summaryrefslogtreecommitdiffstats
path: root/fs/hugetlbfs/inode.c
blob: d746866ae3b6ba79a4ed1d8b6600c29cfc28e005 (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
/*
 * hugetlbpage-backed filesystem.  Based on ramfs.
 *
 * Nadia Yvette Chambers, 2002
 *
 * Copyright (C) 2002 Linus Torvalds.
 * License: GPL
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/thread_info.h>
#include <asm/current.h>
#include <linux/falloc.h>
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <linux/kernel.h>
#include <linux/writeback.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/capability.h>
#include <linux/ctype.h>
#include <linux/backing-dev.h>
#include <linux/hugetlb.h>
#include <linux/pagevec.h>
#include <linux/fs_parser.h>
#include <linux/mman.h>
#include <linux/slab.h>
#include <linux/dnotify.h>
#include <linux/statfs.h>
#include <linux/security.h>
#include <linux/magic.h>
#include <linux/migrate.h>
#include <linux/uio.h>

#include <linux/uaccess.h>
#include <linux/sched/mm.h>

static const struct address_space_operations hugetlbfs_aops;
const struct file_operations hugetlbfs_file_operations;
static const struct inode_operations hugetlbfs_dir_inode_operations;
static const struct inode_operations hugetlbfs_inode_operations;

enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT };

struct hugetlbfs_fs_context {
	struct hstate		*hstate;
	unsigned long long	max_size_opt;
	unsigned long long	min_size_opt;
	long			max_hpages;
	long			nr_inodes;
	long			min_hpages;
	enum hugetlbfs_size_type max_val_type;
	enum hugetlbfs_size_type min_val_type;
	kuid_t			uid;
	kgid_t			gid;
	umode_t			mode;
};

int sysctl_hugetlb_shm_group;

enum hugetlb_param {
	Opt_gid,
	Opt_min_size,
	Opt_mode,
	Opt_nr_inodes,
	Opt_pagesize,
	Opt_size,
	Opt_uid,
};

static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
	fsparam_u32   ("gid",		Opt_gid),
	fsparam_string("min_size",	Opt_min_size),
	fsparam_u32oct("mode",		Opt_mode),
	fsparam_string("nr_inodes",	Opt_nr_inodes),
	fsparam_string("pagesize",	Opt_pagesize),
	fsparam_string("size",		Opt_size),
	fsparam_u32   ("uid",		Opt_uid),
	{}
};

/*
 * Mask used when checking the page offset value passed in via system
 * calls.  This value will be converted to a loff_t which is signed.
 * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the
 * value.  The extra bit (- 1 in the shift value) is to take the sign
 * bit into account.
 */
#define PGOFF_LOFFT_MAX \
	(((1UL << (PAGE_SHIFT + 1)) - 1) <<  (BITS_PER_LONG - (PAGE_SHIFT + 1)))

static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct inode *inode = file_inode(file);
	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
	loff_t len, vma_len;
	int ret;
	struct hstate *h = hstate_file(file);
	vm_flags_t vm_flags;

	/*
	 * vma address alignment (but not the pgoff alignment) has
	 * already been checked by prepare_hugepage_range.  If you add
	 * any error returns here, do so after setting VM_HUGETLB, so
	 * is_vm_hugetlb_page tests below unmap_region go the right
	 * way when do_mmap unwinds (may be important on powerpc
	 * and ia64).
	 */
	vm_flags_set(vma, VM_HUGETLB | VM_DONTEXPAND);
	vma->vm_ops = &hugetlb_vm_ops;

	ret = seal_check_write(info->seals, vma);
	if (ret)
		return ret;

	/*
	 * page based offset in vm_pgoff could be sufficiently large to
	 * overflow a loff_t when converted to byte offset.  This can
	 * only happen on architectures where sizeof(loff_t) ==
	 * sizeof(unsigned long).  So, only check in those instances.
	 */
	if (sizeof(unsigned long) == sizeof(loff_t)) {
		if (vma->vm_pgoff & PGOFF_LOFFT_MAX)
			return -EINVAL;
	}

	/* must be huge page aligned */
	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
		return -EINVAL;

	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
	/* check for overflow */
	if (len < vma_len)
		return -EINVAL;

	inode_lock(inode);
	file_accessed(file);

	ret = -ENOMEM;

	vm_flags = vma->vm_flags;
	/*
	 * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip
	 * reserving here. Note: only for SHM hugetlbfs file, the inode
	 * flag S_PRIVATE is set.
	 */
	if (inode->i_flags & S_PRIVATE)
		vm_flags |= VM_NORESERVE;

	if (!hugetlb_reserve_pages(inode,
				vma->vm_pgoff >> huge_page_order(h),
				len >> huge_page_shift(h), vma,
				vm_flags))
		goto out;

	ret = 0;
	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
		i_size_write(inode, len);
out:
	inode_unlock(inode);

	return ret;
}

/*
 * Called under mmap_write_lock(mm).
 */

static unsigned long
hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr,
		unsigned long len, unsigned long pgoff, unsigned long flags)
{
	struct hstate *h = hstate_file(file);
	struct vm_unmapped_area_info info;

	info.flags = 0;
	info.length = len;
	info.low_limit = current->mm->mmap_base;
	info.high_limit = arch_get_mmap_end(addr, len, flags);
	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
	info.align_offset = 0;
	return vm_unmapped_area(&info);
}

static unsigned long
hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr,
		unsigned long len, unsigned long pgoff, unsigned long flags)
{
	struct hstate *h = hstate_file(file);
	struct vm_unmapped_area_info info;

	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
	info.length = len;
	info.low_limit = PAGE_SIZE;
	info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base);
	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
	info.align_offset = 0;
	addr = vm_unmapped_area(&info);

	/*
	 * A failed mmap() very likely causes application failure,
	 * so fall back to the bottom-up function here. This scenario
	 * can happen with large stack limits and large mmap()
	 * allocations.
	 */
	if (unlikely(offset_in_page(addr))) {
		VM_BUG_ON(addr != -ENOMEM);
		info.flags = 0;
		info.low_limit = current->mm->mmap_base;
		info.high_limit = arch_get_mmap_end(addr, len, flags);
		addr = vm_unmapped_area(&info);
	}

	return addr;
}

unsigned long
generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
				  unsigned long len, unsigned long pgoff,
				  unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	struct hstate *h = hstate_file(file);
	const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags);

	if (len & ~huge_page_mask(h))
		return -EINVAL;
	if (len > TASK_SIZE)
		return -ENOMEM;

	if (flags & MAP_FIXED) {
		if (prepare_hugepage_range(file, addr, len))
			return -EINVAL;
		return addr;
	}

	if (addr) {
		addr = ALIGN(addr, huge_page_size(h));
		vma = find_vma(mm, addr);
		if (mmap_end - len >= addr &&
		    (!vma || addr + len <= vm_start_gap(vma)))
			return addr;
	}

