summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/super.c
blob: 58e7de9cc90cb47d2c4047acb9a8d14cdc933f40 (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
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that 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.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/buffer_head.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/seq_file.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/mount.h>
#include <linux/mpage.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/parser.h>
#include <linux/ctype.h>
#include <linux/namei.h>
#include <linux/miscdevice.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "ioctl.h"
#include "print-tree.h"
#include "xattr.h"
#include "volumes.h"
#include "version.h"
#include "export.h"
#include "compression.h"

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

static const struct super_operations btrfs_super_ops;

static const char *btrfs_decode_error(struct btrfs_fs_info *fs_info, int errno,
				      char nbuf[16])
{
	char *errstr = NULL;

	switch (errno) {
	case -EIO:
		errstr = "IO failure";
		break;
	case -ENOMEM:
		errstr = "Out of memory";
		break;
	case -EROFS:
		errstr = "Readonly filesystem";
		break;
	default:
		if (nbuf) {
			if (snprintf(nbuf, 16, "error %d", -errno) >= 0)
				errstr = nbuf;
		}
		break;
	}

	return errstr;
}

static void __save_error_info(struct btrfs_fs_info *fs_info)
{
	/*
	 * today we only save the error info into ram.  Long term we'll
	 * also send it down to the disk
	 */
	fs_info->fs_state = BTRFS_SUPER_FLAG_ERROR;
}

/* NOTE:
 *	We move write_super stuff at umount in order to avoid deadlock
 *	for umount hold all lock.
 */
static void save_error_info(struct btrfs_fs_info *fs_info)
{
	__save_error_info(fs_info);
}

/* btrfs handle error by forcing the filesystem readonly */
static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
{
	struct super_block *sb = fs_info->sb;

	if (sb->s_flags & MS_RDONLY)
		return;

	if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) {
		sb->s_flags |= MS_RDONLY;
		printk(KERN_INFO "btrfs is forced readonly\n");
	}
}

/*
 * __btrfs_std_error decodes expected errors from the caller and
 * invokes the approciate error response.
 */
void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
		     unsigned int line, int errno)
{
	struct super_block *sb = fs_info->sb;
	char nbuf[16];
	const char *errstr;

	/*
	 * Special case: if the error is EROFS, and we're already
	 * under MS_RDONLY, then it is safe here.
	 */
	if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
		return;

	errstr = btrfs_decode_error(fs_info, errno, nbuf);
	printk(KERN_CRIT "BTRFS error (device %s) in %s:%d: %s\n",
		sb->s_id, function, line, errstr);
	save_error_info(fs_info);

	btrfs_handle_error(fs_info);
}

static void btrfs_put_super(struct super_block *sb)
{
	struct btrfs_root *root = btrfs_sb(sb);
	int ret;

	ret = close_ctree(root);
	sb->s_fs_info = NULL;

	(void)ret; /* FIXME: need to fix VFS to return error? */
}

enum {
	Opt_degraded, Opt_subvol, Opt_subvolid, Opt_device, Opt_nodatasum,
	Opt_nodatacow, Opt_max_inline, Opt_alloc_start, Opt_nobarrier, Opt_ssd,
	Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, Opt_compress,
	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
	Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
	Opt_enospc_debug, Opt_err,
};

static match_table_t tokens = {
	{Opt_degraded, "degraded"},
	{Opt_subvol, "subvol=%s"},
	{Opt_subvolid, "subvolid=%d"},
	{Opt_device, "device=%s"},
	{Opt_nodatasum, "nodatasum"},
	{Opt_nodatacow, "nodatacow"},
	{Opt_nobarrier, "nobarrier"},
	{Opt_max_inline, "max_inline=%s"},
	{Opt_alloc_start, "alloc_start=%s"},
	{Opt_thread_pool, "thread_pool=%d"},
	{Opt_compress, "compress"},
	{Opt_compress_type, "compress=%s"},
	{Opt_compress_force, "compress-force"},
	{Opt_compress_force_type, "compress-force=%s"},
	{Opt_ssd, "ssd"},
	{Opt_ssd_spread, "ssd_spread"},
	{Opt_nossd, "nossd"},
	{Opt_noacl, "noacl"},
	{Opt_notreelog, "notreelog"},
	{Opt_flushoncommit, "flushoncommit"},
	{Opt_ratio, "metadata_ratio=%d"},
	{Opt_discard, "discard"},
	{Opt_space_cache, "space_cache"},
	{Opt_clear_cache, "clear_cache"},
	{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
	{Opt_enospc_debug, "enospc_debug"},
	{Opt_err, NULL},
};

