Home Home > GIT Browse > SLE15-AZURE
summaryrefslogtreecommitdiff
path: root/fs/dax.c
blob: 37bb4e047a357058a532a414424ff4606aa42de2 (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
/*
 * 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>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 */

#include <linux/atomic.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>
#include <linux/dax.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/highmem.h>
#include <linux/memcontrol.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/pagevec.h>
#include <linux/pmem.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 <asm/pgalloc.h>
#include "internal.h"

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

/* 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)

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);

static int dax_is_pmd_entry(void *entry)
{
	return (unsigned long)entry & RADIX_DAX_PMD;
}

static int dax_is_pte_entry(void *entry)
{
	return !((unsigned long)entry & RADIX_DAX_PMD);
}

static int dax_is_zero_entry(void *entry)
{
	return (unsigned long)entry & RADIX_DAX_ZERO_PAGE;
}

static int dax_is_empty_entry(void *entry)
{
	return (unsigned long)entry & RADIX_DAX_EMPTY;
}

/*
 * DAX radix tree locking
 */
struct exceptional_entry_key {
	struct address_space *mapping;
	pgoff_t entry_start;
};

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

static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
		pgoff_t index, void *entry, struct exceptional_entry_key *key)
{
	unsigned long hash;

	/*
	 * 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->mapping = mapping;
	key->entry_start = index;

	hash = hash_long((unsigned long)mapping ^ 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->mapping != ewait->key.mapping ||
	    key->entry_start != ewait->key.entry_start)
		return 0;
	return autoremove_wake_function(wait, mode, sync, NULL);
}

/*
 * We do not necessarily hold the mapping->tree_lock when we call this
 * function so it is possible that 'entry' is no longer a valid item in the
 * radix tree.  This is okay because all we really need to do is to find the
 * correct waitqueue where tasks might be waiting for that old 'entry' and
 * wake them.
 */
static void dax_wake_mapping_entry_waiter(struct address_space *mapping,
		pgoff_t index, void *entry, bool wake_all)
{
	struct exceptional_entry_key key;
	wait_queue_head_t *wq;

	wq = dax_entry_waitqueue(mapping, index, entry, &key);

	/*
	 * Checking for locked entry and prepare_to_wait_exclusive() happens
	 * under mapping->tree_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, wake_all ? 0 : 1, &key);
}

/*
 * Check whether the given slot is locked. The function must be called with
 * mapping->tree_lock held
 */
static inline int slot_locked(struct address_space *mapping, void **slot)
{
	unsigned long entry = (unsigned long)
		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);
	return entry & RADIX_DAX_ENTRY_LOCK;
}

/*
 * Mark the given slot is locked. The function must be called with
 * mapping->tree_lock held
 */
static inline void *lock_slot(struct address_space *mapping, void **slot)
{
	unsigned long entry = (unsigned long)
		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);

	entry |= RADIX_DAX_ENTRY_LOCK;
	radix_tree_replace_slot(&mapping->page_tree, slot, (void *)entry);
	return (void *)entry;
}

/*
 * Mark the given slot is unlocked. The function must be called with
 * mapping->tree_lock held
 */
static inline void *unlock_slot(struct address_space *mapping, void **slot)
{
	unsigned long entry = (unsigned long)
		radix_tree_deref_slot_protected(slot, &mapping->tree_lock);

	entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK;
	radix_tree_replace_slot(&mapping->page_tree, slot, (void *)entry);
	return (void *)entry;
}

/*
 * Lookup entry in radix tree, wait for it to become unlocked if it is
 * exceptional entry and return it. The caller must call
 * put_unlocked_mapping_entry() when he decided not to lock the entry or
 * put_locked_mapping_entry() when he locked the entry and now wants to
 * unlock it.
 *
 * The function must be called with mapping->tree_lock held. When -EAGAIN is
 * reported, the tree_lock is dropped.
 */
static void *__get_unlocked_mapping_entry(struct address_space *mapping,
		pgoff_t index, void ***slotp, bool (*wait_fn)(void))
{
	void *entry, **slot;
	struct wait_exceptional_entry_queue ewait;
	wait_queue_head_t *wq;

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

	for (;;) {
		bool revalidate;

		entry = __radix_tree_lookup(&mapping->page_tree, index, NULL,
					  &slot);
		if (!entry ||
		    WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) ||
		    !slot_locked(mapping, slot)) {
			if (slotp)
				*slotp = slot;
			return entry;
		}

		wq = dax_entry_waitqueue(mapping, index, entry, &ewait.key);
		prepare_to_wait_exclusive(wq, &ewait.wait,
					  TASK_UNINTERRUPTIBLE);
		spin_unlock_irq(&mapping->tree_lock);
		revalidate = wait_fn();
		finish_wait(wq, &ewait.wait);
		if (revalidate) {
			/*
			 * Entry lock waits are exclusive. Wake up the next
			 * waiter since we aren't sure we will acquire the
			 * entry lock and thus wake the next waiter up on
			 * unlock.
			 */
			if (waitqueue_active(wq))
				__wake_up(wq, TASK_NORMAL, 1, &ewait.key);
			return ERR_PTR(-EAGAIN);
		}
		spin_lock_irq(&mapping->tree_lock);
	}
}

