aboutsummaryrefslogtreecommitdiff
path: root/fs/dax.c
blob: 906ecbd541a3de074f784a77cdeeef73f49ace0a (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * fs/dax.c - Direct Access filesystem code
 * Copyright (c) 2013-2014 Intel Corporation
 * Author: Matthew Wilcox <matthew.r.wilcox@intel.com>
 * Author: Ross Zwisler <ross.zwisler@linux.intel.com>
 */

#include <linux/atomic.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/highmem.h>
#include <linux/memcontrol.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/pagevec.h>
#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/uio.h>
#include <linux/vmstat.h>
#include <linux/pfn_t.h>
#include <linux/sizes.h>
#include <linux/mmu_notifier.h>
#include <linux/iomap.h>
#include <linux/rmap.h>
#include <asm/pgalloc.h>

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

static inline unsigned int pe_order(enum page_entry_size pe_size)
{
	if (pe_size == PE_SIZE_PTE)
		return PAGE_SHIFT - PAGE_SHIFT;
	if (pe_size == PE_SIZE_PMD)
		return PMD_SHIFT - PAGE_SHIFT;
	if (pe_size == PE_SIZE_PUD)
		return PUD_SHIFT - PAGE_SHIFT;
	return ~0;
}

/* We choose 4096 entries - same as per-zone page wait tables */
#define DAX_WAIT_TABLE_BITS 12
#define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)

/* The 'colour' (ie low bits) within a PMD of a page offset.  */
#define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
#define PG_PMD_NR	(PMD_SIZE >> PAGE_SHIFT)

/* The order of a PMD entry */
#define PMD_ORDER	(PMD_SHIFT - PAGE_SHIFT)

static wait_queue_head_t wait_table[DAX_WAIT_TABLE_ENTRIES];

static int __init init_dax_wait_table(void)
{
	int i;

	for (i = 0; i < DAX_WAIT_TABLE_ENTRIES; i++)
		init_waitqueue_head(wait_table + i);
	return 0;
}
fs_initcall(init_dax_wait_table);

/*
 * DAX pagecache entries use XArray value entries so they can't be mistaken
 * for pages.  We use one bit for locking, one bit for the entry size (PMD)
 * and two more to tell us if the entry is a zero page or an empty entry that
 * is just used for locking.  In total four special bits.
 *
 * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE
 * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem
 * block allocation.
 */
#define DAX_SHIFT	(4)
#define DAX_LOCKED	(1UL << 0)
#define DAX_PMD		(1UL << 1)
#define DAX_ZERO_PAGE	(1UL << 2)
#define DAX_EMPTY	(1UL << 3)

static unsigned long dax_to_pfn(void *entry)
{
	return xa_to_value(entry) >> DAX_SHIFT;
}

static void *dax_make_entry(pfn_t pfn, unsigned long flags)
{
	return xa_mk_value(flags | (pfn_t_to_pfn(pfn) << DAX_SHIFT));
}

static bool dax_is_locked(void *entry)
{
	return xa_to_value(entry) & DAX_LOCKED;
}

static unsigned int dax_entry_order(void *entry)
{
	if (xa_to_value(entry) & DAX_PMD)
		return PMD_ORDER;
	return 0;
}

static unsigned long dax_is_pmd_entry(void *entry)
{
	return xa_to_value(entry) & DAX_PMD;
}

static bool dax_is_pte_entry(void *entry)
{
	return !(xa_to_value(entry) & DAX_PMD);
}

static int dax_is_zero_entry(void *entry)
{
	return xa_to_value(entry) & DAX_ZERO_PAGE;
}

static int dax_is_empty_entry(void *entry)
{
	return xa_to_value(entry) & DAX_EMPTY;
}

/*
 * true if the entry that was found is of a smaller order than the entry
 * we were looking for
 */
static bool dax_is_conflict(void *entry)
{
	return entry == XA_RETRY_ENTRY;
}

/*
 * DAX page cache entry locking
 */
struct exceptional_entry_key {
	struct xarray *xa;
	pgoff_t entry_start;
};

struct wait_exceptional_entry_queue {
	wait_queue_entry_t wait;
	struct exceptional_entry_key key;
};

/**
 * enum dax_wake_mode: waitqueue wakeup behaviour
 * @WAKE_ALL: wake all waiters in the waitqueue
 * @WAKE_NEXT: wake only the first waiter in the waitqueue
 */
enum dax_wake_mode {
	WAKE_ALL,
	WAKE_NEXT,
};

static wait_queue_head_t *dax_entry_waitqueue(struct xa_state *xas,
		void *entry, struct exceptional_entry_key *key)
{
	unsigned long hash;
	unsigned long index = xas->xa_index;

	/*
	 * If 'entry' is a PMD, align the 'index' that we use for the wait
	 * queue to the start of that PMD.  This ensures that all offsets in
	 * the range covered by the PMD map to the same bit lock.
	 */
	if (dax_is_pmd_entry(entry))
		index &= ~PG_PMD_COLOUR;
	key->xa = xas->xa;
	key->entry_start = index;

	hash = hash_long((unsigned long)xas->xa ^ index, DAX_WAIT_TABLE_BITS);
	return wait_table + hash;
}

static int wake_exceptional_entry_func(wait_queue_entry_t *wait,
		unsigned int mode, int sync, void *keyp)
{
	struct exceptional_entry_key *key = keyp;
	struct wait_exceptional_entry_queue *ewait =
		container_of(wait, struct wait_exceptional_entry_queue, wait);

	if (key->xa != ewait->key.xa ||
	    key->entry_start != ewait->key.entry_start)
		return 0;
	return autoremove_wake_function(wait, mode, sync, NULL);
}

/*
 * @entry may no longer be the entry at the index in the mapping.
 * The important information it's conveying is whether the entry at
 * this index used to be a PMD entry.
 */
static void dax_wake_entry(struct xa_state *xas, void *entry,
			   enum dax_wake_mode mode)
{
	struct exceptional_entry_key key;
	wait_queue_head_t *wq;

	wq = dax_entry_waitqueue(xas, entry, &key);

	/*
	 * Checking for locked entry and prepare_to_wait_exclusive() happens
	 * under the i_pages lock, ditto for entry handling in our callers.
	 * So at this point all tasks that could have seen our entry locked
	 * must be in the waitqueue and the following check will see them.
	 */
	if (waitqueue_active(wq))
		__wake_up(wq, TASK_NORMAL, mode == WAKE_ALL ? 0 : 1, &key);
}

/*
 * Look up entry in page cache, wait for it to become unlocked if it
 * is a DAX entry and return it.  The caller must subsequently call
 * put_unlocked_entry() if it did not lock the entry or dax_unlock_entry()
 * if it did.  The entry returned may have a larger order than @order.
 * If @order is larger than the order of the entry found in i_pages, this
 * function returns a dax_is_conflict entry.
 *
 * Must be called with the i_pages lock held.
 */
static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
{
	void *entry;
	struct wait_exceptional_entry_queue ewait;
	wait_queue_head_t *wq;

	init_wait(&ewait.wait);
	ewait.wait.func = wake_exceptional_entry_func;

	for (;;) {
		entry = xas_find_conflict(xas);
		if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
			return entry;
		if (dax_entry_order(entry) < order)
			return XA_RETRY_ENTRY;
		if (!dax_is_locked(entry))
			return entry;

		wq = dax_entry_waitqueue(xas, entry, &ewait.key);
		prepare_to_wait_exclusive(wq, &ewait.wait,
					  TASK_UNINTERRUPTIBLE);
		xas_unlock_irq(xas);
		xas_reset(xas);
		schedule();
		finish_wait(wq, &ewait.wait);
		xas_lock_irq(xas);
	}
}