/*
 * Regular mount options parser.  Everything that is needed only when
 * reading in a new superblock is parsed here.
 */
int btrfs_parse_options(struct btrfs_root *root, char *options)
{
	struct btrfs_fs_info *info = root->fs_info;
	substring_t args[MAX_OPT_ARGS];
	char *p, *num, *orig;
	int intarg;
	int ret = 0;
	char *compress_type;
	bool compress_force = false;

	if (!options)
		return 0;

	/*
	 * strsep changes the string, duplicate it because parse_options
	 * gets called twice
	 */
	options = kstrdup(options, GFP_NOFS);
	if (!options)
		return -ENOMEM;

	orig = options;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;
		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_degraded:
			printk(KERN_INFO "btrfs: allowing degraded mounts\n");
			btrfs_set_opt(info->mount_opt, DEGRADED);
			break;
		case Opt_subvol:
		case Opt_subvolid:
		case Opt_device:
			/*
			 * These are parsed by btrfs_parse_early_options
			 * and can be happily ignored here.
			 */
			break;
		case Opt_nodatasum:
			printk(KERN_INFO "btrfs: setting nodatasum\n");
			btrfs_set_opt(info->mount_opt, NODATASUM);
			break;
		case Opt_nodatacow:
			printk(KERN_INFO "btrfs: setting nodatacow\n");
			btrfs_set_opt(info->mount_opt, NODATACOW);
			btrfs_set_opt(info->mount_opt, NODATASUM);
			break;
		case Opt_compress_force:
		case Opt_compress_force_type:
			compress_force = true;
		case Opt_compress:
		case Opt_compress_type:
			if (token == Opt_compress ||
			    token == Opt_compress_force ||
			    strcmp(args[0].from, "zlib") == 0) {
				compress_type = "zlib";
				info->compress_type = BTRFS_COMPRESS_ZLIB;
			} else if (strcmp(args[0].from, "lzo") == 0) {
				compress_type = "lzo";
				info->compress_type = BTRFS_COMPRESS_LZO;
			} else {
				ret = -EINVAL;
				goto out;
			}

			btrfs_set_opt(info->mount_opt, COMPRESS);
			if (compress_force) {
				btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
				pr_info("btrfs: force %s compression\n",
					compress_type);
			} else
				pr_info("btrfs: use %s compression\n",
					compress_type);
			break;
		case Opt_ssd:
			printk(KERN_INFO "btrfs: use ssd allocation scheme\n");
			btrfs_set_opt(info->mount_opt, SSD);
			break;
		case Opt_ssd_spread:
			printk(KERN_INFO "btrfs: use spread ssd "
			       "allocation scheme\n");
			btrfs_set_opt(info->mount_opt, SSD);
			btrfs_set_opt(info->mount_opt, SSD_SPREAD);
			break;
		case Opt_nossd:
			printk(KERN_INFO "btrfs: not using ssd allocation "
			       "scheme\n");
			btrfs_set_opt(info->mount_opt, NOSSD);
			btrfs_clear_opt(info->mount_opt, SSD);
			btrfs_clear_opt(info->mount_opt, SSD_SPREAD);
			break;
		case Opt_nobarrier:
			printk(KERN_INFO "btrfs: turning off barriers\n");
			btrfs_set_opt(info->mount_opt, NOBARRIER);
			break;
		case Opt_thread_pool:
			intarg = 0;
			match_int(&args[0], &intarg);
			if (intarg) {
				info->thread_pool_size = intarg;
				printk(KERN_INFO "btrfs: thread pool %d\n",
				       info->thread_pool_size);
			}
			break;
		case Opt_max_inline:
			num = match_strdup(&args[0]);
			if (num) {
				info->max_inline = memparse(num, NULL);
				kfree(num);