static bool entry_wait(void)
{
	schedule();
	/*
	 * Never return an ERR_PTR() from
	 * __get_unlocked_mapping_entry(), just keep looping.
	 */
	return false;
}

static void *get_unlocked_mapping_entry(struct address_space *mapping,
		pgoff_t index, void ***slotp)
{
	return __get_unlocked_mapping_entry(mapping, index, slotp, entry_wait);
}

static void unlock_mapping_entry(struct address_space *mapping, pgoff_t index)
{
	void *entry, **slot;

	spin_lock_irq(&mapping->tree_lock);
	entry = __radix_tree_lookup(&mapping->page_tree, index, NULL, &slot);
	if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) ||
			 !slot_locked(mapping, slot))) {
		spin_unlock_irq(&mapping->tree_lock);
		return;
	}
	unlock_slot(mapping, slot);
	spin_unlock_irq(&mapping->tree_lock);
	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
}

static void put_locked_mapping_entry(struct address_space *mapping,
		pgoff_t index)
{
	unlock_mapping_entry(mapping, index);
}

/*
 * Called when we are done with radix tree entry we looked up via
 * get_unlocked_mapping_entry() and which we didn't lock in the end.
 */
static void put_unlocked_mapping_entry(struct address_space *mapping,
				       pgoff_t index, void *entry)
{
	if (!entry)
		return;

	/* We have to wake up next waiter for the radix tree entry lock */
	dax_wake_mapping_entry_waiter(mapping, index, entry, false);
}

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_radix_end_pfn(void *entry)
{
	return dax_radix_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_radix_pfn(entry); \
			pfn < dax_radix_end_pfn(entry); pfn++)

/*
 * TODO: for reflink+dax we need a way to associate a single page with
 * multiple address_space instances at different linear_page_index()
 * offsets.
 */
static void dax_associate_entry(void *entry, struct address_space *mapping,
		struct vm_area_struct *vma, unsigned long address)
{
	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);

		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);
		WARN_ON_ONCE(page->mapping && page->mapping != mapping);
		page->mapping = NULL;
		page->index = 0;
	}
}

static bool entry_wait_revalidate(void)
{
	rcu_read_unlock();
	schedule();
	rcu_read_lock();

	/*
	 * Tell __get_unlocked_mapping_entry() to take a break, we need
	 * to revalidate page->mapping after dropping locks
	 */
	return true;
}

bool dax_lock_mapping_entry(struct page *page)
{
	pgoff_t index;
	struct inode *inode;
	bool did_lock = false;
	void *entry = NULL, **slot;
	struct address_space *mapping;

	rcu_read_lock();
	for (;;) {
		mapping = READ_ONCE(page->mapping);

		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.
		 */
		inode = mapping->host;
		if (S_ISCHR(inode->i_mode)) {
			did_lock = true;
			break;
		}

		spin_lock_irq(&mapping->tree_lock);
		if (mapping != page->mapping) {
			spin_unlock_irq(&mapping->tree_lock);
			continue;
		}
		index = page->index;

		entry = __get_unlocked_mapping_entry(mapping, index, &slot,
				entry_wait_revalidate);
		if (!entry) {
			spin_unlock_irq(&mapping->tree_lock);
			break;
		} else if (IS_ERR(entry)) {
			WARN_ON_ONCE(PTR_ERR(entry) != -EAGAIN);
			/* tree_lock gets unlocked on error return */
			continue;
		}
		lock_slot(mapping, slot);
		did_lock = true;
		spin_unlock_irq(&mapping->tree_lock);
		break;
	}
	rcu_read_unlock();

	return did_lock;
}

void dax_unlock_mapping_entry(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct inode *inode = mapping->host;

	if (S_ISCHR(inode->i_mode))
		return;

	unlock_mapping_entry(mapping, page->index);
}

/*
 * Find radix tree entry at given index. If it points to an exceptional entry,
 * return it with the radix tree entry locked. If the radix tree doesn't
 * contain given index, create an empty exceptional entry for the index and
 * return with it locked.
 *
 * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will
 * either return that locked entry or will return an error.  This error will
 * happen if there are any 4k entries within the 2MiB range that we are
 * requesting.
 *
 * We always favor 4k entries over 2MiB entries. There isn't a flow where we
 * evict 4k entries in order to 'upgrade' them to a 2MiB entry.  A 2MiB
 * insertion will fail if it finds any 4k entries already in the tree, and a
 * 4k insertion will cause an existing 2MiB entry to be unmapped and
 * downgraded to 4k entries.  This happens for both 2MiB huge zero pages as
 * well as 2MiB empty entries.
 *
 * The exception to this downgrade path is for 2MiB DAX PMD entries that have
 * real storage backing them.  We will leave these real 2MiB DAX entries in
 * the tree, and PTE writes will simply dirty the entire 2MiB DAX 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.
 */
static void *grab_mapping_entry(struct address_space *mapping, pgoff_t index,
		unsigned long size_flag)
{
	bool pmd_downgrade = false; /* splitting 2MiB entry into 4k entries? */
	void *entry, **slot;

