, and does not
 * consider boot time allocations. For example, memory ballooning adjusts the
 * managed pages when inflating/deflating the balloon, and balloon compaction
 * can even migrate inflated pages between zones.
 *
 * Using "present pages" is better but some things to keep in mind are:
 *
 * a) Some memblock allocations, such as for the crashkernel area, are
 *    effectively unused by the kernel, yet they account to "present pages".
 *    Fortunately, these allocations are comparatively small in relevant setups
 *    (e.g., fraction of system memory).
 * b) Some hotplugged memory blocks in virtualized environments, esecially
 *    hotplugged by virtio-mem, look like they are completely present, however,
 *    only parts of the memory block are actually currently usable.
 *    "present pages" is an upper limit that can get reached at runtime. As
 *    we base our calculations on KERNEL_EARLY, this is not an issue.
 */
static struct zone *auto_movable_zone_for_pfn(int nid,
					      struct memory_group *group,
					      unsigned long pfn,
					      unsigned long nr_pages)
{
	unsigned long online_pages = 0, max_pages, end_pfn;
	struct page *page;

	if (!auto_movable_ratio)
		goto kernel_zone;

	if (group && !group->is_dynamic) {
		max_pages = group->s.max_pages;
		online_pages = group->present_movable_pages;

		/* If anything is !MOVABLE online the rest !MOVABLE. */
		if (group->present_kernel_pages)
			goto kernel_zone;
	} else if (!group || group->d.unit_pages == nr_pages) {
		max_pages = nr_pages;
	} else {
		max_pages = group->d.unit_pages;
		/*
		 * Take a look at all online sections in the current unit.
		 * We can safely assume that all pages within a section belong
		 * to the same zone, because dynamic memory groups only deal
		 * with hotplugged memory.
		 */
		pfn = ALIGN_DOWN(pfn, group->d.unit_pages);
		end_pfn = pfn + group->d.unit_pages;
		for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
			page = pfn_to_online_page(pfn);
			if (!page)
				continue;
			/* If anything is !MOVABLE online the rest !MOVABLE. */
			if (!is_zone_movable_page(page))
				goto kernel_zone;
			online_pages += PAGES_PER_SECTION;
		}
	}

	/*
	 * Online MOVABLE if we could *currently* online all remaining parts
	 * MOVABLE. We expect to (add+) online them immediately next, so if
	 * nobody interferes, all will be MOVABLE if possible.
	 */
	nr_pages = max_pages - online_pages;
	if (!auto_movable_can_online_movable(NUMA_NO_NODE, group, nr_pages))
		goto kernel_zone;

#ifdef CONFIG_NUMA
	if (auto_movable_numa_aware &&
	    !auto_movable_can_online_movable(nid, group, nr_pages))
		goto kernel_zone;
#endif /* CONFIG_NUMA */

	return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];
kernel_zone:
	return default_kernel_zone_for_pfn(nid, pfn, nr_pages);
}

static inline struct zone *default_zone_for_pfn(int nid, unsigned long start_pfn,
		unsigned long nr_pages)
{
	struct zone *kernel_zone = default_kernel_zone_for_pfn(nid, start_pfn,
			nr_pages);
	struct zone *movable_zone = &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];
	bool in_kernel = zone_intersects(kernel_zone, start_pfn, nr_pages);
	bool in_movable = zone_intersects(movable_zone, start_pfn, nr_pages);

	/*
	 * We inherit the existing zone in a simple case where zones do not
	 * overlap in the given range
	 */
	if (in_kernel ^ in_movable)
		return (in_kernel) ? kernel_zone : movable_zone;

	/*
	 * If the range doesn't belong to any zone or two zones overlap in the
	 * given range then we use movable zone only if movable_node is
	 * enabled because we always online to a kernel zone by default.
	 */
	return movable_node_enabled ? movable_zone : kernel_zone;
}

struct zone *zone_for_pfn_range(int online_type, int nid,
		struct memory_group *group, unsigned long start_pfn,
		unsigned long nr_pages)
{
	if (online_type == MMOP_ONLINE_KERNEL)
		return default_kernel_zone_for_pfn(nid, start_pfn, nr_pages);

	if (online_type == MMOP_ONLINE_MOVABLE)
		return &NODE_DATA(nid)->node_zones[ZONE_MOVABLE];

	if (online_policy == ONLINE_POLICY_AUTO_MOVABLE)
		return auto_movable_zone_for_pfn(nid, group, start_pfn, nr_pages);

	return default_zone_for_pfn(nid, start_pfn, nr_pages);
}

/*
 * This function should only be called by memory_block_{online,offline},
 * and {online,offline}_pages.
 */
void adjust_present_page_count(struct page *page, struct memory_group *group,
			       long nr_pages)
{
	struct zone *zone = page_zone(page);
	const bool movable = zone_idx(zone) == ZONE_MOVABLE;

	/*
	 * We only support onlining/offlining/adding/removing of complete
	 * memory blocks; therefore, either all is either early or hotplugged.
	 */
	if (early_section(__pfn_to_section(page_to_pfn(page))))
		zone->present_early_pages += nr_pages;
	zone->present_pages += nr_pages;
	zone->zone_pgdat->node_present_pages += nr_pages;

	if (group && movable)
		group->present_movable_pages += nr_pages;
	else if (group && !movable)
		group->present_kernel_pages += nr_pages;
}

int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
			      struct zone *zone)
{
	unsigned long end_pfn = pfn + nr_pages;
	int ret, i;

	ret = kasan_add_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages));
	if (ret)
		return ret;