				if (info->max_inline) {
					info->max_inline = max_t(u64,
						info->max_inline,
						root->sectorsize);
				}
				printk(KERN_INFO "btrfs: max_inline at %llu\n",
					(unsigned long long)info->max_inline);
			}
			break;
		case Opt_alloc_start:
			num = match_strdup(&args[0]);
			if (num) {
				info->alloc_start = memparse(num, NULL);
				kfree(num);
				printk(KERN_INFO
					"btrfs: allocations start at %llu\n",
					(unsigned long long)info->alloc_start);
			}
			break;
		case Opt_noacl:
			root->fs_info->sb->s_flags &= ~MS_POSIXACL;
			break;
		case Opt_notreelog:
			printk(KERN_INFO "btrfs: disabling tree log\n");
			btrfs_set_opt(info->mount_opt, NOTREELOG);
			break;
		case Opt_flushoncommit:
			printk(KERN_INFO "btrfs: turning on flush-on-commit\n");
			btrfs_set_opt(info->mount_opt, FLUSHONCOMMIT);
			break;
		case Opt_ratio:
			intarg = 0;
			match_int(&args[0], &intarg);
			if (intarg) {
				info->metadata_ratio = intarg;
				printk(KERN_INFO "btrfs: metadata ratio %d\n",
				       info->metadata_ratio);
			}
			break;
		case Opt_discard:
			btrfs_set_opt(info->mount_opt, DISCARD);
			break;
		case Opt_space_cache:
			printk(KERN_INFO "btrfs: enabling disk space caching\n");
			btrfs_set_opt(info->mount_opt, SPACE_CACHE);
			break;
		case Opt_clear_cache:
			printk(KERN_INFO "btrfs: force clearing of disk cache\n");
			btrfs_set_opt(info->mount_opt, CLEAR_CACHE);
			break;
		case Opt_user_subvol_rm_allowed:
			btrfs_set_opt(info->mount_opt, USER_SUBVOL_RM_ALLOWED);
			break;
		case Opt_enospc_debug:
			btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG);
			break;
		case Opt_err:
			printk(KERN_INFO "btrfs: unrecognized mount option "
			       "'%s'\n", p);
			ret = -EINVAL;
			goto out;
		default:
			break;
		}
	}
out:
	kfree(orig);
	return ret;
}

/*
 * Parse mount options that are required early in the mount process.
 *
 * All other options will be parsed on much later in the mount process and
 * only when we need to allocate a new super block.
 */
static int btrfs_parse_early_options(const char *options, fmode_t flags,
		void *holder, char **subvol_name, u64 *subvol_objectid,
		struct btrfs_fs_devices **fs_devices)
{
	substring_t args[MAX_OPT_ARGS];
	char *opts, *orig, *p;
	int error = 0;
	int intarg;

	if (!options)
		goto out;

	/*
	 * strsep changes the string, duplicate it because parse_options
	 * gets called twice
	 */
	opts = kstrdup(options, GFP_KERNEL);
	if (!opts)
		return -ENOMEM;
	orig = opts;

	while ((p = strsep(&opts, ",")) != NULL) {
		int token;
		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_subvol:
			*subvol_name = match_strdup(&args[0]);
			break;
		case Opt_subvolid:
			intarg = 0;
			error = match_int(&args[0], &intarg);
			if (!error) {
				/* we want the original fs_tree */
				if (!intarg)
					*subvol_objectid =
						BTRFS_FS_TREE_OBJECTID;
				else
					*subvol_objectid = intarg;
			}
			break;
		case Opt_device:
			error = btrfs_scan_one_device(match_strdup(&args[0]),
					flags, holder, fs_devices);
			if (error)
				goto out_free_opts;
			break;
		default:
			break;
		}
	}

 out_free_opts:
	kfree(orig);
 out:
	/*
	 * If no subvolume name is specified we use the default one.  Allocate
	 * a copy of the string "." here so that code later in the
	 * mount path doesn't care if it's the default volume or another one.
	 */
	if (!*subvol_name) {
		*subvol_name = kstrdup(".", GFP_KERNEL);
		if (!*subvol_name)
			return -ENOMEM;
	}
	return error;
}

static struct dentry *get_default_root(struct super_block *sb,
				       u64 subvol_objectid)
{
	struct btrfs_root *root = sb->s_fs_info;
	struct btrfs_root *new_root;
	struct btrfs_dir_item *di;
	struct btrfs_path *path;
	struct btrfs_key location;
	struct inode *inode;
	struct dentry *dentry;
	u64 dir_id;
	int new = 0;

	/*
	 * We have a specific subvol we want to mount, just setup location and
	 * go look up the root.
	 */
	if (subvol_objectid) {
		location.objectid = subvol_objectid;
		location.type = BTRFS_ROOT_ITEM_KEY;
		location.offset = (u64)-1;
		goto find_root;
	}

	path = btrfs_alloc_path();
	if (!path)
		return ERR_PTR(-ENOMEM);
	path->leave_spinning = 1;