restart:
	spin_lock_irq(&mapping->tree_lock);
	entry = get_unlocked_mapping_entry(mapping, index, &slot);

	if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) {
		entry = ERR_PTR(-EIO);
		goto out_unlock;
	}

	if (entry) {
		if (size_flag & RADIX_DAX_PMD) {
			if (dax_is_pte_entry(entry)) {
				put_unlocked_mapping_entry(mapping, index,
						entry);
				entry = ERR_PTR(-EEXIST);
				goto out_unlock;
			}
		} else { /* trying to grab a PTE entry */
			if (dax_is_pmd_entry(entry) &&
			    (dax_is_zero_entry(entry) ||
			     dax_is_empty_entry(entry))) {
				pmd_downgrade = true;
			}
		}
	}

	/* No entry for given index? Make sure radix tree is big enough. */
	if (!entry || pmd_downgrade) {
		int err;

		if (pmd_downgrade) {
			/*
			 * Make sure 'entry' remains valid while we drop
			 * mapping->tree_lock.
			 */
			entry = lock_slot(mapping, slot);
		}

		spin_unlock_irq(&mapping->tree_lock);
		/*
		 * Besides huge zero pages the only other thing that gets
		 * downgraded are empty entries which don't need to be
		 * unmapped.
		 */
		if (pmd_downgrade && dax_is_zero_entry(entry))
			unmap_mapping_range(mapping,
				(index << PAGE_SHIFT) & PMD_MASK, PMD_SIZE, 0);

		err = radix_tree_preload(
				mapping_gfp_mask(mapping) & ~__GFP_HIGHMEM);
		if (err) {
			if (pmd_downgrade)
				put_locked_mapping_entry(mapping, index);
			return ERR_PTR(err);
		}
		spin_lock_irq(&mapping->tree_lock);

		if (!entry) {
			/*
			 * We needed to drop the page_tree lock while calling
			 * radix_tree_preload() and we didn't have an entry to
			 * lock.  See if another thread inserted an entry at
			 * our index during this time.
			 */
			entry = __radix_tree_lookup(&mapping->page_tree, index,
					NULL, &slot);
			if (entry) {
				radix_tree_preload_end();
				spin_unlock_irq(&mapping->tree_lock);
				goto restart;
			}
		}

		if (pmd_downgrade) {
			dax_disassociate_entry(entry, mapping, false);
			radix_tree_delete(&mapping->page_tree, index);
			mapping->nrexceptional--;
			dax_wake_mapping_entry_waiter(mapping, index, entry,
					true);
		}

		entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY);

		err = __radix_tree_insert(&mapping->page_tree, index,
				dax_radix_order(entry), entry);
		radix_tree_preload_end();
		if (err) {
			spin_unlock_irq(&mapping->tree_lock);
			/*
			 * Our insertion of a DAX entry failed, most likely
			 * because we were inserting a PMD entry and it
			 * collided with a PTE sized entry at a different
			 * index in the PMD range.  We haven't inserted
			 * anything into the radix tree and have no waiters to
			 * wake.
			 */
			return ERR_PTR(err);
		}
		/* Good, we have inserted empty locked entry into the tree. */
		mapping->nrexceptional++;
		spin_unlock_irq(&mapping->tree_lock);
		return entry;
	}
	entry = lock_slot(mapping, slot);
 out_unlock:
	spin_unlock_irq(&mapping->tree_lock);
	return entry;
}

static int __dax_invalidate_mapping_entry(struct address_space *mapping,
					  pgoff_t index, bool trunc)
{
	int ret = 0;
	void *entry;
	struct radix_tree_root *page_tree = &mapping->page_tree;

	spin_lock_irq(&mapping->tree_lock);
	entry = get_unlocked_mapping_entry(mapping, index, NULL);
	if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)))
		goto out;
	if (!trunc &&
	    (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
	     radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE)))
		goto out;
	dax_disassociate_entry(entry, mapping, trunc);
	radix_tree_delete(page_tree, index);
	mapping->nrexceptional--;
	ret = 1;
out:
	put_unlocked_mapping_entry(mapping, index, entry);
	spin_unlock_irq(&mapping->tree_lock);
	return ret;
}
/*
 * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree
 * entry to get unlocked before deleting it.
 */
int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
{
	int ret = __dax_invalidate_mapping_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
	 * radix tree (usually fs-private i_mmap_sem for writing). Since the
	 * caller has seen exceptional entry for this index, we better find it
	 * at that index as well...
	 */
	WARN_ON_ONCE(!ret);
	return ret;
}