	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE);

	for (i = 0; i < nr_pages; i++)
		SetPageVmemmapSelfHosted(pfn_to_page(pfn + i));

	/*
	 * It might be that the vmemmap_pages fully span sections. If that is
	 * the case, mark those sections online here as otherwise they will be
	 * left offline.
	 */
	if (nr_pages >= PAGES_PER_SECTION)
	        online_mem_sections(pfn, ALIGN_DOWN(end_pfn, PAGES_PER_SECTION));

	return ret;
}

void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages)
{
	unsigned long end_pfn = pfn + nr_pages;

	/*
	 * It might be that the vmemmap_pages fully span sections. If that is
	 * the case, mark those sections offline here as otherwise they will be
	 * left online.
	 */
	if (nr_pages >= PAGES_PER_SECTION)
		offline_mem_sections(pfn, ALIGN_DOWN(end_pfn, PAGES_PER_SECTION));

        /*
	 * The pages associated with this vmemmap have been offlined, so
	 * we can reset its state here.
	 */
	remove_pfn_range_from_zone(page_zone(pfn_to_page(pfn)), pfn, nr_pages);
	kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages));
}

/*
 * Must be called with mem_hotplug_lock in write mode.
 */
int __ref online_pages(unsigned long pfn, unsigned long nr_pages,
		       struct zone *zone, struct memory_group *group)
{
	unsigned long flags;
	int need_zonelists_rebuild = 0;
	const int nid = zone_to_nid(zone);
	int ret;
	struct memory_notify arg;

	/*
	 * {on,off}lining is constrained to full memory sections (or more
	 * precisely to memory blocks from the user space POV).
	 * memmap_on_memory is an exception because it reserves initial part
	 * of the physical memory space for vmemmaps. That space is pageblock
	 * aligned.
	 */
	if (WARN_ON_ONCE(!nr_pages || !pageblock_aligned(pfn) ||
			 !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION)))
		return -EINVAL;


	/* associate pfn range with the zone */
	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE);

	arg.start_pfn = pfn;
	arg.nr_pages = nr_pages;
	node_states_check_changes_online(nr_pages, zone, &arg);

	ret = memory_notify(MEM_GOING_ONLINE, &arg);
	ret = notifier_to_errno(ret);
	if (ret)
		goto failed_addition;

	/*
	 * Fixup the number of isolated pageblocks before marking the sections
	 * onlining, such that undo_isolate_page_range() works correctly.
	 */
	spin_lock_irqsave(&zone->lock, flags);
	zone->nr_isolate_pageblock += nr_pages / pageblock_nr_pages;
	spin_unlock_irqrestore(&zone->lock, flags);

	/*
	 * If this zone is not populated, then it is not in zonelist.
	 * This means the page allocator ignores this zone.
	 * So, zonelist must be updated after online.
	 */
	if (!populated_zone(zone)) {
		need_zonelists_rebuild = 1;
		setup_zone_pageset(zone);
	}

	online_pages_range(pfn, nr_pages);
	adjust_present_page_count(pfn_to_page(pfn), group, nr_pages);

	node_states_set_node(nid, &arg);
	if (need_zonelists_rebuild)
		build_all_zonelists(NULL);

	/* Basic onlining is complete, allow allocation of onlined pages. */
	undo_isolate_page_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE);

	/*
	 * Freshly onlined pages aren't shuffled (e.g., all pages are placed to
	 * the tail of the freelist when undoing isolation). Shuffle the whole
	 * zone to make sure the just onlined pages are properly distributed
	 * across the whole freelist - to create an initial shuffle.
	 */
	shuffle_zone(zone);

	/* reinitialise watermarks and update pcp limits */
	init_per_zone_wmark_min();

	kswapd_run(nid);
	kcompactd_run(nid);

	writeback_set_ratelimit();

	memory_notify(MEM_ONLINE, &arg);
	return 0;

failed_addition:
	pr_debug("online_pages [mem %#010llx-%#010llx] failed\n",
		 (unsigned long long) pfn << PAGE_SHIFT,
		 (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
	memory_notify(MEM_CANCEL_ONLINE, &arg);
	remove_pfn_range_from_zone(zone, pfn, nr_pages);
	return ret;
}

/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */
static pg_data_t __ref *hotadd_init_pgdat(int nid)
{
	struct pglist_data *pgdat;

	/*
	 * NODE_DATA is preallocated (free_area_init) but its internal
	 * state is not allocated completely. Add missing pieces.
	 * Completely offline nodes stay around and they just need
	 * reintialization.
	 */
	pgdat = NODE_DATA(nid);

	/* init node's zones as empty zones, we don't have any present pages.*/
	free_area_init_core_hotplug(pgdat);

	/*
	 * The node we allocated has no zone fallback lists. For avoiding
	 * to access not-initialized zonelist, build here.
	 */
	build_all_zonelists(pgdat);

	return pgdat;
}

/*
 * __try_online_node - online a node if offlined
 * @nid: the node ID
 * @set_node_online: Whether we want to online the node
 * called by cpu_up() to online a node without onlined memory.
 *
 * Returns:
 * 1 -> a new node has been allocated
 * 0 -> the node is already online
 * -ENOMEM -> the node could not be allocated
 */
static int __try_online_node(int nid, bool set_node_online)
{
	pg_data_t *pgdat;
	int ret = 1;

	if (node_online(nid))
		return 0;

	pgdat = hotadd_init_pgdat(nid);
	if (!pgdat) {
		pr_err("Cannot online node %d due to NULL pgdat\n", nid);
		ret = -ENOMEM;
		goto out;
	}

	if (set_node_online) {
		node_set_online(nid);
		ret = register_one_node(nid);
		BUG_ON(ret);
	}
out:
	return ret;
}