	/*
	 * Use mm->get_unmapped_area value as a hint to use topdown routine.
	 * If architectures have special needs, they should define their own
	 * version of hugetlb_get_unmapped_area.
	 */
	if (mm->get_unmapped_area == arch_get_unmapped_area_topdown)
		return hugetlb_get_unmapped_area_topdown(file, addr, len,
				pgoff, flags);
	return hugetlb_get_unmapped_area_bottomup(file, addr, len,
			pgoff, flags);
}

#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
static unsigned long
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
			  unsigned long len, unsigned long pgoff,
			  unsigned long flags)
{
	return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
}
#endif

/*
 * Someone wants to read @bytes from a HWPOISON hugetlb @page from @offset.
 * Returns the maximum number of bytes one can read without touching the 1st raw
 * HWPOISON subpage.
 *
 * The implementation borrows the iteration logic from copy_page_to_iter*.
 */
static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t bytes)
{
	size_t n = 0;
	size_t res = 0;

	/* First subpage to start the loop. */
	page = nth_page(page, offset / PAGE_SIZE);
	offset %= PAGE_SIZE;
	while (1) {
		if (is_raw_hwpoison_page_in_hugepage(page))
			break;

		/* Safe to read n bytes without touching HWPOISON subpage. */
		n = min(bytes, (size_t)PAGE_SIZE - offset);
		res += n;
		bytes -= n;
		if (!bytes || !n)
			break;
		offset += n;
		if (offset == PAGE_SIZE) {
			page = nth_page(page, 1);
			offset = 0;
		}
	}

	return res;
}

/*
 * Support for read() - Find the page attached to f_mapping and copy out the
 * data. This provides functionality similar to filemap_read().
 */
static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct file *file = iocb->ki_filp;
	struct hstate *h = hstate_file(file);
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	unsigned long index = iocb->ki_pos >> huge_page_shift(h);
	unsigned long offset = iocb->ki_pos & ~huge_page_mask(h);
	unsigned long end_index;
	loff_t isize;
	ssize_t retval = 0;

	while (iov_iter_count(to)) {
		struct folio *folio;
		size_t nr, copied, want;

		/* nr is the maximum number of bytes to copy from this page */
		nr = huge_page_size(h);
		isize = i_size_read(inode);
		if (!isize)
			break;
		end_index = (isize - 1) >> huge_page_shift(h);
		if (index > end_index)
			break;
		if (index == end_index) {
			nr = ((isize - 1) & ~huge_page_mask(h)) + 1;
			if (nr <= offset)
				break;
		}
		nr = nr - offset;

		/* Find the folio */
		folio = filemap_lock_hugetlb_folio(h, mapping, index);
		if (IS_ERR(folio)) {
			/*
			 * We have a HOLE, zero out the user-buffer for the
			 * length of the hole or request.
			 */
			copied = iov_iter_zero(nr, to);
		} else {
			folio_unlock(folio);

			if (!folio_test_hwpoison(folio))
				want = nr;
			else {
				/*
				 * Adjust how many bytes safe to read without
				 * touching the 1st raw HWPOISON subpage after
				 * offset.
				 */
				want = adjust_range_hwpoison(&folio->page, offset, nr);
				if (want == 0) {
					folio_put(folio);
					retval = -EIO;
					break;
				}
			}

			/*
			 * We have the folio, copy it to user space buffer.
			 */
			copied = copy_folio_to_iter(folio, offset, want, to);
			folio_put(folio);
		}
		offset += copied;
		retval += copied;
		if (copied != nr && iov_iter_count(to)) {
			if (!retval)
				retval = -EFAULT;
			break;
		}
		index += offset >> huge_page_shift(h);
		offset &= ~huge_page_mask(h);
	}
	iocb->ki_pos = ((loff_t)index << huge_page_shift(h)) + offset;
	return retval;
}

static int hugetlbfs_write_begin(struct file *file,
			struct address_space *mapping,
			loff_t pos, unsigned len,
			struct page **pagep, void **fsdata)
{
	return -EINVAL;
}

static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	BUG();
	return -EINVAL;
}

static void hugetlb_delete_from_page_cache(struct folio *folio)
{
	folio_clear_dirty(folio);
	folio_clear_uptodate(folio);
	filemap_remove_folio(folio);
}

/*
 * Called with i_mmap_rwsem held for inode based vma maps.  This makes
 * sure vma (and vm_mm) will not go away.  We also hold the hugetlb fault
 * mutex for the page in the mapping.  So, we can not race with page being
 * faulted into the vma.
 */
static bool hugetlb_vma_maps_page(struct vm_area_struct *vma,
				unsigned long addr, struct page *page)
{
	pte_t *ptep, pte;

	ptep = hugetlb_walk(vma, addr, huge_page_size(hstate_vma(vma)));
	if (!ptep)
		return false;

	pte = huge_ptep_get(ptep);
	if (huge_pte_none(pte) || !pte_present(pte))
		return false;

	if (pte_page(pte) == page)
		return true;

	return false;
}

/*
 * Can vma_offset_start/vma_offset_end overflow on 32-bit arches?
 * No, because the interval tree returns us only those vmas
 * which overlap the truncated area starting at pgoff,
 * and no vma on a 32-bit arch can span beyond the 4GB.
 */
static unsigned long vma_offset_start(struct vm_area_struct *vma, pgoff_t start)
{
	unsigned long offset = 0;

	if (vma->vm_pgoff < start)
		offset = (start - vma->vm_pgoff) << PAGE_SHIFT;

	return vma->vm_start + offset;
}

static unsigned long vma_offset_end(struct vm_area_struct *vma, pgoff_t end)
{
	unsigned long t_end;

	if (!end)
		return vma->vm_end;

	t_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + vma->vm_start;
	if (t_end > vma->vm_end)
		t_end = vma->vm_end;
	return t_end;
}

