super.c 85.8 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
/*
 * super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.
 *
4
 * Copyright (c) 2001-2005 Anton Altaparmakov
Linus Torvalds's avatar
Linus Torvalds committed
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
 * Copyright (c) 2001,2002 Richard Russon
 *
 * This program/include file is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as published
 * by the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program/include file 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 (in the main directory of the Linux-NTFS
 * distribution in the file COPYING); if not, write to the Free Software
 * Foundation,Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 */

#include <linux/stddef.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/spinlock.h>
#include <linux/blkdev.h>	/* For bdev_hardsect_size(). */
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/vfs.h>
#include <linux/moduleparam.h>
#include <linux/smp_lock.h>

#include "sysctl.h"
#include "logfile.h"
#include "quota.h"
#include "dir.h"
#include "debug.h"
#include "index.h"
#include "aops.h"
#include "malloc.h"
#include "ntfs.h"

44
/* Number of mounted filesystems which have compression enabled. */
Linus Torvalds's avatar
Linus Torvalds committed
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
static unsigned long ntfs_nr_compression_users;

/* A global default upcase table and a corresponding reference count. */
static ntfschar *default_upcase = NULL;
static unsigned long ntfs_nr_upcase_users = 0;

/* Error constants/strings used in inode.c::ntfs_show_options(). */
typedef enum {
	/* One of these must be present, default is ON_ERRORS_CONTINUE. */
	ON_ERRORS_PANIC			= 0x01,
	ON_ERRORS_REMOUNT_RO		= 0x02,
	ON_ERRORS_CONTINUE		= 0x04,
	/* Optional, can be combined with any of the above. */
	ON_ERRORS_RECOVER		= 0x10,
} ON_ERRORS_ACTIONS;

const option_t on_errors_arr[] = {
	{ ON_ERRORS_PANIC,	"panic" },
	{ ON_ERRORS_REMOUNT_RO,	"remount-ro", },
	{ ON_ERRORS_CONTINUE,	"continue", },
	{ ON_ERRORS_RECOVER,	"recover" },
	{ 0,			NULL }
};

/**
 * simple_getbool -
 *
 * Copied from old ntfs driver (which copied from vfat driver).
 */
static int simple_getbool(char *s, BOOL *setval)
{
	if (s) {
		if (!strcmp(s, "1") || !strcmp(s, "yes") || !strcmp(s, "true"))
			*setval = TRUE;
		else if (!strcmp(s, "0") || !strcmp(s, "no") ||
							!strcmp(s, "false"))
			*setval = FALSE;
		else
			return 0;
	} else
		*setval = TRUE;
	return 1;
}

/**
 * parse_options - parse the (re)mount options
 * @vol:	ntfs volume
 * @opt:	string containing the (re)mount options
 *
 * Parse the recognized options in @opt for the ntfs volume described by @vol.
 */
static BOOL parse_options(ntfs_volume *vol, char *opt)
{
	char *p, *v, *ov;
	static char *utf8 = "utf8";
	int errors = 0, sloppy = 0;
	uid_t uid = (uid_t)-1;
	gid_t gid = (gid_t)-1;
	mode_t fmask = (mode_t)-1, dmask = (mode_t)-1;
	int mft_zone_multiplier = -1, on_errors = -1;
105
	int show_sys_files = -1, case_sensitive = -1, disable_sparse = -1;
Linus Torvalds's avatar
Linus Torvalds committed
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
	struct nls_table *nls_map = NULL, *old_nls;

	/* I am lazy... (-8 */
#define NTFS_GETOPT_WITH_DEFAULT(option, variable, default_value)	\
	if (!strcmp(p, option)) {					\
		if (!v || !*v)						\
			variable = default_value;			\
		else {							\
			variable = simple_strtoul(ov = v, &v, 0);	\
			if (*v)						\
				goto needs_val;				\
		}							\
	}
#define NTFS_GETOPT(option, variable)					\
	if (!strcmp(p, option)) {					\
		if (!v || !*v)						\
			goto needs_arg;					\
		variable = simple_strtoul(ov = v, &v, 0);		\
		if (*v)							\
			goto needs_val;					\
	}
#define NTFS_GETOPT_BOOL(option, variable)				\
	if (!strcmp(p, option)) {					\
		BOOL val;						\
		if (!simple_getbool(v, &val))				\
			goto needs_bool;				\
		variable = val;						\
	}
#define NTFS_GETOPT_OPTIONS_ARRAY(option, variable, opt_array)		\
	if (!strcmp(p, option)) {					\
		int _i;							\
		if (!v || !*v)						\
			goto needs_arg;					\
		ov = v;							\
		if (variable == -1)					\
			variable = 0;					\
		for (_i = 0; opt_array[_i].str && *opt_array[_i].str; _i++) \
			if (!strcmp(opt_array[_i].str, v)) {		\
				variable |= opt_array[_i].val;		\
				break;					\
			}						\
		if (!opt_array[_i].str || !*opt_array[_i].str)		\
			goto needs_val;					\
	}
	if (!opt || !*opt)
		goto no_mount_options;
	ntfs_debug("Entering with mount options string: %s", opt);
	while ((p = strsep(&opt, ","))) {
		if ((v = strchr(p, '=')))
			*v++ = 0;
		NTFS_GETOPT("uid", uid)
		else NTFS_GETOPT("gid", gid)
		else NTFS_GETOPT("umask", fmask = dmask)
		else NTFS_GETOPT("fmask", fmask)
		else NTFS_GETOPT("dmask", dmask)
		else NTFS_GETOPT("mft_zone_multiplier", mft_zone_multiplier)
		else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, TRUE)
		else NTFS_GETOPT_BOOL("show_sys_files", show_sys_files)
		else NTFS_GETOPT_BOOL("case_sensitive", case_sensitive)
165
		else NTFS_GETOPT_BOOL("disable_sparse", disable_sparse)
Linus Torvalds's avatar
Linus Torvalds committed
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
		else NTFS_GETOPT_OPTIONS_ARRAY("errors", on_errors,
				on_errors_arr)
		else if (!strcmp(p, "posix") || !strcmp(p, "show_inodes"))
			ntfs_warning(vol->sb, "Ignoring obsolete option %s.",
					p);
		else if (!strcmp(p, "nls") || !strcmp(p, "iocharset")) {
			if (!strcmp(p, "iocharset"))
				ntfs_warning(vol->sb, "Option iocharset is "
						"deprecated. Please use "
						"option nls=<charsetname> in "
						"the future.");
			if (!v || !*v)
				goto needs_arg;
use_utf8:
			old_nls = nls_map;
			nls_map = load_nls(v);
			if (!nls_map) {
				if (!old_nls) {
					ntfs_error(vol->sb, "NLS character set "
							"%s not found.", v);
					return FALSE;
				}
				ntfs_error(vol->sb, "NLS character set %s not "
						"found. Using previous one %s.",
						v, old_nls->charset);
				nls_map = old_nls;
			} else /* nls_map */ {
				if (old_nls)
					unload_nls(old_nls);
			}
		} else if (!strcmp(p, "utf8")) {
			BOOL val = FALSE;
			ntfs_warning(vol->sb, "Option utf8 is no longer "
				   "supported, using option nls=utf8. Please "
				   "use option nls=utf8 in the future and "
				   "make sure utf8 is compiled either as a "
				   "module or into the kernel.");
			if (!v || !*v)
				val = TRUE;
			else if (!simple_getbool(v, &val))
				goto needs_bool;
			if (val) {
				v = utf8;
				goto use_utf8;
			}
		} else {
			ntfs_error(vol->sb, "Unrecognized mount option %s.", p);
			if (errors < INT_MAX)
				errors++;
		}
#undef NTFS_GETOPT_OPTIONS_ARRAY
#undef NTFS_GETOPT_BOOL
#undef NTFS_GETOPT
#undef NTFS_GETOPT_WITH_DEFAULT
	}
no_mount_options:
	if (errors && !sloppy)
		return FALSE;
	if (sloppy)
		ntfs_warning(vol->sb, "Sloppy option given. Ignoring "
				"unrecognized mount option(s) and continuing.");
	/* Keep this first! */
	if (on_errors != -1) {
		if (!on_errors) {
			ntfs_error(vol->sb, "Invalid errors option argument "
					"or bug in options parser.");
			return FALSE;
		}
	}
	if (nls_map) {
		if (vol->nls_map && vol->nls_map != nls_map) {
			ntfs_error(vol->sb, "Cannot change NLS character set "
					"on remount.");
			return FALSE;
		} /* else (!vol->nls_map) */
		ntfs_debug("Using NLS character set %s.", nls_map->charset);
		vol->nls_map = nls_map;
	} else /* (!nls_map) */ {
		if (!vol->nls_map) {
			vol->nls_map = load_nls_default();
			if (!vol->nls_map) {
				ntfs_error(vol->sb, "Failed to load default "
						"NLS character set.");
				return FALSE;
			}
			ntfs_debug("Using default NLS character set (%s).",
					vol->nls_map->charset);
		}
	}
	if (mft_zone_multiplier != -1) {
		if (vol->mft_zone_multiplier && vol->mft_zone_multiplier !=
				mft_zone_multiplier) {
			ntfs_error(vol->sb, "Cannot change mft_zone_multiplier "
					"on remount.");
			return FALSE;
		}
		if (mft_zone_multiplier < 1 || mft_zone_multiplier > 4) {
			ntfs_error(vol->sb, "Invalid mft_zone_multiplier. "
					"Using default value, i.e. 1.");
			mft_zone_multiplier = 1;
		}
		vol->mft_zone_multiplier = mft_zone_multiplier;
	}
	if (!vol->mft_zone_multiplier)
		vol->mft_zone_multiplier = 1;
	if (on_errors != -1)
		vol->on_errors = on_errors;
	if (!vol->on_errors || vol->on_errors == ON_ERRORS_RECOVER)
		vol->on_errors |= ON_ERRORS_CONTINUE;
	if (uid != (uid_t)-1)
		vol->uid = uid;
	if (gid != (gid_t)-1)
		vol->gid = gid;
	if (fmask != (mode_t)-1)
		vol->fmask = fmask;
	if (dmask != (mode_t)-1)
		vol->dmask = dmask;
	if (show_sys_files != -1) {
		if (show_sys_files)
			NVolSetShowSystemFiles(vol);
		else
			NVolClearShowSystemFiles(vol);
	}
	if (case_sensitive != -1) {
		if (case_sensitive)
			NVolSetCaseSensitive(vol);
		else
			NVolClearCaseSensitive(vol);
	}
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
	if (disable_sparse != -1) {
		if (disable_sparse)
			NVolClearSparseEnabled(vol);
		else {
			if (!NVolSparseEnabled(vol) &&
					vol->major_ver && vol->major_ver < 3)
				ntfs_warning(vol->sb, "Not enabling sparse "
						"support due to NTFS volume "
						"version %i.%i (need at least "
						"version 3.0).", vol->major_ver,
						vol->minor_ver);
			else
				NVolSetSparseEnabled(vol);
		}
	}
Linus Torvalds's avatar
Linus Torvalds committed
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
	return TRUE;
needs_arg:
	ntfs_error(vol->sb, "The %s option requires an argument.", p);
	return FALSE;
needs_bool:
	ntfs_error(vol->sb, "The %s option requires a boolean argument.", p);
	return FALSE;
needs_val:
	ntfs_error(vol->sb, "Invalid %s option argument: %s", p, ov);
	return FALSE;
}