/*
 * Users of this function always want to online/register the node
 */
int try_online_node(int nid)
{
	int ret;

	mem_hotplug_begin();
	ret =  __try_online_node(nid, true);
	mem_hotplug_done();
	return ret;
}

static int check_hotplug_memory_range(u64 start, u64 size)
{
	/* memory range must be block size aligned */
	if (!size || !IS_ALIGNED(start, memory_block_size_bytes()) ||
	    !IS_ALIGNED(size, memory_block_size_bytes())) {
		pr_err("Block size [%#lx] unaligned hotplug range: start %#llx, size %#llx",
		       memory_block_size_bytes(), start, size);
		return -EINVAL;
	}

	return 0;
}

static int online_memory_block(struct memory_block *mem, void *arg)
{
	mem->online_type = mhp_default_online_type;
	return device_online(&mem->dev);
}

#ifndef arch_supports_memmap_on_memory
static inline bool arch_supports_memmap_on_memory(unsigned long vmemmap_size)
{
	/*
	 * As default, we want the vmemmap to span a complete PMD such that we
	 * can map the vmemmap using a single PMD if supported by the
	 * architecture.
	 */
	return IS_ALIGNED(vmemmap_size, PMD_SIZE);
}
#endif

static bool mhp_supports_memmap_on_memory(unsigned long size)
{
	unsigned long vmemmap_size = memory_block_memmap_size();
	unsigned long memmap_pages = memory_block_memmap_on_memory_pages();

	/*
	 * Besides having arch support and the feature enabled at runtime, we
	 * need a few more assumptions to hold true:
	 *
	 * a) We span a single memory block: memory onlining/offlinin;g happens
	 *    in memory block granularity. We don't want the vmemmap of online
	 *    memory blocks to reside on offline memory blocks. In the future,
	 *    we might want to support variable-sized memory blocks to make the
	 *    feature more versatile.
	 *
	 * b) The vmemmap pages span complete PMDs: We don't want vmemmap code
	 *    to populate memory from the altmap for unrelated parts (i.e.,
	 *    other memory blocks)
	 *
	 * c) The vmemmap pages (and thereby the pages that will be exposed to
	 *    the buddy) have to cover full pageblocks: memory onlining/offlining
	 *    code requires applicable ranges to be page-aligned, for example, to
	 *    set the migratetypes properly.
	 *
	 * TODO: Although we have a check here to make sure that vmemmap pages
	 *       fully populate a PMD, it is not the right place to check for
	 *       this. A much better solution involves improving vmemmap code
	 *       to fallback to base pages when trying to populate vmemmap using
	 *       altmap as an alternative source of memory, and we do not exactly
	 *       populate a single PMD.
	 */
	if (!mhp_memmap_on_memory() || size != memory_block_size_bytes())
		return false;

	/*
	 * Make sure the vmemmap allocation is fully contained
	 * so that we always allocate vmemmap memory from altmap area.
	 */
	if (!IS_ALIGNED(vmemmap_size, PAGE_SIZE))
		return false;

	/*
	 * start pfn should be pageblock_nr_pages aligned for correctly
	 * setting migrate types
	 */
	if (!pageblock_aligned(memmap_pages))
		return false;

	if (memmap_pages == PHYS_PFN(memory_block_size_bytes()))
		/* No effective hotplugged memory doesn't make sense. */
		return false;

	return arch_supports_memmap_on_memory(vmemmap_size);
}

/*
 * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
 * and online/offline operations (triggered e.g. by sysfs).
 *
 * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG
 */
int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
{
	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
	enum memblock_flags memblock_flags = MEMBLOCK_NONE;
	struct vmem_altmap mhp_altmap = {
		.base_pfn =  PHYS_PFN(res->start),
		.end_pfn  =  PHYS_PFN(res->end),
	};
	struct memory_group *group = NULL;
	u64 start, size;
	bool new_node = false;
	int ret;

	start = res->start;
	size = resource_size(res);

	ret = check_hotplug_memory_range(start, size);
	if (ret)
		return ret;

	if (mhp_flags & MHP_NID_IS_MGID) {
		group = memory_group_find_by_id(nid);
		if (!group)
			return -EINVAL;
		nid = group->nid;
	}

	if (!node_possible(nid)) {
		WARN(1, "node %d was absent from the node_possible_map\n", nid);
		return -EINVAL;
	}

	mem_hotplug_begin();

	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
		if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED)
			memblock_flags = MEMBLOCK_DRIVER_MANAGED;
		ret = memblock_add_node(start, size, nid, memblock_flags);
		if (ret)
			goto error_mem_hotplug_end;
	}

	ret = __try_online_node(nid, false);
	if (ret < 0)
		goto error;
	new_node = ret;

	/*
	 * Self hosted memmap array
	 */
	if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
		if (mhp_supports_memmap_on_memory(size)) {
			mhp_altmap.free = memory_block_memmap_on_memory_pages();
			params.altmap = kmemdup(&mhp_altmap,
						sizeof(struct vmem_altmap),
						GFP_KERNEL);
			if (!params.altmap) {
				ret = -ENOMEM;
				goto error;
			}
		}
		/* fallback to not using altmap  */
	}

	/* call arch's memory hotadd */
	ret = arch_add_memory(nid, start, size, &params);
	if (ret < 0)
		goto error_free;