/*
 * The only thing keeping the address space around is the i_pages lock
 * (it's cycled in clear_inode() after removing the entries from i_pages)
 * After we call xas_unlock_irq(), we cannot touch xas->xa.
 */
static void wait_entry_unlocked(struct xa_state *xas, void *entry)
{
	struct wait_exceptional_entry_queue ewait;
	wait_queue_head_t *wq;

	init_wait(&ewait.wait);
	ewait.wait.func = wake_exceptional_entry_func;

	wq = dax_entry_waitqueue(xas, entry, &ewait.key);
	/*
	 * Unlike get_unlocked_entry() there is no guarantee that this
	 * path ever successfully retrieves an unlocked entry before an
	 * inode dies. Perform a non-exclusive wait in case this path
	 * never successfully performs its own wake up.
	 */
	prepare_to_wait(wq, &ewait.wait, TASK_UNINTERRUPTIBLE);
	xas_unlock_irq(xas);
	schedule();
	finish_wait(wq, &ewait.wait);
}

static void put_unlocked_entry(struct xa_state *xas, void *entry,
			       enum dax_wake_mode mode)
{
	if (entry && !dax_is_conflict(entry))
		dax_wake_entry(xas, entry, mode);
}

/*
 * We used the xa_state to get the entry, but then we locked the entry and
 * dropped the xa_lock, so we know the xa_state is stale and must be reset
 * before use.
 */
static void dax_unlock_entry(struct xa_state *xas, void *entry)
{
	void *old;

	BUG_ON(dax_is_locked(entry));
	xas_reset(xas);
	xas_lock_irq(xas);
	old = xas_store(xas, entry);
	xas_unlock_irq(xas);
	BUG_ON(!dax_is_locked(old));
	dax_wake_entry(xas, entry, WAKE_NEXT);
}

/*
 * Return: The entry stored at this location before it was locked.
 */
static void *dax_lock_entry(struct xa_state *xas, void *entry)
{
	unsigned long v = xa_to_value(entry);
	return xas_store(xas, xa_mk_value(v | DAX_LOCKED));
}

static unsigned long dax_entry_size(void *entry)
{
	if (dax_is_zero_entry(entry))
		return 0;
	else if (dax_is_empty_entry(entry))
		return 0;
	else if (dax_is_pmd_entry(entry))
		return PMD_SIZE;
	else
		return PAGE_SIZE;
}

static unsigned long dax_end_pfn(void *entry)
{
	return dax_to_pfn(entry) + dax_entry_size(entry) / PAGE_SIZE;
}

/*
 * Iterate through all mapped pfns represented by an entry, i.e. skip
 * 'empty' and 'zero' entries.
 */
#define for_each_mapped_pfn(entry, pfn) \
	for (pfn = dax_to_pfn(entry); \
			pfn < dax_end_pfn(entry); pfn++)

static inline bool dax_page_is_shared(struct page *page)
{
	return page->mapping == PAGE_MAPPING_DAX_SHARED;
}

/*
 * Set the page->mapping with PAGE_MAPPING_DAX_SHARED flag, increase the
 * refcount.
 */
static inline void dax_page_share_get(struct page *page)
{
	if (page->mapping != PAGE_MAPPING_DAX_SHARED) {
		/*
		 * Reset the index if the page was already mapped
		 * regularly before.
		 */
		if (page->mapping)
			page->share = 1;
		page->mapping = PAGE_MAPPING_DAX_SHARED;
	}
	page->share++;
}

static inline unsigned long dax_page_share_put(struct page *page)
{
	return --page->share;
}

/*
 * When it is called in dax_insert_entry(), the shared flag will indicate that
 * whether this entry is shared by multiple files.  If so, set the page->mapping
 * PAGE_MAPPING_DAX_SHARED, and use page->share as refcount.
 */
static void dax_associate_entry(void *entry, struct address_space *mapping,
		struct vm_area_struct *vma, unsigned long address, bool shared)
{
	unsigned long size = dax_entry_size(entry), pfn, index;
	int i = 0;

	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
		return;

	index = linear_page_index(vma, address & ~(size - 1));
	for_each_mapped_pfn(entry, pfn) {
		struct page *page = pfn_to_page(pfn);

		if (shared) {
			dax_page_share_get(page);
		} else {
			WARN_ON_ONCE(page->mapping);
			page->mapping = mapping;
			page->index = index + i++;
		}
	}
}

static void dax_disassociate_entry(void *entry, struct address_space *mapping,
		bool trunc)
{
	unsigned long pfn;

	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
		return;

	for_each_mapped_pfn(entry, pfn) {
		struct page *page = pfn_to_page(pfn);

		WARN_ON_ONCE(trunc && page_ref_count(page) > 1);
		if (dax_page_is_shared(page)) {
			/* keep the shared flag if this page is still shared */
			if (dax_page_share_put(page) > 0)
				continue;
		} else
			WARN_ON_ONCE(page->mapping && page->mapping != mapping);
		page->mapping = NULL;
		page->index = 0;
	}
}

static struct page *dax_busy_page(void *entry)
{
	unsigned long pfn;

	for_each_mapped_pfn(entry, pfn) {
		struct page *page = pfn_to_page(pfn);

		if (page_ref_count(page) > 1)
			return page;
	}
	return NULL;
}

/*
 * dax_lock_page - Lock the DAX entry corresponding to a page
 * @page: The page whose entry we want to lock
 *
 * Context: Process context.
 * Return: A cookie to pass to dax_unlock_page() or 0 if the entry could
 * not be locked.
 */
dax_entry_t dax_lock_page(struct page *page)
{
	XA_STATE(xas, NULL, 0);
	void *entry;

	/* Ensure page->mapping isn't freed while we look at it */
	rcu_read_lock();
	for (;;) {
		struct address_space *mapping = READ_ONCE(page->mapping);

		entry = NULL;
		if (!mapping || !dax_mapping(mapping))
			break;

		/*
		 * In the device-dax case there's no need to lock, a
		 * struct dev_pagemap pin is sufficient to keep the
		 * inode alive, and we assume we have dev_pagemap pin
		 * otherwise we would not have a valid pfn_to_page()
		 * translation.
		 */
		entry = (void *)~0UL;
		if (S_ISCHR(mapping->host->i_mode))
			break;

		xas.xa = &mapping->i_pages;
		xas_lock_irq(&xas);
		if (mapping != page->mapping) {
			xas_unlock_irq(&xas);
			continue;
		}
		xas_set(&xas, page->index);
		entry = xas_load(&xas);
		if (dax_is_locked(entry)) {
			rcu_read_unlock();
			wait_entry_unlocked(&xas, entry);
			rcu_read_lock();
			continue;
		}
		dax_lock_entry(&xas, entry);
		xas_unlock_irq(&xas);
		break;
	}
	rcu_read_unlock();
	return (dax_entry_t)entry;
}

void dax_unlock_page(struct page *page, dax_entry_t cookie)
{
	struct address_space *mapping = page->mapping;
	XA_STATE(xas, &mapping->i_pages, page->index);

	if (S_ISCHR(mapping->host->i_mode))
		return;

	dax_unlock_entry(&xas, (void *)cookie);
}

/*
 * dax_lock_mapping_entry - Lock the DAX entry corresponding to a mapping
 * @mapping: the file's mapping whose entry we want to lock
 * @index: the offset within this file
 * @page: output the dax page corresponding to this dax entry
 *
 * Return: A cookie to pass to dax_unlock_mapping_entry() or 0 if the entry
 * could not be locked.
 */
dax_entry_t dax_lock_mapping_entry(struct address_space *mapping, pgoff_t index,
		struct page **page)
{
	XA_STATE(xas, NULL, 0);
	void *entry;

	rcu_read_lock();
	for (;;) {
		entry = NULL;
		if (!dax_mapping(mapping))
			break;

		xas.xa = &mapping->i_pages;
		xas_lock_irq(&xas);
		xas_set(&xas, index);
		entry = xas_load(&xas);
		if (dax_is_locked(entry)) {
			rcu_read_unlock();
			wait_entry_unlocked(&xas, entry);
			rcu_read_lock();
			continue;
		}
		if (!entry ||
		    dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
			/*
			 * Because we are looking for entry from file's mapping
			 * and index, so the entry may not be inserted for now,
			 * or even a zero/empty entry.  We don't think this is
			 * an error case.  So, return a special value and do
			 * not output @page.
			 */
			entry = (void *)~0UL;
		} else {
			*page = pfn_to_page(dax_to_pfn(entry));
			dax_lock_entry(&xas, entry);
		}
		xas_unlock_irq(&xas);
		break;
	}
	rcu_read_unlock();
	return (dax_entry_t)entry;
}

void dax_unlock_mapping_entry(struct address_space *mapping, pgoff_t index,
		dax_entry_t cookie)
{
	XA_STATE(xas, &mapping->i_pages, index);

