aboutsummaryrefslogtreecommitdiff
path: root/fs/super.c
blob: 221cfa1f4e92596101c6b2edf3febe6fc7c546b2 (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
/*
 *  linux/fs/super.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  super.c contains code to handle: - mount structures
 *                                   - super-block tables
 *                                   - filesystem drivers list
 *                                   - mount system call
 *                                   - umount system call
 *                                   - ustat system call
 *
 * GK 2/5/95  -  Changed to support mounting the root fs via NFS
 *
 *  Added kerneld support: Jacques Gelinas and Bjorn Ekwall
 *  Added change_root: Werner Almesberger & Hans Lermen, Feb '96
 *  Added options to /proc/mounts:
 *    Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996.
 *  Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 13-JAN-1998
 *  Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000
 */

#include <linux/export.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/mount.h>
#include <linux/security.h>
#include <linux/writeback.h>		/* for the emergency remount stuff */
#include <linux/idr.h>
#include <linux/mutex.h>
#include <linux/backing-dev.h>
#include <linux/rculist_bl.h>
#include <linux/cleancache.h>
#include <linux/fsnotify.h>
#include <linux/lockdep.h>
#include <linux/user_namespace.h>
#include "internal.h"


static LIST_HEAD(super_blocks);
static DEFINE_SPINLOCK(sb_lock);

static char *sb_writers_name[SB_FREEZE_LEVELS] = {
	"sb_writers",
	"sb_pagefaults",
	"sb_internal",
};

/*
 * One thing we have to be careful of with a per-sb shrinker is that we don't
 * drop the last active reference to the superblock from within the shrinker.
 * If that happens we could trigger unregistering the shrinker from within the
 * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we
 * take a passive reference to the superblock to avoid this from occurring.
 */
static unsigned long super_cache_scan(struct shrinker *shrink,
				      struct shrink_control *sc)
{
	struct super_block *sb;
	long	fs_objects = 0;
	long	total_objects;
	long	freed = 0;
	long	dentries;
	long	inodes;

	sb = container_of(shrink, struct super_block, s_shrink);

	/*
	 * Deadlock avoidance.  We may hold various FS locks, and we don't want
	 * to recurse into the FS that called us in clear_inode() and friends..
	 */
	if (!(sc->gfp_mask & __GFP_FS))
		return SHRINK_STOP;

	if (!trylock_super(sb))
		return SHRINK_STOP;

	if (sb->s_op->nr_cached_objects)
		fs_objects = sb->s_op->nr_cached_objects(sb, sc);

	inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);
	dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc);
	total_objects = dentries + inodes + fs_objects + 1;
	if (!total_objects)
		total_objects = 1;

	/* proportion the scan between the caches */
	dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
	inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
	fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects);

	/*
	 * prune the dcache first as the icache is pinned by it, then
	 * prune the icache, followed by the filesystem specific caches
	 *
	 * Ensure that we always scan at least one object - memcg kmem
	 * accounting uses this to fully empty the caches.
	 */
	sc->nr_to_scan = dentries + 1;
	freed = prune_dcache_sb(sb, sc);
	sc->nr_to_scan = inodes + 1;
	freed += prune_icache_sb(sb, sc);

	if (fs_objects) {
		sc->nr_to_scan = fs_objects + 1;
		freed += sb->s_op->free_cached_objects(sb, sc);
	}

	up_read(&sb->s_umount);
	return freed;
}

static unsigned long super_cache_count(struct shrinker *shrink,
				       struct shrink_control *sc)
{
	struct super_block *sb;
	long	total_objects = 0;

	sb = container_of(shrink, struct super_block, s_shrink);

	/*
	 * Don't call trylock_super as it is a potential
	 * scalability bottleneck. The counts could get updated
	 * between super_cache_count and super_cache_scan anyway.
	 * Call to super_cache_count with shrinker_rwsem held
	 * ensures the safety of call to list_lru_shrink_count() and
	 * s_op->nr_cached_objects().
	 */
	if (sb->s_op && sb->s_op->nr_cached_objects)
		total_objects = sb->s_op->nr_cached_objects(sb, sc);

	total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
	total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc);

	total_objects = vfs_pressure_ratio(total_objects);
	return total_objects;
}

static void destroy_super_work(struct work_struct *work)
{
	struct super_block *s = container_of(work, struct super_block,
							destroy_work);
	int i;

	for (i = 0; i < SB_FREEZE_LEVELS; i++)
		percpu_free_rwsem(&s->s_writers.rw_sem[i]);
	kfree(s);
}

static void destroy_super_rcu(struct rcu_head *head)
{
	struct super_block *s = container_of(head, struct super_block, rcu);
	INIT_WORK(&s->destroy_work, destroy_super_work);
	schedule_work(&s->destroy_work);
}

/**
 *	destroy_super	-	frees a superblock
 *	@s: superblock to free
 *
 *	Frees a superblock.
 */
static void destroy_super(struct super_block *s)
{
	list_lru_destroy(&s->s_dentry_lru);
	list_lru_destroy(&s->s_inode_lru);
	security_sb_free(s);
	WARN_ON(!list_empty(&s->s_mounts));
	put_user_ns(s->s_user_ns);
	kfree(s->s_subtype);
	call_rcu(&s->rcu, destroy_super_rcu);
}

/**
 *	alloc_super	-	create new superblock
 *	@type:	filesystem type superblock should belong to
 *	@flags: the mount flags
 *	@user_ns: User namespace for the super_block
 *
 *	Allocates and initializes a new &struct super_block.  alloc_super()
 *	returns a pointer new superblock or %NULL if allocation had failed.
 */
static struct super_block *alloc_super(struct file_system_type *type, int flags,
				       struct user_namespace *user_ns)
{
	struct super_block *s = kzalloc(sizeof(struct super_block),  GFP_USER);
	static const struct super_operations default_op;
	int i;

	if (!s)
		return NULL;