	/* create memory block devices after memory was added */
	ret = create_memory_block_devices(start, size, params.altmap, group);
	if (ret) {
		arch_remove_memory(start, size, params.altmap);
		goto error_free;
	}

	if (new_node) {
		/* If sysfs file of new node can't be created, cpu on the node
		 * can't be hot-added. There is no rollback way now.
		 * So, check by BUG_ON() to catch it reluctantly..
		 * We online node here. We can't roll back from here.
		 */
		node_set_online(nid);
		ret = __register_one_node(nid);
		BUG_ON(ret);
	}

	register_memory_blocks_under_node(nid, PFN_DOWN(start),
					  PFN_UP(start + size - 1),
					  MEMINIT_HOTPLUG);

	/* create new memmap entry */
	if (!strcmp(res->name, "System RAM"))
		firmware_map_add_hotplug(start, start + size, "System RAM");

	/* device_online() will take the lock when calling online_pages() */
	mem_hotplug_done();

	/*
	 * In case we're allowed to merge the resource, flag it and trigger
	 * merging now that adding succeeded.
	 */
	if (mhp_flags & MHP_MERGE_RESOURCE)
		merge_system_ram_resource(res);

	/* online pages if requested */
	if (mhp_default_online_type != MMOP_OFFLINE)
		walk_memory_blocks(start, size, NULL, online_memory_block);

	return ret;
error_free:
	kfree(params.altmap);
error:
	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
		memblock_remove(start, size);
error_mem_hotplug_end:
	mem_hotplug_done();
	return ret;
}

/* requires device_hotplug_lock, see add_memory_resource() */
int __ref __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
{
	struct resource *res;
	int ret;

	res = register_memory_resource(start, size, "System RAM");
	if (IS_ERR(res))
		return PTR_ERR(res);

	ret = add_memory_resource(nid, res, mhp_flags);
	if (ret < 0)
		release_memory_resource(res);
	return ret;
}

int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags)
{
	int rc;

	lock_device_hotplug();
	rc = __add_memory(nid, start, size, mhp_flags);
	unlock_device_hotplug();

	return rc;
}
EXPORT_SYMBOL_GPL(add_memory);

/*
 * Add special, driver-managed memory to the system as system RAM. Such
 * memory is not exposed via the raw firmware-provided memmap as system
 * RAM, instead, it is detected and added by a driver - during cold boot,
 * after a reboot, and after kexec.
 *
 * Reasons why this memory should not be used for the initial memmap of a
 * kexec kernel or for placing kexec images:
 * - The booting kernel is in charge of determining how this memory will be
 *   used (e.g., use persistent memory as system RAM)
 * - Coordination with a hypervisor is required before this memory
 *   can be used (e.g., inaccessible parts).
 *
 * For this memory, no entries in /sys/firmware/memmap ("raw firmware-provided
 * memory map") are created. Also, the created memory resource is flagged
 * with IORESOURCE_SYSRAM_DRIVER_MANAGED, so in-kernel users can special-case
 * this memory as well (esp., not place kexec images onto it).
 *
 * The resource_name (visible via /proc/iomem) has to have the format
 * "System RAM ($DRIVER)".
 */
int add_memory_driver_managed(int nid, u64 start, u64 size,
			      const char *resource_name, mhp_t mhp_flags)
{
	struct resource *res;
	int rc;

	if (!resource_name ||
	    strstr(resource_name, "System RAM (") != resource_name ||
	    resource_name[strlen(resource_name) - 1] != ')')
		return -EINVAL;

	lock_device_hotplug();

	res = register_memory_resource(start, size, resource_name);
	if (IS_ERR(res)) {
		rc = PTR_ERR(res);
		goto out_unlock;
	}

	rc = add_memory_resource(nid, res, mhp_flags);
	if (rc < 0)
		release_memory_resource(res);

out_unlock:
	unlock_device_hotplug();
	return rc;
}
EXPORT_SYMBOL_GPL(add_memory_driver_managed);

/*
 * Platforms should define arch_get_mappable_range() that provides
 * maximum possible addressable physical memory range for which the
 * linear mapping could be created. The platform returned address
 * range must adhere to these following semantics.
 *
 * - range.start <= range.end
 * - Range includes both end points [range.start..range.end]
 *
 * There is also a fallback definition provided here, allowing the
 * entire possible physical address range in case any platform does
 * not define arch_get_mappable_range().
 */
struct range __weak arch_get_mappable_range(void)
{
	struct range mhp_range = {
		.start = 0UL,
		.end = -1ULL,
	};
	return mhp_range;
}

struct range mhp_get_pluggable_range(bool need_mapping)
{
	const u64 max_phys = (1ULL << MAX_PHYSMEM_BITS) - 1;
	struct range mhp_range;

	if (need_mapping) {
		mhp_range = arch_get_mappable_range();
		if (mhp_range.start > max_phys) {
			mhp_range.start = 0;
			mhp_range.end = 0;
		}
		mhp_range.end = min_t(u64, mhp_range.end, max_phys);
	} else {
		mhp_range.start = 0;
		mhp_range.end = max_phys;
	}
	return mhp_range;
}
EXPORT_SYMBOL_GPL(mhp_get_pluggable_range);

bool mhp_range_allowed(u64 start, u64 size, bool need_mapping)
{
	struct range mhp_range = mhp_get_pluggable_range(need_mapping);
	u64 end = start + size;

	if (start < end && start >= mhp_range.start && (end - 1) <= mhp_range.end)
		return true;

	pr_warn("Hotplug memory [%#llx-%#llx] exceeds maximum addressable range [%#llx-%#llx]\n",
		start, end, mhp_range.start, mhp_range.end);
	return false;
}