/*
 * Called with hugetlb fault mutex held.  Therefore, no more mappings to
 * this folio can be created while executing the routine.
 */
static void hugetlb_unmap_file_folio(struct hstate *h,
					struct address_space *mapping,
					struct folio *folio, pgoff_t index)
{
	struct rb_root_cached *root = &mapping->i_mmap;
	struct hugetlb_vma_lock *vma_lock;
	struct page *page = &folio->page;
	struct vm_area_struct *vma;
	unsigned long v_start;
	unsigned long v_end;
	pgoff_t start, end;

	start = index * pages_per_huge_page(h);
	end = (index + 1) * pages_per_huge_page(h);

	i_mmap_lock_write(mapping);
retry:
	vma_lock = NULL;
	vma_interval_tree_foreach(vma, root, start, end - 1) {
		v_start = vma_offset_start(vma, start);
		v_end = vma_offset_end(vma, end);

		if (!hugetlb_vma_maps_page(vma, v_start, page))
			continue;

		if (!hugetlb_vma_trylock_write(vma)) {
			vma_lock = vma->vm_private_data;
			/*
			 * If we can not get vma lock, we need to drop
			 * immap_sema and take locks in order.  First,
			 * take a ref on the vma_lock structure so that
			 * we can be guaranteed it will not go away when
			 * dropping immap_sema.
			 */
			kref_get(&vma_lock->refs);
			break;
		}

		unmap_hugepage_range(vma, v_start, v_end, NULL,
				     ZAP_FLAG_DROP_MARKER);
		hugetlb_vma_unlock_write(vma);
	}

	i_mmap_unlock_write(mapping);

	if (vma_lock) {
		/*
		 * Wait on vma_lock.  We know it is still valid as we have
		 * a reference.  We must 'open code' vma locking as we do
		 * not know if vma_lock is still attached to vma.
		 */
		down_write(&vma_lock->rw_sema);
		i_mmap_lock_write(mapping);

		vma = vma_lock->vma;
		if (!vma) {
			/*
			 * If lock is no longer attached to vma, then just
			 * unlock, drop our reference and retry looking for
			 * other vmas.
			 */
			up_write(&vma_lock->rw_sema);
			kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
			goto retry;
		}

		/*
		 * vma_lock is still attached to vma.  Check to see if vma
		 * still maps page and if so, unmap.
		 */
		v_start = vma_offset_start(vma, start);
		v_end = vma_offset_end(vma, end);
		if (hugetlb_vma_maps_page(vma, v_start, page))
			unmap_hugepage_range(vma, v_start, v_end, NULL,
					     ZAP_FLAG_DROP_MARKER);

		kref_put(&vma_lock->refs, hugetlb_vma_lock_release);
		hugetlb_vma_unlock_write(vma);

		goto retry;
	}
}

static void
hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end,
		      zap_flags_t zap_flags)
{
	struct vm_area_struct *vma;

	/*
	 * end == 0 indicates that the entire range after start should be
	 * unmapped.  Note, end is exclusive, whereas the interval tree takes
	 * an inclusive "last".
	 */
	vma_interval_tree_foreach(vma, root, start, end ? end - 1 : ULONG_MAX) {
		unsigned long v_start;
		unsigned long v_end;

		if (!hugetlb_vma_trylock_write(vma))
			continue;

		v_start = vma_offset_start(vma, start);
		v_end = vma_offset_end(vma, end);

		unmap_hugepage_range(vma, v_start, v_end, NULL, zap_flags);

		/*
		 * Note that vma lock only exists for shared/non-private
		 * vmas.  Therefore, lock is not held when calling
		 * unmap_hugepage_range for private vmas.
		 */
		hugetlb_vma_unlock_write(vma);
	}
}

/*
 * Called with hugetlb fault mutex held.
 * Returns true if page was actually removed, false otherwise.
 */
static bool remove_inode_single_folio(struct hstate *h, struct inode *inode,
					struct address_space *mapping,
					struct folio *folio, pgoff_t index,
					bool truncate_op)
{
	bool ret = false;

	/*
	 * If folio is mapped, it was faulted in after being
	 * unmapped in caller.  Unmap (again) while holding
	 * the fault mutex.  The mutex will prevent faults
	 * until we finish removing the folio.
	 */
	if (unlikely(folio_mapped(folio)))
		hugetlb_unmap_file_folio(h, mapping, folio, index);

	folio_lock(folio);
	/*
	 * We must remove the folio from page cache before removing
	 * the region/ reserve map (hugetlb_unreserve_pages).  In
	 * rare out of memory conditions, removal of the region/reserve
	 * map could fail.  Correspondingly, the subpool and global
	 * reserve usage count can need to be adjusted.
	 */
	VM_BUG_ON_FOLIO(folio_test_hugetlb_restore_reserve(folio), folio);
	hugetlb_delete_from_page_cache(folio);
	ret = true;
	if (!truncate_op) {
		if (unlikely(hugetlb_unreserve_pages(inode, index,
							index + 1, 1)))
			hugetlb_fix_reserve_counts(inode);
	}

	folio_unlock(folio);
	return ret;
}

/*
 * remove_inode_hugepages handles two distinct cases: truncation and hole
 * punch.  There are subtle differences in operation for each case.
 *
 * truncation is indicated by end of range being LLONG_MAX
 *	In this case, we first scan the range and release found pages.
 *	After releasing pages, hugetlb_unreserve_pages cleans up region/reserve
 *	maps and global counts.  Page faults can race with truncation.
 *	During faults, hugetlb_no_page() checks i_size before page allocation,
 *	and again after obtaining page table lock.  It will 'back out'
 *	allocations in the truncated range.
 * hole punch is indicated if end is not LLONG_MAX
 *	In the hole punch case we scan the range and release found pages.
 *	Only when releasing a page is the associated region/reserve map
 *	deleted.  The region/reserve map for ranges without associated
 *	pages are not modified.  Page faults can race with hole punch.
 *	This is indicated if we find a mapped page.
 * Note: If the passed end of range value is beyond the end of file, but
 * not LLONG_MAX this routine still performs a hole punch operation.
 */
static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
				   loff_t lend)
{
	struct hstate *h = hstate_inode(inode);
	struct address_space *mapping = &inode->i_data;
	const pgoff_t end = lend >> PAGE_SHIFT;
	struct folio_batch fbatch;
	pgoff_t next, index;
	int i, freed = 0;
	bool truncate_op = (lend == LLONG_MAX);

	folio_batch_init(&fbatch);
	next = lstart >> PAGE_SHIFT;
	while (filemap_get_folios(mapping, &next, end - 1, &fbatch)) {
		for (i = 0; i < folio_batch_count(&fbatch); ++i) {
			struct folio *folio = fbatch.folios[i];
			u32 hash = 0;

			index = folio->index >> huge_page_order(h);
			hash = hugetlb_fault_mutex_hash(mapping, index);
			mutex_lock(&hugetlb_fault_mutex_table[hash]);