	/*
	 * Find the "default" dir item which points to the root item that we
	 * will mount by default if we haven't been given a specific subvolume
	 * to mount.
	 */
	dir_id = btrfs_super_root_dir(&root->fs_info->super_copy);
	di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0);
	if (IS_ERR(di))
		return ERR_CAST(di);
	if (!di) {
		/*
		 * Ok the default dir item isn't there.  This is weird since
		 * it's always been there, but don't freak out, just try and
		 * mount to root most subvolume.
		 */
		btrfs_free_path(path);
		dir_id = BTRFS_FIRST_FREE_OBJECTID;
		new_root = root->fs_info->fs_root;
		goto setup_root;
	}

	btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location);
	btrfs_free_path(path);

find_root:
	new_root = btrfs_read_fs_root_no_name(root->fs_info, &location);
	if (IS_ERR(new_root))
		return ERR_CAST(new_root);

	if (btrfs_root_refs(&new_root->root_item) == 0)
		return ERR_PTR(-ENOENT);

	dir_id = btrfs_root_dirid(&new_root->root_item);
setup_root:
	location.objectid = dir_id;
	location.type = BTRFS_INODE_ITEM_KEY;
	location.offset = 0;

	inode = btrfs_iget(sb, &location, new_root, &new);
	if (IS_ERR(inode))
		return ERR_CAST(inode);

	/*
	 * If we're just mounting the root most subvol put the inode and return
	 * a reference to the dentry.  We will have already gotten a reference
	 * to the inode in btrfs_fill_super so we're good to go.
	 */
	if (!new && sb->s_root->d_inode == inode) {
		iput(inode);
		return dget(sb->s_root);
	}

	if (new) {
		const struct qstr name = { .name = "/", .len = 1 };

		/*
		 * New inode, we need to make the dentry a sibling of s_root so
		 * everything gets cleaned up properly on unmount.
		 */
		dentry = d_alloc(sb->s_root, &name);
		if (!dentry) {
			iput(inode);
			return ERR_PTR(-ENOMEM);
		}
		d_splice_alias(inode, dentry);
	} else {
		/*
		 * We found the inode in cache, just find a dentry for it and
		 * put the reference to the inode we just got.
		 */
		dentry = d_find_alias(inode);
		iput(inode);
	}

	return dentry;
}

static int btrfs_fill_super(struct super_block *sb,
			    struct btrfs_fs_devices *fs_devices,
			    void *data, int silent)
{
	struct inode *inode;
	struct dentry *root_dentry;
	struct btrfs_root *tree_root;
	struct btrfs_key key;
	int err;

	sb->s_maxbytes = MAX_LFS_FILESIZE;
	sb->s_magic = BTRFS_SUPER_MAGIC;
	sb->s_op = &btrfs_super_ops;
	sb->s_d_op = &btrfs_dentry_operations;
	sb->s_export_op = &btrfs_export_ops;
	sb->s_xattr = btrfs_xattr_handlers;
	sb->s_time_gran = 1;
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
	sb->s_flags |= MS_POSIXACL;
#endif

	tree_root = open_ctree(sb, fs_devices, (char *)data);

	if (IS_ERR(tree_root)) {
		printk("btrfs: open_ctree failed\n");
		return PTR_ERR(tree_root);
	}
	sb->s_fs_info = tree_root;

	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
	key.type = BTRFS_INODE_ITEM_KEY;
	key.offset = 0;
	inode = btrfs_iget(sb, &key, tree_root->fs_info->fs_root, NULL);
	if (IS_ERR(inode)) {
		err = PTR_ERR(inode);
		goto fail_close;
	}

	root_dentry = d_alloc_root(inode);
	if (!root_dentry) {
		iput(inode);
		err = -ENOMEM;
		goto fail_close;
	}

	sb->s_root = root_dentry;

	save_mount_options(sb, data);
	return 0;

fail_close:
	close_ctree(tree_root);
	return err;
}

int btrfs_sync_fs(struct super_block *sb, int wait)
{
	struct btrfs_trans_handle *trans;
	struct btrfs_root *root = btrfs_sb(sb);
	int ret;

	trace_btrfs_sync_fs(wait);

	if (!wait) {
		filemap_flush(root->fs_info->btree_inode->i_mapping);
		return 0;
	}

	btrfs_start_delalloc_inodes(root, 0);
	btrfs_wait_ordered_extents(root, 0, 0);