	INIT_LIST_HEAD(&s->s_mounts);
	s->s_user_ns = get_user_ns(user_ns);

	if (security_sb_alloc(s))
		goto fail;

	for (i = 0; i < SB_FREEZE_LEVELS; i++) {
		if (__percpu_init_rwsem(&s->s_writers.rw_sem[i],
					sb_writers_name[i],
					&type->s_writers_key[i]))
			goto fail;
	}
	init_waitqueue_head(&s->s_writers.wait_unfrozen);
	s->s_bdi = &noop_backing_dev_info;
	s->s_flags = flags;
	if (s->s_user_ns != &init_user_ns)
		s->s_iflags |= SB_I_NODEV;
	INIT_HLIST_NODE(&s->s_instances);
	INIT_HLIST_BL_HEAD(&s->s_anon);
	mutex_init(&s->s_sync_lock);
	INIT_LIST_HEAD(&s->s_inodes);
	spin_lock_init(&s->s_inode_list_lock);
	INIT_LIST_HEAD(&s->s_inodes_wb);
	spin_lock_init(&s->s_inode_wblist_lock);

	if (list_lru_init_memcg(&s->s_dentry_lru))
		goto fail;
	if (list_lru_init_memcg(&s->s_inode_lru))
		goto fail;

	init_rwsem(&s->s_umount);
	lockdep_set_class(&s->s_umount, &type->s_umount_key);
	/*
	 * sget() can have s_umount recursion.
	 *
	 * When it cannot find a suitable sb, it allocates a new
	 * one (this one), and tries again to find a suitable old
	 * one.
	 *
	 * In case that succeeds, it will acquire the s_umount
	 * lock of the old one. Since these are clearly distrinct
	 * locks, and this object isn't exposed yet, there's no
	 * risk of deadlocks.
	 *
	 * Annotate this by putting this lock in a different
	 * subclass.
	 */
	down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING);
	s->s_count = 1;
	atomic_set(&s->s_active, 1);
	mutex_init(&s->s_vfs_rename_mutex);
	lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key);
	init_rwsem(&s->s_dquot.dqio_sem);
	s->s_maxbytes = MAX_NON_LFS;
	s->s_op = &default_op;
	s->s_time_gran = 1000000000;
	s->cleancache_poolid = CLEANCACHE_NO_POOL;

	s->s_shrink.seeks = DEFAULT_SEEKS;
	s->s_shrink.scan_objects = super_cache_scan;
	s->s_shrink.count_objects = super_cache_count;
	s->s_shrink.batch = 1024;
	s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
	return s;

fail:
	destroy_super(s);
	return NULL;
}

/* Superblock refcounting  */

/*
 * Drop a superblock's refcount.  The caller must hold sb_lock.
 */
static void __put_super(struct super_block *sb)
{
	if (!--sb->s_count) {
		list_del_init(&sb->s_list);
		destroy_super(sb);
	}
}

/**
 *	put_super	-	drop a temporary reference to superblock
 *	@sb: superblock in question
 *
 *	Drops a temporary reference, frees superblock if there's no
 *	references left.
 */
static void put_super(struct super_block *sb)
{
	spin_lock(&sb_lock);
	__put_super(sb);
	spin_unlock(&sb_lock);
}


/**
 *	deactivate_locked_super	-	drop an active reference to superblock
 *	@s: superblock to deactivate
 *
 *	Drops an active reference to superblock, converting it into a temporary
 *	one if there is no other active references left.  In that case we
 *	tell fs driver to shut it down and drop the temporary reference we
 *	had just acquired.
 *
 *	Caller holds exclusive lock on superblock; that lock is released.
 */
void deactivate_locked_super(struct super_block *s)
{
	struct file_system_type *fs = s->s_type;
	if (atomic_dec_and_test(&s->s_active)) {
		cleancache_invalidate_fs(s);
		unregister_shrinker(&s->s_shrink);
		fs->kill_sb(s);

		/*
		 * Since list_lru_destroy() may sleep, we cannot call it from
		 * put_super(), where we hold the sb_lock. Therefore we destroy
		 * the lru lists right now.
		 */
		list_lru_destroy(&s->s_dentry_lru);
		list_lru_destroy(&s->s_inode_lru);

		put_filesystem(fs);
		put_super(s);
	} else {
		up_write(&s->s_umount);
	}
}

EXPORT_SYMBOL(deactivate_locked_super);

/**
 *	deactivate_super	-	drop an active reference to superblock
 *	@s: superblock to deactivate
 *
 *	Variant of deactivate_locked_super(), except that superblock is *not*
 *	locked by caller.  If we are going to drop the final active reference,
 *	lock will be acquired prior to that.
 */
void deactivate_super(struct super_block *s)
{
        if (!atomic_add_unless(&s->s_active, -1, 1)) {
		down_write(&s->s_umount);
		deactivate_locked_super(s);
	}
}

EXPORT_SYMBOL(deactivate_super);

/**
 *	grab_super - acquire an active reference
 *	@s: reference we are trying to make active
 *
 *	Tries to acquire an active reference.  grab_super() is used when we
 * 	had just found a superblock in super_blocks or fs_type->fs_supers
 *	and want to turn it into a full-blown active reference.  grab_super()
 *	is called with sb_lock held and drops it.  Returns 1 in case of
 *	success, 0 if we had failed (superblock contents was already dead or
 *	dying when grab_super() had been called).  Note that this is only
 *	called for superblocks not in rundown mode (== ones still on ->fs_supers
 *	of their type), so increment of ->s_count is OK here.
 */
static int grab_super(struct super_block *s) __releases(sb_lock)
{
	s->s_count++;
	spin_unlock(&sb_lock);
	down_write(&s->s_umount);
	if ((s->s_flags & MS_BORN) && atomic_inc_not_zero(&s->s_active)) {
		put_super(s);
		return 1;
	}
	up_write(&s->s_umount);
	put_super(s);
	return 0;
}