#ifdef NTFS_RW

/**
 * ntfs_write_volume_flags - write new flags to the volume information flags
 * @vol:	ntfs volume on which to modify the flags
 * @flags:	new flags value for the volume information flags
 *
 * Internal function.  You probably want to use ntfs_{set,clear}_volume_flags()
 * instead (see below).
 *
 * Replace the volume information flags on the volume @vol with the value
 * supplied in @flags.  Note, this overwrites the volume information flags, so
 * make sure to combine the flags you want to modify with the old flags and use
 * the result when calling ntfs_write_volume_flags().
 *
 * Return 0 on success and -errno on error.
 */
static int ntfs_write_volume_flags(ntfs_volume *vol, const VOLUME_FLAGS flags)
{
	ntfs_inode *ni = NTFS_I(vol->vol_ino);
	MFT_RECORD *m;
	VOLUME_INFORMATION *vi;
	ntfs_attr_search_ctx *ctx;
	int err;

	ntfs_debug("Entering, old flags = 0x%x, new flags = 0x%x.",
			le16_to_cpu(vol->vol_flags), le16_to_cpu(flags));
	if (vol->vol_flags == flags)
		goto done;
	BUG_ON(!ni);
	m = map_mft_record(ni);
	if (IS_ERR(m)) {
		err = PTR_ERR(m);
		goto err_out;
	}
	ctx = ntfs_attr_get_search_ctx(ni, m);
	if (!ctx) {
		err = -ENOMEM;
		goto put_unm_err_out;
	}
	err = ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,
			ctx);
	if (err)
		goto put_unm_err_out;
	vi = (VOLUME_INFORMATION*)((u8*)ctx->attr +
			le16_to_cpu(ctx->attr->data.resident.value_offset));
	vol->vol_flags = vi->flags = flags;
	flush_dcache_mft_record_page(ctx->ntfs_ino);
	mark_mft_record_dirty(ctx->ntfs_ino);
	ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(ni);
done:
	ntfs_debug("Done.");
	return 0;
put_unm_err_out:
	if (ctx)
		ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(ni);
err_out:
	ntfs_error(vol->sb, "Failed with error code %i.", -err);
	return err;
}

/**
 * ntfs_set_volume_flags - set bits in the volume information flags
 * @vol:	ntfs volume on which to modify the flags
 * @flags:	flags to set on the volume
 *
 * Set the bits in @flags in the volume information flags on the volume @vol.
 *
 * Return 0 on success and -errno on error.
 */
static inline int ntfs_set_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)
{
	flags &= VOLUME_FLAGS_MASK;
	return ntfs_write_volume_flags(vol, vol->vol_flags | flags);
}

/**
 * ntfs_clear_volume_flags - clear bits in the volume information flags
 * @vol:	ntfs volume on which to modify the flags
 * @flags:	flags to clear on the volume
 *
 * Clear the bits in @flags in the volume information flags on the volume @vol.
 *
 * Return 0 on success and -errno on error.
 */
static inline int ntfs_clear_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)
{
	flags &= VOLUME_FLAGS_MASK;
	flags = vol->vol_flags & cpu_to_le16(~le16_to_cpu(flags));
	return ntfs_write_volume_flags(vol, flags);
}

#endif /* NTFS_RW */

/**
 * ntfs_remount - change the mount options of a mounted ntfs filesystem
 * @sb:		superblock of mounted ntfs filesystem
 * @flags:	remount flags
 * @opt:	remount options string
 *
 * Change the mount options of an already mounted ntfs filesystem.
 *
 * NOTE:  The VFS sets the @sb->s_flags remount flags to @flags after
 * ntfs_remount() returns successfully (i.e. returns 0).  Otherwise,
 * @sb->s_flags are not changed.
 */
static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
{
	ntfs_volume *vol = NTFS_SB(sb);

	ntfs_debug("Entering with remount options string: %s", opt);
#ifndef NTFS_RW
	/* For read-only compiled driver, enforce all read-only flags. */
	*flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
#else /* NTFS_RW */
	/*
	 * For the read-write compiled driver, if we are remounting read-write,
	 * make sure there are no volume errors and that no unsupported volume
	 * flags are set.  Also, empty the logfile journal as it would become
	 * stale as soon as something is written to the volume and mark the
	 * volume dirty so that chkdsk is run if the volume is not umounted
	 * cleanly.  Finally, mark the quotas out of date so Windows rescans
	 * the volume on boot and updates them.
	 *
	 * When remounting read-only, mark the volume clean if no volume errors
	 * have occured.
	 */
	if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) {
		static const char *es = ".  Cannot remount read-write.";

		/* Remounting read-write. */
		if (NVolErrors(vol)) {
			ntfs_error(sb, "Volume has errors and is read-only%s",
					es);
			return -EROFS;
		}
		if (vol->vol_flags & VOLUME_IS_DIRTY) {
			ntfs_error(sb, "Volume is dirty and read-only%s", es);
			return -EROFS;
		}
		if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
			ntfs_error(sb, "Volume has unsupported flags set and "
					"is read-only%s", es);
			return -EROFS;
		}
		if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
			ntfs_error(sb, "Failed to set dirty bit in volume "
					"information flags%s", es);
			return -EROFS;
		}
#if 0
		// TODO: Enable this code once we start modifying anything that
		//	 is different between NTFS 1.2 and 3.x...
		/* Set NT4 compatibility flag on newer NTFS version volumes. */
		if ((vol->major_ver > 1)) {
			if (ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {
				ntfs_error(sb, "Failed to set NT4 "
						"compatibility flag%s", es);
				NVolSetErrors(vol);
				return -EROFS;
			}
		}
#endif
		if (!ntfs_empty_logfile(vol->logfile_ino)) {
			ntfs_error(sb, "Failed to empty journal $LogFile%s",
					es);
			NVolSetErrors(vol);
			return -EROFS;
		}
		if (!ntfs_mark_quotas_out_of_date(vol)) {
			ntfs_error(sb, "Failed to mark quotas out of date%s",
					es);
			NVolSetErrors(vol);
			return -EROFS;
		}
	} else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) {
		/* Remounting read-only. */
		if (!NVolErrors(vol)) {
			if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))
				ntfs_warning(sb, "Failed to clear dirty bit "
						"in volume information "
						"flags.  Run chkdsk.");
		}
	}
#endif /* NTFS_RW */

	// TODO: Deal with *flags.

	if (!parse_options(vol, opt))
		return -EINVAL;
	ntfs_debug("Done.");
	return 0;
}

/**
 * is_boot_sector_ntfs - check whether a boot sector is a valid NTFS boot sector
 * @sb:		Super block of the device to which @b belongs.
 * @b:		Boot sector of device @sb to check.
 * @silent:	If TRUE, all output will be silenced.
 *
 * is_boot_sector_ntfs() checks whether the boot sector @b is a valid NTFS boot
 * sector. Returns TRUE if it is valid and FALSE if not.
 *
 * @sb is only needed for warning/error output, i.e. it can be NULL when silent
 * is TRUE.
 */
static BOOL is_boot_sector_ntfs(const struct super_block *sb,
		const NTFS_BOOT_SECTOR *b, const BOOL silent)
{
	/*
	 * Check that checksum == sum of u32 values from b to the checksum
	 * field. If checksum is zero, no checking is done.
	 */
	if ((void*)b < (void*)&b->checksum && b->checksum) {
		le32 *u;
		u32 i;

		for (i = 0, u = (le32*)b; u < (le32*)(&b->checksum); ++u)
			i += le32_to_cpup(u);
		if (le32_to_cpu(b->checksum) != i)
			goto not_ntfs;
	}
	/* Check OEMidentifier is "NTFS    " */
	if (b->oem_id != magicNTFS)
		goto not_ntfs;
	/* Check bytes per sector value is between 256 and 4096. */
	if (le16_to_cpu(b->bpb.bytes_per_sector) < 0x100 ||
			le16_to_cpu(b->bpb.bytes_per_sector) > 0x1000)
		goto not_ntfs;
	/* Check sectors per cluster value is valid. */
	switch (b->bpb.sectors_per_cluster) {
	case 1: case 2: case 4: case 8: case 16: case 32: case 64: case 128:
		break;
	default:
		goto not_ntfs;
	}
	/* Check the cluster size is not above 65536 bytes. */
	if ((u32)le16_to_cpu(b->bpb.bytes_per_sector) *
			b->bpb.sectors_per_cluster > 0x10000)
		goto not_ntfs;
	/* Check reserved/unused fields are really zero. */
	if (le16_to_cpu(b->bpb.reserved_sectors) ||
			le16_to_cpu(b->bpb.root_entries) ||
			le16_to_cpu(b->bpb.sectors) ||
			le16_to_cpu(b->bpb.sectors_per_fat) ||
			le32_to_cpu(b->bpb.large_sectors) || b->bpb.fats)
		goto not_ntfs;
	/* Check clusters per file mft record value is valid. */
	if ((u8)b->clusters_per_mft_record < 0xe1 ||
			(u8)b->clusters_per_mft_record > 0xf7)
		switch (b->clusters_per_mft_record) {
		case 1: case 2: case 4: case 8: case 16: case 32: case 64:
			break;
		default:
			goto not_ntfs;
		}
	/* Check clusters per index block value is valid. */
	if ((u8)b->clusters_per_index_record < 0xe1 ||
			(u8)b->clusters_per_index_record > 0xf7)
		switch (b->clusters_per_index_record) {
		case 1: case 2: case 4: case 8: case 16: case 32: case 64:
			break;
		default:
			goto not_ntfs;
		}
	/*
	 * Check for valid end of sector marker. We will work without it, but
	 * many BIOSes will refuse to boot from a bootsector if the magic is
	 * incorrect, so we emit a warning.
	 */
	if (!silent && b->end_of_sector_marker != cpu_to_le16(0xaa55))
		ntfs_warning(sb, "Invalid end of sector marker.");
	return TRUE;
not_ntfs:
	return FALSE;
}