			/*
			 * Remove folio that was part of folio_batch.
			 */
			if (remove_inode_single_folio(h, inode, mapping, folio,
							index, truncate_op))
				freed++;

			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
		}
		folio_batch_release(&fbatch);
		cond_resched();
	}

	if (truncate_op)
		(void)hugetlb_unreserve_pages(inode,
				lstart >> huge_page_shift(h),
				LONG_MAX, freed);
}

static void hugetlbfs_evict_inode(struct inode *inode)
{
	struct resv_map *resv_map;

	remove_inode_hugepages(inode, 0, LLONG_MAX);

	/*
	 * Get the resv_map from the address space embedded in the inode.
	 * This is the address space which points to any resv_map allocated
	 * at inode creation time.  If this is a device special inode,
	 * i_mapping may not point to the original address space.
	 */
	resv_map = (struct resv_map *)(&inode->i_data)->i_private_data;
	/* Only regular and link inodes have associated reserve maps */
	if (resv_map)
		resv_map_release(&resv_map->refs);
	clear_inode(inode);
}

static void hugetlb_vmtruncate(struct inode *inode, loff_t offset)
{
	pgoff_t pgoff;
	struct address_space *mapping = inode->i_mapping;
	struct hstate *h = hstate_inode(inode);

	BUG_ON(offset & ~huge_page_mask(h));
	pgoff = offset >> PAGE_SHIFT;

	i_size_write(inode, offset);
	i_mmap_lock_write(mapping);
	if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0,
				      ZAP_FLAG_DROP_MARKER);
	i_mmap_unlock_write(mapping);
	remove_inode_hugepages(inode, offset, LLONG_MAX);
}

static void hugetlbfs_zero_partial_page(struct hstate *h,
					struct address_space *mapping,
					loff_t start,
					loff_t end)
{
	pgoff_t idx = start >> huge_page_shift(h);
	struct folio *folio;

	folio = filemap_lock_hugetlb_folio(h, mapping, idx);
	if (IS_ERR(folio))
		return;

	start = start & ~huge_page_mask(h);
	end = end & ~huge_page_mask(h);
	if (!end)
		end = huge_page_size(h);

	folio_zero_segment(folio, (size_t)start, (size_t)end);

	folio_unlock(folio);
	folio_put(folio);
}

static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
	struct address_space *mapping = inode->i_mapping;
	struct hstate *h = hstate_inode(inode);
	loff_t hpage_size = huge_page_size(h);
	loff_t hole_start, hole_end;

	/*
	 * hole_start and hole_end indicate the full pages within the hole.
	 */
	hole_start = round_up(offset, hpage_size);
	hole_end = round_down(offset + len, hpage_size);

	inode_lock(inode);

	/* protected by i_rwsem */
	if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) {
		inode_unlock(inode);
		return -EPERM;
	}

	i_mmap_lock_write(mapping);

	/* If range starts before first full page, zero partial page. */
	if (offset < hole_start)
		hugetlbfs_zero_partial_page(h, mapping,
				offset, min(offset + len, hole_start));

	/* Unmap users of full pages in the hole. */
	if (hole_end > hole_start) {
		if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root))
			hugetlb_vmdelete_list(&mapping->i_mmap,
					      hole_start >> PAGE_SHIFT,
					      hole_end >> PAGE_SHIFT, 0);
	}

	/* If range extends beyond last full page, zero partial page. */
	if ((offset + len) > hole_end && (offset + len) > hole_start)
		hugetlbfs_zero_partial_page(h, mapping,
				hole_end, offset + len);

	i_mmap_unlock_write(mapping);

	/* Remove full pages from the file. */
	if (hole_end > hole_start)
		remove_inode_hugepages(inode, hole_start, hole_end);

	inode_unlock(inode);

	return 0;
}

static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
				loff_t len)
{
	struct inode *inode = file_inode(file);
	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
	struct address_space *mapping = inode->i_mapping;
	struct hstate *h = hstate_inode(inode);
	struct vm_area_struct pseudo_vma;
	struct mm_struct *mm = current->mm;
	loff_t hpage_size = huge_page_size(h);
	unsigned long hpage_shift = huge_page_shift(h);
	pgoff_t start, index, end;
	int error;
	u32 hash;

	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
		return -EOPNOTSUPP;

	if (mode & FALLOC_FL_PUNCH_HOLE)
		return hugetlbfs_punch_hole(inode, offset, len);

	/*
	 * Default preallocate case.
	 * For this range, start is rounded down and end is rounded up
	 * as well as being converted to page offsets.
	 */
	start = offset >> hpage_shift;
	end = (offset + len + hpage_size - 1) >> hpage_shift;

	inode_lock(inode);

	/* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */
	error = inode_newsize_ok(inode, offset + len);
	if (error)
		goto out;

	if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) {
		error = -EPERM;
		goto out;
	}

	/*
	 * Initialize a pseudo vma as this is required by the huge page
	 * allocation routines.
	 */
	vma_init(&pseudo_vma, mm);
	vm_flags_init(&pseudo_vma, VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
	pseudo_vma.vm_file = file;

	for (index = start; index < end; index++) {
		/*
		 * This is supposed to be the vaddr where the page is being
		 * faulted in, but we have no vaddr here.
		 */
		struct folio *folio;
		unsigned long addr;

		cond_resched();

		/*
		 * fallocate(2) manpage permits EINTR; we may have been
		 * interrupted because we are using up too much memory.
		 */
		if (signal_pending(current)) {
			error = -EINTR;
			break;
		}

		/* addr is the offset within the file (zero based) */
		addr = index * hpage_size;

		/* mutex taken here, fault path and hole punch */
		hash = hugetlb_fault_mutex_hash(mapping, index);
		mutex_lock(&hugetlb_fault_mutex_table[hash]);