/*
 *	trylock_super - try to grab ->s_umount shared
 *	@sb: reference we are trying to grab
 *
 *	Try to prevent fs shutdown.  This is used in places where we
 *	cannot take an active reference but we need to ensure that the
 *	filesystem is not shut down while we are working on it. It returns
 *	false if we cannot acquire s_umount or if we lose the race and
 *	filesystem already got into shutdown, and returns true with the s_umount
 *	lock held in read mode in case of success. On successful return,
 *	the caller must drop the s_umount lock when done.
 *
 *	Note that unlike get_super() et.al. this one does *not* bump ->s_count.
 *	The reason why it's safe is that we are OK with doing trylock instead
 *	of down_read().  There's a couple of places that are OK with that, but
 *	it's very much not a general-purpose interface.
 */
bool trylock_super(struct super_block *sb)
{
	if (down_read_trylock(&sb->s_umount)) {
		if (!hlist_unhashed(&sb->s_instances) &&
		    sb->s_root && (sb->s_flags & MS_BORN))
			return true;
		up_read(&sb->s_umount);
	}

	return false;
}

/**
 *	generic_shutdown_super	-	common helper for ->kill_sb()
 *	@sb: superblock to kill
 *
 *	generic_shutdown_super() does all fs-independent work on superblock
 *	shutdown.  Typical ->kill_sb() should pick all fs-specific objects
 *	that need destruction out of superblock, call generic_shutdown_super()
 *	and release aforementioned objects.  Note: dentries and inodes _are_
 *	taken care of and do not need specific handling.
 *
 *	Upon calling this function, the filesystem may no longer alter or
 *	rearrange the set of dentries belonging to this super_block, nor may it
 *	change the attachments of dentries to inodes.
 */
void generic_shutdown_super(struct super_block *sb)
{
	const struct super_operations *sop = sb->s_op;

	if (sb->s_root) {
		shrink_dcache_for_umount(sb);
		sync_filesystem(sb);
		sb->s_flags &= ~MS_ACTIVE;

		fsnotify_unmount_inodes(sb);
		cgroup_writeback_umount();

		evict_inodes(sb);

		if (sb->s_dio_done_wq) {
			destroy_workqueue(sb->s_dio_done_wq);
			sb->s_dio_done_wq = NULL;
		}

		if (sop->put_super)
			sop->put_super(sb);

		if (!list_empty(&sb->s_inodes)) {
			printk("VFS: Busy inodes after unmount of %s. "
			   "Self-destruct in 5 seconds.  Have a nice day...\n",
			   sb->s_id);
		}
	}
	spin_lock(&sb_lock);
	/* should be initialized for __put_super_and_need_restart() */
	hlist_del_init(&sb->s_instances);
	spin_unlock(&sb_lock);
	up_write(&sb->s_umount);
	if (sb->s_bdi != &noop_backing_dev_info) {
		bdi_put(sb->s_bdi);
		sb->s_bdi = &noop_backing_dev_info;
	}
}

EXPORT_SYMBOL(generic_shutdown_super);

/**
 *	sget_userns -	find or create a superblock
 *	@type:	filesystem type superblock should belong to
 *	@test:	comparison callback
 *	@set:	setup callback
 *	@flags:	mount flags
 *	@user_ns: User namespace for the super_block
 *	@data:	argument to each of them
 */
struct super_block *sget_userns(struct file_system_type *type,
			int (*test)(struct super_block *,void *),
			int (*set)(struct super_block *,void *),
			int flags, struct user_namespace *user_ns,
			void *data)
{
	struct super_block *s = NULL;
	struct super_block *old;
	int err;

	if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) &&
	    !(type->fs_flags & FS_USERNS_MOUNT) &&
	    !capable(CAP_SYS_ADMIN))
		return ERR_PTR(-EPERM);
retry:
	spin_lock(&sb_lock);
	if (test) {
		hlist_for_each_entry(old, &type->fs_supers, s_instances) {
			if (!test(old, data))
				continue;
			if (user_ns != old->s_user_ns) {
				spin_unlock(&sb_lock);
				if (s) {
					up_write(&s->s_umount);
					destroy_super(s);
				}
				return ERR_PTR(-EBUSY);
			}
			if (!grab_super(old))
				goto retry;
			if (s) {
				up_write(&s->s_umount);
				destroy_super(s);
				s = NULL;
			}
			return old;
		}
	}
	if (!s) {
		spin_unlock(&sb_lock);
		s = alloc_super(type, (flags & ~MS_SUBMOUNT), user_ns);
		if (!s)
			return ERR_PTR(-ENOMEM);
		goto retry;
	}

	err = set(s, data);
	if (err) {
		spin_unlock(&sb_lock);
		up_write(&s->s_umount);
		destroy_super(s);
		return ERR_PTR(err);
	}
	s->s_type = type;
	strlcpy(s->s_id, type->name, sizeof(s->s_id));
	list_add_tail(&s->s_list, &super_blocks);
	hlist_add_head(&s->s_instances, &type->fs_supers);
	spin_unlock(&sb_lock);
	get_filesystem(type);
	register_shrinker(&s->s_shrink);
	return s;
}

EXPORT_SYMBOL(sget_userns);

/**
 *	sget	-	find or create a superblock
 *	@type:	  filesystem type superblock should belong to
 *	@test:	  comparison callback
 *	@set:	  setup callback
 *	@flags:	  mount flags
 *	@data:	  argument to each of them
 */
struct super_block *sget(struct file_system_type *type,
			int (*test)(struct super_block *,void *),
			int (*set)(struct super_block *,void *),
			int flags,
			void *data)
{
	struct user_namespace *user_ns = current_user_ns();