/**
 * read_ntfs_boot_sector - read the NTFS boot sector of a device
 * @sb:		super block of device to read the boot sector from
 * @silent:	if true, suppress all output
 *
 * Reads the boot sector from the device and validates it. If that fails, tries
 * to read the backup boot sector, first from the end of the device a-la NT4 and
 * later and then from the middle of the device a-la NT3.51 and before.
 *
 * If a valid boot sector is found but it is not the primary boot sector, we
 * repair the primary boot sector silently (unless the device is read-only or
 * the primary boot sector is not accessible).
 *
 * NOTE: To call this function, @sb must have the fields s_dev, the ntfs super
 * block (u.ntfs_sb), nr_blocks and the device flags (s_flags) initialized
 * to their respective values.
 *
 * Return the unlocked buffer head containing the boot sector or NULL on error.
 */
static struct buffer_head *read_ntfs_boot_sector(struct super_block *sb,
		const int silent)
{
	const char *read_err_str = "Unable to read %s boot sector.";
	struct buffer_head *bh_primary, *bh_backup;
	long nr_blocks = NTFS_SB(sb)->nr_blocks;

	/* Try to read primary boot sector. */
	if ((bh_primary = sb_bread(sb, 0))) {
		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
				bh_primary->b_data, silent))
			return bh_primary;
		if (!silent)
			ntfs_error(sb, "Primary boot sector is invalid.");
	} else if (!silent)
		ntfs_error(sb, read_err_str, "primary");
	if (!(NTFS_SB(sb)->on_errors & ON_ERRORS_RECOVER)) {
		if (bh_primary)
			brelse(bh_primary);
		if (!silent)
			ntfs_error(sb, "Mount option errors=recover not used. "
					"Aborting without trying to recover.");
		return NULL;
	}
	/* Try to read NT4+ backup boot sector. */
	if ((bh_backup = sb_bread(sb, nr_blocks - 1))) {
		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
				bh_backup->b_data, silent))
			goto hotfix_primary_boot_sector;
		brelse(bh_backup);
	} else if (!silent)
		ntfs_error(sb, read_err_str, "backup");
	/* Try to read NT3.51- backup boot sector. */
	if ((bh_backup = sb_bread(sb, nr_blocks >> 1))) {
		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
				bh_backup->b_data, silent))
			goto hotfix_primary_boot_sector;
		if (!silent)
			ntfs_error(sb, "Could not find a valid backup boot "
					"sector.");
		brelse(bh_backup);
	} else if (!silent)
		ntfs_error(sb, read_err_str, "backup");
	/* We failed. Cleanup and return. */
	if (bh_primary)
		brelse(bh_primary);
	return NULL;
hotfix_primary_boot_sector:
	if (bh_primary) {
		/*
		 * If we managed to read sector zero and the volume is not
		 * read-only, copy the found, valid backup boot sector to the
		 * primary boot sector.
		 */
		if (!(sb->s_flags & MS_RDONLY)) {
			ntfs_warning(sb, "Hot-fix: Recovering invalid primary "
					"boot sector from backup copy.");
			memcpy(bh_primary->b_data, bh_backup->b_data,
					sb->s_blocksize);
			mark_buffer_dirty(bh_primary);
			sync_dirty_buffer(bh_primary);
			if (buffer_uptodate(bh_primary)) {
				brelse(bh_backup);
				return bh_primary;
			}
			ntfs_error(sb, "Hot-fix: Device write error while "
					"recovering primary boot sector.");
		} else {
			ntfs_warning(sb, "Hot-fix: Recovery of primary boot "
					"sector failed: Read-only mount.");
		}
		brelse(bh_primary);
	}
	ntfs_warning(sb, "Using backup boot sector.");
	return bh_backup;
}

/**
 * parse_ntfs_boot_sector - parse the boot sector and store the data in @vol
 * @vol:	volume structure to initialise with data from boot sector
 * @b:		boot sector to parse
 *
 * Parse the ntfs boot sector @b and store all imporant information therein in
 * the ntfs super block @vol.  Return TRUE on success and FALSE on error.
 */
static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
{
	unsigned int sectors_per_cluster_bits, nr_hidden_sects;
	int clusters_per_mft_record, clusters_per_index_record;
	s64 ll;

	vol->sector_size = le16_to_cpu(b->bpb.bytes_per_sector);
	vol->sector_size_bits = ffs(vol->sector_size) - 1;
	ntfs_debug("vol->sector_size = %i (0x%x)", vol->sector_size,
			vol->sector_size);
	ntfs_debug("vol->sector_size_bits = %i (0x%x)", vol->sector_size_bits,
			vol->sector_size_bits);
	if (vol->sector_size != vol->sb->s_blocksize)
		ntfs_warning(vol->sb, "The boot sector indicates a sector size "
				"different from the device sector size.");
	ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster);
	sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1;
	ntfs_debug("sectors_per_cluster_bits = 0x%x",
			sectors_per_cluster_bits);
	nr_hidden_sects = le32_to_cpu(b->bpb.hidden_sectors);
	ntfs_debug("number of hidden sectors = 0x%x", nr_hidden_sects);
	vol->cluster_size = vol->sector_size << sectors_per_cluster_bits;
	vol->cluster_size_mask = vol->cluster_size - 1;
	vol->cluster_size_bits = ffs(vol->cluster_size) - 1;
	ntfs_debug("vol->cluster_size = %i (0x%x)", vol->cluster_size,
			vol->cluster_size);
	ntfs_debug("vol->cluster_size_mask = 0x%x", vol->cluster_size_mask);
	ntfs_debug("vol->cluster_size_bits = %i (0x%x)",
			vol->cluster_size_bits, vol->cluster_size_bits);
	if (vol->sector_size > vol->cluster_size) {
		ntfs_error(vol->sb, "Sector sizes above the cluster size are "
				"not supported.  Sorry.");
		return FALSE;
	}
	if (vol->sb->s_blocksize > vol->cluster_size) {
		ntfs_error(vol->sb, "Cluster sizes smaller than the device "
				"sector size are not supported.  Sorry.");
		return FALSE;
	}
	clusters_per_mft_record = b->clusters_per_mft_record;
	ntfs_debug("clusters_per_mft_record = %i (0x%x)",
			clusters_per_mft_record, clusters_per_mft_record);
	if (clusters_per_mft_record > 0)
		vol->mft_record_size = vol->cluster_size <<
				(ffs(clusters_per_mft_record) - 1);
	else
		/*
		 * When mft_record_size < cluster_size, clusters_per_mft_record
		 * = -log2(mft_record_size) bytes. mft_record_size normaly is
		 * 1024 bytes, which is encoded as 0xF6 (-10 in decimal).
		 */
		vol->mft_record_size = 1 << -clusters_per_mft_record;
	vol->mft_record_size_mask = vol->mft_record_size - 1;
	vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1;
	ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size,
			vol->mft_record_size);
	ntfs_debug("vol->mft_record_size_mask = 0x%x",
			vol->mft_record_size_mask);
	ntfs_debug("vol->mft_record_size_bits = %i (0x%x)",
			vol->mft_record_size_bits, vol->mft_record_size_bits);
	/*
	 * We cannot support mft record sizes above the PAGE_CACHE_SIZE since
	 * we store $MFT/$DATA, the table of mft records in the page cache.
	 */
	if (vol->mft_record_size > PAGE_CACHE_SIZE) {
		ntfs_error(vol->sb, "Mft record size %i (0x%x) exceeds the "
				"page cache size on your system %lu (0x%lx).  "
				"This is not supported.  Sorry.",
				vol->mft_record_size, vol->mft_record_size,
				PAGE_CACHE_SIZE, PAGE_CACHE_SIZE);
		return FALSE;
	}
	clusters_per_index_record = b->clusters_per_index_record;
	ntfs_debug("clusters_per_index_record = %i (0x%x)",
			clusters_per_index_record, clusters_per_index_record);
	if (clusters_per_index_record > 0)
		vol->index_record_size = vol->cluster_size <<
				(ffs(clusters_per_index_record) - 1);
	else
		/*
		 * When index_record_size < cluster_size,
		 * clusters_per_index_record = -log2(index_record_size) bytes.
		 * index_record_size normaly equals 4096 bytes, which is
		 * encoded as 0xF4 (-12 in decimal).
		 */
		vol->index_record_size = 1 << -clusters_per_index_record;
	vol->index_record_size_mask = vol->index_record_size - 1;
	vol->index_record_size_bits = ffs(vol->index_record_size) - 1;
	ntfs_debug("vol->index_record_size = %i (0x%x)",
			vol->index_record_size, vol->index_record_size);
	ntfs_debug("vol->index_record_size_mask = 0x%x",
			vol->index_record_size_mask);
	ntfs_debug("vol->index_record_size_bits = %i (0x%x)",
			vol->index_record_size_bits,
			vol->index_record_size_bits);
	/*
	 * Get the size of the volume in clusters and check for 64-bit-ness.
	 * Windows currently only uses 32 bits to save the clusters so we do
	 * the same as it is much faster on 32-bit CPUs.
	 */
	ll = sle64_to_cpu(b->number_of_sectors) >> sectors_per_cluster_bits;
	if ((u64)ll >= 1ULL << 32) {
		ntfs_error(vol->sb, "Cannot handle 64-bit clusters.  Sorry.");
		return FALSE;
	}
	vol->nr_clusters = ll;
	ntfs_debug("vol->nr_clusters = 0x%llx", (long long)vol->nr_clusters);
	/*
	 * On an architecture where unsigned long is 32-bits, we restrict the
	 * volume size to 2TiB (2^41). On a 64-bit architecture, the compiler
	 * will hopefully optimize the whole check away.
	 */
	if (sizeof(unsigned long) < 8) {
		if ((ll << vol->cluster_size_bits) >= (1ULL << 41)) {
			ntfs_error(vol->sb, "Volume size (%lluTiB) is too "
					"large for this architecture.  "
					"Maximum supported is 2TiB.  Sorry.",
					(unsigned long long)ll >> (40 -
					vol->cluster_size_bits));
			return FALSE;
		}
	}
	ll = sle64_to_cpu(b->mft_lcn);
	if (ll >= vol->nr_clusters) {
		ntfs_error(vol->sb, "MFT LCN is beyond end of volume.  Weird.");
		return FALSE;
	}
	vol->mft_lcn = ll;
	ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn);
	ll = sle64_to_cpu(b->mftmirr_lcn);
	if (ll >= vol->nr_clusters) {
		ntfs_error(vol->sb, "MFTMirr LCN is beyond end of volume.  "
				"Weird.");
		return FALSE;
	}
	vol->mftmirr_lcn = ll;
	ntfs_debug("vol->mftmirr_lcn = 0x%llx", (long long)vol->mftmirr_lcn);
#ifdef NTFS_RW
	/*
	 * Work out the size of the mft mirror in number of mft records. If the
	 * cluster size is less than or equal to the size taken by four mft
	 * records, the mft mirror stores the first four mft records. If the
	 * cluster size is bigger than the size taken by four mft records, the
	 * mft mirror contains as many mft records as will fit into one
	 * cluster.
	 */
	if (vol->cluster_size <= (4 << vol->mft_record_size_bits))
		vol->mftmirr_size = 4;
	else
		vol->mftmirr_size = vol->cluster_size >>
				vol->mft_record_size_bits;
	ntfs_debug("vol->mftmirr_size = %i", vol->mftmirr_size);
#endif /* NTFS_RW */
	vol->serial_no = le64_to_cpu(b->volume_serial_number);
	ntfs_debug("vol->serial_no = 0x%llx",
			(unsigned long long)vol->serial_no);
	return TRUE;
}