	if (cookie == ~0UL)
		return;

	dax_unlock_entry(&xas, (void *)cookie);
}

/*
 * Find page cache entry at given index. If it is a DAX entry, return it
 * with the entry locked. If the page cache doesn't contain an entry at
 * that index, add a locked empty entry.
 *
 * When requesting an entry with size DAX_PMD, grab_mapping_entry() will
 * either return that locked entry or will return VM_FAULT_FALLBACK.
 * This will happen if there are any PTE entries within the PMD range
 * that we are requesting.
 *
 * We always favor PTE entries over PMD entries. There isn't a flow where we
 * evict PTE entries in order to 'upgrade' them to a PMD entry.  A PMD
 * insertion will fail if it finds any PTE entries already in the tree, and a
 * PTE insertion will cause an existing PMD entry to be unmapped and
 * downgraded to PTE entries.  This happens for both PMD zero pages as
 * well as PMD empty entries.
 *
 * The exception to this downgrade path is for PMD entries that have
 * real storage backing them.  We will leave these real PMD entries in
 * the tree, and PTE writes will simply dirty the entire PMD entry.
 *
 * Note: Unlike filemap_fault() we don't honor FAULT_FLAG_RETRY flags. For
 * persistent memory the benefit is doubtful. We can add that later if we can
 * show it helps.
 *
 * On error, this function does not return an ERR_PTR.  Instead it returns
 * a VM_FAULT code, encoded as an xarray internal entry.  The ERR_PTR values
 * overlap with xarray value entries.
 */
static void *grab_mapping_entry(struct xa_state *xas,
		struct address_space *mapping, unsigned int order)
{
	unsigned long index = xas->xa_index;
	bool pmd_downgrade;	/* splitting PMD entry into PTE entries? */
	void *entry;

retry:
	pmd_downgrade = false;
	xas_lock_irq(xas);
	entry = get_unlocked_entry(xas, order);

	if (entry) {
		if (dax_is_conflict(entry))
			goto fallback;
		if (!xa_is_value(entry)) {
			xas_set_err(xas, -EIO);
			goto out_unlock;
		}

		if (order == 0) {
			if (dax_is_pmd_entry(entry) &&
			    (dax_is_zero_entry(entry) ||
			     dax_is_empty_entry(entry))) {
				pmd_downgrade = true;
			}
		}
	}

	if (pmd_downgrade) {
		/*
		 * Make sure 'entry' remains valid while we drop
		 * the i_pages lock.
		 */
		dax_lock_entry(xas, entry);

		/*
		 * Besides huge zero pages the only other thing that gets
		 * downgraded are empty entries which don't need to be
		 * unmapped.
		 */
		if (dax_is_zero_entry(entry)) {
			xas_unlock_irq(xas);
			unmap_mapping_pages(mapping,
					xas->xa_index & ~PG_PMD_COLOUR,
					PG_PMD_NR, false);
			xas_reset(xas);
			xas_lock_irq(xas);
		}

		dax_disassociate_entry(entry, mapping, false);
		xas_store(xas, NULL);	/* undo the PMD join */
		dax_wake_entry(xas, entry, WAKE_ALL);
		mapping->nrpages -= PG_PMD_NR;
		entry = NULL;
		xas_set(xas, index);
	}

	if (entry) {
		dax_lock_entry(xas, entry);
	} else {
		unsigned long flags = DAX_EMPTY;

		if (order > 0)
			flags |= DAX_PMD;
		entry = dax_make_entry(pfn_to_pfn_t(0), flags);
		dax_lock_entry(xas, entry);
		if (xas_error(xas))
			goto out_unlock;
		mapping->nrpages += 1UL << order;
	}

out_unlock:
	xas_unlock_irq(xas);
	if (xas_nomem(xas, mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM))
		goto retry;
	if (xas->xa_node == XA_ERROR(-ENOMEM))
		return xa_mk_internal(VM_FAULT_OOM);
	if (xas_error(xas))
		return xa_mk_internal(VM_FAULT_SIGBUS);
	return entry;
fallback:
	xas_unlock_irq(xas);
	return xa_mk_internal(VM_FAULT_FALLBACK);
}

/**
 * dax_layout_busy_page_range - find first pinned page in @mapping
 * @mapping: address space to scan for a page with ref count > 1
 * @start: Starting offset. Page containing 'start' is included.
 * @end: End offset. Page containing 'end' is included. If 'end' is LLONG_MAX,
 *       pages from 'start' till the end of file are included.
 *
 * DAX requires ZONE_DEVICE mapped pages. These pages are never
 * 'onlined' to the page allocator so they are considered idle when
 * page->count == 1. A filesystem uses this interface to determine if
 * any page in the mapping is busy, i.e. for DMA, or other
 * get_user_pages() usages.
 *
 * It is expected that the filesystem is holding locks to block the
 * establishment of new mappings in this address_space. I.e. it expects
 * to be able to run unmap_mapping_range() and subsequently not race
 * mapping_mapped() becoming true.
 */
struct page *dax_layout_busy_page_range(struct address_space *mapping,
					loff_t start, loff_t end)
{
	void *entry;
	unsigned int scanned = 0;
	struct page *page = NULL;
	pgoff_t start_idx = start >> PAGE_SHIFT;
	pgoff_t end_idx;
	XA_STATE(xas, &mapping->i_pages, start_idx);

	/*
	 * In the 'limited' case get_user_pages() for dax is disabled.
	 */
	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
		return NULL;

	if (!dax_mapping(mapping) || !mapping_mapped(mapping))
		return NULL;

	/* If end == LLONG_MAX, all pages from start to till end of file */
	if (end == LLONG_MAX)
		end_idx = ULONG_MAX;
	else
		end_idx = end >> PAGE_SHIFT;
	/*
	 * If we race get_user_pages_fast() here either we'll see the
	 * elevated page count in the iteration and wait, or
	 * get_user_pages_fast() will see that the page it took a reference
	 * against is no longer mapped in the page tables and bail to the
	 * get_user_pages() slow path.  The slow path is protected by
	 * pte_lock() and pmd_lock(). New references are not taken without
	 * holding those locks, and unmap_mapping_pages() will not zero the
	 * pte or pmd without holding the respective lock, so we are
	 * guaranteed to either see new references or prevent new
	 * references from being established.
	 */
	unmap_mapping_pages(mapping, start_idx, end_idx - start_idx + 1, 0);

	xas_lock_irq(&xas);
	xas_for_each(&xas, entry, end_idx) {
		if (WARN_ON_ONCE(!xa_is_value(entry)))
			continue;
		if (unlikely(dax_is_locked(entry)))
			entry = get_unlocked_entry(&xas, 0);
		if (entry)
			page = dax_busy_page(entry);
		put_unlocked_entry(&xas, entry, WAKE_NEXT);
		if (page)
			break;
		if (++scanned % XA_CHECK_SCHED)
			continue;

		xas_pause(&xas);
		xas_unlock_irq(&xas);
		cond_resched();
		xas_lock_irq(&xas);
	}
	xas_unlock_irq(&xas);
	return page;
}
EXPORT_SYMBOL_GPL(dax_layout_busy_page_range);

struct page *dax_layout_busy_page(struct address_space *mapping)
{
	return dax_layout_busy_page_range(mapping, 0, LLONG_MAX);
}
EXPORT_SYMBOL_GPL(dax_layout_busy_page);

static int __dax_invalidate_entry(struct address_space *mapping,
					  pgoff_t index, bool trunc)
{
	XA_STATE(xas, &mapping->i_pages, index);
	int ret = 0;
	void *entry;

	xas_lock_irq(&xas);
	entry = get_unlocked_entry(&xas, 0);
	if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
		goto out;
	if (!trunc &&
	    (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY) ||
	     xas_get_mark(&xas, PAGECACHE_TAG_TOWRITE)))
		goto out;
	dax_disassociate_entry(entry, mapping, trunc);
	xas_store(&xas, NULL);
	mapping->nrpages -= 1UL << dax_entry_order(entry);
	ret = 1;
out:
	put_unlocked_entry(&xas, entry, WAKE_ALL);
	xas_unlock_irq(&xas);
	return ret;
}

static int __dax_clear_dirty_range(struct address_space *mapping,
		pgoff_t start, pgoff_t end)
{
	XA_STATE(xas, &mapping->i_pages, start);
	unsigned int scanned = 0;
	void *entry;

	xas_lock_irq(&xas);
	xas_for_each(&xas, entry, end) {
		entry = get_unlocked_entry(&xas, 0);
		xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
		xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
		put_unlocked_entry(&xas, entry, WAKE_NEXT);

		if (++scanned % XA_CHECK_SCHED)
			continue;

		xas_pause(&xas);
		xas_unlock_irq(&xas);
		cond_resched();
		xas_lock_irq(&xas);
	}
	xas_unlock_irq(&xas);

	return 0;
}

/*
 * Delete DAX entry at @index from @mapping.  Wait for it
 * to be unlocked before deleting it.
 */
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
{
	int ret = __dax_invalidate_entry(mapping, index, true);