	/* We don't yet pass the user namespace of the parent
	 * mount through to here so always use &init_user_ns
	 * until that changes.
	 */
	if (flags & MS_SUBMOUNT)
		user_ns = &init_user_ns;

	/* Ensure the requestor has permissions over the target filesystem */
	if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && !ns_capable(user_ns, CAP_SYS_ADMIN))
		return ERR_PTR(-EPERM);

	return sget_userns(type, test, set, flags, user_ns, data);
}

EXPORT_SYMBOL(sget);

void drop_super(struct super_block *sb)
{
	up_read(&sb->s_umount);
	put_super(sb);
}

EXPORT_SYMBOL(drop_super);

void drop_super_exclusive(struct super_block *sb)
{
	up_write(&sb->s_umount);
	put_super(sb);
}
EXPORT_SYMBOL(drop_super_exclusive);

/**
 *	iterate_supers - call function for all active superblocks
 *	@f: function to call
 *	@arg: argument to pass to it
 *
 *	Scans the superblock list and calls given function, passing it
 *	locked superblock and given argument.
 */
void iterate_supers(void (*f)(struct super_block *, void *), void *arg)
{
	struct super_block *sb, *p = NULL;

	spin_lock(&sb_lock);
	list_for_each_entry(sb, &super_blocks, s_list) {
		if (hlist_unhashed(&sb->s_instances))
			continue;
		sb->s_count++;
		spin_unlock(&sb_lock);

		down_read(&sb->s_umount);
		if (sb->s_root && (sb->s_flags & MS_BORN))
			f(sb, arg);
		up_read(&sb->s_umount);

		spin_lock(&sb_lock);
		if (p)
			__put_super(p);
		p = sb;
	}
	if (p)
		__put_super(p);
	spin_unlock(&sb_lock);
}

/**
 *	iterate_supers_type - call function for superblocks of given type
 *	@type: fs type
 *	@f: function to call
 *	@arg: argument to pass to it
 *
 *	Scans the superblock list and calls given function, passing it
 *	locked superblock and given argument.
 */
void iterate_supers_type(struct file_system_type *type,
	void (*f)(struct super_block *, void *), void *arg)
{
	struct super_block *sb, *p = NULL;

	spin_lock(&sb_lock);
	hlist_for_each_entry(sb, &type->fs_supers, s_instances) {
		sb->s_count++;
		spin_unlock(&sb_lock);

		down_read(&sb->s_umount);
		if (sb->s_root && (sb->s_flags & MS_BORN))
			f(sb, arg);
		up_read(&sb->s_umount);

		spin_lock(&sb_lock);
		if (p)
			__put_super(p);
		p = sb;
	}
	if (p)
		__put_super(p);
	spin_unlock(&sb_lock);
}

EXPORT_SYMBOL(iterate_supers_type);

static struct super_block *__get_super(struct block_device *bdev, bool excl)
{
	struct super_block *sb;

	if (!bdev)
		return NULL;

	spin_lock(&sb_lock);
rescan:
	list_for_each_entry(sb, &super_blocks, s_list) {
		if (hlist_unhashed(&sb->s_instances))
			continue;
		if (sb->s_bdev == bdev) {
			sb->s_count++;
			spin_unlock(&sb_lock);
			if (!excl)
				down_read(&sb->s_umount);
			else
				down_write(&sb->s_umount);
			/* still alive? */
			if (sb->s_root && (sb->s_flags & MS_BORN))
				return sb;
			if (!excl)
				up_read(&sb->s_umount);
			else
				up_write(&sb->s_umount);
			/* nope, got unmounted */
			spin_lock(&sb_lock);
			__put_super(sb);
			goto rescan;
		}
	}
	spin_unlock(&sb_lock);
	return NULL;
}

/**
 *	get_super - get the superblock of a device
 *	@bdev: device to get the superblock for
 *
 *	Scans the superblock list and finds the superblock of the file system
 *	mounted on the device given. %NULL is returned if no match is found.
 */
struct super_block *get_super(struct block_device *bdev)
{
	return __get_super(bdev, false);
}
EXPORT_SYMBOL(get_super);

static struct super_block *__get_super_thawed(struct block_device *bdev,
					      bool excl)
{
	while (1) {
		struct super_block *s = __get_super(bdev, excl);
		if (!s || s->s_writers.frozen == SB_UNFROZEN)
			return s;
		if (!excl)
			up_read(&s->s_umount);
		else
			up_write(&s->s_umount);
		wait_event(s->s_writers.wait_unfrozen,
			   s->s_writers.frozen == SB_UNFROZEN);
		put_super(s);
	}
}

/**
 *	get_super_thawed - get thawed superblock of a device
 *	@bdev: device to get the superblock for
 *
 *	Scans the superblock list and finds the superblock of the file system
 *	mounted on the device. The superblock is returned once it is thawed
 *	(or immediately if it was not frozen). %NULL is returned if no match
 *	is found.
 */
struct super_block *get_super_thawed(struct block_device *bdev)
{
	return __get_super_thawed(bdev, false);
}
EXPORT_SYMBOL(get_super_thawed);

/**
 *	get_super_exclusive_thawed - get thawed superblock of a device
 *	@bdev: device to get the superblock for
 *
 *	Scans the superblock list and finds the superblock of the file system
 *	mounted on the device. The superblock is returned once it is thawed
 *	(or immediately if it was not frozen) and s_umount semaphore is held
 *	in exclusive mode. %NULL is returned if no match is found.
 */
struct super_block *get_super_exclusive_thawed(struct block_device *bdev)
{
	return __get_super_thawed(bdev, true);
}
EXPORT_SYMBOL(get_super_exclusive_thawed);