/**
 * ntfs_setup_allocators - initialize the cluster and mft allocators
 * @vol:	volume structure for which to setup the allocators
 *
 * Setup the cluster (lcn) and mft allocators to the starting values.
 */
static void ntfs_setup_allocators(ntfs_volume *vol)
{
#ifdef NTFS_RW
	LCN mft_zone_size, mft_lcn;
#endif /* NTFS_RW */

	ntfs_debug("vol->mft_zone_multiplier = 0x%x",
			vol->mft_zone_multiplier);
#ifdef NTFS_RW
	/* Determine the size of the MFT zone. */
	mft_zone_size = vol->nr_clusters;
	switch (vol->mft_zone_multiplier) {  /* % of volume size in clusters */
	case 4:
		mft_zone_size >>= 1;			/* 50%   */
		break;
	case 3:
		mft_zone_size = (mft_zone_size +
				(mft_zone_size >> 1)) >> 2;	/* 37.5% */
		break;
	case 2:
		mft_zone_size >>= 2;			/* 25%   */
		break;
	/* case 1: */
	default:
		mft_zone_size >>= 3;			/* 12.5% */
		break;
	}
	/* Setup the mft zone. */
	vol->mft_zone_start = vol->mft_zone_pos = vol->mft_lcn;
	ntfs_debug("vol->mft_zone_pos = 0x%llx",
			(unsigned long long)vol->mft_zone_pos);
	/*
	 * Calculate the mft_lcn for an unmodified NTFS volume (see mkntfs
	 * source) and if the actual mft_lcn is in the expected place or even
	 * further to the front of the volume, extend the mft_zone to cover the
	 * beginning of the volume as well.  This is in order to protect the
	 * area reserved for the mft bitmap as well within the mft_zone itself.
	 * On non-standard volumes we do not protect it as the overhead would
	 * be higher than the speed increase we would get by doing it.
	 */
	mft_lcn = (8192 + 2 * vol->cluster_size - 1) / vol->cluster_size;
	if (mft_lcn * vol->cluster_size < 16 * 1024)
		mft_lcn = (16 * 1024 + vol->cluster_size - 1) /
				vol->cluster_size;
	if (vol->mft_zone_start <= mft_lcn)
		vol->mft_zone_start = 0;
	ntfs_debug("vol->mft_zone_start = 0x%llx",
			(unsigned long long)vol->mft_zone_start);
	/*
	 * Need to cap the mft zone on non-standard volumes so that it does
	 * not point outside the boundaries of the volume.  We do this by
	 * halving the zone size until we are inside the volume.
	 */
	vol->mft_zone_end = vol->mft_lcn + mft_zone_size;
	while (vol->mft_zone_end >= vol->nr_clusters) {
		mft_zone_size >>= 1;
		vol->mft_zone_end = vol->mft_lcn + mft_zone_size;
	}
	ntfs_debug("vol->mft_zone_end = 0x%llx",
			(unsigned long long)vol->mft_zone_end);
	/*
	 * Set the current position within each data zone to the start of the
	 * respective zone.
	 */
	vol->data1_zone_pos = vol->mft_zone_end;
	ntfs_debug("vol->data1_zone_pos = 0x%llx",
			(unsigned long long)vol->data1_zone_pos);
	vol->data2_zone_pos = 0;
	ntfs_debug("vol->data2_zone_pos = 0x%llx",
			(unsigned long long)vol->data2_zone_pos);

	/* Set the mft data allocation position to mft record 24. */
	vol->mft_data_pos = 24;
	ntfs_debug("vol->mft_data_pos = 0x%llx",
			(unsigned long long)vol->mft_data_pos);
#endif /* NTFS_RW */
}

#ifdef NTFS_RW

/**
 * load_and_init_mft_mirror - load and setup the mft mirror inode for a volume
 * @vol:	ntfs super block describing device whose mft mirror to load
 *
 * Return TRUE on success or FALSE on error.
 */
static BOOL load_and_init_mft_mirror(ntfs_volume *vol)
{
	struct inode *tmp_ino;
	ntfs_inode *tmp_ni;

	ntfs_debug("Entering.");
	/* Get mft mirror inode. */
	tmp_ino = ntfs_iget(vol->sb, FILE_MFTMirr);
	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
		if (!IS_ERR(tmp_ino))
			iput(tmp_ino);
		/* Caller will display error message. */
		return FALSE;
	}
	/*
	 * Re-initialize some specifics about $MFTMirr's inode as
	 * ntfs_read_inode() will have set up the default ones.
	 */
	/* Set uid and gid to root. */
	tmp_ino->i_uid = tmp_ino->i_gid = 0;
	/* Regular file.  No access for anyone. */
	tmp_ino->i_mode = S_IFREG;
	/* No VFS initiated operations allowed for $MFTMirr. */
	tmp_ino->i_op = &ntfs_empty_inode_ops;
	tmp_ino->i_fop = &ntfs_empty_file_ops;
	/* Put in our special address space operations. */
	tmp_ino->i_mapping->a_ops = &ntfs_mst_aops;
	tmp_ni = NTFS_I(tmp_ino);
	/* The $MFTMirr, like the $MFT is multi sector transfer protected. */
	NInoSetMstProtected(tmp_ni);
986
	NInoSetSparseDisabled(tmp_ni);
Linus Torvalds's avatar
Linus Torvalds committed
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
	/*
	 * Set up our little cheat allowing us to reuse the async read io
	 * completion handler for directories.
	 */
	tmp_ni->itype.index.block_size = vol->mft_record_size;
	tmp_ni->itype.index.block_size_bits = vol->mft_record_size_bits;
	vol->mftmirr_ino = tmp_ino;
	ntfs_debug("Done.");
	return TRUE;
}

/**
 * check_mft_mirror - compare contents of the mft mirror with the mft
 * @vol:	ntfs super block describing device whose mft mirror to check
 *
 * Return TRUE on success or FALSE on error.
 *
 * Note, this function also results in the mft mirror runlist being completely
 * mapped into memory.  The mft mirror write code requires this and will BUG()
 * should it find an unmapped runlist element.
 */
static BOOL check_mft_mirror(ntfs_volume *vol)
{
	struct super_block *sb = vol->sb;
	ntfs_inode *mirr_ni;
	struct page *mft_page, *mirr_page;
	u8 *kmft, *kmirr;
	runlist_element *rl, rl2[2];
1015
	pgoff_t index;
Linus Torvalds's avatar
Linus Torvalds committed
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
	int mrecs_per_page, i;

	ntfs_debug("Entering.");
	/* Compare contents of $MFT and $MFTMirr. */
	mrecs_per_page = PAGE_CACHE_SIZE / vol->mft_record_size;
	BUG_ON(!mrecs_per_page);
	BUG_ON(!vol->mftmirr_size);
	mft_page = mirr_page = NULL;
	kmft = kmirr = NULL;
	index = i = 0;
	do {
		u32 bytes;