#ifdef CONFIG_MEMORY_HOTREMOVE
/*
 * Scan pfn range [start,end) to find movable/migratable pages (LRU pages,
 * non-lru movable pages and hugepages). Will skip over most unmovable
 * pages (esp., pages that can be skipped when offlining), but bail out on
 * definitely unmovable pages.
 *
 * Returns:
 *	0 in case a movable page is found and movable_pfn was updated.
 *	-ENOENT in case no movable page was found.
 *	-EBUSY in case a definitely unmovable page was found.
 */
static int scan_movable_pages(unsigned long start, unsigned long end,
			      unsigned long *movable_pfn)
{
	unsigned long pfn;

	for (pfn = start; pfn < end; pfn++) {
		struct page *page, *head;
		unsigned long skip;

		if (!pfn_valid(pfn))
			continue;
		page = pfn_to_page(pfn);
		if (PageLRU(page))
			goto found;
		if (__PageMovable(page))
			goto found;

		/*
		 * PageOffline() pages that are not marked __PageMovable() and
		 * have a reference count > 0 (after MEM_GOING_OFFLINE) are
		 * definitely unmovable. If their reference count would be 0,
		 * they could at least be skipped when offlining memory.
		 */
		if (PageOffline(page) && page_count(page))
			return -EBUSY;

		if (!PageHuge(page))
			continue;
		head = compound_head(page);
		/*
		 * This test is racy as we hold no reference or lock.  The
		 * hugetlb page could have been free'ed and head is no longer
		 * a hugetlb page before the following check.  In such unlikely
		 * cases false positives and negatives are possible.  Calling
		 * code must deal with these scenarios.
		 */
		if (HPageMigratable(head))
			goto found;
		skip = compound_nr(head) - (pfn - page_to_pfn(head));
		pfn += skip - 1;
	}
	return -ENOENT;
found:
	*movable_pfn = pfn;
	return 0;
}

static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
{
	unsigned long pfn;
	struct page *page, *head;
	LIST_HEAD(source);
	static DEFINE_RATELIMIT_STATE(migrate_rs, DEFAULT_RATELIMIT_INTERVAL,
				      DEFAULT_RATELIMIT_BURST);

	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
		struct folio *folio;
		bool isolated;

		if (!pfn_valid(pfn))
			continue;
		page = pfn_to_page(pfn);
		folio = page_folio(page);
		head = &folio->page;

		if (PageHuge(page)) {
			pfn = page_to_pfn(head) + compound_nr(head) - 1;
			isolate_hugetlb(folio, &source);
			continue;
		} else if (PageTransHuge(page))
			pfn = page_to_pfn(head) + thp_nr_pages(page) - 1;

		/*
		 * HWPoison pages have elevated reference counts so the migration would
		 * fail on them. It also doesn't make any sense to migrate them in the
		 * first place. Still try to unmap such a page in case it is still mapped
		 * (e.g. current hwpoison implementation doesn't unmap KSM pages but keep
		 * the unmap as the catch all safety net).
		 */
		if (PageHWPoison(page)) {
			if (WARN_ON(folio_test_lru(folio)))
				folio_isolate_lru(folio);
			if (folio_mapped(folio))
				try_to_unmap(folio, TTU_IGNORE_MLOCK);
			continue;
		}

		if (!get_page_unless_zero(page))
			continue;
		/*
		 * We can skip free pages. And we can deal with pages on
		 * LRU and non-lru movable pages.
		 */
		if (PageLRU(page))
			isolated = isolate_lru_page(page);
		else
			isolated = isolate_movable_page(page, ISOLATE_UNEVICTABLE);
		if (isolated) {
			list_add_tail(&page->lru, &source);
			if (!__PageMovable(page))
				inc_node_page_state(page, NR_ISOLATED_ANON +
						    page_is_file_lru(page));

		} else {
			if (__ratelimit(&migrate_rs)) {
				pr_warn("failed to isolate pfn %lx\n", pfn);
				dump_page(page, "isolation failed");
			}
		}
		put_page(page);
	}
	if (!list_empty(&source)) {
		nodemask_t nmask = node_states[N_MEMORY];
		struct migration_target_control mtc = {
			.nmask = &nmask,
			.gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
		};
		int ret;

		/*
		 * We have checked that migration range is on a single zone so
		 * we can use the nid of the first page to all the others.
		 */
		mtc.nid = page_to_nid(list_first_entry(&source, struct page, lru));

		/*
		 * try to allocate from a different node but reuse this node
		 * if there are no other online nodes to be used (e.g. we are
		 * offlining a part of the only existing node)
		 */
		node_clear(mtc.nid, nmask);
		if (nodes_empty(nmask))
			node_set(mtc.nid, nmask);
		ret = migrate_pages(&source, alloc_migration_target, NULL,
			(unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_HOTPLUG, NULL);
		if (ret) {
			list_for_each_entry(page, &source, lru) {
				if (__ratelimit(&migrate_rs)) {
					pr_warn("migrating pfn %lx failed ret:%d\n",
						page_to_pfn(page), ret);
					dump_page(page, "migration failure");
				}
			}
			putback_movable_pages(&source);
		}
	}
}

static int __init cmdline_parse_movable_node(char *p)
{
	movable_node_enabled = true;
	return 0;
}
early_param("movable_node", cmdline_parse_movable_node);

/* check which state of node_states will be changed when offline memory */
static void node_states_check_changes_offline(unsigned long nr_pages,
		struct zone *zone, struct memory_notify *arg)
{
	struct pglist_data *pgdat = zone->zone_pgdat;
	unsigned long present_pages = 0;
	enum zone_type zt;

	arg->status_change_nid = NUMA_NO_NODE;
	arg->status_change_nid_normal = NUMA_NO_NODE;