		/* See if already present in mapping to avoid alloc/free */
		folio = filemap_get_folio(mapping, index << huge_page_order(h));
		if (!IS_ERR(folio)) {
			folio_put(folio);
			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
			continue;
		}

		/*
		 * Allocate folio without setting the avoid_reserve argument.
		 * There certainly are no reserves associated with the
		 * pseudo_vma.  However, there could be shared mappings with
		 * reserves for the file at the inode level.  If we fallocate
		 * folios in these areas, we need to consume the reserves
		 * to keep reservation accounting consistent.
		 */
		folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0);
		if (IS_ERR(folio)) {
			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
			error = PTR_ERR(folio);
			goto out;
		}
		clear_huge_page(&folio->page, addr, pages_per_huge_page(h));
		__folio_mark_uptodate(folio);
		error = hugetlb_add_to_page_cache(folio, mapping, index);
		if (unlikely(error)) {
			restore_reserve_on_error(h, &pseudo_vma, addr, folio);
			folio_put(folio);
			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
			goto out;
		}

		mutex_unlock(&hugetlb_fault_mutex_table[hash]);

		folio_set_hugetlb_migratable(folio);
		/*
		 * folio_unlock because locked by hugetlb_add_to_page_cache()
		 * folio_put() due to reference from alloc_hugetlb_folio()
		 */
		folio_unlock(folio);
		folio_put(folio);
	}

	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
		i_size_write(inode, offset + len);
	inode_set_ctime_current(inode);
out:
	inode_unlock(inode);
	return error;
}

static int hugetlbfs_setattr(struct mnt_idmap *idmap,
			     struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = d_inode(dentry);
	struct hstate *h = hstate_inode(inode);
	int error;
	unsigned int ia_valid = attr->ia_valid;
	struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);

	error = setattr_prepare(&nop_mnt_idmap, dentry, attr);
	if (error)
		return error;

	if (ia_valid & ATTR_SIZE) {
		loff_t oldsize = inode->i_size;
		loff_t newsize = attr->ia_size;

		if (newsize & ~huge_page_mask(h))
			return -EINVAL;
		/* protected by i_rwsem */
		if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
		    (newsize > oldsize && (info->seals & F_SEAL_GROW)))
			return -EPERM;
		hugetlb_vmtruncate(inode, newsize);
	}

	setattr_copy(&nop_mnt_idmap, inode, attr);
	mark_inode_dirty(inode);
	return 0;
}

static struct inode *hugetlbfs_get_root(struct super_block *sb,
					struct hugetlbfs_fs_context *ctx)
{
	struct inode *inode;

	inode = new_inode(sb);
	if (inode) {
		inode->i_ino = get_next_ino();
		inode->i_mode = S_IFDIR | ctx->mode;
		inode->i_uid = ctx->uid;
		inode->i_gid = ctx->gid;
		simple_inode_init_ts(inode);
		inode->i_op = &hugetlbfs_dir_inode_operations;
		inode->i_fop = &simple_dir_operations;
		/* directory inodes start off with i_nlink == 2 (for "." entry) */
		inc_nlink(inode);
		lockdep_annotate_inode_mutex_key(inode);
	}
	return inode;
}

/*
 * Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never
 * be taken from reclaim -- unlike regular filesystems. This needs an
 * annotation because huge_pmd_share() does an allocation under hugetlb's
 * i_mmap_rwsem.
 */
static struct lock_class_key hugetlbfs_i_mmap_rwsem_key;

static struct inode *hugetlbfs_get_inode(struct super_block *sb,
					struct inode *dir,
					umode_t mode, dev_t dev)
{
	struct inode *inode;
	struct resv_map *resv_map = NULL;

	/*
	 * Reserve maps are only needed for inodes that can have associated
	 * page allocations.
	 */
	if (S_ISREG(mode) || S_ISLNK(mode)) {
		resv_map = resv_map_alloc();
		if (!resv_map)
			return NULL;
	}

	inode = new_inode(sb);
	if (inode) {
		struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);

		inode->i_ino = get_next_ino();
		inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
				&hugetlbfs_i_mmap_rwsem_key);
		inode->i_mapping->a_ops = &hugetlbfs_aops;
		simple_inode_init_ts(inode);
		inode->i_mapping->i_private_data = resv_map;
		info->seals = F_SEAL_SEAL;
		switch (mode & S_IFMT) {
		default:
			init_special_inode(inode, mode, dev);
			break;
		case S_IFREG:
			inode->i_op = &hugetlbfs_inode_operations;
			inode->i_fop = &hugetlbfs_file_operations;
			break;
		case S_IFDIR:
			inode->i_op = &hugetlbfs_dir_inode_operations;
			inode->i_fop = &simple_dir_operations;

			/* directory inodes start off with i_nlink == 2 (for "." entry) */
			inc_nlink(inode);
			break;
		case S_IFLNK:
			inode->i_op = &page_symlink_inode_operations;
			inode_nohighmem(inode);
			break;
		}
		lockdep_annotate_inode_mutex_key(inode);
	} else {
		if (resv_map)
			kref_put(&resv_map->refs, resv_map_release);
	}

	return inode;
}

/*
 * File creation. Allocate an inode, and we're done..
 */
static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
			   struct dentry *dentry, umode_t mode, dev_t dev)
{
	struct inode *inode;

	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode, dev);
	if (!inode)
		return -ENOSPC;
	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
	d_instantiate(dentry, inode);
	dget(dentry);/* Extra count - pin the dentry in core */
	return 0;
}

static int hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
			   struct dentry *dentry, umode_t mode)
{
	int retval = hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry,
				     mode | S_IFDIR, 0);
	if (!retval)
		inc_nlink(dir);
	return retval;
}

static int hugetlbfs_create(struct mnt_idmap *idmap,
			    struct inode *dir, struct dentry *dentry,
			    umode_t mode, bool excl)
{
	return hugetlbfs_mknod(&nop_mnt_idmap, dir, dentry, mode | S_IFREG, 0);
}

static int hugetlbfs_tmpfile(struct mnt_idmap *idmap,
			     struct inode *dir, struct file *file,
			     umode_t mode)
{
	struct inode *inode;

	inode = hugetlbfs_get_inode(dir->i_sb, dir, mode | S_IFREG, 0);
	if (!inode)
		return -ENOSPC;
	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
	d_tmpfile(file, inode);
	return finish_open_simple(file, 0);
}