		/* Switch pages if necessary. */
		if (!(i % mrecs_per_page)) {
			if (index) {
				ntfs_unmap_page(mft_page);
				ntfs_unmap_page(mirr_page);
			}
			/* Get the $MFT page. */
			mft_page = ntfs_map_page(vol->mft_ino->i_mapping,
					index);
			if (IS_ERR(mft_page)) {
				ntfs_error(sb, "Failed to read $MFT.");
				return FALSE;
			}
			kmft = page_address(mft_page);
			/* Get the $MFTMirr page. */
			mirr_page = ntfs_map_page(vol->mftmirr_ino->i_mapping,
					index);
			if (IS_ERR(mirr_page)) {
				ntfs_error(sb, "Failed to read $MFTMirr.");
				goto mft_unmap_out;
			}
			kmirr = page_address(mirr_page);
			++index;
		}
		/* Make sure the record is ok. */
		if (ntfs_is_baad_recordp((le32*)kmft)) {
			ntfs_error(sb, "Incomplete multi sector transfer "
					"detected in mft record %i.", i);
mm_unmap_out:
			ntfs_unmap_page(mirr_page);
mft_unmap_out:
			ntfs_unmap_page(mft_page);
			return FALSE;
		}
		if (ntfs_is_baad_recordp((le32*)kmirr)) {
			ntfs_error(sb, "Incomplete multi sector transfer "
					"detected in mft mirror record %i.", i);
			goto mm_unmap_out;
		}
		/* Get the amount of data in the current record. */
		bytes = le32_to_cpu(((MFT_RECORD*)kmft)->bytes_in_use);
		if (!bytes || bytes > vol->mft_record_size) {
			bytes = le32_to_cpu(((MFT_RECORD*)kmirr)->bytes_in_use);
			if (!bytes || bytes > vol->mft_record_size)
				bytes = vol->mft_record_size;
		}
		/* Compare the two records. */
		if (memcmp(kmft, kmirr, bytes)) {
			ntfs_error(sb, "$MFT and $MFTMirr (record %i) do not "
					"match.  Run ntfsfix or chkdsk.", i);
			goto mm_unmap_out;
		}
		kmft += vol->mft_record_size;
		kmirr += vol->mft_record_size;
	} while (++i < vol->mftmirr_size);
	/* Release the last pages. */
	ntfs_unmap_page(mft_page);
	ntfs_unmap_page(mirr_page);

	/* Construct the mft mirror runlist by hand. */
	rl2[0].vcn = 0;
	rl2[0].lcn = vol->mftmirr_lcn;
	rl2[0].length = (vol->mftmirr_size * vol->mft_record_size +
			vol->cluster_size - 1) / vol->cluster_size;
	rl2[1].vcn = rl2[0].length;
	rl2[1].lcn = LCN_ENOENT;
	rl2[1].length = 0;
	/*
	 * Because we have just read all of the mft mirror, we know we have
	 * mapped the full runlist for it.
	 */
	mirr_ni = NTFS_I(vol->mftmirr_ino);
	down_read(&mirr_ni->runlist.lock);
	rl = mirr_ni->runlist.rl;
	/* Compare the two runlists.  They must be identical. */
	i = 0;
	do {
		if (rl2[i].vcn != rl[i].vcn || rl2[i].lcn != rl[i].lcn ||
				rl2[i].length != rl[i].length) {
			ntfs_error(sb, "$MFTMirr location mismatch.  "
					"Run chkdsk.");
			up_read(&mirr_ni->runlist.lock);
			return FALSE;
		}
	} while (rl2[i++].length);
	up_read(&mirr_ni->runlist.lock);
	ntfs_debug("Done.");
	return TRUE;
}

/**
 * load_and_check_logfile - load and check the logfile inode for a volume
 * @vol:	ntfs super block describing device whose logfile to load
 *
 * Return TRUE on success or FALSE on error.
 */
static BOOL load_and_check_logfile(ntfs_volume *vol)
{
	struct inode *tmp_ino;

	ntfs_debug("Entering.");
	tmp_ino = ntfs_iget(vol->sb, FILE_LogFile);
	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
		if (!IS_ERR(tmp_ino))
			iput(tmp_ino);
		/* Caller will display error message. */
		return FALSE;
	}
	if (!ntfs_check_logfile(tmp_ino)) {
		iput(tmp_ino);
		/* ntfs_check_logfile() will have displayed error output. */
		return FALSE;
	}
1142
	NInoSetSparseDisabled(NTFS_I(tmp_ino));
Linus Torvalds's avatar
Linus Torvalds committed
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
	vol->logfile_ino = tmp_ino;
	ntfs_debug("Done.");
	return TRUE;
}

/**
 * load_and_init_quota - load and setup the quota file for a volume if present
 * @vol:	ntfs super block describing device whose quota file to load
 *
 * Return TRUE on success or FALSE on error.  If $Quota is not present, we
 * leave vol->quota_ino as NULL and return success.
 */
static BOOL load_and_init_quota(ntfs_volume *vol)
{
	MFT_REF mref;
	struct inode *tmp_ino;
	ntfs_name *name = NULL;
	static const ntfschar Quota[7] = { const_cpu_to_le16('$'),
			const_cpu_to_le16('Q'), const_cpu_to_le16('u'),
			const_cpu_to_le16('o'), const_cpu_to_le16('t'),
			const_cpu_to_le16('a'), 0 };
	static ntfschar Q[3] = { const_cpu_to_le16('$'),
			const_cpu_to_le16('Q'), 0 };

	ntfs_debug("Entering.");
	/*
	 * Find the inode number for the quota file by looking up the filename
	 * $Quota in the extended system files directory $Extend.
	 */
	down(&vol->extend_ino->i_sem);
	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), Quota, 6,
			&name);
	up(&vol->extend_ino->i_sem);
	if (IS_ERR_MREF(mref)) {
		/*
		 * If the file does not exist, quotas are disabled and have
		 * never been enabled on this volume, just return success.
		 */
		if (MREF_ERR(mref) == -ENOENT) {
			ntfs_debug("$Quota not present.  Volume does not have "
					"quotas enabled.");
			/*
			 * No need to try to set quotas out of date if they are
			 * not enabled.
			 */
			NVolSetQuotaOutOfDate(vol);
			return TRUE;
		}
		/* A real error occured. */
		ntfs_error(vol->sb, "Failed to find inode number for $Quota.");
		return FALSE;
	}
	/* We do not care for the type of match that was found. */
	if (name)
		kfree(name);
	/* Get the inode. */
	tmp_ino = ntfs_iget(vol->sb, MREF(mref));
	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
		if (!IS_ERR(tmp_ino))
			iput(tmp_ino);
		ntfs_error(vol->sb, "Failed to load $Quota.");
		return FALSE;
	}
	vol->quota_ino = tmp_ino;
	/* Get the $Q index allocation attribute. */
	tmp_ino = ntfs_index_iget(vol->quota_ino, Q, 2);
	if (IS_ERR(tmp_ino)) {
		ntfs_error(vol->sb, "Failed to load $Quota/$Q index.");
		return FALSE;
	}
	vol->quota_q_ino = tmp_ino;
	ntfs_debug("Done.");
	return TRUE;
}

/**
 * load_and_init_attrdef - load the attribute definitions table for a volume
 * @vol:	ntfs super block describing device whose attrdef to load
 *
 * Return TRUE on success or FALSE on error.
 */
static BOOL load_and_init_attrdef(ntfs_volume *vol)
{
1226
	loff_t i_size;
Linus Torvalds's avatar
Linus Torvalds committed
1227
1228
1229
	struct super_block *sb = vol->sb;
	struct inode *ino;
	struct page *page;
1230
	pgoff_t index, max_index;
Linus Torvalds's avatar
Linus Torvalds committed
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
	unsigned int size;

	ntfs_debug("Entering.");
	/* Read attrdef table and setup vol->attrdef and vol->attrdef_size. */
	ino = ntfs_iget(sb, FILE_AttrDef);
	if (IS_ERR(ino) || is_bad_inode(ino)) {
		if (!IS_ERR(ino))
			iput(ino);
		goto failed;
	}
1241
	NInoSetSparseDisabled(NTFS_I(ino));
Linus Torvalds's avatar
Linus Torvalds committed
1242
	/* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */
1243
1244
	i_size = i_size_read(ino);
	if (i_size <= 0 || i_size > 0x7fffffff)
Linus Torvalds's avatar
Linus Torvalds committed
1245
		goto iput_failed;
1246
	vol->attrdef = (ATTR_DEF*)ntfs_malloc_nofs(i_size);
Linus Torvalds's avatar
Linus Torvalds committed
1247
1248
1249
	if (!vol->attrdef)
		goto iput_failed;
	index = 0;
1250
	max_index = i_size >> PAGE_CACHE_SHIFT;
Linus Torvalds's avatar
Linus Torvalds committed
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
	size = PAGE_CACHE_SIZE;
	while (index < max_index) {
		/* Read the attrdef table and copy it into the linear buffer. */
read_partial_attrdef_page:
		page = ntfs_map_page(ino->i_mapping, index);
		if (IS_ERR(page))
			goto free_iput_failed;
		memcpy((u8*)vol->attrdef + (index++ << PAGE_CACHE_SHIFT),
				page_address(page), size);
		ntfs_unmap_page(page);
	};
	if (size == PAGE_CACHE_SIZE) {
1263
		size = i_size & ~PAGE_CACHE_MASK;
Linus Torvalds's avatar
Linus Torvalds committed
1264
1265
1266
		if (size)
			goto read_partial_attrdef_page;
	}
1267
1268
	vol->attrdef_size = i_size;
	ntfs_debug("Read %llu bytes from $AttrDef.", i_size);
Linus Torvalds's avatar
Linus Torvalds committed
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
	iput(ino);
	return TRUE;
free_iput_failed:
	ntfs_free(vol->attrdef);
	vol->attrdef = NULL;
iput_failed:
	iput(ino);
failed:
	ntfs_error(sb, "Failed to initialize attribute definition table.");
	return FALSE;
}