/**
 * get_active_super - get an active reference to the superblock of a device
 * @bdev: device to get the superblock for
 *
 * Scans the superblock list and finds the superblock of the file system
 * mounted on the device given.  Returns the superblock with an active
 * reference or %NULL if none was found.
 */
struct super_block *get_active_super(struct block_device *bdev)
{
	struct super_block *sb;

	if (!bdev)
		return NULL;

restart:
	spin_lock(&sb_lock);
	list_for_each_entry(sb, &super_blocks, s_list) {
		if (hlist_unhashed(&sb->s_instances))
			continue;
		if (sb->s_bdev == bdev) {
			if (!grab_super(sb))
				goto restart;
			up_write(&sb->s_umount);
			return sb;
		}
	}
	spin_unlock(&sb_lock);
	return NULL;
}

struct super_block *user_get_super(dev_t dev)
{
	struct super_block *sb;

	spin_lock(&sb_lock);
rescan:
	list_for_each_entry(sb, &super_blocks, s_list) {
		if (hlist_unhashed(&sb->s_instances))
			continue;
		if (sb->s_dev ==  dev) {
			sb->s_count++;
			spin_unlock(&sb_lock);
			down_read(&sb->s_umount);
			/* still alive? */
			if (sb->s_root && (sb->s_flags & MS_BORN))
				return sb;
			up_read(&sb->s_umount);
			/* nope, got unmounted */
			spin_lock(&sb_lock);
			__put_super(sb);
			goto rescan;
		}
	}
	spin_unlock(&sb_lock);
	return NULL;
}

/**
 *	do_remount_sb - asks filesystem to change mount options.
 *	@sb:	superblock in question
 *	@flags:	numeric part of options
 *	@data:	the rest of options
 *      @force: whether or not to force the change
 *
 *	Alters the mount options of a mounted file system.
 */
int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
{
	int retval;
	int remount_ro;

	if (sb->s_writers.frozen != SB_UNFROZEN)
		return -EBUSY;

#ifdef CONFIG_BLOCK
	if (!(flags & MS_RDONLY) && bdev_read_only(sb->s_bdev))
		return -EACCES;
#endif

	remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY);

	if (remount_ro) {
		if (!hlist_empty(&sb->s_pins)) {
			up_write(&sb->s_umount);
			group_pin_kill(&sb->s_pins);
			down_write(&sb->s_umount);
			if (!sb->s_root)
				return 0;
			if (sb->s_writers.frozen != SB_UNFROZEN)
				return -EBUSY;
			remount_ro = (flags & MS_RDONLY) && !(sb->s_flags & MS_RDONLY);
		}
	}
	shrink_dcache_sb(sb);

	/* If we are remounting RDONLY and current sb is read/write,
	   make sure there are no rw files opened */
	if (remount_ro) {
		if (force) {
			sb->s_readonly_remount = 1;
			smp_wmb();
		} else {
			retval = sb_prepare_remount_readonly(sb);
			if (retval)
				return retval;
		}
	}

	if (sb->s_op->remount_fs) {
		retval = sb->s_op->remount_fs(sb, &flags, data);
		if (retval) {
			if (!force)
				goto cancel_readonly;
			/* If forced remount, go ahead despite any errors */
			WARN(1, "forced remount of a %s fs returned %i\n",
			     sb->s_type->name, retval);
		}
	}
	sb->s_flags = (sb->s_flags & ~MS_RMT_MASK) | (flags & MS_RMT_MASK);
	/* Needs to be ordered wrt mnt_is_readonly() */
	smp_wmb();
	sb->s_readonly_remount = 0;

	/*
	 * Some filesystems modify their metadata via some other path than the
	 * bdev buffer cache (eg. use a private mapping, or directories in
	 * pagecache, etc). Also file data modifications go via their own
	 * mappings. So If we try to mount readonly then copy the filesystem
	 * from bdev, we could get stale data, so invalidate it to give a best
	 * effort at coherency.
	 */
	if (remount_ro && sb->s_bdev)
		invalidate_bdev(sb->s_bdev);
	return 0;

cancel_readonly:
	sb->s_readonly_remount = 0;
	return retval;
}

static void do_emergency_remount(struct work_struct *work)
{
	struct super_block *sb, *p = NULL;

	spin_lock(&sb_lock);
	list_for_each_entry(sb, &super_blocks, s_list) {
		if (hlist_unhashed(&sb->s_instances))
			continue;
		sb->s_count++;
		spin_unlock(&sb_lock);
		down_write(&sb->s_umount);
		if (sb->s_root && sb->s_bdev && (sb->s_flags & MS_BORN) &&
		    !(sb->s_flags & MS_RDONLY)) {
			/*
			 * What lock protects sb->s_flags??
			 */
			do_remount_sb(sb, MS_RDONLY, NULL, 1);
		}
		up_write(&sb->s_umount);
		spin_lock(&sb_lock);
		if (p)
			__put_super(p);
		p = sb;
	}
	if (p)
		__put_super(p);
	spin_unlock(&sb_lock);
	kfree(work);
	printk("Emergency Remount complete\n");
}

void emergency_remount(void)
{
	struct work_struct *work;

	work = kmalloc(sizeof(*work), GFP_ATOMIC);
	if (work) {
		INIT_WORK(work, do_emergency_remount);
		schedule_work(work);
	}
}