static int hugetlbfs_symlink(struct mnt_idmap *idmap,
			     struct inode *dir, struct dentry *dentry,
			     const char *symname)
{
	struct inode *inode;
	int error = -ENOSPC;

	inode = hugetlbfs_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0);
	if (inode) {
		int l = strlen(symname)+1;
		error = page_symlink(inode, symname, l);
		if (!error) {
			d_instantiate(dentry, inode);
			dget(dentry);
		} else
			iput(inode);
	}
	inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));

	return error;
}

#ifdef CONFIG_MIGRATION
static int hugetlbfs_migrate_folio(struct address_space *mapping,
				struct folio *dst, struct folio *src,
				enum migrate_mode mode)
{
	int rc;

	rc = migrate_huge_page_move_mapping(mapping, dst, src);
	if (rc != MIGRATEPAGE_SUCCESS)
		return rc;

	if (hugetlb_folio_subpool(src)) {
		hugetlb_set_folio_subpool(dst,
					hugetlb_folio_subpool(src));
		hugetlb_set_folio_subpool(src, NULL);
	}

	if (mode != MIGRATE_SYNC_NO_COPY)
		folio_migrate_copy(dst, src);
	else
		folio_migrate_flags(dst, src);

	return MIGRATEPAGE_SUCCESS;
}
#else
#define hugetlbfs_migrate_folio NULL
#endif

static int hugetlbfs_error_remove_folio(struct address_space *mapping,
				struct folio *folio)
{
	return 0;
}

/*
 * Display the mount options in /proc/mounts.
 */
static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root)
{
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb);
	struct hugepage_subpool *spool = sbinfo->spool;
	unsigned long hpage_size = huge_page_size(sbinfo->hstate);
	unsigned hpage_shift = huge_page_shift(sbinfo->hstate);
	char mod;

	if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID))
		seq_printf(m, ",uid=%u",
			   from_kuid_munged(&init_user_ns, sbinfo->uid));
	if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID))
		seq_printf(m, ",gid=%u",
			   from_kgid_munged(&init_user_ns, sbinfo->gid));
	if (sbinfo->mode != 0755)
		seq_printf(m, ",mode=%o", sbinfo->mode);
	if (sbinfo->max_inodes != -1)
		seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes);

	hpage_size /= 1024;
	mod = 'K';
	if (hpage_size >= 1024) {
		hpage_size /= 1024;
		mod = 'M';
	}
	seq_printf(m, ",pagesize=%lu%c", hpage_size, mod);
	if (spool) {
		if (spool->max_hpages != -1)
			seq_printf(m, ",size=%llu",
				   (unsigned long long)spool->max_hpages << hpage_shift);
		if (spool->min_hpages != -1)
			seq_printf(m, ",min_size=%llu",
				   (unsigned long long)spool->min_hpages << hpage_shift);
	}
	return 0;
}

static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
	struct hstate *h = hstate_inode(d_inode(dentry));
	u64 id = huge_encode_dev(dentry->d_sb->s_dev);

	buf->f_fsid = u64_to_fsid(id);
	buf->f_type = HUGETLBFS_MAGIC;
	buf->f_bsize = huge_page_size(h);
	if (sbinfo) {
		spin_lock(&sbinfo->stat_lock);
		/* If no limits set, just report 0 or -1 for max/free/used
		 * blocks, like simple_statfs() */
		if (sbinfo->spool) {
			long free_pages;

			spin_lock_irq(&sbinfo->spool->lock);
			buf->f_blocks = sbinfo->spool->max_hpages;
			free_pages = sbinfo->spool->max_hpages
				- sbinfo->spool->used_hpages;
			buf->f_bavail = buf->f_bfree = free_pages;
			spin_unlock_irq(&sbinfo->spool->lock);
			buf->f_files = sbinfo->max_inodes;
			buf->f_ffree = sbinfo->free_inodes;
		}
		spin_unlock(&sbinfo->stat_lock);
	}
	buf->f_namelen = NAME_MAX;
	return 0;
}

static void hugetlbfs_put_super(struct super_block *sb)
{
	struct hugetlbfs_sb_info *sbi = HUGETLBFS_SB(sb);

	if (sbi) {
		sb->s_fs_info = NULL;

		if (sbi->spool)
			hugepage_put_subpool(sbi->spool);

		kfree(sbi);
	}
}

static inline int hugetlbfs_dec_free_inodes(struct hugetlbfs_sb_info *sbinfo)
{
	if (sbinfo->free_inodes >= 0) {
		spin_lock(&sbinfo->stat_lock);
		if (unlikely(!sbinfo->free_inodes)) {
			spin_unlock(&sbinfo->stat_lock);
			return 0;
		}
		sbinfo->free_inodes--;
		spin_unlock(&sbinfo->stat_lock);
	}

	return 1;
}

static void hugetlbfs_inc_free_inodes(struct hugetlbfs_sb_info *sbinfo)
{
	if (sbinfo->free_inodes >= 0) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_inodes++;
		spin_unlock(&sbinfo->stat_lock);
	}
}


static struct kmem_cache *hugetlbfs_inode_cachep;

static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
{
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb);
	struct hugetlbfs_inode_info *p;

	if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo)))
		return NULL;
	p = alloc_inode_sb(sb, hugetlbfs_inode_cachep, GFP_KERNEL);
	if (unlikely(!p)) {
		hugetlbfs_inc_free_inodes(sbinfo);
		return NULL;
	}
	return &p->vfs_inode;
}

static void hugetlbfs_free_inode(struct inode *inode)
{
	kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
}

static void hugetlbfs_destroy_inode(struct inode *inode)
{
	hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb));
}

static const struct address_space_operations hugetlbfs_aops = {
	.write_begin	= hugetlbfs_write_begin,
	.write_end	= hugetlbfs_write_end,
	.dirty_folio	= noop_dirty_folio,
	.migrate_folio  = hugetlbfs_migrate_folio,
	.error_remove_folio	= hugetlbfs_error_remove_folio,
};


static void init_once(void *foo)
{
	struct hugetlbfs_inode_info *ei = foo;

	inode_init_once(&ei->vfs_inode);
}

const struct file_operations hugetlbfs_file_operations = {
	.read_iter		= hugetlbfs_read_iter,
	.mmap			= hugetlbfs_file_mmap,
	.fsync			= noop_fsync,
	.get_unmapped_area	= hugetlb_get_unmapped_area,
	.llseek			= default_llseek,
	.fallocate		= hugetlbfs_fallocate,
};