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

static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
		sector_t sector, size_t size, struct page *to,
		unsigned long vaddr)
{
	void *vto, *kaddr;
	pgoff_t pgoff;
	pfn_t pfn;
	long rc;
	int id;

	rc = bdev_dax_pgoff(bdev, sector, size, &pgoff);
	if (rc)
		return rc;

	id = dax_read_lock();
	rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, &pfn);
	if (rc < 0) {
		dax_read_unlock(id);
		return rc;
	}
	vto = kmap_atomic(to);
	copy_user_page(vto, (void __force *)kaddr, vaddr, to);
	kunmap_atomic(vto);
	dax_read_unlock(id);
	return 0;
}

/*
 * 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_mapping_entry(struct address_space *mapping,
				      struct vm_fault *vmf,
				      void *entry, pfn_t pfn_t,
				      unsigned long flags, bool dirty)
{
	struct radix_tree_root *page_tree = &mapping->page_tree;
	unsigned long pfn = pfn_t_to_pfn(pfn_t);
	pgoff_t index = vmf->pgoff;
	void *new_entry;

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

	if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) {
		/* we are replacing a zero page with block mapping */
		if (dax_is_pmd_entry(entry))
			unmap_mapping_range(mapping,
					(vmf->pgoff << PAGE_SHIFT) & PMD_MASK,
					PMD_SIZE, 0);
		else /* pte entry */
			unmap_mapping_range(mapping, vmf->pgoff << PAGE_SHIFT,
					PAGE_SIZE, 0);
	}

	spin_lock_irq(&mapping->tree_lock);
	new_entry = dax_radix_locked_entry(pfn, flags);
	if (dax_is_zero_entry(entry) || dax_is_empty_entry(entry)) {
		struct radix_tree_node *node;
		void **slot;
		void *ret;

		dax_disassociate_entry(entry, mapping, false);
		dax_associate_entry(new_entry, mapping, vmf->vma, vmf->address);

		/*
		 * Only swap our new entry into the radix tree if the current
		 * entry is a zero page or an empty entry.  If a normal PTE or
		 * PMD entry is already in the tree, 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.
		 */
		ret = __radix_tree_lookup(page_tree, index, &node, &slot);
		WARN_ON_ONCE(ret != entry);
		__radix_tree_replace(page_tree, node, slot,
				     new_entry, NULL);
		entry = new_entry;
	}

	if (dirty)
		radix_tree_tag_set(page_tree, index, PAGECACHE_TAG_DIRTY);

	spin_unlock_irq(&mapping->tree_lock);
	return entry;
}

static inline unsigned long
pgoff_address(pgoff_t pgoff, struct vm_area_struct *vma)
{
	unsigned long address;

	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
	return address;
}

/* Walk all mappings of a given index of a file and writeprotect them */
static void dax_mapping_entry_mkclean(struct address_space *mapping,
				      pgoff_t index, unsigned long pfn)
{
	struct vm_area_struct *vma;
	pte_t pte, *ptep = NULL;
	pmd_t *pmdp = NULL;
	spinlock_t *ptl;
	bool changed;

	i_mmap_lock_read(mapping);
	vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
		unsigned long address;

		cond_resched();

		if (!(vma->vm_flags & VM_SHARED))
			continue;

		address = pgoff_address(index, vma);
		changed = false;
		if (follow_pte_pmd(vma->vm_mm, address, &ptep, &pmdp, &ptl))
			continue;

		if (pmdp) {
#ifdef CONFIG_FS_DAX_PMD
			pmd_t pmd;

			if (pfn != pmd_pfn(*pmdp))
				goto unlock_pmd;
			if (!pmd_dirty(*pmdp) && !pmd_write(*pmdp))
				goto unlock_pmd;

			flush_cache_page(vma, address, pfn);
			pmd = pmdp_huge_clear_flush(vma, address, pmdp);
			pmd = pmd_wrprotect(pmd);
			pmd = pmd_mkclean(pmd);
			set_pmd_at(vma->vm_mm, address, pmdp, pmd);
			changed = true;
unlock_pmd:
#endif
			spin_unlock(ptl);
		} else {
			if (pfn != pte_pfn(*ptep))
				goto unlock_pte;
			if (!pte_dirty(*ptep) && !pte_write(*ptep))
				goto unlock_pte;

			flush_cache_page(vma, address, pfn);
			pte = ptep_clear_flush(vma, address, ptep);
			pte = pte_wrprotect(pte);
			pte = pte_mkclean(pte);
			set_pte_at(vma->vm_mm, address, ptep, pte);
			changed = true;
unlock_pte:
			pte_unmap_unlock(ptep, ptl);
		}

		if (changed)
			mmu_notifier_invalidate_page(vma->vm_mm, address);
	}
	i_mmap_unlock_read(mapping);
}

static int dax_writeback_one(struct dax_device *dax_dev,
		struct address_space *mapping, pgoff_t index, void *entry)
{
	struct radix_tree_root *page_tree = &mapping->page_tree;
	void *entry2, **slot;
	unsigned long pfn;
	long ret = 0;
	size_t size;