	/*
	 * Check whether node_states[N_NORMAL_MEMORY] will be changed.
	 * If the memory to be offline is within the range
	 * [0..ZONE_NORMAL], and it is the last present memory there,
	 * the zones in that range will become empty after the offlining,
	 * thus we can determine that we need to clear the node from
	 * node_states[N_NORMAL_MEMORY].
	 */
	for (zt = 0; zt <= ZONE_NORMAL; zt++)
		present_pages += pgdat->node_zones[zt].present_pages;
	if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages)
		arg->status_change_nid_normal = zone_to_nid(zone);

	/*
	 * We have accounted the pages from [0..ZONE_NORMAL); ZONE_HIGHMEM
	 * does not apply as we don't support 32bit.
	 * Here we count the possible pages from ZONE_MOVABLE.
	 * If after having accounted all the pages, we see that the nr_pages
	 * to be offlined is over or equal to the accounted pages,
	 * we know that the node will become empty, and so, we can clear
	 * it for N_MEMORY as well.
	 */
	present_pages += pgdat->node_zones[ZONE_MOVABLE].present_pages;

	if (nr_pages >= present_pages)
		arg->status_change_nid = zone_to_nid(zone);
}

static void node_states_clear_node(int node, struct memory_notify *arg)
{
	if (arg->status_change_nid_normal >= 0)
		node_clear_state(node, N_NORMAL_MEMORY);

	if (arg->status_change_nid >= 0)
		node_clear_state(node, N_MEMORY);
}

static int count_system_ram_pages_cb(unsigned long start_pfn,
				     unsigned long nr_pages, void *data)
{
	unsigned long *nr_system_ram_pages = data;

	*nr_system_ram_pages += nr_pages;
	return 0;
}

/*
 * Must be called with mem_hotplug_lock in write mode.
 */
int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
			struct zone *zone, struct memory_group *group)
{
	const unsigned long end_pfn = start_pfn + nr_pages;
	unsigned long pfn, system_ram_pages = 0;
	const int node = zone_to_nid(zone);
	unsigned long flags;
	struct memory_notify arg;
	char *reason;
	int ret;

	/*
	 * {on,off}lining is constrained to full memory sections (or more
	 * precisely to memory blocks from the user space POV).
	 * memmap_on_memory is an exception because it reserves initial part
	 * of the physical memory space for vmemmaps. That space is pageblock
	 * aligned.
	 */
	if (WARN_ON_ONCE(!nr_pages || !pageblock_aligned(start_pfn) ||
			 !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION)))
		return -EINVAL;

	/*
	 * Don't allow to offline memory blocks that contain holes.
	 * Consequently, memory blocks with holes can never get onlined
	 * via the hotplug path - online_pages() - as hotplugged memory has
	 * no holes. This way, we e.g., don't have to worry about marking
	 * memory holes PG_reserved, don't need pfn_valid() checks, and can
	 * avoid using walk_system_ram_range() later.
	 */
	walk_system_ram_range(start_pfn, nr_pages, &system_ram_pages,
			      count_system_ram_pages_cb);
	if (system_ram_pages != nr_pages) {
		ret = -EINVAL;
		reason = "memory holes";
		goto failed_removal;
	}

	/*
	 * We only support offlining of memory blocks managed by a single zone,
	 * checked by calling code. This is just a sanity check that we might
	 * want to remove in the future.
	 */
	if (WARN_ON_ONCE(page_zone(pfn_to_page(start_pfn)) != zone ||
			 page_zone(pfn_to_page(end_pfn - 1)) != zone)) {
		ret = -EINVAL;
		reason = "multizone range";
		goto failed_removal;
	}

	/*
	 * Disable pcplists so that page isolation cannot race with freeing
	 * in a way that pages from isolated pageblock are left on pcplists.
	 */
	zone_pcp_disable(zone);
	lru_cache_disable();

	/* set above range as isolated */
	ret = start_isolate_page_range(start_pfn, end_pfn,
				       MIGRATE_MOVABLE,
				       MEMORY_OFFLINE | REPORT_FAILURE,
				       GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL);
	if (ret) {
		reason = "failure to isolate range";
		goto failed_removal_pcplists_disabled;
	}

	arg.start_pfn = start_pfn;
	arg.nr_pages = nr_pages;
	node_states_check_changes_offline(nr_pages, zone, &arg);

	ret = memory_notify(MEM_GOING_OFFLINE, &arg);
	ret = notifier_to_errno(ret);
	if (ret) {
		reason = "notifier failure";
		goto failed_removal_isolated;
	}

	do {
		pfn = start_pfn;
		do {
			/*
			 * Historically we always checked for any signal and
			 * can't limit it to fatal signals without eventually
			 * breaking user space.
			 */
			if (signal_pending(current)) {
				ret = -EINTR;
				reason = "signal backoff";
				goto failed_removal_isolated;
			}

			cond_resched();

			ret = scan_movable_pages(pfn, end_pfn, &pfn);
			if (!ret) {
				/*
				 * TODO: fatal migration failures should bail
				 * out
				 */
				do_migrate_range(pfn, end_pfn);
			}
		} while (!ret);

		if (ret != -ENOENT) {
			reason = "unmovable page";
			goto failed_removal_isolated;
		}

		/*
		 * Dissolve free hugepages in the memory block before doing
		 * offlining actually in order to make hugetlbfs's object
		 * counting consistent.
		 */
		ret = dissolve_free_huge_pages(start_pfn, end_pfn);
		if (ret) {
			reason = "failure to dissolve huge pages";
			goto failed_removal_isolated;
		}

		ret = test_pages_isolated(start_pfn, end_pfn, MEMORY_OFFLINE);