	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans))
		return PTR_ERR(trans);
	ret = btrfs_commit_transaction(trans, root);
	return ret;
}

static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
	struct btrfs_root *root = btrfs_sb(vfs->mnt_sb);
	struct btrfs_fs_info *info = root->fs_info;
	char *compress_type;

	if (btrfs_test_opt(root, DEGRADED))
		seq_puts(seq, ",degraded");
	if (btrfs_test_opt(root, NODATASUM))
		seq_puts(seq, ",nodatasum");
	if (btrfs_test_opt(root, NODATACOW))
		seq_puts(seq, ",nodatacow");
	if (btrfs_test_opt(root, NOBARRIER))
		seq_puts(seq, ",nobarrier");
	if (info->max_inline != 8192 * 1024)
		seq_printf(seq, ",max_inline=%llu",
			   (unsigned long long)info->max_inline);
	if (info->alloc_start != 0)
		seq_printf(seq, ",alloc_start=%llu",
			   (unsigned long long)info->alloc_start);
	if (info->thread_pool_size !=  min_t(unsigned long,
					     num_online_cpus() + 2, 8))
		seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
	if (btrfs_test_opt(root, COMPRESS)) {
		if (info->compress_type == BTRFS_COMPRESS_ZLIB)
			compress_type = "zlib";
		else
			compress_type = "lzo";
		if (btrfs_test_opt(root, FORCE_COMPRESS))
			seq_printf(seq, ",compress-force=%s", compress_type);
		else
			seq_printf(seq, ",compress=%s", compress_type);
	}
	if (btrfs_test_opt(root, NOSSD))
		seq_puts(seq, ",nossd");
	if (btrfs_test_opt(root, SSD_SPREAD))
		seq_puts(seq, ",ssd_spread");
	else if (btrfs_test_opt(root, SSD))
		seq_puts(seq, ",ssd");
	if (btrfs_test_opt(root, NOTREELOG))
		seq_puts(seq, ",notreelog");
	if (btrfs_test_opt(root, FLUSHONCOMMIT))
		seq_puts(seq, ",flushoncommit");
	if (btrfs_test_opt(root, DISCARD))
		seq_puts(seq, ",discard");
	if (!(root->fs_info->sb->s_flags & MS_POSIXACL))
		seq_puts(seq, ",noacl");
	if (btrfs_test_opt(root, SPACE_CACHE))
		seq_puts(seq, ",space_cache");
	if (btrfs_test_opt(root, CLEAR_CACHE))
		seq_puts(seq, ",clear_cache");
	if (btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED))
		seq_puts(seq, ",user_subvol_rm_allowed");
	return 0;
}

static int btrfs_test_super(struct super_block *s, void *data)
{
	struct btrfs_root *test_root = data;
	struct btrfs_root *root = btrfs_sb(s);

	/*
	 * If this super block is going away, return false as it
	 * can't match as an existing super block.
	 */
	if (!atomic_read(&s->s_active))
		return 0;
	return root->fs_info->fs_devices == test_root->fs_info->fs_devices;
}

static int btrfs_set_super(struct super_block *s, void *data)
{
	s->s_fs_info = data;

	return set_anon_super(s, data);
}


/*
 * Find a superblock for the given device / mount point.
 *
 * Note:  This is based on get_sb_bdev from fs/super.c with a few additions
 *	  for multiple device setup.  Make sure to keep it in sync.
 */
static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
		const char *dev_name, void *data)
{
	struct block_device *bdev = NULL;
	struct super_block *s;
	struct dentry *root;
	struct btrfs_fs_devices *fs_devices = NULL;
	struct btrfs_root *tree_root = NULL;
	struct btrfs_fs_info *fs_info = NULL;
	fmode_t mode = FMODE_READ;
	char *subvol_name = NULL;
	u64 subvol_objectid = 0;
	int error = 0;

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

	error = btrfs_parse_early_options(data, mode, fs_type,
					  &subvol_name, &subvol_objectid,
					  &fs_devices);
	if (error)
		return ERR_PTR(error);

	error = btrfs_scan_one_device(dev_name, mode, fs_type, &fs_devices);
	if (error)
		goto error_free_subvol_name;

	error = btrfs_open_devices(fs_devices, mode, fs_type);
	if (error)
		goto error_free_subvol_name;

	if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) {
		error = -EACCES;
		goto error_close_devices;
	}