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

	spin_lock_irq(&mapping->tree_lock);
	entry2 = get_unlocked_mapping_entry(mapping, index, &slot);
	/* Entry got punched out / reallocated? */
	if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2)))
		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_radix_pfn(entry2) != dax_radix_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 written back this entry */
	if (!radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
		goto put_unlocked;
	/* Lock the entry to serialize with page faults */
	entry = lock_slot(mapping, slot);
	/*
	 * 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 tree_lock and once they do that they will
	 * see the entry locked and wait for it to unlock.
	 */
	radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_TOWRITE);
	spin_unlock_irq(&mapping->tree_lock);

	/*
	 * Even if dax_writeback_mapping_range() was given a wbc->range_start
	 * in the middle of a PMD, the 'index' we are given will be aligned to
	 * the start index of the PMD, as will the pfn we pull from 'entry'.
	 * This allows us to flush for PMD_SIZE and not have to worry about
	 * partial PMD writebacks.
	 */
	pfn = dax_radix_pfn(entry);
	size = PAGE_SIZE << dax_radix_order(entry);

	dax_mapping_entry_mkclean(mapping, index, pfn);
	dax_flush(dax_dev, page_address(pfn_to_page(pfn)), 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.
	 */
	spin_lock_irq(&mapping->tree_lock);
	radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_DIRTY);
	spin_unlock_irq(&mapping->tree_lock);
	trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT);
	put_locked_mapping_entry(mapping, index);
	return ret;

 put_unlocked:
	put_unlocked_mapping_entry(mapping, index, entry2);
	spin_unlock_irq(&mapping->tree_lock);
	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 block_device *bdev, struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	pgoff_t start_index, end_index;
	pgoff_t indices[PAGEVEC_SIZE];
	struct dax_device *dax_dev;
	struct pagevec pvec;
	bool done = false;
	int i, ret = 0;

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

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

	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
	if (!dax_dev)
		return -EIO;

	start_index = wbc->range_start >> PAGE_SHIFT;
	end_index = wbc->range_end >> PAGE_SHIFT;

	trace_dax_writeback_range(inode, start_index, end_index);

	tag_pages_for_writeback(mapping, start_index, end_index);

	pagevec_init(&pvec);
	while (!done) {
		pvec.nr = find_get_entries_tag(mapping, start_index,
				PAGECACHE_TAG_TOWRITE, PAGEVEC_SIZE,
				pvec.pages, indices);

		if (pvec.nr == 0)
			break;

		for (i = 0; i < pvec.nr; i++) {
			if (indices[i] > end_index) {
				done = true;
				break;
			}

			ret = dax_writeback_one(dax_dev, mapping, indices[i],
					pvec.pages[i]);
			if (ret < 0) {
				mapping_set_error(mapping, ret);
				goto out;
			}
		}
		start_index = indices[pvec.nr - 1] + 1;
	}
out:
	put_dax(dax_dev);
	trace_dax_writeback_range_done(inode, start_index, end_index);
	return (ret < 0 ? ret : 0);
}
EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);

static sector_t dax_iomap_sector(struct iomap *iomap, loff_t pos)
{
	return iomap->blkno + (((pos & PAGE_MASK) - iomap->offset) >> 9);
}

static int dax_iomap_pfn(struct iomap *iomap, loff_t pos, size_t size,
			 pfn_t *pfnp)
{
	const sector_t sector = dax_iomap_sector(iomap, pos);
	pgoff_t pgoff;
	void *kaddr;
	int id, rc;
	long length;

	rc = bdev_dax_pgoff(iomap->bdev, sector, size, &pgoff);
	if (rc)
		return rc;
	id = dax_read_lock();
	length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
				   &kaddr, pfnp);
	if (length < 0) {
		rc = length;
		goto out;
	}
	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:
	dax_read_unlock(id);
	return rc;
}

/*
 * 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 int dax_load_hole(struct address_space *mapping, void *entry,
			 struct vm_fault *vmf)
{
	struct inode *inode = mapping->host;
	unsigned long vaddr = vmf->address;
	int ret = VM_FAULT_NOPAGE;
	struct page *zero_page;
	void *entry2;
	pfn_t pfn;

	zero_page = ZERO_PAGE(0);
	if (unlikely(!zero_page)) {
		ret = VM_FAULT_OOM;
		goto out;
	}

	pfn = page_to_pfn_t(zero_page);
	entry2 = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
			RADIX_DAX_ZERO_PAGE, false);
	if (IS_ERR(entry2)) {
		ret = VM_FAULT_SIGBUS;
		goto out;
	}

	vm_insert_mixed(vmf->vma, vaddr, pfn);
out:
	trace_dax_load_hole(inode, vmf, ret);
	return ret;
}

static bool dax_range_is_aligned(struct block_device *bdev,
				 unsigned int offset, unsigned int length)
{
	unsigned short sector_size = bdev_logical_block_size(bdev);

	if (!IS_ALIGNED(offset, sector_size))
		return false;
	if (!IS_ALIGNED(length, sector_size))
		return false;