static const struct inode_operations hugetlbfs_dir_inode_operations = {
	.create		= hugetlbfs_create,
	.lookup		= simple_lookup,
	.link		= simple_link,
	.unlink		= simple_unlink,
	.symlink	= hugetlbfs_symlink,
	.mkdir		= hugetlbfs_mkdir,
	.rmdir		= simple_rmdir,
	.mknod		= hugetlbfs_mknod,
	.rename		= simple_rename,
	.setattr	= hugetlbfs_setattr,
	.tmpfile	= hugetlbfs_tmpfile,
};

static const struct inode_operations hugetlbfs_inode_operations = {
	.setattr	= hugetlbfs_setattr,
};

static const struct super_operations hugetlbfs_ops = {
	.alloc_inode    = hugetlbfs_alloc_inode,
	.free_inode     = hugetlbfs_free_inode,
	.destroy_inode  = hugetlbfs_destroy_inode,
	.evict_inode	= hugetlbfs_evict_inode,
	.statfs		= hugetlbfs_statfs,
	.put_super	= hugetlbfs_put_super,
	.show_options	= hugetlbfs_show_options,
};

/*
 * Convert size option passed from command line to number of huge pages
 * in the pool specified by hstate.  Size option could be in bytes
 * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT).
 */
static long
hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt,
			 enum hugetlbfs_size_type val_type)
{
	if (val_type == NO_SIZE)
		return -1;

	if (val_type == SIZE_PERCENT) {
		size_opt <<= huge_page_shift(h);
		size_opt *= h->max_huge_pages;
		do_div(size_opt, 100);
	}

	size_opt >>= huge_page_shift(h);
	return size_opt;
}

/*
 * Parse one mount parameter.
 */
static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
{
	struct hugetlbfs_fs_context *ctx = fc->fs_private;
	struct fs_parse_result result;
	struct hstate *h;
	char *rest;
	unsigned long ps;
	int opt;

	opt = fs_parse(fc, hugetlb_fs_parameters, param, &result);
	if (opt < 0)
		return opt;

	switch (opt) {
	case Opt_uid:
		ctx->uid = make_kuid(current_user_ns(), result.uint_32);
		if (!uid_valid(ctx->uid))
			goto bad_val;
		return 0;

	case Opt_gid:
		ctx->gid = make_kgid(current_user_ns(), result.uint_32);
		if (!gid_valid(ctx->gid))
			goto bad_val;
		return 0;

	case Opt_mode:
		ctx->mode = result.uint_32 & 01777U;
		return 0;

	case Opt_size:
		/* memparse() will accept a K/M/G without a digit */
		if (!param->string || !isdigit(param->string[0]))
			goto bad_val;
		ctx->max_size_opt = memparse(param->string, &rest);
		ctx->max_val_type = SIZE_STD;
		if (*rest == '%')
			ctx->max_val_type = SIZE_PERCENT;
		return 0;

	case Opt_nr_inodes:
		/* memparse() will accept a K/M/G without a digit */
		if (!param->string || !isdigit(param->string[0]))
			goto bad_val;
		ctx->nr_inodes = memparse(param->string, &rest);
		return 0;

	case Opt_pagesize:
		ps = memparse(param->string, &rest);
		h = size_to_hstate(ps);
		if (!h) {
			pr_err("Unsupported page size %lu MB\n", ps / SZ_1M);
			return -EINVAL;
		}
		ctx->hstate = h;
		return 0;

	case Opt_min_size:
		/* memparse() will accept a K/M/G without a digit */
		if (!param->string || !isdigit(param->string[0]))
			goto bad_val;
		ctx->min_size_opt = memparse(param->string, &rest);
		ctx->min_val_type = SIZE_STD;
		if (*rest == '%')
			ctx->min_val_type = SIZE_PERCENT;
		return 0;

	default:
		return -EINVAL;
	}

bad_val:
	return invalfc(fc, "Bad value '%s' for mount option '%s'\n",
		      param->string, param->key);
}

/*
 * Validate the parsed options.
 */
static int hugetlbfs_validate(struct fs_context *fc)
{
	struct hugetlbfs_fs_context *ctx = fc->fs_private;

	/*
	 * Use huge page pool size (in hstate) to convert the size
	 * options to number of huge pages.  If NO_SIZE, -1 is returned.
	 */
	ctx->max_hpages = hugetlbfs_size_to_hpages(ctx->hstate,
						   ctx->max_size_opt,
						   ctx->max_val_type);
	ctx->min_hpages = hugetlbfs_size_to_hpages(ctx->hstate,
						   ctx->min_size_opt,
						   ctx->min_val_type);

	/*
	 * If max_size was specified, then min_size must be smaller
	 */
	if (ctx->max_val_type > NO_SIZE &&
	    ctx->min_hpages > ctx->max_hpages) {
		pr_err("Minimum size can not be greater than maximum size\n");
		return -EINVAL;
	}

	return 0;
}

static int
hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
	struct hugetlbfs_fs_context *ctx = fc->fs_private;
	struct hugetlbfs_sb_info *sbinfo;

	sbinfo = kmalloc(sizeof(struct hugetlbfs_sb_info), GFP_KERNEL);
	if (!sbinfo)
		return -ENOMEM;
	sb->s_fs_info = sbinfo;
	spin_lock_init(&sbinfo->stat_lock);
	sbinfo->hstate		= ctx->hstate;
	sbinfo->max_inodes	= ctx->nr_inodes;
	sbinfo->free_inodes	= ctx->nr_inodes;
	sbinfo->spool		= NULL;
	sbinfo->uid		= ctx->uid;
	sbinfo->gid		= ctx->gid;
	sbinfo->mode		= ctx->mode;

	/*
	 * Allocate and initialize subpool if maximum or minimum size is
	 * specified.  Any needed reservations (for minimum size) are taken
	 * when the subpool is created.
	 */
	if (ctx->max_hpages != -1 || ctx->min_hpages != -1) {
		sbinfo->spool = hugepage_new_subpool(ctx->hstate,
						     ctx->max_hpages,
						     ctx->min_hpages);
		if (!sbinfo->spool)
			goto out_free;
	}
	sb->s_maxbytes = MAX_LFS_FILESIZE;
	sb->s_blocksize = huge_page_size(ctx->hstate);
	sb->s_blocksize_bits = huge_page_shift(ctx->hstate);
	sb->s_magic = HUGETLBFS_MAGIC;
	sb->s_op = &hugetlbfs_ops;
	sb->s_time_gran = 1;