/*
 * Unnamed block devices are dummy devices used by virtual
 * filesystems which don't use real block-devices.  -- jrs
 */

static DEFINE_IDA(unnamed_dev_ida);
static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */
/* Many userspace utilities consider an FSID of 0 invalid.
 * Always return at least 1 from get_anon_bdev.
 */
static int unnamed_dev_start = 1;

int get_anon_bdev(dev_t *p)
{
	int dev;
	int error;

 retry:
	if (ida_pre_get(&unnamed_dev_ida, GFP_ATOMIC) == 0)
		return -ENOMEM;
	spin_lock(&unnamed_dev_lock);
	error = ida_get_new_above(&unnamed_dev_ida, unnamed_dev_start, &dev);
	if (!error)
		unnamed_dev_start = dev + 1;
	spin_unlock(&unnamed_dev_lock);
	if (error == -EAGAIN)
		/* We raced and lost with another CPU. */
		goto retry;
	else if (error)
		return -EAGAIN;

	if (dev >= (1 << MINORBITS)) {
		spin_lock(&unnamed_dev_lock);
		ida_remove(&unnamed_dev_ida, dev);
		if (unnamed_dev_start > dev)
			unnamed_dev_start = dev;
		spin_unlock(&unnamed_dev_lock);
		return -EMFILE;
	}
	*p = MKDEV(0, dev & MINORMASK);
	return 0;
}
EXPORT_SYMBOL(get_anon_bdev);

void free_anon_bdev(dev_t dev)
{
	int slot = MINOR(dev);
	spin_lock(&unnamed_dev_lock);
	ida_remove(&unnamed_dev_ida, slot);
	if (slot < unnamed_dev_start)
		unnamed_dev_start = slot;
	spin_unlock(&unnamed_dev_lock);
}
EXPORT_SYMBOL(free_anon_bdev);

int set_anon_super(struct super_block *s, void *data)
{
	return get_anon_bdev(&s->s_dev);
}

EXPORT_SYMBOL(set_anon_super);

void kill_anon_super(struct super_block *sb)
{
	dev_t dev = sb->s_dev;
	generic_shutdown_super(sb);
	free_anon_bdev(dev);
}

EXPORT_SYMBOL(kill_anon_super);

void kill_litter_super(struct super_block *sb)
{
	if (sb->s_root)
		d_genocide(sb->s_root);
	kill_anon_super(sb);
}

EXPORT_SYMBOL(kill_litter_super);

static int ns_test_super(struct super_block *sb, void *data)
{
	return sb->s_fs_info == data;
}

static int ns_set_super(struct super_block *sb, void *data)
{
	sb->s_fs_info = data;
	return set_anon_super(sb, NULL);
}

struct dentry *mount_ns(struct file_system_type *fs_type,
	int flags, void *data, void *ns, struct user_namespace *user_ns,
	int (*fill_super)(struct super_block *, void *, int))
{
	struct super_block *sb;

	/* Don't allow mounting unless the caller has CAP_SYS_ADMIN
	 * over the namespace.
	 */
	if (!(flags & MS_KERNMOUNT) && !ns_capable(user_ns, CAP_SYS_ADMIN))
		return ERR_PTR(-EPERM);

	sb = sget_userns(fs_type, ns_test_super, ns_set_super, flags,
			 user_ns, ns);
	if (IS_ERR(sb))
		return ERR_CAST(sb);

	if (!sb->s_root) {
		int err;
		err = fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
		if (err) {
			deactivate_locked_super(sb);
			return ERR_PTR(err);
		}

		sb->s_flags |= MS_ACTIVE;
	}

	return dget(sb->s_root);
}

EXPORT_SYMBOL(mount_ns);

#ifdef CONFIG_BLOCK
static int set_bdev_super(struct super_block *s, void *data)
{
	s->s_bdev = data;
	s->s_dev = s->s_bdev->bd_dev;
	s->s_bdi = bdi_get(s->s_bdev->bd_bdi);

	return 0;
}

static int test_bdev_super(struct super_block *s, void *data)
{
	return (void *)s->s_bdev == data;
}

struct dentry *mount_bdev(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data,
	int (*fill_super)(struct super_block *, void *, int))
{
	struct block_device *bdev;
	struct super_block *s;
	fmode_t mode = FMODE_READ | FMODE_EXCL;
	int error = 0;

	if (!(flags & MS_RDONLY))
		mode |= FMODE_WRITE;

	bdev = blkdev_get_by_path(dev_name, mode, fs_type);
	if (IS_ERR(bdev))
		return ERR_CAST(bdev);

	/*
	 * once the super is inserted into the list by sget, s_umount
	 * will protect the lockfs code from trying to start a snapshot
	 * while we are mounting
	 */
	mutex_lock(&bdev->bd_fsfreeze_mutex);
	if (bdev->bd_fsfreeze_count > 0) {
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		error = -EBUSY;
		goto error_bdev;
	}
	s = sget(fs_type, test_bdev_super, set_bdev_super, flags | MS_NOSEC,
		 bdev);
	mutex_unlock(&bdev->bd_fsfreeze_mutex);
	if (IS_ERR(s))
		goto error_s;

	if (s->s_root) {
		if ((flags ^ s->s_flags) & MS_RDONLY) {
			deactivate_locked_super(s);
			error = -EBUSY;
			goto error_bdev;
		}

		/*
		 * s_umount nests inside bd_mutex during
		 * __invalidate_device().  blkdev_put() acquires
		 * bd_mutex and can't be called under s_umount.  Drop
		 * s_umount temporarily.  This is safe as we're
		 * holding an active reference.
		 */
		up_write(&s->s_umount);
		blkdev_put(bdev, mode);
		down_write(&s->s_umount);
	} else {
		s->s_mode = mode;
		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
		sb_set_blocksize(s, block_size(bdev));
		error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
		if (error) {
			deactivate_locked_super(s);
			goto error;
		}

		s->s_flags |= MS_ACTIVE;
		bdev->bd_super = s;
	}

	return dget(s->s_root);

error_s:
	error = PTR_ERR(s);
error_bdev:
	blkdev_put(bdev, mode);
error:
	return ERR_PTR(error);
}
EXPORT_SYMBOL(mount_bdev);

void kill_block_super(struct super_block *sb)
{
	struct block_device *bdev = sb->s_bdev;
	fmode_t mode = sb->s_mode;

	bdev->bd_super = NULL;
	generic_shutdown_super(sb);
	sync_blockdev(bdev);
	WARN_ON_ONCE(!(mode & FMODE_EXCL));
	blkdev_put(bdev, mode | FMODE_EXCL);
}