	return true;
}

int __dax_zero_page_range(struct block_device *bdev,
		struct dax_device *dax_dev, sector_t sector,
		unsigned int offset, unsigned int size)
{
	if (dax_range_is_aligned(bdev, offset, size)) {
		sector_t start_sector = sector + (offset >> 9);

		return blkdev_issue_zeroout(bdev, start_sector,
				size >> 9, GFP_NOFS, 0);
	} else {
		pgoff_t pgoff;
		long rc, id;
		void *kaddr;
		pfn_t pfn;

		rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff);
		if (rc)
			return rc;

		id = dax_read_lock();
		rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr,
				&pfn);
		if (rc < 0) {
			dax_read_unlock(id);
			return rc;
		}
		memset(kaddr + offset, 0, size);
		dax_flush(dax_dev, kaddr + offset, size);
		dax_read_unlock(id);
	}
	return 0;
}
EXPORT_SYMBOL_GPL(__dax_zero_page_range);

static loff_t
dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
		struct iomap *iomap)
{
	struct block_device *bdev = iomap->bdev;
	struct dax_device *dax_dev = iomap->dax_dev;
	struct iov_iter *iter = data;
	loff_t end = pos + length, done = 0;
	ssize_t ret = 0;
	size_t xfer;
	int id;

	if (iov_iter_rw(iter) == READ) {
		end = min(end, i_size_read(inode));
		if (pos >= end)
			return 0;

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

	if (WARN_ON_ONCE(iomap->type != IOMAP_MAPPED))
		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) {
		invalidate_inode_pages2_range(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);
		const sector_t sector = dax_iomap_sector(iomap, pos);
		ssize_t map_len;
		pgoff_t pgoff;
		void *kaddr;
		pfn_t pfn;

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

		ret = bdev_dax_pgoff(bdev, sector, size, &pgoff);
		if (ret)
			break;

		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
				&kaddr, &pfn);
		if (map_len < 0) {
			ret = map_len;
			break;
		}

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

		/*
		 * The userspace address for the memory copy has already been
		 * validated via access_ok() in either vfs_read() or
		 * vfs_write(), depending on which operation we are doing.
		 */
		if (iov_iter_rw(iter) == 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 address_space *mapping = iocb->ki_filp->f_mapping;
	struct inode *inode = mapping->host;
	loff_t pos = iocb->ki_pos, ret = 0, done = 0;
	unsigned flags = 0;

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

	while (iov_iter_count(iter)) {
		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
				iter, dax_iomap_actor);
		if (ret <= 0)
			break;
		pos += ret;
		done += ret;
	}

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

static int dax_fault_return(int error)
{
	if (error == 0)
		return VM_FAULT_NOPAGE;
	if (error == -ENOMEM)
		return VM_FAULT_OOM;
	return VM_FAULT_SIGBUS;
}

/*
 * 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(unsigned long flags,
		struct vm_area_struct *vma, struct iomap *iomap)
{
	return (flags & IOMAP_WRITE) && (vma->vm_flags & VM_SYNC)
		&& (iomap->flags & IOMAP_F_DIRTY);
}

static int dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
			       int *iomap_errp, const struct iomap_ops *ops)
{
	struct vm_area_struct *vma = vmf->vma;
	struct address_space *mapping = vma->vm_file->f_mapping;
	struct inode *inode = mapping->host;
	unsigned long vaddr = vmf->address;
	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
	struct iomap iomap = { 0 };
	unsigned flags = IOMAP_FAULT;
	int error, major = 0;
	bool write = vmf->flags & FAULT_FLAG_WRITE;
	bool sync;
	int vmf_ret = 0;
	void *entry;
	pfn_t pfn;

	trace_dax_pte_fault(inode, vmf, 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 (pos >= i_size_read(inode)) {
		vmf_ret = VM_FAULT_SIGBUS;
		goto out;
	}

	if (write && !vmf->cow_page)
		flags |= IOMAP_WRITE;

	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
	if (IS_ERR(entry)) {
		vmf_ret = dax_fault_return(PTR_ERR(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)) {
		vmf_ret = VM_FAULT_NOPAGE;
		goto unlock_entry;
	}

	/*
	 * Note that we don't bother to use iomap_apply here: DAX required
	 * the file system block size to be equal the page size, which means
	 * that we never have to deal with more than a single extent here.
	 */
	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
	if (iomap_errp)
		*iomap_errp = error;
	if (error) {
		vmf_ret = dax_fault_return(error);
		goto unlock_entry;
	}
	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
		error = -EIO;	/* fs corruption? */
		goto error_finish_iomap;
	}

	if (vmf->cow_page) {
		sector_t sector = dax_iomap_sector(&iomap, pos);

		switch (iomap.type) {
		case IOMAP_HOLE:
		case IOMAP_UNWRITTEN:
			clear_user_highpage(vmf->cow_page, vaddr);
			break;
		case IOMAP_MAPPED:
			error = copy_user_dax(iomap.bdev, iomap.dax_dev,
					sector, PAGE_SIZE, vmf->cow_page, vaddr);
			break;
		default:
			WARN_ON_ONCE(1);
			error = -EIO;
			break;
		}

		if (error)
			goto error_finish_iomap;