#endif /* NTFS_RW */

/**
 * load_and_init_upcase - load the upcase table for an ntfs volume
 * @vol:	ntfs super block describing device whose upcase to load
 *
 * Return TRUE on success or FALSE on error.
 */
static BOOL load_and_init_upcase(ntfs_volume *vol)
{
1291
	loff_t i_size;
Linus Torvalds's avatar
Linus Torvalds committed
1292
1293
1294
	struct super_block *sb = vol->sb;
	struct inode *ino;
	struct page *page;
1295
	pgoff_t index, max_index;
Linus Torvalds's avatar
Linus Torvalds committed
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
	unsigned int size;
	int i, max;

	ntfs_debug("Entering.");
	/* Read upcase table and setup vol->upcase and vol->upcase_len. */
	ino = ntfs_iget(sb, FILE_UpCase);
	if (IS_ERR(ino) || is_bad_inode(ino)) {
		if (!IS_ERR(ino))
			iput(ino);
		goto upcase_failed;
	}
	/*
	 * The upcase size must not be above 64k Unicode characters, must not
	 * be zero and must be a multiple of sizeof(ntfschar).
	 */
1311
1312
1313
	i_size = i_size_read(ino);
	if (!i_size || i_size & (sizeof(ntfschar) - 1) ||
			i_size > 64ULL * 1024 * sizeof(ntfschar))
Linus Torvalds's avatar
Linus Torvalds committed
1314
		goto iput_upcase_failed;
1315
	vol->upcase = (ntfschar*)ntfs_malloc_nofs(i_size);
Linus Torvalds's avatar
Linus Torvalds committed
1316
1317
1318
	if (!vol->upcase)
		goto iput_upcase_failed;
	index = 0;
1319
	max_index = i_size >> PAGE_CACHE_SHIFT;
Linus Torvalds's avatar
Linus Torvalds committed
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
	size = PAGE_CACHE_SIZE;
	while (index < max_index) {
		/* Read the upcase table and copy it into the linear buffer. */
read_partial_upcase_page:
		page = ntfs_map_page(ino->i_mapping, index);
		if (IS_ERR(page))
			goto iput_upcase_failed;
		memcpy((char*)vol->upcase + (index++ << PAGE_CACHE_SHIFT),
				page_address(page), size);
		ntfs_unmap_page(page);
	};
	if (size == PAGE_CACHE_SIZE) {
1332
		size = i_size & ~PAGE_CACHE_MASK;
Linus Torvalds's avatar
Linus Torvalds committed
1333
1334
1335
		if (size)
			goto read_partial_upcase_page;
	}
1336
	vol->upcase_len = i_size >> UCHAR_T_SIZE_BITS;
Linus Torvalds's avatar
Linus Torvalds committed
1337
	ntfs_debug("Read %llu bytes from $UpCase (expected %zu bytes).",
1338
			i_size, 64 * 1024 * sizeof(ntfschar));
Linus Torvalds's avatar
Linus Torvalds committed
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
	iput(ino);
	down(&ntfs_lock);
	if (!default_upcase) {
		ntfs_debug("Using volume specified $UpCase since default is "
				"not present.");
		up(&ntfs_lock);
		return TRUE;
	}
	max = default_upcase_len;
	if (max > vol->upcase_len)
		max = vol->upcase_len;
	for (i = 0; i < max; i++)
		if (vol->upcase[i] != default_upcase[i])
			break;
	if (i == max) {
		ntfs_free(vol->upcase);
		vol->upcase = default_upcase;
		vol->upcase_len = max;
		ntfs_nr_upcase_users++;
		up(&ntfs_lock);
		ntfs_debug("Volume specified $UpCase matches default. Using "
				"default.");
		return TRUE;
	}
	up(&ntfs_lock);
	ntfs_debug("Using volume specified $UpCase since it does not match "
			"the default.");
	return TRUE;
iput_upcase_failed:
	iput(ino);
	ntfs_free(vol->upcase);
	vol->upcase = NULL;
upcase_failed:
	down(&ntfs_lock);
	if (default_upcase) {
		vol->upcase = default_upcase;
		vol->upcase_len = default_upcase_len;
		ntfs_nr_upcase_users++;
		up(&ntfs_lock);
		ntfs_error(sb, "Failed to load $UpCase from the volume. Using "
				"default.");
		return TRUE;
	}
	up(&ntfs_lock);
	ntfs_error(sb, "Failed to initialize upcase table.");
	return FALSE;
}

/**
 * load_system_files - open the system files using normal functions
 * @vol:	ntfs super block describing device whose system files to load
 *
 * Open the system files with normal access functions and complete setting up
 * the ntfs super block @vol.
 *
 * Return TRUE on success or FALSE on error.
 */
static BOOL load_system_files(ntfs_volume *vol)
{
	struct super_block *sb = vol->sb;
	MFT_RECORD *m;
	VOLUME_INFORMATION *vi;
	ntfs_attr_search_ctx *ctx;

	ntfs_debug("Entering.");
#ifdef NTFS_RW
	/* Get mft mirror inode compare the contents of $MFT and $MFTMirr. */
	if (!load_and_init_mft_mirror(vol) || !check_mft_mirror(vol)) {
		static const char *es1 = "Failed to load $MFTMirr";
		static const char *es2 = "$MFTMirr does not match $MFT";
		static const char *es3 = ".  Run ntfsfix and/or chkdsk.";

		/* If a read-write mount, convert it to a read-only mount. */
		if (!(sb->s_flags & MS_RDONLY)) {
			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
					ON_ERRORS_CONTINUE))) {
				ntfs_error(sb, "%s and neither on_errors="
						"continue nor on_errors="
						"remount-ro was specified%s",
						!vol->mftmirr_ino ? es1 : es2,
						es3);
				goto iput_mirr_err_out;
			}
			sb->s_flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
			ntfs_error(sb, "%s.  Mounting read-only%s",
					!vol->mftmirr_ino ? es1 : es2, es3);
		} else
			ntfs_warning(sb, "%s.  Will not be able to remount "
					"read-write%s",
					!vol->mftmirr_ino ? es1 : es2, es3);
		/* This will prevent a read-write remount. */
		NVolSetErrors(vol);
	}
#endif /* NTFS_RW */
	/* Get mft bitmap attribute inode. */
	vol->mftbmp_ino = ntfs_attr_iget(vol->mft_ino, AT_BITMAP, NULL, 0);
	if (IS_ERR(vol->mftbmp_ino)) {
		ntfs_error(sb, "Failed to load $MFT/$BITMAP attribute.");
		goto iput_mirr_err_out;
	}
	/* Read upcase table and setup @vol->upcase and @vol->upcase_len. */
	if (!load_and_init_upcase(vol))
		goto iput_mftbmp_err_out;
#ifdef NTFS_RW
	/*
	 * Read attribute definitions table and setup @vol->attrdef and
	 * @vol->attrdef_size.
	 */
	if (!load_and_init_attrdef(vol))
		goto iput_upcase_err_out;
#endif /* NTFS_RW */
	/*
	 * Get the cluster allocation bitmap inode and verify the size, no
	 * need for any locking at this stage as we are already running
	 * exclusively as we are mount in progress task.
	 */
	vol->lcnbmp_ino = ntfs_iget(sb, FILE_Bitmap);
	if (IS_ERR(vol->lcnbmp_ino) || is_bad_inode(vol->lcnbmp_ino)) {
		if (!IS_ERR(vol->lcnbmp_ino))
			iput(vol->lcnbmp_ino);
		goto bitmap_failed;
	}
1461
	NInoSetSparseDisabled(NTFS_I(vol->lcnbmp_ino));
1462
	if ((vol->nr_clusters + 7) >> 3 > i_size_read(vol->lcnbmp_ino)) {
Linus Torvalds's avatar
Linus Torvalds committed
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
		iput(vol->lcnbmp_ino);
bitmap_failed:
		ntfs_error(sb, "Failed to load $Bitmap.");
		goto iput_attrdef_err_out;
	}
	/*
	 * Get the volume inode and setup our cache of the volume flags and
	 * version.
	 */
	vol->vol_ino = ntfs_iget(sb, FILE_Volume);
	if (IS_ERR(vol->vol_ino) || is_bad_inode(vol->vol_ino)) {
		if (!IS_ERR(vol->vol_ino))
			iput(vol->vol_ino);
volume_failed:
		ntfs_error(sb, "Failed to load $Volume.");
		goto iput_lcnbmp_err_out;
	}
	m = map_mft_record(NTFS_I(vol->vol_ino));
	if (IS_ERR(m)) {
iput_volume_failed:
		iput(vol->vol_ino);
		goto volume_failed;
	}
	if (!(ctx = ntfs_attr_get_search_ctx(NTFS_I(vol->vol_ino), m))) {
		ntfs_error(sb, "Failed to get attribute search context.");
		goto get_ctx_vol_failed;
	}
	if (ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,
			ctx) || ctx->attr->non_resident || ctx->attr->flags) {
err_put_vol:
		ntfs_attr_put_search_ctx(ctx);
get_ctx_vol_failed:
		unmap_mft_record(NTFS_I(vol->vol_ino));
		goto iput_volume_failed;
	}
	vi = (VOLUME_INFORMATION*)((char*)ctx->attr +
			le16_to_cpu(ctx->attr->data.resident.value_offset));
	/* Some bounds checks. */
	if ((u8*)vi < (u8*)ctx->attr || (u8*)vi +
			le32_to_cpu(ctx->attr->data.resident.value_length) >
			(u8*)ctx->attr + le32_to_cpu(ctx->attr->length))
		goto err_put_vol;
	/* Copy the volume flags and version to the ntfs_volume structure. */
	vol->vol_flags = vi->flags;
	vol->major_ver = vi->major_ver;
	vol->minor_ver = vi->minor_ver;
	ntfs_attr_put_search_ctx(ctx);
	unmap_mft_record(NTFS_I(vol->vol_ino));
	printk(KERN_INFO "NTFS volume version %i.%i.\n", vol->major_ver,
			vol->minor_ver);
1513
1514
1515
1516
1517
1518
	if (vol->major_ver < 3 && NVolSparseEnabled(vol)) {
		ntfs_warning(vol->sb, "Disabling sparse support due to NTFS "
				"volume version %i.%i (need at least version "
				"3.0).", vol->major_ver, vol->minor_ver);
		NVolClearSparseEnabled(vol);
	}
Linus Torvalds's avatar
Linus Torvalds committed
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
#ifdef NTFS_RW
	/* Make sure that no unsupported volume flags are set. */
	if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
		static const char *es1a = "Volume is dirty";
		static const char *es1b = "Volume has unsupported flags set";
		static const char *es2 = ".  Run chkdsk and mount in Windows.";
		const char *es1;
		