EXPORT_SYMBOL(kill_block_super);
#endif

struct dentry *mount_nodev(struct file_system_type *fs_type,
	int flags, void *data,
	int (*fill_super)(struct super_block *, void *, int))
{
	int error;
	struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL);

	if (IS_ERR(s))
		return ERR_CAST(s);

	error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
	if (error) {
		deactivate_locked_super(s);
		return ERR_PTR(error);
	}
	s->s_flags |= MS_ACTIVE;
	return dget(s->s_root);
}
EXPORT_SYMBOL(mount_nodev);

static int compare_single(struct super_block *s, void *p)
{
	return 1;
}

struct dentry *mount_single(struct file_system_type *fs_type,
	int flags, void *data,
	int (*fill_super)(struct super_block *, void *, int))
{
	struct super_block *s;
	int error;

	s = sget(fs_type, compare_single, set_anon_super, flags, NULL);
	if (IS_ERR(s))
		return ERR_CAST(s);
	if (!s->s_root) {
		error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
		if (error) {
			deactivate_locked_super(s);
			return ERR_PTR(error);
		}
		s->s_flags |= MS_ACTIVE;
	} else {
		do_remount_sb(s, flags, data, 0);
	}
	return dget(s->s_root);
}
EXPORT_SYMBOL(mount_single);

struct dentry *
mount_fs(struct file_system_type *type, int flags, const char *name, void *data)
{
	struct dentry *root;
	struct super_block *sb;
	char *secdata = NULL;
	int error = -ENOMEM;

	if (data && !(type->fs_flags & FS_BINARY_MOUNTDATA)) {
		secdata = alloc_secdata();
		if (!secdata)
			goto out;

		error = security_sb_copy_data(data, secdata);
		if (error)
			goto out_free_secdata;
	}

	root = type->mount(type, flags, name, data);
	if (IS_ERR(root)) {
		error = PTR_ERR(root);
		goto out_free_secdata;
	}
	sb = root->d_sb;
	BUG_ON(!sb);
	WARN_ON(!sb->s_bdi);
	sb->s_flags |= MS_BORN;

	error = security_sb_kern_mount(sb, flags, secdata);
	if (error)
		goto out_sb;

	/*
	 * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE
	 * but s_maxbytes was an unsigned long long for many releases. Throw
	 * this warning for a little while to try and catch filesystems that
	 * violate this rule.
	 */
	WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to "
		"negative value (%lld)\n", type->name, sb->s_maxbytes);

	up_write(&sb->s_umount);
	free_secdata(secdata);
	return root;
out_sb:
	dput(root);
	deactivate_locked_super(sb);
out_free_secdata:
	free_secdata(secdata);
out:
	return ERR_PTR(error);
}

/*
 * Setup private BDI for given superblock. It gets automatically cleaned up
 * in generic_shutdown_super().
 */
int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
{
	struct backing_dev_info *bdi;
	int err;
	va_list args;

	bdi = bdi_alloc(GFP_KERNEL);
	if (!bdi)
		return -ENOMEM;

	bdi->name = sb->s_type->name;

	va_start(args, fmt);
	err = bdi_register_va(bdi, fmt, args);
	va_end(args);
	if (err) {
		bdi_put(bdi);
		return err;
	}
	WARN_ON(sb->s_bdi != &noop_backing_dev_info);
	sb->s_bdi = bdi;

	return 0;
}
EXPORT_SYMBOL(super_setup_bdi_name);

/*
 * Setup private BDI for given superblock. I gets automatically cleaned up
 * in generic_shutdown_super().
 */
int super_setup_bdi(struct super_block *sb)
{
	static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);

	return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name,
				    atomic_long_inc_return(&bdi_seq));
}
EXPORT_SYMBOL(super_setup_bdi);

/*
 * This is an internal function, please use sb_end_{write,pagefault,intwrite}
 * instead.
 */
void __sb_end_write(struct super_block *sb, int level)
{
	percpu_up_read(sb->s_writers.rw_sem + level-1);
}
EXPORT_SYMBOL(__sb_end_write);

/*
 * This is an internal function, please use sb_start_{write,pagefault,intwrite}
 * instead.
 */
int __sb_start_write(struct super_block *sb, int level, bool wait)
{
	bool force_trylock = false;
	int ret = 1;

#ifdef CONFIG_LOCKDEP
	/*
	 * We want lockdep to tell us about possible deadlocks with freezing
	 * but it's it bit tricky to properly instrument it. Getting a freeze
	 * protection works as getting a read lock but there are subtle
	 * problems. XFS for example gets freeze protection on internal level
	 * twice in some cases, which is OK only because we already hold a
	 * freeze protection also on higher level. Due to these cases we have
	 * to use wait == F (trylock mode) which must not fail.
	 */
	if (wait) {
		int i;

		for (i = 0; i < level - 1; i++)
			if (percpu_rwsem_is_held(sb->s_writers.rw_sem + i)) {
				force_trylock = true;
				break;
			}
	}
#endif
	if (wait && !force_trylock)
		percpu_down_read(sb->s_writers.rw_sem + level-1);
	else
		ret = percpu_down_read_trylock(sb->s_writers.rw_sem + level-1);

	WARN_ON(force_trylock && !ret);
	return ret;
}
EXPORT_SYMBOL(__sb_start_write);