	/*
	 * This gets called from truncate / punch_hole path. As such, the caller
	 * must hold locks protecting against concurrent modifications of the
	 * page cache (usually fs-private i_mmap_sem for writing). Since the
	 * caller has seen a DAX entry for this index, we better find it
	 * at that index as well...
	 */
	WARN_ON_ONCE(!ret);
	return ret;
}

/*
 * Invalidate DAX entry if it is clean.
 */
int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
				      pgoff_t index)
{
	return __dax_invalidate_entry(mapping, index, false);
}

static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos)
{
	return PHYS_PFN(iomap->addr + (pos & PAGE_MASK) - iomap->offset);
}

static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter)
{
	pgoff_t pgoff = dax_iomap_pgoff(&iter->iomap, iter->pos);
	void *vto, *kaddr;
	long rc;
	int id;

	id = dax_read_lock();
	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, DAX_ACCESS,
				&kaddr, NULL);
	if (rc < 0) {
		dax_read_unlock(id);
		return rc;
	}
	vto = kmap_atomic(vmf->cow_page);
	copy_user_page(vto, kaddr, vmf->address, vmf->cow_page);
	kunmap_atomic(vto);
	dax_read_unlock(id);
	return 0;
}

/*
 * MAP_SYNC on a dax mapping guarantees dirty metadata is
 * flushed on write-faults (non-cow), but not read-faults.
 */
static bool dax_fault_is_synchronous(const struct iomap_iter *iter,
		struct vm_area_struct *vma)
{
	return (iter->flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC) &&
		(iter->iomap.flags & IOMAP_F_DIRTY);
}

/*
 * By this point grab_mapping_entry() has ensured that we have a locked entry
 * of the appropriate size so we don't have to worry about downgrading PMDs to
 * PTEs.  If we happen to be trying to insert a PTE and there is a PMD
 * already in the tree, we will skip the insertion and just dirty the PMD as
 * appropriate.
 */
static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf,
		const struct iomap_iter *iter, void *entry, pfn_t pfn,
		unsigned long flags)
{
	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
	void *new_entry = dax_make_entry(pfn, flags);
	bool write = iter->flags & IOMAP_WRITE;
	bool dirty = write && !dax_fault_is_synchronous(iter, vmf->vma);
	bool shared = iter->iomap.flags & IOMAP_F_SHARED;

	if (dirty)
		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);

	if (shared || (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE))) {
		unsigned long index = xas->xa_index;
		/* we are replacing a zero page with block mapping */
		if (dax_is_pmd_entry(entry))
			unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR,
					PG_PMD_NR, false);
		else /* pte entry */
			unmap_mapping_pages(mapping, index, 1, false);
	}

	xas_reset(xas);
	xas_lock_irq(xas);
	if (shared || dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
		void *old;

		dax_disassociate_entry(entry, mapping, false);
		dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address,
				shared);
		/*
		 * Only swap our new entry into the page cache if the current
		 * entry is a zero page or an empty entry.  If a normal PTE or
		 * PMD entry is already in the cache, we leave it alone.  This
		 * means that if we are trying to insert a PTE and the
		 * existing entry is a PMD, we will just leave the PMD in the
		 * tree and dirty it if necessary.
		 */
		old = dax_lock_entry(xas, new_entry);
		WARN_ON_ONCE(old != xa_mk_value(xa_to_value(entry) |
					DAX_LOCKED));
		entry = new_entry;
	} else {
		xas_load(xas);	/* Walk the xa_state */
	}

	if (dirty)
		xas_set_mark(xas, PAGECACHE_TAG_DIRTY);

	if (write && shared)
		xas_set_mark(xas, PAGECACHE_TAG_TOWRITE);

	xas_unlock_irq(xas);
	return entry;
}

static int dax_writeback_one(struct xa_state *xas, struct dax_device *dax_dev,
		struct address_space *mapping, void *entry)
{
	unsigned long pfn, index, count, end;
	long ret = 0;
	struct vm_area_struct *vma;

	/*
	 * A page got tagged dirty in DAX mapping? Something is seriously
	 * wrong.
	 */
	if (WARN_ON(!xa_is_value(entry)))
		return -EIO;

	if (unlikely(dax_is_locked(entry))) {
		void *old_entry = entry;

		entry = get_unlocked_entry(xas, 0);

		/* Entry got punched out / reallocated? */
		if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
			goto put_unlocked;
		/*
		 * Entry got reallocated elsewhere? No need to writeback.
		 * We have to compare pfns as we must not bail out due to
		 * difference in lockbit or entry type.
		 */
		if (dax_to_pfn(old_entry) != dax_to_pfn(entry))
			goto put_unlocked;
		if (WARN_ON_ONCE(dax_is_empty_entry(entry) ||
					dax_is_zero_entry(entry))) {
			ret = -EIO;
			goto put_unlocked;
		}

		/* Another fsync thread may have already done this entry */
		if (!xas_get_mark(xas, PAGECACHE_TAG_TOWRITE))
			goto put_unlocked;
	}

	/* Lock the entry to serialize with page faults */
	dax_lock_entry(xas, entry);

	/*
	 * We can clear the tag now but we have to be careful so that concurrent
	 * dax_writeback_one() calls for the same index cannot finish before we
	 * actually flush the caches. This is achieved as the calls will look
	 * at the entry only under the i_pages lock and once they do that
	 * they will see the entry locked and wait for it to unlock.
	 */
	xas_clear_mark(xas, PAGECACHE_TAG_TOWRITE);
	xas_unlock_irq(xas);

	/*
	 * If dax_writeback_mapping_range() was given a wbc->range_start
	 * in the middle of a PMD, the 'index' we use needs to be
	 * aligned to the start of the PMD.
	 * This allows us to flush for PMD_SIZE and not have to worry about
	 * partial PMD writebacks.
	 */
	pfn = dax_to_pfn(entry);
	count = 1UL << dax_entry_order(entry);
	index = xas->xa_index & ~(count - 1);
	end = index + count - 1;

	/* Walk all mappings of a given index of a file and writeprotect them */
	i_mmap_lock_read(mapping);
	vma_interval_tree_foreach(vma, &mapping->i_mmap, index, end) {
		pfn_mkclean_range(pfn, count, index, vma);
		cond_resched();
	}
	i_mmap_unlock_read(mapping);

	dax_flush(dax_dev, page_address(pfn_to_page(pfn)), count * PAGE_SIZE);
	/*
	 * After we have flushed the cache, we can clear the dirty tag. There
	 * cannot be new dirty data in the pfn after the flush has completed as
	 * the pfn mappings are writeprotected and fault waits for mapping
	 * entry lock.
	 */
	xas_reset(xas);
	xas_lock_irq(xas);
	xas_store(xas, entry);
	xas_clear_mark(xas, PAGECACHE_TAG_DIRTY);
	dax_wake_entry(xas, entry, WAKE_NEXT);

	trace_dax_writeback_one(mapping->host, index, count);
	return ret;

 put_unlocked:
	put_unlocked_entry(xas, entry, WAKE_NEXT);
	return ret;
}

/*
 * Flush the mapping to the persistent domain within the byte range of [start,
 * end]. This is required by data integrity operations to ensure file data is
 * on persistent storage prior to completion of the operation.
 */
int dax_writeback_mapping_range(struct address_space *mapping,
		struct dax_device *dax_dev, struct writeback_control *wbc)
{
	XA_STATE(xas, &mapping->i_pages, wbc->range_start >> PAGE_SHIFT);
	struct inode *inode = mapping->host;
	pgoff_t end_index = wbc->range_end >> PAGE_SHIFT;
	void *entry;
	int ret = 0;
	unsigned int scanned = 0;