	} while (ret);

	/* Mark all sections offline and remove free pages from the buddy. */
	__offline_isolated_pages(start_pfn, end_pfn);
	pr_debug("Offlined Pages %ld\n", nr_pages);

	/*
	 * The memory sections are marked offline, and the pageblock flags
	 * effectively stale; nobody should be touching them. Fixup the number
	 * of isolated pageblocks, memory onlining will properly revert this.
	 */
	spin_lock_irqsave(&zone->lock, flags);
	zone->nr_isolate_pageblock -= nr_pages / pageblock_nr_pages;
	spin_unlock_irqrestore(&zone->lock, flags);

	lru_cache_enable();
	zone_pcp_enable(zone);

	/* removal success */
	adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages);
	adjust_present_page_count(pfn_to_page(start_pfn), group, -nr_pages);

	/* reinitialise watermarks and update pcp limits */
	init_per_zone_wmark_min();

	/*
	 * Make sure to mark the node as memory-less before rebuilding the zone
	 * list. Otherwise this node would still appear in the fallback lists.
	 */
	node_states_clear_node(node, &arg);
	if (!populated_zone(zone)) {
		zone_pcp_reset(zone);
		build_all_zonelists(NULL);
	}

	if (arg.status_change_nid >= 0) {
		kcompactd_stop(node);
		kswapd_stop(node);
	}

	writeback_set_ratelimit();

	memory_notify(MEM_OFFLINE, &arg);
	remove_pfn_range_from_zone(zone, start_pfn, nr_pages);
	return 0;

failed_removal_isolated:
	/* pushback to free area */
	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
	memory_notify(MEM_CANCEL_OFFLINE, &arg);
failed_removal_pcplists_disabled:
	lru_cache_enable();
	zone_pcp_enable(zone);
failed_removal:
	pr_debug("memory offlining [mem %#010llx-%#010llx] failed due to %s\n",
		 (unsigned long long) start_pfn << PAGE_SHIFT,
		 ((unsigned long long) end_pfn << PAGE_SHIFT) - 1,
		 reason);
	return ret;
}

static int check_memblock_offlined_cb(struct memory_block *mem, void *arg)
{
	int *nid = arg;

	*nid = mem->nid;
	if (unlikely(mem->state != MEM_OFFLINE)) {
		phys_addr_t beginpa, endpa;

		beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr));
		endpa = beginpa + memory_block_size_bytes() - 1;
		pr_warn("removing memory fails, because memory [%pa-%pa] is onlined\n",
			&beginpa, &endpa);

		return -EBUSY;
	}
	return 0;
}

static int test_has_altmap_cb(struct memory_block *mem, void *arg)
{
	struct memory_block **mem_ptr = (struct memory_block **)arg;
	/*
	 * return the memblock if we have altmap
	 * and break callback.
	 */
	if (mem->altmap) {
		*mem_ptr = mem;
		return 1;
	}
	return 0;
}

static int check_cpu_on_node(int nid)
{
	int cpu;

	for_each_present_cpu(cpu) {
		if (cpu_to_node(cpu) == nid)
			/*
			 * the cpu on this node isn't removed, and we can't
			 * offline this node.
			 */
			return -EBUSY;
	}

	return 0;
}

static int check_no_memblock_for_node_cb(struct memory_block *mem, void *arg)
{
	int nid = *(int *)arg;

	/*
	 * If a memory block belongs to multiple nodes, the stored nid is not
	 * reliable. However, such blocks are always online (e.g., cannot get
	 * offlined) and, therefore, are still spanned by the node.
	 */
	return mem->nid == nid ? -EEXIST : 0;
}

/**
 * try_offline_node
 * @nid: the node ID
 *
 * Offline a node if all memory sections and cpus of the node are removed.
 *
 * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
 * and online/offline operations before this call.
 */
void try_offline_node(int nid)
{
	int rc;

	/*
	 * If the node still spans pages (especially ZONE_DEVICE), don't
	 * offline it. A node spans memory after move_pfn_range_to_zone(),
	 * e.g., after the memory block was onlined.
	 */
	if (node_spanned_pages(nid))
		return;

	/*
	 * Especially offline memory blocks might not be spanned by the
	 * node. They will get spanned by the node once they get onlined.
	 * However, they link to the node in sysfs and can get onlined later.
	 */
	rc = for_each_memory_block(&nid, check_no_memblock_for_node_cb);
	if (rc)
		return;

	if (check_cpu_on_node(nid))
		return;

	/*
	 * all memory/cpu of this node are removed, we can offline this
	 * node now.
	 */
	node_set_offline(nid);
	unregister_one_node(nid);
}
EXPORT_SYMBOL(try_offline_node);

static int __ref try_remove_memory(u64 start, u64 size)
{
	struct memory_block *mem;
	int rc = 0, nid = NUMA_NO_NODE;
	struct vmem_altmap *altmap = NULL;

	BUG_ON(check_hotplug_memory_range(start, size));

	/*
	 * All memory blocks must be offlined before removing memory.  Check
	 * whether all memory blocks in question are offline and return error
	 * if this is not the case.
	 *
	 * While at it, determine the nid. Note that if we'd have mixed nodes,
	 * we'd only try to offline the last determined one -- which is good
	 * enough for the cases we care about.
	 */
	rc = walk_memory_blocks(start, size, &nid, check_memblock_offlined_cb);
	if (rc)
		return rc;