		es1 = vol->vol_flags & VOLUME_IS_DIRTY ? es1a : es1b;
		/* If a read-write mount, convert it to a read-only mount. */
		if (!(sb->s_flags & MS_RDONLY)) {
			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
					ON_ERRORS_CONTINUE))) {
				ntfs_error(sb, "%s and neither on_errors="
						"continue nor on_errors="
						"remount-ro was specified%s",
						es1, es2);
				goto iput_vol_err_out;
			}
			sb->s_flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
		} else
			ntfs_warning(sb, "%s.  Will not be able to remount "
					"read-write%s", es1, es2);
		/*
		 * Do not set NVolErrors() because ntfs_remount() re-checks the
		 * flags which we need to do in case any flags have changed.
		 */
	}
	/*
	 * Get the inode for the logfile, check it and determine if the volume
	 * was shutdown cleanly.
	 */
	if (!load_and_check_logfile(vol) ||
			!ntfs_is_logfile_clean(vol->logfile_ino)) {
		static const char *es1a = "Failed to load $LogFile";
		static const char *es1b = "$LogFile is not clean";
		static const char *es2 = ".  Mount in Windows.";
		const char *es1;

		es1 = !vol->logfile_ino ? es1a : es1b;
		/* If a read-write mount, convert it to a read-only mount. */
		if (!(sb->s_flags & MS_RDONLY)) {
			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
					ON_ERRORS_CONTINUE))) {
				ntfs_error(sb, "%s and neither on_errors="
						"continue nor on_errors="
						"remount-ro was specified%s",
						es1, es2);
				goto iput_logfile_err_out;
			}
			sb->s_flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
		} else
			ntfs_warning(sb, "%s.  Will not be able to remount "
					"read-write%s", es1, es2);
		/* This will prevent a read-write remount. */
		NVolSetErrors(vol);
	}
	/* If (still) a read-write mount, mark the volume dirty. */
	if (!(sb->s_flags & MS_RDONLY) &&
			ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
		static const char *es1 = "Failed to set dirty bit in volume "
				"information flags";
		static const char *es2 = ".  Run chkdsk.";

		/* Convert to a read-only mount. */
		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
				ON_ERRORS_CONTINUE))) {
			ntfs_error(sb, "%s and neither on_errors=continue nor "
					"on_errors=remount-ro was specified%s",
					es1, es2);
			goto iput_logfile_err_out;
		}
		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
		sb->s_flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
		/*
		 * Do not set NVolErrors() because ntfs_remount() might manage
		 * to set the dirty flag in which case all would be well.
		 */
	}
#if 0
	// TODO: Enable this code once we start modifying anything that is
	//	 different between NTFS 1.2 and 3.x...
	/*
	 * If (still) a read-write mount, set the NT4 compatibility flag on
	 * newer NTFS version volumes.
	 */
	if (!(sb->s_flags & MS_RDONLY) && (vol->major_ver > 1) &&
			ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {
		static const char *es1 = "Failed to set NT4 compatibility flag";
		static const char *es2 = ".  Run chkdsk.";

		/* Convert to a read-only mount. */
		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
				ON_ERRORS_CONTINUE))) {
			ntfs_error(sb, "%s and neither on_errors=continue nor "
					"on_errors=remount-ro was specified%s",
					es1, es2);
			goto iput_logfile_err_out;
		}
		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
		sb->s_flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
		NVolSetErrors(vol);
	}
#endif
	/* If (still) a read-write mount, empty the logfile. */
	if (!(sb->s_flags & MS_RDONLY) &&
			!ntfs_empty_logfile(vol->logfile_ino)) {
		static const char *es1 = "Failed to empty $LogFile";
		static const char *es2 = ".  Mount in Windows.";

		/* Convert to a read-only mount. */
		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
				ON_ERRORS_CONTINUE))) {
			ntfs_error(sb, "%s and neither on_errors=continue nor "
					"on_errors=remount-ro was specified%s",
					es1, es2);
			goto iput_logfile_err_out;
		}
		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
		sb->s_flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
		NVolSetErrors(vol);
	}
#endif /* NTFS_RW */
	/* Get the root directory inode. */
	vol->root_ino = ntfs_iget(sb, FILE_root);
	if (IS_ERR(vol->root_ino) || is_bad_inode(vol->root_ino)) {
		if (!IS_ERR(vol->root_ino))
			iput(vol->root_ino);
		ntfs_error(sb, "Failed to load root directory.");
		goto iput_logfile_err_out;
	}
	/* If on NTFS versions before 3.0, we are done. */
	if (vol->major_ver < 3)
		return TRUE;
	/* NTFS 3.0+ specific initialization. */
	/* Get the security descriptors inode. */
	vol->secure_ino = ntfs_iget(sb, FILE_Secure);
	if (IS_ERR(vol->secure_ino) || is_bad_inode(vol->secure_ino)) {
		if (!IS_ERR(vol->secure_ino))
			iput(vol->secure_ino);
		ntfs_error(sb, "Failed to load $Secure.");
		goto iput_root_err_out;
	}
	// FIXME: Initialize security.
	/* Get the extended system files' directory inode. */
	vol->extend_ino = ntfs_iget(sb, FILE_Extend);
	if (IS_ERR(vol->extend_ino) || is_bad_inode(vol->extend_ino)) {
		if (!IS_ERR(vol->extend_ino))
			iput(vol->extend_ino);
		ntfs_error(sb, "Failed to load $Extend.");
		goto iput_sec_err_out;
	}
#ifdef NTFS_RW
	/* Find the quota file, load it if present, and set it up. */
	if (!load_and_init_quota(vol)) {
		static const char *es1 = "Failed to load $Quota";
		static const char *es2 = ".  Run chkdsk.";

		/* If a read-write mount, convert it to a read-only mount. */
		if (!(sb->s_flags & MS_RDONLY)) {
			if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
					ON_ERRORS_CONTINUE))) {
				ntfs_error(sb, "%s and neither on_errors="
						"continue nor on_errors="
						"remount-ro was specified%s",
						es1, es2);
				goto iput_quota_err_out;
			}
			sb->s_flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
			ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
		} else
			ntfs_warning(sb, "%s.  Will not be able to remount "
					"read-write%s", es1, es2);
		/* This will prevent a read-write remount. */
		NVolSetErrors(vol);
	}
	/* If (still) a read-write mount, mark the quotas out of date. */
	if (!(sb->s_flags & MS_RDONLY) &&
			!ntfs_mark_quotas_out_of_date(vol)) {
		static const char *es1 = "Failed to mark quotas out of date";
		static const char *es2 = ".  Run chkdsk.";

		/* Convert to a read-only mount. */
		if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO |
				ON_ERRORS_CONTINUE))) {
			ntfs_error(sb, "%s and neither on_errors=continue nor "
					"on_errors=remount-ro was specified%s",
					es1, es2);
			goto iput_quota_err_out;
		}
		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
		sb->s_flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
		NVolSetErrors(vol);
	}
	// TODO: Delete or checkpoint the $UsnJrnl if it exists.
#endif /* NTFS_RW */
	return TRUE;
#ifdef NTFS_RW
iput_quota_err_out:
	if (vol->quota_q_ino)
		iput(vol->quota_q_ino);
	if (vol->quota_ino)
		iput(vol->quota_ino);
	iput(vol->extend_ino);
#endif /* NTFS_RW */
iput_sec_err_out:
	iput(vol->secure_ino);
iput_root_err_out:
	iput(vol->root_ino);
iput_logfile_err_out:
#ifdef NTFS_RW
	if (vol->logfile_ino)
		iput(vol->logfile_ino);
iput_vol_err_out:
#endif /* NTFS_RW */
	iput(vol->vol_ino);
iput_lcnbmp_err_out:
	iput(vol->lcnbmp_ino);
iput_attrdef_err_out:
	vol->attrdef_size = 0;
	if (vol->attrdef) {
		ntfs_free(vol->attrdef);
		vol->attrdef = NULL;
	}
#ifdef NTFS_RW
iput_upcase_err_out:
#endif /* NTFS_RW */
	vol->upcase_len = 0;
	down(&ntfs_lock);
	if (vol->upcase == default_upcase) {
		ntfs_nr_upcase_users--;
		vol->upcase = NULL;
	}
	up(&ntfs_lock);
	if (vol->upcase) {
		ntfs_free(vol->upcase);
		vol->upcase = NULL;
	}
iput_mftbmp_err_out:
	iput(vol->mftbmp_ino);
iput_mirr_err_out:
#ifdef NTFS_RW
	if (vol->mftmirr_ino)
		iput(vol->mftmirr_ino);
#endif /* NTFS_RW */
	return FALSE;
}

/**
 * ntfs_put_super - called by the vfs to unmount a volume
 * @sb:		vfs superblock of volume to unmount
 *
 * ntfs_put_super() is called by the VFS (from fs/super.c::do_umount()) when
 * the volume is being unmounted (umount system call has been invoked) and it
 * releases all inodes and memory belonging to the NTFS specific part of the
 * super block.
 */
static void ntfs_put_super(struct super_block *sb)
{
	ntfs_volume *vol = NTFS_SB(sb);

	ntfs_debug("Entering.");
#ifdef NTFS_RW
	/*
	 * Commit all inodes while they are still open in case some of them
	 * cause others to be dirtied.
	 */
	ntfs_commit_inode(vol->vol_ino);