		__SetPageUptodate(vmf->cow_page);
		vmf_ret = finish_fault(vmf);
		if (!vmf_ret)
			vmf_ret = VM_FAULT_DONE_COW;
		goto finish_iomap;
	}

	sync = dax_fault_is_synchronous(flags, vma, &iomap);

	switch (iomap.type) {
	case IOMAP_MAPPED:
		if (iomap.flags & IOMAP_F_NEW) {
			count_vm_event(PGMAJFAULT);
			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
			major = VM_FAULT_MAJOR;
		}
		error = dax_iomap_pfn(&iomap, pos, PAGE_SIZE, &pfn);
		if (error < 0)
			goto error_finish_iomap;

		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
						 0, write && !sync);
		if (IS_ERR(entry)) {
			error = PTR_ERR(entry);
			goto error_finish_iomap;
		}

		/*
		 * If we are doing synchronous page fault and inode needs fsync,
		 * we can insert PTE into page tables only after that happens.
		 * Skip insertion for now and return the pfn so that caller can
		 * insert it after fsync is done.
		 */
		if (sync) {
			if (WARN_ON_ONCE(!pfnp)) {
				error = -EIO;
				goto error_finish_iomap;
			}
			*pfnp = pfn;
			vmf_ret = VM_FAULT_NEEDDSYNC | major;
			goto finish_iomap;
		}
		trace_dax_insert_mapping(inode, vmf, entry);
		if (write)
			error = vm_insert_mixed_mkwrite(vma, vaddr, pfn);
		else
			error = vm_insert_mixed(vma, vaddr, pfn);

		/* -EBUSY is fine, somebody else faulted on the same PTE */
		if (error == -EBUSY)
			error = 0;
		break;
	case IOMAP_UNWRITTEN:
	case IOMAP_HOLE:
		if (!write) {
			vmf_ret = dax_load_hole(mapping, entry, vmf);
			goto finish_iomap;
		}
		/*FALLTHRU*/
	default:
		WARN_ON_ONCE(1);
		error = -EIO;
		break;
	}

 error_finish_iomap:
	vmf_ret = dax_fault_return(error) | major;
 finish_iomap:
	if (ops->iomap_end) {
		int copied = PAGE_SIZE;

		if (vmf_ret & VM_FAULT_ERROR)
			copied = 0;
		/*
		 * The fault is done by now and there's no way back (other
		 * thread may be already happily using PTE we have installed).
		 * Just ignore error from ->iomap_end since we cannot do much
		 * with it.
		 */
		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
	}
 unlock_entry:
	put_locked_mapping_entry(mapping, vmf->pgoff);
 out:
	trace_dax_pte_fault_done(inode, vmf, vmf_ret);
	return vmf_ret;
}

#ifdef CONFIG_FS_DAX_PMD
/*
 * The 'colour' (ie low bits) within a PMD of a page offset.  This comes up
 * more often than one might expect in the below functions.
 */
#define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)

static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
		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;
	void *ret = NULL;
	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);
	ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
			RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
	if (IS_ERR(ret))
		goto fallback;

	if (arch_needs_pgtable_deposit()) {
		pgtable = pte_alloc_one(vma->vm_mm, vmf->address);
		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);
		atomic_long_inc(&vma->vm_mm->nr_ptes);
	}
	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, ret);
	return VM_FAULT_NOPAGE;

fallback:
	if (pgtable)
		pte_free(vma->vm_mm, pgtable);
	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, ret);
	return VM_FAULT_FALLBACK;
}

static int dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
			       const struct iomap_ops *ops)
{
	struct vm_area_struct *vma = vmf->vma;
	struct address_space *mapping = vma->vm_file->f_mapping;
	unsigned long pmd_addr = vmf->address & PMD_MASK;
	bool write = vmf->flags & FAULT_FLAG_WRITE;
	bool sync;
	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
	struct inode *inode = mapping->host;
	int result = VM_FAULT_FALLBACK;
	struct iomap iomap = { 0 };
	pgoff_t max_pgoff, pgoff;
	void *entry;
	loff_t pos;
	int error;
	pfn_t pfn;

	/*
	 * 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.
	 */
	pgoff = linear_page_index(vma, pmd_addr);
	max_pgoff = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);

	trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);

	/*
	 * 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 radix tree.
	 */
	if ((vmf->pgoff & PG_PMD_COLOUR) !=
	    ((vmf->address >> PAGE_SHIFT) & PG_PMD_COLOUR))
		goto fallback;

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

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

	if (pgoff >= max_pgoff) {
		result = VM_FAULT_SIGBUS;
		goto out;
	}

	/* If the PMD would extend beyond the file size */
	if ((pgoff | PG_PMD_COLOUR) >= max_pgoff)
		goto fallback;