	/*
	 * Setup a dummy root and fs_info for test/set super.  This is because
	 * we don't actually fill this stuff out until open_ctree, but we need
	 * it for searching for existing supers, so this lets us do that and
	 * then open_ctree will properly initialize everything later.
	 */
	fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_NOFS);
	tree_root = kzalloc(sizeof(struct btrfs_root), GFP_NOFS);
	if (!fs_info || !tree_root) {
		error = -ENOMEM;
		goto error_close_devices;
	}
	fs_info->tree_root = tree_root;
	fs_info->fs_devices = fs_devices;
	tree_root->fs_info = fs_info;

	bdev = fs_devices->latest_bdev;
	s = sget(fs_type, btrfs_test_super, btrfs_set_super, tree_root);
	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_close_devices;
		}

		btrfs_close_devices(fs_devices);
		kfree(fs_info);
		kfree(tree_root);
	} else {
		char b[BDEVNAME_SIZE];

		s->s_flags = flags;
		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
		error = btrfs_fill_super(s, fs_devices, data,
					 flags & MS_SILENT ? 1 : 0);
		if (error) {
			deactivate_locked_super(s);
			goto error_free_subvol_name;
		}

		btrfs_sb(s)->fs_info->bdev_holder = fs_type;
		s->s_flags |= MS_ACTIVE;
	}

	root = get_default_root(s, subvol_objectid);
	if (IS_ERR(root)) {
		error = PTR_ERR(root);
		deactivate_locked_super(s);
		goto error_free_subvol_name;
	}
	/* if they gave us a subvolume name bind mount into that */
	if (strcmp(subvol_name, ".")) {
		struct dentry *new_root;
		mutex_lock(&root->d_inode->i_mutex);
		new_root = lookup_one_len(subvol_name, root,
				      strlen(subvol_name));
		mutex_unlock(&root->d_inode->i_mutex);

		if (IS_ERR(new_root)) {
			dput(root);
			deactivate_locked_super(s);
			error = PTR_ERR(new_root);
			goto error_free_subvol_name;
		}
		if (!new_root->d_inode) {
			dput(root);
			dput(new_root);
			deactivate_locked_super(s);
			error = -ENXIO;
			goto error_free_subvol_name;
		}
		dput(root);
		root = new_root;
	}

	kfree(subvol_name);
	return root;

error_s:
	error = PTR_ERR(s);
error_close_devices:
	btrfs_close_devices(fs_devices);
	kfree(fs_info);
	kfree(tree_root);
error_free_subvol_name:
	kfree(subvol_name);
	return ERR_PTR(error);
}

static int btrfs_remount(struct super_block *sb, int *flags, char *data)
{
	struct btrfs_root *root = btrfs_sb(sb);
	int ret;

	ret = btrfs_parse_options(root, data);
	if (ret)
		return -EINVAL;

	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
		return 0;

	if (*flags & MS_RDONLY) {
		sb->s_flags |= MS_RDONLY;

		ret =  btrfs_commit_super(root);
		WARN_ON(ret);
	} else {
		if (root->fs_info->fs_devices->rw_devices == 0)
			return -EACCES;

		if (btrfs_super_log_root(&root->fs_info->super_copy) != 0)
			return -EINVAL;

		ret = btrfs_cleanup_fs_roots(root->fs_info);
		WARN_ON(ret);

		/* recover relocation */
		ret = btrfs_recover_relocation(root);
		WARN_ON(ret);

		sb->s_flags &= ~MS_RDONLY;
	}

	return 0;
}

/*
 * The helper to calc the free space on the devices that can be used to store
 * file data.
 */
static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_device_info *devices_info;
	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
	struct btrfs_device *device;
	u64 skip_space;
	u64 type;
	u64 avail_space;
	u64 used_space;
	u64 min_stripe_size;
	int min_stripes = 1;
	int i = 0, nr_devices;
	int ret;

	nr_devices = fs_info->fs_devices->rw_devices;
	BUG_ON(!nr_devices);

	devices_info = kmalloc(sizeof(*devices_info) * nr_devices,
			       GFP_NOFS);
	if (!devices_info)
		return -ENOMEM;

	/* calc min stripe number for data space alloction */
	type = btrfs_get_alloc_profile(root, 1);
	if (type & BTRFS_BLOCK_GROUP_RAID0)
		min_stripes = 2;
	else if (type & BTRFS_BLOCK_GROUP_RAID1)
		min_stripes = 2;
	else if (type & BTRFS_BLOCK_GROUP_RAID10)
		min_stripes = 4;

	if (type & BTRFS_BLOCK_GROUP_DUP)
		min_stripe_size = 2 * BTRFS_STRIPE_LEN;
	else
		min_stripe_size = BTRFS_STRIPE_LEN;