	if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT))
		return -EIO;

	if (mapping_empty(mapping) || wbc->sync_mode != WB_SYNC_ALL)
		return 0;

	trace_dax_writeback_range(inode, xas.xa_index, end_index);

	tag_pages_for_writeback(mapping, xas.xa_index, end_index);

	xas_lock_irq(&xas);
	xas_for_each_marked(&xas, entry, end_index, PAGECACHE_TAG_TOWRITE) {
		ret = dax_writeback_one(&xas, dax_dev, mapping, entry);
		if (ret < 0) {
			mapping_set_error(mapping, ret);
			break;
		}
		if (++scanned % XA_CHECK_SCHED)
			continue;

		xas_pause(&xas);
		xas_unlock_irq(&xas);
		cond_resched();
		xas_lock_irq(&xas);
	}
	xas_unlock_irq(&xas);
	trace_dax_writeback_range_done(inode, xas.xa_index, end_index);
	return ret;
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);

static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos,
		size_t size, void **kaddr, pfn_t *pfnp)
{
	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
	int id, rc = 0;
	long length;

	id = dax_read_lock();
	length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
				   DAX_ACCESS, kaddr, pfnp);
	if (length < 0) {
		rc = length;
		goto out;
	}
	if (!pfnp)
		goto out_check_addr;
	rc = -EINVAL;
	if (PFN_PHYS(length) < size)
		goto out;
	if (pfn_t_to_pfn(*pfnp) & (PHYS_PFN(size)-1))
		goto out;
	/* For larger pages we need devmap */
	if (length > 1 && !pfn_t_devmap(*pfnp))
		goto out;
	rc = 0;

out_check_addr:
	if (!kaddr)
		goto out;
	if (!*kaddr)
		rc = -EFAULT;
out:
	dax_read_unlock(id);
	return rc;
}

/**
 * dax_iomap_copy_around - Prepare for an unaligned write to a shared/cow page
 * by copying the data before and after the range to be written.
 * @pos:	address to do copy from.
 * @length:	size of copy operation.
 * @align_size:	aligned w.r.t align_size (either PMD_SIZE or PAGE_SIZE)
 * @srcmap:	iomap srcmap
 * @daddr:	destination address to copy to.
 *
 * This can be called from two places. Either during DAX write fault (page
 * aligned), to copy the length size data to daddr. Or, while doing normal DAX
 * write operation, dax_iomap_iter() might call this to do the copy of either
 * start or end unaligned address. In the latter case the rest of the copy of
 * aligned ranges is taken care by dax_iomap_iter() itself.
 * If the srcmap contains invalid data, such as HOLE and UNWRITTEN, zero the
 * area to make sure no old data remains.
 */
static int dax_iomap_copy_around(loff_t pos, uint64_t length, size_t align_size,
		const struct iomap *srcmap, void *daddr)
{
	loff_t head_off = pos & (align_size - 1);
	size_t size = ALIGN(head_off + length, align_size);
	loff_t end = pos + length;
	loff_t pg_end = round_up(end, align_size);
	/* copy_all is usually in page fault case */
	bool copy_all = head_off == 0 && end == pg_end;
	/* zero the edges if srcmap is a HOLE or IOMAP_UNWRITTEN */
	bool zero_edge = srcmap->flags & IOMAP_F_SHARED ||
			 srcmap->type == IOMAP_UNWRITTEN;
	void *saddr = 0;
	int ret = 0;

	if (!zero_edge) {
		ret = dax_iomap_direct_access(srcmap, pos, size, &saddr, NULL);
		if (ret)
			return dax_mem2blk_err(ret);
	}

	if (copy_all) {
		if (zero_edge)
			memset(daddr, 0, size);
		else
			ret = copy_mc_to_kernel(daddr, saddr, length);
		goto out;
	}

	/* Copy the head part of the range */
	if (head_off) {
		if (zero_edge)
			memset(daddr, 0, head_off);
		else {
			ret = copy_mc_to_kernel(daddr, saddr, head_off);
			if (ret)
				return -EIO;
		}
	}

	/* Copy the tail part of the range */
	if (end < pg_end) {
		loff_t tail_off = head_off + length;
		loff_t tail_len = pg_end - end;

		if (zero_edge)
			memset(daddr + tail_off, 0, tail_len);
		else {
			ret = copy_mc_to_kernel(daddr + tail_off,
						saddr + tail_off, tail_len);
			if (ret)
				return -EIO;
		}
	}
out:
	if (zero_edge)
		dax_flush(srcmap->dax_dev, daddr, size);
	return ret ? -EIO : 0;
}

/*
 * The user has performed a load from a hole in the file.  Allocating a new
 * page in the file would cause excessive storage usage for workloads with
 * sparse files.  Instead we insert a read-only mapping of the 4k zero page.
 * If this page is ever written to we will re-fault and change the mapping to
 * point to real DAX storage instead.
 */
static vm_fault_t dax_load_hole(struct xa_state *xas, struct vm_fault *vmf,
		const struct iomap_iter *iter, void **entry)
{
	struct inode *inode = iter->inode;
	unsigned long vaddr = vmf->address;
	pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr));
	vm_fault_t ret;

	*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, DAX_ZERO_PAGE);

	ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
	trace_dax_load_hole(inode, vmf, ret);
	return ret;
}

#ifdef CONFIG_FS_DAX_PMD
static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
		const struct iomap_iter *iter, void **entry)
{
	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
	unsigned long pmd_addr = vmf->address & PMD_MASK;
	struct vm_area_struct *vma = vmf->vma;
	struct inode *inode = mapping->host;
	pgtable_t pgtable = NULL;
	struct page *zero_page;
	spinlock_t *ptl;
	pmd_t pmd_entry;
	pfn_t pfn;

	zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);

	if (unlikely(!zero_page))
		goto fallback;

	pfn = page_to_pfn_t(zero_page);
	*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn,
				  DAX_PMD | DAX_ZERO_PAGE);

	if (arch_needs_pgtable_deposit()) {
		pgtable = pte_alloc_one(vma->vm_mm);
		if (!pgtable)
			return VM_FAULT_OOM;
	}

	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
	if (!pmd_none(*(vmf->pmd))) {
		spin_unlock(ptl);
		goto fallback;
	}

	if (pgtable) {
		pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable);
		mm_inc_nr_ptes(vma->vm_mm);
	}
	pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
	pmd_entry = pmd_mkhuge(pmd_entry);
	set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
	spin_unlock(ptl);
	trace_dax_pmd_load_hole(inode, vmf, zero_page, *entry);
	return VM_FAULT_NOPAGE;

fallback:
	if (pgtable)
		pte_free(vma->vm_mm, pgtable);
	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, *entry);
	return VM_FAULT_FALLBACK;
}
#else
static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
		const struct iomap_iter *iter, void **entry)
{
	return VM_FAULT_FALLBACK;
}
#endif /* CONFIG_FS_DAX_PMD */

static s64 dax_unshare_iter(struct iomap_iter *iter)
{
	struct iomap *iomap = &iter->iomap;
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	loff_t pos = iter->pos;
	loff_t length = iomap_length(iter);
	int id = 0;
	s64 ret = 0;
	void *daddr = NULL, *saddr = NULL;

	/* don't bother with blocks that are not shared to start with */
	if (!(iomap->flags & IOMAP_F_SHARED))
		return length;

	id = dax_read_lock();
	ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL);
	if (ret < 0)
		goto out_unlock;

	/* zero the distance if srcmap is HOLE or UNWRITTEN */
	if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) {
		memset(daddr, 0, length);
		dax_flush(iomap->dax_dev, daddr, length);
		ret = length;
		goto out_unlock;
	}

	ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL);
	if (ret < 0)
		goto out_unlock;

	if (copy_mc_to_kernel(daddr, saddr, length) == 0)
		ret = length;
	else
		ret = -EIO;

out_unlock:
	dax_read_unlock(id);
	return dax_mem2blk_err(ret);
}

int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len,
		const struct iomap_ops *ops)
{
	struct iomap_iter iter = {
		.inode		= inode,
		.pos		= pos,
		.len		= len,
		.flags		= IOMAP_WRITE | IOMAP_UNSHARE | IOMAP_DAX,
	};
	int ret;

	while ((ret = iomap_iter(&iter, ops)) > 0)
		iter.processed = dax_unshare_iter(&iter);
	return ret;
}
EXPORT_SYMBOL_GPL(dax_file_unshare);

static int dax_memzero(struct iomap_iter *iter, loff_t pos, size_t size)
{
	const struct iomap *iomap = &iter->iomap;
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	unsigned offset = offset_in_page(pos);
	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
	void *kaddr;
	long ret;

	ret = dax_direct_access(iomap->dax_dev, pgoff, 1, DAX_ACCESS, &kaddr,
				NULL);
	if (ret < 0)
		return dax_mem2blk_err(ret);

	memset(kaddr + offset, 0, size);
	if (iomap->flags & IOMAP_F_SHARED)
		ret = dax_iomap_copy_around(pos, size, PAGE_SIZE, srcmap,
					    kaddr);
	else
		dax_flush(iomap->dax_dev, kaddr + offset, size);
	return ret;
}

static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero)
{
	const struct iomap *iomap = &iter->iomap;
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	loff_t pos = iter->pos;
	u64 length = iomap_length(iter);
	s64 written = 0;

	/* already zeroed?  we're done. */
	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
		return length;

	/*
	 * invalidate the pages whose sharing state is to be changed
	 * because of CoW.
	 */
	if (iomap->flags & IOMAP_F_SHARED)
		invalidate_inode_pages2_range(iter->inode->i_mapping,
					      pos >> PAGE_SHIFT,
					      (pos + length - 1) >> PAGE_SHIFT);

	do {
		unsigned offset = offset_in_page(pos);
		unsigned size = min_t(u64, PAGE_SIZE - offset, length);
		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
		long rc;
		int id;

		id = dax_read_lock();
		if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
			rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
		else
			rc = dax_memzero(iter, pos, size);
		dax_read_unlock(id);

		if (rc < 0)
			return rc;
		pos += size;
		length -= size;
		written += size;
	} while (length > 0);

	if (did_zero)
		*did_zero = true;
	return written;
}

int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
		const struct iomap_ops *ops)
{
	struct iomap_iter iter = {
		.inode		= inode,
		.pos		= pos,
		.len		= len,
		.flags		= IOMAP_DAX | IOMAP_ZERO,
	};
	int ret;

	while ((ret = iomap_iter(&iter, ops)) > 0)
		iter.processed = dax_zero_iter(&iter, did_zero);
	return ret;
}
EXPORT_SYMBOL_GPL(dax_zero_range);

int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
		const struct iomap_ops *ops)
{
	unsigned int blocksize = i_blocksize(inode);
	unsigned int off = pos & (blocksize - 1);

	/* Block boundary? Nothing to do */
	if (!off)
		return 0;
	return dax_zero_range(inode, pos, blocksize - off, did_zero, ops);
}
EXPORT_SYMBOL_GPL(dax_truncate_page);

static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
		struct iov_iter *iter)
{
	const struct iomap *iomap = &iomi->iomap;
	const struct iomap *srcmap = iomap_iter_srcmap(iomi);
	loff_t length = iomap_length(iomi);
	loff_t pos = iomi->pos;
	struct dax_device *dax_dev = iomap->dax_dev;
	loff_t end = pos + length, done = 0;
	bool write = iov_iter_rw(iter) == WRITE;
	bool cow = write && iomap->flags & IOMAP_F_SHARED;
	ssize_t ret = 0;
	size_t xfer;
	int id;

	if (!write) {
		end = min(end, i_size_read(iomi->inode));
		if (pos >= end)
			return 0;

		if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN)
			return iov_iter_zero(min(length, end - pos), iter);
	}

	/*
	 * In DAX mode, enforce either pure overwrites of written extents, or
	 * writes to unwritten extents as part of a copy-on-write operation.
	 */
	if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED &&
			!(iomap->flags & IOMAP_F_SHARED)))
		return -EIO;

	/*
	 * Write can allocate block for an area which has a hole page mapped
	 * into page tables. We have to tear down these mappings so that data
	 * written by write(2) is visible in mmap.
	 */
	if (iomap->flags & IOMAP_F_NEW || cow) {
		/*
		 * Filesystem allows CoW on non-shared extents. The src extents
		 * may have been mmapped with dirty mark before. To be able to
		 * invalidate its dax entries, we need to clear the dirty mark
		 * in advance.
		 */
		if (cow)
			__dax_clear_dirty_range(iomi->inode->i_mapping,
						pos >> PAGE_SHIFT,
						(end - 1) >> PAGE_SHIFT);
		invalidate_inode_pages2_range(iomi->inode->i_mapping,
					      pos >> PAGE_SHIFT,
					      (end - 1) >> PAGE_SHIFT);
	}

	id = dax_read_lock();
	while (pos < end) {
		unsigned offset = pos & (PAGE_SIZE - 1);
		const size_t size = ALIGN(length + offset, PAGE_SIZE);
		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
		ssize_t map_len;
		bool recovery = false;
		void *kaddr;

		if (fatal_signal_pending(current)) {
			ret = -EINTR;
			break;
		}

		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
				DAX_ACCESS, &kaddr, NULL);
		if (map_len == -EHWPOISON && iov_iter_rw(iter) == WRITE) {
			map_len = dax_direct_access(dax_dev, pgoff,
					PHYS_PFN(size), DAX_RECOVERY_WRITE,
					&kaddr, NULL);
			if (map_len > 0)
				recovery = true;
		}
		if (map_len < 0) {
			ret = dax_mem2blk_err(map_len);
			break;
		}

		if (cow) {
			ret = dax_iomap_copy_around(pos, length, PAGE_SIZE,
						    srcmap, kaddr);
			if (ret)
				break;
		}

		map_len = PFN_PHYS(map_len);
		kaddr += offset;
		map_len -= offset;
		if (map_len > end - pos)
			map_len = end - pos;

		if (recovery)
			xfer = dax_recovery_write(dax_dev, pgoff, kaddr,
					map_len, iter);
		else if (write)
			xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
					map_len, iter);
		else
			xfer = dax_copy_to_iter(dax_dev, pgoff, kaddr,
					map_len, iter);

		pos += xfer;
		length -= xfer;
		done += xfer;

		if (xfer == 0)
			ret = -EFAULT;
		if (xfer < map_len)
			break;
	}
	dax_read_unlock(id);

	return done ? done : ret;
}

/**
 * dax_iomap_rw - Perform I/O to a DAX file
 * @iocb:	The control block for this I/O
 * @iter:	The addresses to do I/O from or to
 * @ops:	iomap ops passed from the file system
 *
 * This function performs read and write operations to directly mapped
 * persistent memory.  The callers needs to take care of read/write exclusion
 * and evicting any page cache pages in the region under I/O.
 */
ssize_t
dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
		const struct iomap_ops *ops)
{
	struct iomap_iter iomi = {
		.inode		= iocb->ki_filp->f_mapping->host,
		.pos		= iocb->ki_pos,
		.len		= iov_iter_count(iter),
		.flags		= IOMAP_DAX,
	};
	loff_t done = 0;
	int ret;

	if (!iomi.len)
		return 0;

	if (iov_iter_rw(iter) == WRITE) {
		lockdep_assert_held_write(&iomi.inode->i_rwsem);
		iomi.flags |= IOMAP_WRITE;
	} else {
		lockdep_assert_held(&iomi.inode->i_rwsem);
	}

	if (iocb->ki_flags & IOCB_NOWAIT)
		iomi.flags |= IOMAP_NOWAIT;

	while ((ret = iomap_iter(&iomi, ops)) > 0)
		iomi.processed = dax_iomap_iter(&iomi, iter);

	done = iomi.pos - iocb->ki_pos;
	iocb->ki_pos = iomi.pos;
	return done ? done : ret;
}
EXPORT_SYMBOL_GPL(dax_iomap_rw);

static vm_fault_t dax_fault_return(int error)
{
	if (error == 0)
		return VM_FAULT_NOPAGE;
	return vmf_error(error);
}