	/*
	 * grab_mapping_entry() will make sure we get a 2MiB empty entry, a
	 * 2MiB zero page entry or a DAX PMD.  If it can't (because a 4k page
	 * is already in the tree, for instance), it will return -EEXIST and
	 * we just fall back to 4k entries.
	 */
	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
	if (IS_ERR(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)) {
		result = 0;
		goto unlock_entry;
	}

	/*
	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
	 * setting up a mapping, so really we're using iomap_begin() as a way
	 * to look up our filesystem block.
	 */
	pos = (loff_t)pgoff << PAGE_SHIFT;
	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
	if (error)
		goto unlock_entry;

	if (iomap.offset + iomap.length < pos + PMD_SIZE)
		goto finish_iomap;

	sync = dax_fault_is_synchronous(iomap_flags, vma, &iomap);

	switch (iomap.type) {
	case IOMAP_MAPPED:
		error = dax_iomap_pfn(&iomap, pos, PMD_SIZE, &pfn);
		if (error < 0)
			goto finish_iomap;

		entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
						RADIX_DAX_PMD, write && !sync);
		if (IS_ERR(entry))
			goto finish_iomap;

		/*
		 * If we are doing synchronous page fault and inode needs fsync,
		 * we can insert PMD into page tables only after that happens.
		 * Skip insertion for now and return the pfn so that caller can
		 * insert it after fsync is done.
		 */
		if (sync) {
			if (WARN_ON_ONCE(!pfnp))
				goto finish_iomap;
			*pfnp = pfn;
			result = VM_FAULT_NEEDDSYNC;
			goto finish_iomap;
		}

		trace_dax_pmd_insert_mapping(inode, vmf, PMD_SIZE, pfn, entry);
		result = vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn,
					    write);
		break;
	case IOMAP_UNWRITTEN:
	case IOMAP_HOLE:
		if (WARN_ON_ONCE(write))
			break;
		result = dax_pmd_load_hole(vmf, &iomap, entry);
		break;
	default:
		WARN_ON_ONCE(1);
		break;
	}

 finish_iomap:
	if (ops->iomap_end) {
		int copied = PMD_SIZE;

		if (result == VM_FAULT_FALLBACK)
			copied = 0;
		/*
		 * The fault is done by now and there's no way back (other
		 * thread may be already happily using PMD we have installed).
		 * Just ignore error from ->iomap_end since we cannot do much
		 * with it.
		 */
		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
				&iomap);
	}
 unlock_entry:
	put_locked_mapping_entry(mapping, pgoff);
 fallback:
	if (result == VM_FAULT_FALLBACK) {
		split_huge_pmd(vma, vmf->pmd, vmf->address);
		count_vm_event(THP_FAULT_FALLBACK);
	}
out:
	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result);
	return result;
}
#else
static int 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.
 */
int 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
 * @pe_size: Size of entry to be inserted
 * @pfn: PFN to insert
 *
 * This function inserts writeable PTE or PMD entry into page tables for mmaped
 * DAX file.  It takes care of marking corresponding radix tree entry as dirty
 * as well.
 */
static int dax_insert_pfn_mkwrite(struct vm_fault *vmf,
				  enum page_entry_size pe_size,
				  pfn_t pfn)
{
	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
	void *entry, **slot;
	pgoff_t index = vmf->pgoff;
	int vmf_ret, error;

	spin_lock_irq(&mapping->tree_lock);
	entry = get_unlocked_mapping_entry(mapping, index, &slot);
	/* Did we race with someone splitting entry or so? */
	if (!entry ||
	    (pe_size == PE_SIZE_PTE && !dax_is_pte_entry(entry)) ||
	    (pe_size == PE_SIZE_PMD && !dax_is_pmd_entry(entry))) {
		put_unlocked_mapping_entry(mapping, index, entry);
		spin_unlock_irq(&mapping->tree_lock);
		trace_dax_insert_pfn_mkwrite_no_entry(mapping->host, vmf,
						      VM_FAULT_NOPAGE);
		return VM_FAULT_NOPAGE;
	}
	radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY);
	entry = lock_slot(mapping, slot);
	spin_unlock_irq(&mapping->tree_lock);
	switch (pe_size) {
	case PE_SIZE_PTE:
		error = vm_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
		vmf_ret = dax_fault_return(error);
		break;
#ifdef CONFIG_FS_DAX_PMD
	case PE_SIZE_PMD:
		vmf_ret = vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd,
			pfn, true);
		break;
#endif
	default:
		vmf_ret = VM_FAULT_FALLBACK;
	}
	put_locked_mapping_entry(mapping, index);
	trace_dax_insert_pfn_mkwrite(mapping->host, vmf, vmf_ret);
	return vmf_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.
 */
int 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;
	size_t len = 0;

	if (pe_size == PE_SIZE_PTE)
		len = PAGE_SIZE;
	else if (pe_size == PE_SIZE_PMD)
		len = PMD_SIZE;
	else
		WARN_ON_ONCE(1);
	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, pe_size, pfn);
}
EXPORT_SYMBOL_GPL(dax_finish_sync_fault);