	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
		if (!device->in_fs_metadata)
			continue;

		avail_space = device->total_bytes - device->bytes_used;

		/* align with stripe_len */
		do_div(avail_space, BTRFS_STRIPE_LEN);
		avail_space *= BTRFS_STRIPE_LEN;

		/*
		 * In order to avoid overwritting the superblock on the drive,
		 * btrfs starts at an offset of at least 1MB when doing chunk
		 * allocation.
		 */
		skip_space = 1024 * 1024;

		/* user can set the offset in fs_info->alloc_start. */
		if (fs_info->alloc_start + BTRFS_STRIPE_LEN <=
		    device->total_bytes)
			skip_space = max(fs_info->alloc_start, skip_space);

		/*
		 * btrfs can not use the free space in [0, skip_space - 1],
		 * we must subtract it from the total. In order to implement
		 * it, we account the used space in this range first.
		 */
		ret = btrfs_account_dev_extents_size(device, 0, skip_space - 1,
						     &used_space);
		if (ret) {
			kfree(devices_info);
			return ret;
		}

		/* calc the free space in [0, skip_space - 1] */
		skip_space -= used_space;

		/*
		 * we can use the free space in [0, skip_space - 1], subtract
		 * it from the total.
		 */
		if (avail_space && avail_space >= skip_space)
			avail_space -= skip_space;
		else
			avail_space = 0;

		if (avail_space < min_stripe_size)
			continue;

		devices_info[i].dev = device;
		devices_info[i].max_avail = avail_space;

		i++;
	}

	nr_devices = i;

	btrfs_descending_sort_devices(devices_info, nr_devices);

	i = nr_devices - 1;
	avail_space = 0;
	while (nr_devices >= min_stripes) {
		if (devices_info[i].max_avail >= min_stripe_size) {
			int j;
			u64 alloc_size;

			avail_space += devices_info[i].max_avail * min_stripes;
			alloc_size = devices_info[i].max_avail;
			for (j = i + 1 - min_stripes; j <= i; j++)
				devices_info[j].max_avail -= alloc_size;
		}
		i--;
		nr_devices--;
	}

	kfree(devices_info);
	*free_bytes = avail_space;
	return 0;
}

static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct btrfs_root *root = btrfs_sb(dentry->d_sb);
	struct btrfs_super_block *disk_super = &root->fs_info->super_copy;
	struct list_head *head = &root->fs_info->space_info;
	struct btrfs_space_info *found;
	u64 total_used = 0;
	u64 total_free_data = 0;
	int bits = dentry->d_sb->s_blocksize_bits;
	__be32 *fsid = (__be32 *)root->fs_info->fsid;
	int ret;

	/* holding chunk_muext to avoid allocating new chunks */
	mutex_lock(&root->fs_info->chunk_mutex);
	rcu_read_lock();
	list_for_each_entry_rcu(found, head, list) {
		if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
			total_free_data += found->disk_total - found->disk_used;
			total_free_data -=
				btrfs_account_ro_block_groups_free_space(found);
		}

		total_used += found->disk_used;
	}
	rcu_read_unlock();

	buf->f_namelen = BTRFS_NAME_LEN;
	buf->f_blocks = btrfs_super_total_bytes(disk_super) >> bits;
	buf->f_bfree = buf->f_blocks - (total_used >> bits);
	buf->f_bsize = dentry->d_sb->s_blocksize;
	buf->f_type = BTRFS_SUPER_MAGIC;
	buf->f_bavail = total_free_data;
	ret = btrfs_calc_avail_data_space(root, &total_free_data);
	if (ret) {
		mutex_unlock(&root->fs_info->chunk_mutex);
		return ret;
	}
	buf->f_bavail += total_free_data;
	buf->f_bavail = buf->f_bavail >> bits;
	mutex_unlock(&root->fs_info->chunk_mutex);

	/* We treat it as constant endianness (it doesn't matter _which_)
	   because we want the fsid to come out the same whether mounted
	   on a big-endian or little-endian host */
	buf->f_fsid.val[0] = be32_to_cpu(fsid[0]) ^ be32_to_cpu(fsid[2]);
	buf->f_fsid.val[1] = be32_to_cpu(fsid[1]) ^ be32_to_cpu(fsid[3]);
	/* Mask in the root object ID too, to disambiguate subvols */
	buf->f_fsid.val[0] ^= BTRFS_I(dentry->d_inode)->root->objectid >> 32;
	buf->f_fsid.val[1] ^= BTRFS_I(dentry->d_inode)->root->objectid;

	return 0;
}

static struct file_system_type btrfs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "btrfs",
	.mount		= btrfs_mount,
	.kill_sb	= kill_anon_super,
	.fs_flags	= FS_REQUIRES_DEV,
};