/*
 * When handling a synchronous page fault and the inode need a fsync, we can
 * insert the PTE/PMD into page tables only after that fsync happened. Skip
 * insertion for now and return the pfn so that caller can insert it after the
 * fsync is done.
 */
static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn)
{
	if (WARN_ON_ONCE(!pfnp))
		return VM_FAULT_SIGBUS;
	*pfnp = pfn;
	return VM_FAULT_NEEDDSYNC;
}

static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf,
		const struct iomap_iter *iter)
{
	vm_fault_t ret;
	int error = 0;

	switch (iter->iomap.type) {
	case IOMAP_HOLE:
	case IOMAP_UNWRITTEN:
		clear_user_highpage(vmf->cow_page, vmf->address);
		break;
	case IOMAP_MAPPED:
		error = copy_cow_page_dax(vmf, iter);
		break;
	default:
		WARN_ON_ONCE(1);
		error = -EIO;
		break;
	}

	if (error)
		return dax_fault_return(error);

	__SetPageUptodate(vmf->cow_page);
	ret = finish_fault(vmf);
	if (!ret)
		return VM_FAULT_DONE_COW;
	return ret;
}

/**
 * dax_fault_iter - Common actor to handle pfn insertion in PTE/PMD fault.
 * @vmf:	vm fault instance
 * @iter:	iomap iter
 * @pfnp:	pfn to be returned
 * @xas:	the dax mapping tree of a file
 * @entry:	an unlocked dax entry to be inserted
 * @pmd:	distinguish whether it is a pmd fault
 */
static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
		const struct iomap_iter *iter, pfn_t *pfnp,
		struct xa_state *xas, void **entry, bool pmd)
{
	const struct iomap *iomap = &iter->iomap;
	const struct iomap *srcmap = iomap_iter_srcmap(iter);
	size_t size = pmd ? PMD_SIZE : PAGE_SIZE;
	loff_t pos = (loff_t)xas->xa_index << PAGE_SHIFT;
	bool write = iter->flags & IOMAP_WRITE;
	unsigned long entry_flags = pmd ? DAX_PMD : 0;
	int err = 0;
	pfn_t pfn;
	void *kaddr;

	if (!pmd && vmf->cow_page)
		return dax_fault_cow_page(vmf, iter);

	/* if we are reading UNWRITTEN and HOLE, return a hole. */
	if (!write &&
	    (iomap->type == IOMAP_UNWRITTEN || iomap->type == IOMAP_HOLE)) {
		if (!pmd)
			return dax_load_hole(xas, vmf, iter, entry);
		return dax_pmd_load_hole(xas, vmf, iter, entry);
	}

	if (iomap->type != IOMAP_MAPPED && !(iomap->flags & IOMAP_F_SHARED)) {
		WARN_ON_ONCE(1);
		return pmd ? VM_FAULT_FALLBACK : VM_FAULT_SIGBUS;
	}

	err = dax_iomap_direct_access(iomap, pos, size, &kaddr, &pfn);
	if (err)
		return pmd ? VM_FAULT_FALLBACK : dax_fault_return(err);

	*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, entry_flags);

	if (write && iomap->flags & IOMAP_F_SHARED) {
		err = dax_iomap_copy_around(pos, size, size, srcmap, kaddr);
		if (err)
			return dax_fault_return(err);
	}

	if (dax_fault_is_synchronous(iter, vmf->vma))
		return dax_fault_synchronous_pfnp(pfnp, pfn);

	/* insert PMD pfn */
	if (pmd)
		return vmf_insert_pfn_pmd(vmf, pfn, write);

	/* insert PTE pfn */
	if (write)
		return vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
	return vmf_insert_mixed(vmf->vma, vmf->address, pfn);
}

static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
			       int *iomap_errp, const struct iomap_ops *ops)
{
	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
	XA_STATE(xas, &mapping->i_pages, vmf->pgoff);
	struct iomap_iter iter = {
		.inode		= mapping->host,
		.pos		= (loff_t)vmf->pgoff << PAGE_SHIFT,
		.len		= PAGE_SIZE,
		.flags		= IOMAP_DAX | IOMAP_FAULT,
	};
	vm_fault_t ret = 0;
	void *entry;
	int error;

	trace_dax_pte_fault(iter.inode, vmf, ret);
	/*
	 * Check whether offset isn't beyond end of file now. Caller is supposed
	 * to hold locks serializing us with truncate / punch hole so this is
	 * a reliable test.
	 */
	if (iter.pos >= i_size_read(iter.inode)) {
		ret = VM_FAULT_SIGBUS;
		goto out;
	}

	if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
		iter.flags |= IOMAP_WRITE;

	entry = grab_mapping_entry(&xas, mapping, 0);
	if (xa_is_internal(entry)) {
		ret = xa_to_internal(entry);
		goto out;
	}

	/*
	 * It is possible, particularly with mixed reads & writes to private
	 * mappings, that we have raced with a PMD fault that overlaps with
	 * the PTE we need to set up.  If so just return and the fault will be
	 * retried.
	 */
	if (pmd_trans_huge(*vmf->pmd) || pmd_devmap(*vmf->pmd)) {
		ret = VM_FAULT_NOPAGE;
		goto unlock_entry;
	}

	while ((error = iomap_iter(&iter, ops)) > 0) {
		if (WARN_ON_ONCE(iomap_length(&iter) < PAGE_SIZE)) {
			iter.processed = -EIO;	/* fs corruption? */
			continue;
		}

		ret = dax_fault_iter(vmf, &iter, pfnp, &xas, &entry, false);
		if (ret != VM_FAULT_SIGBUS &&
		    (iter.iomap.flags & IOMAP_F_NEW)) {
			count_vm_event(PGMAJFAULT);
			count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
			ret |= VM_FAULT_MAJOR;
		}

		if (!(ret & VM_FAULT_ERROR))
			iter.processed = PAGE_SIZE;
	}

	if (iomap_errp)
		*iomap_errp = error;
	if (!ret && error)
		ret = dax_fault_return(error);

unlock_entry:
	dax_unlock_entry(&xas, entry);
out:
	trace_dax_pte_fault_done(iter.inode, vmf, ret);
	return ret;
}

#ifdef CONFIG_FS_DAX_PMD
static bool dax_fault_check_fallback(struct vm_fault *vmf, struct xa_state *xas,
		pgoff_t max_pgoff)
{
	unsigned long pmd_addr = vmf->address & PMD_MASK;
	bool write = vmf->flags & FAULT_FLAG_WRITE;

	/*
	 * Make sure that the faulting address's PMD offset (color) matches
	 * the PMD offset from the start of the file.  This is necessary so
	 * that a PMD range in the page table overlaps exactly with a PMD
	 * range in the page cache.
	 */
	if ((vmf->pgoff & PG_PMD_COLOUR) !=
	    ((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR))
		return true;

	/* Fall back to PTEs if we're going to COW */
	if (write && !(vmf->vma->vm_flags & VM_SHARED))
		return true;

	/* If the PMD would extend outside the VMA */
	if (pmd_addr < vmf->vma->vm_start)
		return true;
	if ((pmd_addr + PMD_SIZE) > vmf->vma->vm_end)
		return true;

	/* If the PMD would extend beyond the file size */
	if ((xas->xa_index | PG_PMD_COLOUR) >= max_pgoff)
		return true;

	return false;
}

static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
			       const struct iomap_ops *ops)
{
	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
	XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, PMD_ORDER);
	struct iomap_iter iter = {
		.inode		= mapping->host,
		.len		= PMD_SIZE,
		.flags		= IOMAP_DAX | IOMAP_FAULT,
	};
	vm_fault_t ret = VM_FAULT_FALLBACK;
	pgoff_t max_pgoff;
	void *entry;

	if (vmf->flags & FAULT_FLAG_WRITE)
		iter.flags |= IOMAP_WRITE;

	/*
	 * Check whether offset isn't beyond end of file now. Caller is
	 * supposed to hold locks serializing us with truncate / punch hole so
	 * this is a reliable test.
	 */
	max_pgoff = DIV_ROUND_UP(i_size_read(iter.inode), PAGE_SIZE);

	trace_dax_pmd_fault(iter.inode, vmf, max_pgoff, 0);

	if (xas.xa_index >= max_pgoff) {
		ret = VM_FAULT_SIGBUS;
		goto out;
	}

	if (dax_fault_check_fallback(vmf, &xas, max_pgoff))
		goto fallback;