/**
 * sb_wait_write - wait until all writers to given file system finish
 * @sb: the super for which we wait
 * @level: type of writers we wait for (normal vs page fault)
 *
 * This function waits until there are no writers of given type to given file
 * system.
 */
static void sb_wait_write(struct super_block *sb, int level)
{
	percpu_down_write(sb->s_writers.rw_sem + level-1);
}

/*
 * We are going to return to userspace and forget about these locks, the
 * ownership goes to the caller of thaw_super() which does unlock().
 */
static void lockdep_sb_freeze_release(struct super_block *sb)
{
	int level;

	for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
		percpu_rwsem_release(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
}

/*
 * Tell lockdep we are holding these locks before we call ->unfreeze_fs(sb).
 */
static void lockdep_sb_freeze_acquire(struct super_block *sb)
{
	int level;

	for (level = 0; level < SB_FREEZE_LEVELS; ++level)
		percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_);
}

static void sb_freeze_unlock(struct super_block *sb)
{
	int level;

	for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--)
		percpu_up_write(sb->s_writers.rw_sem + level);
}

/**
 * freeze_super - lock the filesystem and force it into a consistent state
 * @sb: the super to lock
 *
 * Syncs the super to make sure the filesystem is consistent and calls the fs's
 * freeze_fs.  Subsequent calls to this without first thawing the fs will return
 * -EBUSY.
 *
 * During this function, sb->s_writers.frozen goes through these values:
 *
 * SB_UNFROZEN: File system is normal, all writes progress as usual.
 *
 * SB_FREEZE_WRITE: The file system is in the process of being frozen.  New
 * writes should be blocked, though page faults are still allowed. We wait for
 * all writes to complete and then proceed to the next stage.
 *
 * SB_FREEZE_PAGEFAULT: Freezing continues. Now also page faults are blocked
 * but internal fs threads can still modify the filesystem (although they
 * should not dirty new pages or inodes), writeback can run etc. After waiting
 * for all running page faults we sync the filesystem which will clean all
 * dirty pages and inodes (no new dirty pages or inodes can be created when
 * sync is running).
 *
 * SB_FREEZE_FS: The file system is frozen. Now all internal sources of fs
 * modification are blocked (e.g. XFS preallocation truncation on inode
 * reclaim). This is usually implemented by blocking new transactions for
 * filesystems that have them and need this additional guard. After all
 * internal writers are finished we call ->freeze_fs() to finish filesystem
 * freezing. Then we transition to SB_FREEZE_COMPLETE state. This state is
 * mostly auxiliary for filesystems to verify they do not modify frozen fs.
 *
 * sb->s_writers.frozen is protected by sb->s_umount.
 */
int freeze_super(struct super_block *sb)
{
	int ret;

	atomic_inc(&sb->s_active);
	down_write(&sb->s_umount);
	if (sb->s_writers.frozen != SB_UNFROZEN) {
		deactivate_locked_super(sb);
		return -EBUSY;
	}

	if (!(sb->s_flags & MS_BORN)) {
		up_write(&sb->s_umount);
		return 0;	/* sic - it's "nothing to do" */
	}

	if (sb->s_flags & MS_RDONLY) {
		/* Nothing to do really... */
		sb->s_writers.frozen = SB_FREEZE_COMPLETE;
		up_write(&sb->s_umount);
		return 0;
	}

	sb->s_writers.frozen = SB_FREEZE_WRITE;
	/* Release s_umount to preserve sb_start_write -> s_umount ordering */
	up_write(&sb->s_umount);
	sb_wait_write(sb, SB_FREEZE_WRITE);
	down_write(&sb->s_umount);

	/* Now we go and block page faults... */
	sb->s_writers.frozen = SB_FREEZE_PAGEFAULT;
	sb_wait_write(sb, SB_FREEZE_PAGEFAULT);

	/* All writers are done so after syncing there won't be dirty data */
	sync_filesystem(sb);

	/* Now wait for internal filesystem counter */
	sb->s_writers.frozen = SB_FREEZE_FS;
	sb_wait_write(sb, SB_FREEZE_FS);

	if (sb->s_op->freeze_fs) {
		ret = sb->s_op->freeze_fs(sb);
		if (ret) {
			printk(KERN_ERR
				"VFS:Filesystem freeze failed\n");
			sb->s_writers.frozen = SB_UNFROZEN;
			sb_freeze_unlock(sb);
			wake_up(&sb->s_writers.wait_unfrozen);
			deactivate_locked_super(sb);
			return ret;
		}
	}
	/*
	 * For debugging purposes so that fs can warn if it sees write activity
	 * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super().
	 */
	sb->s_writers.frozen = SB_FREEZE_COMPLETE;
	lockdep_sb_freeze_release(sb);
	up_write(&sb->s_umount);
	return 0;
}
EXPORT_SYMBOL(freeze_super);

/**
 * thaw_super -- unlock filesystem
 * @sb: the super to thaw
 *
 * Unlocks the filesystem and marks it writeable again after freeze_super().
 */
int thaw_super(struct super_block *sb)
{
	int error;

	down_write(&sb->s_umount);
	if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) {
		up_write(&sb->s_umount);
		return -EINVAL;
	}

	if (sb->s_flags & MS_RDONLY) {
		sb->s_writers.frozen = SB_UNFROZEN;
		goto out;
	}

	lockdep_sb_freeze_acquire(sb);

	if (sb->s_op->unfreeze_fs) {
		error = sb->s_op->unfreeze_fs(sb);
		if (error) {
			printk(KERN_ERR
				"VFS:Filesystem thaw failed\n");
			lockdep_sb_freeze_release(sb);
			up_write(&sb->s_umount);
			return error;
		}
	}

	sb->s_writers.frozen = SB_UNFROZEN;
	sb_freeze_unlock(sb);
out:
	wake_up(&sb->s_writers.wait_unfrozen);
	deactivate_locked_super(sb);
	return 0;
}
EXPORT_SYMBOL(thaw_super);