/*
 * used by btrfsctl to scan devices when no FS is mounted
 */
static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
				unsigned long arg)
{
	struct btrfs_ioctl_vol_args *vol;
	struct btrfs_fs_devices *fs_devices;
	int ret = -ENOTTY;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	vol = memdup_user((void __user *)arg, sizeof(*vol));
	if (IS_ERR(vol))
		return PTR_ERR(vol);

	switch (cmd) {
	case BTRFS_IOC_SCAN_DEV:
		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
					    &btrfs_fs_type, &fs_devices);
		break;
	}

	kfree(vol);
	return ret;
}

static int btrfs_freeze(struct super_block *sb)
{
	struct btrfs_root *root = btrfs_sb(sb);
	mutex_lock(&root->fs_info->transaction_kthread_mutex);
	mutex_lock(&root->fs_info->cleaner_mutex);
	return 0;
}

static int btrfs_unfreeze(struct super_block *sb)
{
	struct btrfs_root *root = btrfs_sb(sb);
	mutex_unlock(&root->fs_info->cleaner_mutex);
	mutex_unlock(&root->fs_info->transaction_kthread_mutex);
	return 0;
}

static const struct super_operations btrfs_super_ops = {
	.drop_inode	= btrfs_drop_inode,
	.evict_inode	= btrfs_evict_inode,
	.put_super	= btrfs_put_super,
	.sync_fs	= btrfs_sync_fs,
	.show_options	= btrfs_show_options,
	.write_inode	= btrfs_write_inode,
	.dirty_inode	= btrfs_dirty_inode,
	.alloc_inode	= btrfs_alloc_inode,
	.destroy_inode	= btrfs_destroy_inode,
	.statfs		= btrfs_statfs,
	.remount_fs	= btrfs_remount,
	.freeze_fs	= btrfs_freeze,
	.unfreeze_fs	= btrfs_unfreeze,
};

static const struct file_operations btrfs_ctl_fops = {
	.unlocked_ioctl	 = btrfs_control_ioctl,
	.compat_ioctl = btrfs_control_ioctl,
	.owner	 = THIS_MODULE,
	.llseek = noop_llseek,
};

static struct miscdevice btrfs_misc = {
	.minor		= BTRFS_MINOR,
	.name		= "btrfs-control",
	.fops		= &btrfs_ctl_fops
};

MODULE_ALIAS_MISCDEV(BTRFS_MINOR);
MODULE_ALIAS("devname:btrfs-control");

static int btrfs_interface_init(void)
{
	return misc_register(&btrfs_misc);
}

static void btrfs_interface_exit(void)
{
	if (misc_deregister(&btrfs_misc) < 0)
		printk(KERN_INFO "misc_deregister failed for control device");
}

static int __init init_btrfs_fs(void)
{
	int err;

	err = btrfs_init_sysfs();
	if (err)
		return err;

	err = btrfs_init_compress();
	if (err)
		goto free_sysfs;

	err = btrfs_init_cachep();
	if (err)
		goto free_compress;

	err = extent_io_init();
	if (err)
		goto free_cachep;

	err = extent_map_init();
	if (err)
		goto free_extent_io;

	err = btrfs_interface_init();
	if (err)
		goto free_extent_map;

	err = register_filesystem(&btrfs_fs_type);
	if (err)
		goto unregister_ioctl;

	printk(KERN_INFO "%s loaded\n", BTRFS_BUILD_VERSION);
	return 0;

unregister_ioctl:
	btrfs_interface_exit();
free_extent_map:
	extent_map_exit();
free_extent_io:
	extent_io_exit();
free_cachep:
	btrfs_destroy_cachep();
free_compress:
	btrfs_exit_compress();
free_sysfs:
	btrfs_exit_sysfs();
	return err;
}

static void __exit exit_btrfs_fs(void)
{
	btrfs_destroy_cachep();
	extent_map_exit();
	extent_io_exit();
	btrfs_interface_exit();
	unregister_filesystem(&btrfs_fs_type);
	btrfs_exit_sysfs();
	btrfs_cleanup_fs_uuids();
	btrfs_exit_compress();
}

module_init(init_btrfs_fs)
module_exit(exit_btrfs_fs)

MODULE_LICENSE("GPL");