	/*
	 * grab_mapping_entry() will make sure we get an empty PMD entry,
	 * a zero PMD entry or a DAX PMD.  If it can't (because a PTE
	 * entry is already in the array, for instance), it will return
	 * VM_FAULT_FALLBACK.
	 */
	entry = grab_mapping_entry(&xas, mapping, PMD_ORDER);
	if (xa_is_internal(entry)) {
		ret = xa_to_internal(entry);
		goto fallback;
	}

	/*
	 * It is possible, particularly with mixed reads & writes to private
	 * mappings, that we have raced with a PTE fault that overlaps with
	 * the PMD we need to set up.  If so just return and the fault will be
	 * retried.
	 */
	if (!pmd_none(*vmf->pmd) && !pmd_trans_huge(*vmf->pmd) &&
			!pmd_devmap(*vmf->pmd)) {
		ret = 0;
		goto unlock_entry;
	}

	iter.pos = (loff_t)xas.xa_index << PAGE_SHIFT;
	while (iomap_iter(&iter, ops) > 0) {
		if (iomap_length(&iter) < PMD_SIZE)
			continue; /* actually breaks out of the loop */

		ret = dax_fault_iter(vmf, &iter, pfnp, &xas, &entry, true);
		if (ret != VM_FAULT_FALLBACK)
			iter.processed = PMD_SIZE;
	}

unlock_entry:
	dax_unlock_entry(&xas, entry);
fallback:
	if (ret == VM_FAULT_FALLBACK) {
		split_huge_pmd(vmf->vma, vmf->pmd, vmf->address);
		count_vm_event(THP_FAULT_FALLBACK);
	}
out:
	trace_dax_pmd_fault_done(iter.inode, vmf, max_pgoff, ret);
	return ret;
}
#else
static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
			       const struct iomap_ops *ops)
{
	return VM_FAULT_FALLBACK;
}
#endif /* CONFIG_FS_DAX_PMD */

/**
 * dax_iomap_fault - handle a page fault on a DAX file
 * @vmf: The description of the fault
 * @pe_size: Size of the page to fault in
 * @pfnp: PFN to insert for synchronous faults if fsync is required
 * @iomap_errp: Storage for detailed error code in case of error
 * @ops: Iomap ops passed from the file system
 *
 * When a page fault occurs, filesystems may call this helper in
 * their fault handler for DAX files. dax_iomap_fault() assumes the caller
 * has done all the necessary locking for page fault to proceed
 * successfully.
 */
vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
		    pfn_t *pfnp, int *iomap_errp, const struct iomap_ops *ops)
{
	switch (pe_size) {
	case PE_SIZE_PTE:
		return dax_iomap_pte_fault(vmf, pfnp, iomap_errp, ops);
	case PE_SIZE_PMD:
		return dax_iomap_pmd_fault(vmf, pfnp, ops);
	default:
		return VM_FAULT_FALLBACK;
	}
}
EXPORT_SYMBOL_GPL(dax_iomap_fault);

/*
 * dax_insert_pfn_mkwrite - insert PTE or PMD entry into page tables
 * @vmf: The description of the fault
 * @pfn: PFN to insert
 * @order: Order of entry to insert.
 *
 * This function inserts a writeable PTE or PMD entry into the page tables
 * for an mmaped DAX file.  It also marks the page cache entry as dirty.
 */
static vm_fault_t
dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
{
	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
	XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, order);
	void *entry;
	vm_fault_t ret;

	xas_lock_irq(&xas);
	entry = get_unlocked_entry(&xas, order);
	/* Did we race with someone splitting entry or so? */
	if (!entry || dax_is_conflict(entry) ||
	    (order == 0 && !dax_is_pte_entry(entry))) {
		put_unlocked_entry(&xas, entry, WAKE_NEXT);
		xas_unlock_irq(&xas);
		trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf,
						      VM_FAULT_NOPAGE);
		return VM_FAULT_NOPAGE;
	}
	xas_set_mark(&xas, PAGECACHE_TAG_DIRTY);
	dax_lock_entry(&xas, entry);
	xas_unlock_irq(&xas);
	if (order == 0)
		ret = vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
#ifdef CONFIG_FS_DAX_PMD
	else if (order == PMD_ORDER)
		ret = vmf_insert_pfn_pmd(vmf, pfn, FAULT_FLAG_WRITE);
#endif
	else
		ret = VM_FAULT_FALLBACK;
	dax_unlock_entry(&xas, entry);
	trace_dax_insert_pfn_mkwrite(mapping->host, vmf, ret);
	return ret;
}

/**
 * dax_finish_sync_fault - finish synchronous page fault
 * @vmf: The description of the fault
 * @pe_size: Size of entry to be inserted
 * @pfn: PFN to insert
 *
 * This function ensures that the file range touched by the page fault is
 * stored persistently on the media and handles inserting of appropriate page
 * table entry.
 */
vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
		enum page_entry_size pe_size, pfn_t pfn)
{
	int err;
	loff_t start = ((loff_t)vmf->pgoff) << PAGE_SHIFT;
	unsigned int order = pe_order(pe_size);
	size_t len = PAGE_SIZE << order;

	err = vfs_fsync_range(vmf->vma->vm_file, start, start + len - 1, 1);
	if (err)
		return VM_FAULT_SIGBUS;
	return dax_insert_pfn_mkwrite(vmf, pfn, order);
}
EXPORT_SYMBOL_GPL(dax_finish_sync_fault);

static loff_t dax_range_compare_iter(struct iomap_iter *it_src,
		struct iomap_iter *it_dest, u64 len, bool *same)
{
	const struct iomap *smap = &it_src->iomap;
	const struct iomap *dmap = &it_dest->iomap;
	loff_t pos1 = it_src->pos, pos2 = it_dest->pos;
	void *saddr, *daddr;
	int id, ret;

	len = min(len, min(smap->length, dmap->length));

	if (smap->type == IOMAP_HOLE && dmap->type == IOMAP_HOLE) {
		*same = true;
		return len;
	}

	if (smap->type == IOMAP_HOLE || dmap->type == IOMAP_HOLE) {
		*same = false;
		return 0;
	}

	id = dax_read_lock();
	ret = dax_iomap_direct_access(smap, pos1, ALIGN(pos1 + len, PAGE_SIZE),
				      &saddr, NULL);
	if (ret < 0)
		goto out_unlock;

	ret = dax_iomap_direct_access(dmap, pos2, ALIGN(pos2 + len, PAGE_SIZE),
				      &daddr, NULL);
	if (ret < 0)
		goto out_unlock;

	*same = !memcmp(saddr, daddr, len);
	if (!*same)
		len = 0;
	dax_read_unlock(id);
	return len;

out_unlock:
	dax_read_unlock(id);
	return -EIO;
}

int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
		struct inode *dst, loff_t dstoff, loff_t len, bool *same,
		const struct iomap_ops *ops)
{
	struct iomap_iter src_iter = {
		.inode		= src,
		.pos		= srcoff,
		.len		= len,
		.flags		= IOMAP_DAX,
	};
	struct iomap_iter dst_iter = {
		.inode		= dst,
		.pos		= dstoff,
		.len		= len,
		.flags		= IOMAP_DAX,
	};
	int ret, compared = 0;

	while ((ret = iomap_iter(&src_iter, ops)) > 0 &&
	       (ret = iomap_iter(&dst_iter, ops)) > 0) {
		compared = dax_range_compare_iter(&src_iter, &dst_iter,
				min(src_iter.len, dst_iter.len), same);
		if (compared < 0)
			return ret;
		src_iter.processed = dst_iter.processed = compared;
	}
	return ret;
}

int dax_remap_file_range_prep(struct file *file_in, loff_t pos_in,
			      struct file *file_out, loff_t pos_out,
			      loff_t *len, unsigned int remap_flags,
			      const struct iomap_ops *ops)
{
	return __generic_remap_file_range_prep(file_in, pos_in, file_out,
					       pos_out, len, remap_flags, ops);
}
EXPORT_SYMBOL_GPL(dax_remap_file_range_prep);