	/*
	 * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in
	 * the same granularity it was added - a single memory block.
	 */
	if (mhp_memmap_on_memory()) {
		rc = walk_memory_blocks(start, size, &mem, test_has_altmap_cb);
		if (rc) {
			if (size != memory_block_size_bytes()) {
				pr_warn("Refuse to remove %#llx - %#llx,"
					"wrong granularity\n",
					start, start + size);
				return -EINVAL;
			}
			altmap = mem->altmap;
			/*
			 * Mark altmap NULL so that we can add a debug
			 * check on memblock free.
			 */
			mem->altmap = NULL;
		}
	}

	/* remove memmap entry */
	firmware_map_remove(start, start + size, "System RAM");

	/*
	 * Memory block device removal under the device_hotplug_lock is
	 * a barrier against racing online attempts.
	 */
	remove_memory_block_devices(start, size);

	mem_hotplug_begin();

	arch_remove_memory(start, size, altmap);

	/* Verify that all vmemmap pages have actually been freed. */
	if (altmap) {
		WARN(altmap->alloc, "Altmap not fully unmapped");
		kfree(altmap);
	}

	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) {
		memblock_phys_free(start, size);
		memblock_remove(start, size);
	}

	release_mem_region_adjustable(start, size);

	if (nid != NUMA_NO_NODE)
		try_offline_node(nid);

	mem_hotplug_done();
	return 0;
}

/**
 * __remove_memory - Remove memory if every memory block is offline
 * @start: physical address of the region to remove
 * @size: size of the region to remove
 *
 * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
 * and online/offline operations before this call, as required by
 * try_offline_node().
 */
void __remove_memory(u64 start, u64 size)
{

	/*
	 * trigger BUG() if some memory is not offlined prior to calling this
	 * function
	 */
	if (try_remove_memory(start, size))
		BUG();
}

/*
 * Remove memory if every memory block is offline, otherwise return -EBUSY is
 * some memory is not offline
 */
int remove_memory(u64 start, u64 size)
{
	int rc;

	lock_device_hotplug();
	rc = try_remove_memory(start, size);
	unlock_device_hotplug();

	return rc;
}
EXPORT_SYMBOL_GPL(remove_memory);

static int try_offline_memory_block(struct memory_block *mem, void *arg)
{
	uint8_t online_type = MMOP_ONLINE_KERNEL;
	uint8_t **online_types = arg;
	struct page *page;
	int rc;

	/*
	 * Sense the online_type via the zone of the memory block. Offlining
	 * with multiple zones within one memory block will be rejected
	 * by offlining code ... so we don't care about that.
	 */
	page = pfn_to_online_page(section_nr_to_pfn(mem->start_section_nr));
	if (page && zone_idx(page_zone(page)) == ZONE_MOVABLE)
		online_type = MMOP_ONLINE_MOVABLE;

	rc = device_offline(&mem->dev);
	/*
	 * Default is MMOP_OFFLINE - change it only if offlining succeeded,
	 * so try_reonline_memory_block() can do the right thing.
	 */
	if (!rc)
		**online_types = online_type;

	(*online_types)++;
	/* Ignore if already offline. */
	return rc < 0 ? rc : 0;
}

static int try_reonline_memory_block(struct memory_block *mem, void *arg)
{
	uint8_t **online_types = arg;
	int rc;

	if (**online_types != MMOP_OFFLINE) {
		mem->online_type = **online_types;
		rc = device_online(&mem->dev);
		if (rc < 0)
			pr_warn("%s: Failed to re-online memory: %d",
				__func__, rc);
	}

	/* Continue processing all remaining memory blocks. */
	(*online_types)++;
	return 0;
}

/*
 * Try to offline and remove memory. Might take a long time to finish in case
 * memory is still in use. Primarily useful for memory devices that logically
 * unplugged all memory (so it's no longer in use) and want to offline + remove
 * that memory.
 */
int offline_and_remove_memory(u64 start, u64 size)
{
	const unsigned long mb_count = size / memory_block_size_bytes();
	uint8_t *online_types, *tmp;
	int rc;

	if (!IS_ALIGNED(start, memory_block_size_bytes()) ||
	    !IS_ALIGNED(size, memory_block_size_bytes()) || !size)
		return -EINVAL;

	/*
	 * We'll remember the old online type of each memory block, so we can
	 * try to revert whatever we did when offlining one memory block fails
	 * after offlining some others succeeded.
	 */
	online_types = kmalloc_array(mb_count, sizeof(*online_types),
				     GFP_KERNEL);
	if (!online_types)
		return -ENOMEM;
	/*
	 * Initialize all states to MMOP_OFFLINE, so when we abort processing in
	 * try_offline_memory_block(), we'll skip all unprocessed blocks in
	 * try_reonline_memory_block().
	 */
	memset(online_types, MMOP_OFFLINE, mb_count);

	lock_device_hotplug();

	tmp = online_types;
	rc = walk_memory_blocks(start, size, &tmp, try_offline_memory_block);

	/*
	 * In case we succeeded to offline all memory, remove it.
	 * This cannot fail as it cannot get onlined in the meantime.
	 */
	if (!rc) {
		rc = try_remove_memory(start, size);
		if (rc)
			pr_err("%s: Failed to remove memory: %d", __func__, rc);
	}

	/*
	 * Rollback what we did. While memory onlining might theoretically fail
	 * (nacked by a notifier), it barely ever happens.
	 */
	if (rc) {
		tmp = online_types;
		walk_memory_blocks(start, size, &tmp,
				   try_reonline_memory_block);
	}
	unlock_device_hotplug();

	kfree(online_types);
	return rc;
}
EXPORT_SYMBOL_GPL(offline_and_remove_memory);
#endif /* CONFIG_MEMORY_HOTREMOVE */