	/*
	 * Due to the special and limited functionality of hugetlbfs, it does
	 * not work well as a stacking filesystem.
	 */
	sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
	sb->s_root = d_make_root(hugetlbfs_get_root(sb, ctx));
	if (!sb->s_root)
		goto out_free;
	return 0;
out_free:
	kfree(sbinfo->spool);
	kfree(sbinfo);
	return -ENOMEM;
}

static int hugetlbfs_get_tree(struct fs_context *fc)
{
	int err = hugetlbfs_validate(fc);
	if (err)
		return err;
	return get_tree_nodev(fc, hugetlbfs_fill_super);
}

static void hugetlbfs_fs_context_free(struct fs_context *fc)
{
	kfree(fc->fs_private);
}

static const struct fs_context_operations hugetlbfs_fs_context_ops = {
	.free		= hugetlbfs_fs_context_free,
	.parse_param	= hugetlbfs_parse_param,
	.get_tree	= hugetlbfs_get_tree,
};

static int hugetlbfs_init_fs_context(struct fs_context *fc)
{
	struct hugetlbfs_fs_context *ctx;

	ctx = kzalloc(sizeof(struct hugetlbfs_fs_context), GFP_KERNEL);
	if (!ctx)
		return -ENOMEM;

	ctx->max_hpages	= -1; /* No limit on size by default */
	ctx->nr_inodes	= -1; /* No limit on number of inodes by default */
	ctx->uid	= current_fsuid();
	ctx->gid	= current_fsgid();
	ctx->mode	= 0755;
	ctx->hstate	= &default_hstate;
	ctx->min_hpages	= -1; /* No default minimum size */
	ctx->max_val_type = NO_SIZE;
	ctx->min_val_type = NO_SIZE;
	fc->fs_private = ctx;
	fc->ops	= &hugetlbfs_fs_context_ops;
	return 0;
}

static struct file_system_type hugetlbfs_fs_type = {
	.name			= "hugetlbfs",
	.init_fs_context	= hugetlbfs_init_fs_context,
	.parameters		= hugetlb_fs_parameters,
	.kill_sb		= kill_litter_super,
};

static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];

static int can_do_hugetlb_shm(void)
{
	kgid_t shm_group;
	shm_group = make_kgid(&init_user_ns, sysctl_hugetlb_shm_group);
	return capable(CAP_IPC_LOCK) || in_group_p(shm_group);
}

static int get_hstate_idx(int page_size_log)
{
	struct hstate *h = hstate_sizelog(page_size_log);

	if (!h)
		return -1;
	return hstate_index(h);
}

/*
 * Note that size should be aligned to proper hugepage size in caller side,
 * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
 */
struct file *hugetlb_file_setup(const char *name, size_t size,
				vm_flags_t acctflag, int creat_flags,
				int page_size_log)
{
	struct inode *inode;
	struct vfsmount *mnt;
	int hstate_idx;
	struct file *file;

	hstate_idx = get_hstate_idx(page_size_log);
	if (hstate_idx < 0)
		return ERR_PTR(-ENODEV);

	mnt = hugetlbfs_vfsmount[hstate_idx];
	if (!mnt)
		return ERR_PTR(-ENOENT);

	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
		struct ucounts *ucounts = current_ucounts();

		if (user_shm_lock(size, ucounts)) {
			pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is obsolete\n",
				current->comm, current->pid);
			user_shm_unlock(size, ucounts);
		}
		return ERR_PTR(-EPERM);
	}

	file = ERR_PTR(-ENOSPC);
	inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0);
	if (!inode)
		goto out;
	if (creat_flags == HUGETLB_SHMFS_INODE)
		inode->i_flags |= S_PRIVATE;

	inode->i_size = size;
	clear_nlink(inode);

	if (!hugetlb_reserve_pages(inode, 0,
			size >> huge_page_shift(hstate_inode(inode)), NULL,
			acctflag))
		file = ERR_PTR(-ENOMEM);
	else
		file = alloc_file_pseudo(inode, mnt, name, O_RDWR,
					&hugetlbfs_file_operations);
	if (!IS_ERR(file))
		return file;

	iput(inode);
out:
	return file;
}

static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h)
{
	struct fs_context *fc;
	struct vfsmount *mnt;

	fc = fs_context_for_mount(&hugetlbfs_fs_type, SB_KERNMOUNT);
	if (IS_ERR(fc)) {
		mnt = ERR_CAST(fc);
	} else {
		struct hugetlbfs_fs_context *ctx = fc->fs_private;
		ctx->hstate = h;
		mnt = fc_mount(fc);
		put_fs_context(fc);
	}
	if (IS_ERR(mnt))
		pr_err("Cannot mount internal hugetlbfs for page size %luK",
		       huge_page_size(h) / SZ_1K);
	return mnt;
}

static int __init init_hugetlbfs_fs(void)
{
	struct vfsmount *mnt;
	struct hstate *h;
	int error;
	int i;

	if (!hugepages_supported()) {
		pr_info("disabling because there are no supported hugepage sizes\n");
		return -ENOTSUPP;
	}

	error = -ENOMEM;
	hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
					sizeof(struct hugetlbfs_inode_info),
					0, SLAB_ACCOUNT, init_once);
	if (hugetlbfs_inode_cachep == NULL)
		goto out;

	error = register_filesystem(&hugetlbfs_fs_type);
	if (error)
		goto out_free;

	/* default hstate mount is required */
	mnt = mount_one_hugetlbfs(&default_hstate);
	if (IS_ERR(mnt)) {
		error = PTR_ERR(mnt);
		goto out_unreg;
	}
	hugetlbfs_vfsmount[default_hstate_idx] = mnt;

	/* other hstates are optional */
	i = 0;
	for_each_hstate(h) {
		if (i == default_hstate_idx) {
			i++;
			continue;
		}

		mnt = mount_one_hugetlbfs(h);
		if (IS_ERR(mnt))
			hugetlbfs_vfsmount[i] = NULL;
		else
			hugetlbfs_vfsmount[i] = mnt;
		i++;
	}

	return 0;

 out_unreg:
	(void)unregister_filesystem(&hugetlbfs_fs_type);
 out_free:
	kmem_cache_destroy(hugetlbfs_inode_cachep);
 out:
	return error;
}
fs_initcall(init_hugetlbfs_fs)