	/* NTFS 3.0+ specific. */
	if (vol->major_ver >= 3) {
		if (vol->quota_q_ino)
			ntfs_commit_inode(vol->quota_q_ino);
		if (vol->quota_ino)
			ntfs_commit_inode(vol->quota_ino);
		if (vol->extend_ino)
			ntfs_commit_inode(vol->extend_ino);
		if (vol->secure_ino)
			ntfs_commit_inode(vol->secure_ino);
	}

	ntfs_commit_inode(vol->root_ino);

	down_write(&vol->lcnbmp_lock);
	ntfs_commit_inode(vol->lcnbmp_ino);
	up_write(&vol->lcnbmp_lock);

	down_write(&vol->mftbmp_lock);
	ntfs_commit_inode(vol->mftbmp_ino);
	up_write(&vol->mftbmp_lock);

	if (vol->logfile_ino)
		ntfs_commit_inode(vol->logfile_ino);

	if (vol->mftmirr_ino)
		ntfs_commit_inode(vol->mftmirr_ino);
	ntfs_commit_inode(vol->mft_ino);

	/*
	 * If a read-write mount and no volume errors have occured, mark the
	 * volume clean.  Also, re-commit all affected inodes.
	 */
	if (!(sb->s_flags & MS_RDONLY)) {
		if (!NVolErrors(vol)) {
			if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))
				ntfs_warning(sb, "Failed to clear dirty bit "
						"in volume information "
						"flags.  Run chkdsk.");
			ntfs_commit_inode(vol->vol_ino);
			ntfs_commit_inode(vol->root_ino);
			if (vol->mftmirr_ino)
				ntfs_commit_inode(vol->mftmirr_ino);
			ntfs_commit_inode(vol->mft_ino);
		} else {
			ntfs_warning(sb, "Volume has errors.  Leaving volume "
					"marked dirty.  Run chkdsk.");
		}
	}
#endif /* NTFS_RW */

	iput(vol->vol_ino);
	vol->vol_ino = NULL;

	/* NTFS 3.0+ specific clean up. */
	if (vol->major_ver >= 3) {
#ifdef NTFS_RW
		if (vol->quota_q_ino) {
			iput(vol->quota_q_ino);
			vol->quota_q_ino = NULL;
		}
		if (vol->quota_ino) {
			iput(vol->quota_ino);
			vol->quota_ino = NULL;
		}
#endif /* NTFS_RW */
		if (vol->extend_ino) {
			iput(vol->extend_ino);
			vol->extend_ino = NULL;
		}
		if (vol->secure_ino) {
			iput(vol->secure_ino);
			vol->secure_ino = NULL;
		}
	}

	iput(vol->root_ino);
	vol->root_ino = NULL;

	down_write(&vol->lcnbmp_lock);
	iput(vol->lcnbmp_ino);
	vol->lcnbmp_ino = NULL;
	up_write(&vol->lcnbmp_lock);

	down_write(&vol->mftbmp_lock);
	iput(vol->mftbmp_ino);
	vol->mftbmp_ino = NULL;
	up_write(&vol->mftbmp_lock);

#ifdef NTFS_RW
	if (vol->logfile_ino) {
		iput(vol->logfile_ino);
		vol->logfile_ino = NULL;
	}
	if (vol->mftmirr_ino) {
		/* Re-commit the mft mirror and mft just in case. */
		ntfs_commit_inode(vol->mftmirr_ino);
		ntfs_commit_inode(vol->mft_ino);
		iput(vol->mftmirr_ino);
		vol->mftmirr_ino = NULL;
	}
	/*
	 * If any dirty inodes are left, throw away all mft data page cache
	 * pages to allow a clean umount.  This should never happen any more
	 * due to mft.c::ntfs_mft_writepage() cleaning all the dirty pages as
	 * the underlying mft records are written out and cleaned.  If it does,
	 * happen anyway, we want to know...
	 */
	ntfs_commit_inode(vol->mft_ino);
	write_inode_now(vol->mft_ino, 1);
	if (!list_empty(&sb->s_dirty)) {
		const char *s1, *s2;

		down(&vol->mft_ino->i_sem);
		truncate_inode_pages(vol->mft_ino->i_mapping, 0);
		up(&vol->mft_ino->i_sem);
		write_inode_now(vol->mft_ino, 1);
		if (!list_empty(&sb->s_dirty)) {
			static const char *_s1 = "inodes";
			static const char *_s2 = "";
			s1 = _s1;
			s2 = _s2;
		} else {
			static const char *_s1 = "mft pages";
			static const char *_s2 = "They have been thrown "
					"away.  ";
			s1 = _s1;
			s2 = _s2;
		}
		ntfs_error(sb, "Dirty %s found at umount time.  %sYou should "
				"run chkdsk.  Please email "
				"linux-ntfs-dev@lists.sourceforge.net and say "
				"that you saw this message.  Thank you.", s1,
				s2);
	}
#endif /* NTFS_RW */

	iput(vol->mft_ino);
	vol->mft_ino = NULL;

	/* Throw away the table of attribute definitions. */
	vol->attrdef_size = 0;
	if (vol->attrdef) {
		ntfs_free(vol->attrdef);
		vol->attrdef = NULL;
	}
	vol->upcase_len = 0;
	/*
	 * Destroy the global default upcase table if necessary.  Also decrease
	 * the number of upcase users if we are a user.
	 */
	down(&ntfs_lock);
	if (vol->upcase == default_upcase) {
		ntfs_nr_upcase_users--;
		vol->upcase = NULL;
	}
	if (!ntfs_nr_upcase_users && default_upcase) {
		ntfs_free(default_upcase);
		default_upcase = NULL;
	}
	if (vol->cluster_size <= 4096 && !--ntfs_nr_compression_users)
		free_compression_buffers();
	up(&ntfs_lock);
	if (vol->upcase) {
		ntfs_free(vol->upcase);
		vol->upcase = NULL;
	}
	if (vol->nls_map) {
		unload_nls(vol->nls_map);
		vol->nls_map = NULL;
	}
	sb->s_fs_info = NULL;
	kfree(vol);
	return;
}

/**
 * get_nr_free_clusters - return the number of free clusters on a volume
 * @vol:	ntfs volume for which to obtain free cluster count
 *
 * Calculate the number of free clusters on the mounted NTFS volume @vol. We
 * actually calculate the number of clusters in use instead because this
 * allows us to not care about partial pages as these will be just zero filled
 * and hence not be counted as allocated clusters.
 *
 * The only particularity is that clusters beyond the end of the logical ntfs
 * volume will be marked as allocated to prevent errors which means we have to
 * discount those at the end. This is important as the cluster bitmap always
 * has a size in multiples of 8 bytes, i.e. up to 63 clusters could be outside
 * the logical volume and marked in use when they are not as they do not exist.
 *
 * If any pages cannot be read we assume all clusters in the erroring pages are
 * in use. This means we return an underestimate on errors which is better than
 * an overestimate.
 */
static s64 get_nr_free_clusters(ntfs_volume *vol)
{
	s64 nr_free = vol->nr_clusters;
	u32 *kaddr;
	struct address_space *mapping = vol->lcnbmp_ino->i_mapping;
	filler_t *readpage = (filler_t*)mapping->a_ops->readpage;
	struct page *page;
1992
	pgoff_t index, max_index;
Linus Torvalds's avatar
Linus Torvalds committed
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003

	ntfs_debug("Entering.");
	/* Serialize accesses to the cluster bitmap. */
	down_read(&vol->lcnbmp_lock);
	/*
	 * Convert the number of bits into bytes rounded up, then convert into
	 * multiples of PAGE_CACHE_SIZE, rounding up so that if we have one
	 * full and one partial page max_index = 2.
	 */
	max_index = (((vol->nr_clusters + 7) >> 3) + PAGE_CACHE_SIZE - 1) >>
			PAGE_CACHE_SHIFT;
2004
2005
2006
2007
	/* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */
	ntfs_debug("Reading $Bitmap, max_index = 0x%lx, max_size = 0x%lx.",
			max_index, PAGE_CACHE_SIZE / 4);
	for (index = 0; index < max_index; index++) {
Linus Torvalds's avatar
Linus Torvalds committed
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
		unsigned int i;
		/*
		 * Read the page from page cache, getting it from backing store
		 * if necessary, and increment the use count.
		 */
		page = read_cache_page(mapping, index, (filler_t*)readpage,
				NULL);
		/* Ignore pages which errored synchronously. */
		if (IS_ERR(page)) {
			ntfs_debug("Sync read_cache_page() error. Skipping "
					"page (index 0x%lx).", index);
			nr_free -= PAGE_CACHE_SIZE * 8;
			continue;
		}
		wait_on_page_locked(page);
		/* Ignore pages which errored asynchronously. */
		if (!PageUptodate(page)) {
			ntfs_debug("Async read_cache_page() error. Skipping "
					"page (index 0x%lx).", index);
			page_cache_release(page);
			nr_free -= PAGE_CACHE_SIZE * 8;
			continue;
		}
		kaddr = (u32*)kmap_atomic(page, KM_USER0);
		/*
		 * For each 4 bytes, subtract the number of set bits. If this
		 * is the last page and it is partial we don't really care as
		 * it just means we do a little extra work but it won't affect
		 * the result as all out of range bytes are set to zero by
		 * ntfs_readpage().
		 */
2039
	  	for (i = 0; i < PAGE_CACHE_SIZE / 4; i++)
Linus Torvalds's avatar
Linus Torvalds committed
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
			nr_free -= (s64)hweight32(kaddr[i]);
		kunmap_atomic(kaddr, KM_USER0);
		page_cache_release(page);
	}
	ntfs_debug("Finished reading $Bitmap, last index = 0x%lx.", index - 1);
	/*
	 * Fixup for eventual bits outside logical ntfs volume (see function
	 * description above).
	 */
	if (vol->nr_clusters & 63)
		nr_free += 64 - (vol->nr_clusters & 63);
	up_read(&vol->lcnbmp_lock);
	/* If errors occured we may well have gone below zero, fix this. */
	if (nr_free < 0)
		nr_free = 0;
	ntfs_debug("Exiting.");
	return nr_free;
}

/**
 * __get_nr_free_mft_records - return the number of free inodes on a volume
 * @vol:	ntfs volume for which to obtain free inode count
2062
 * @nr_free:	number of mft records in filesystem
2063
 * @max_index:	maximum number of pages containing set bits
Linus Torvalds's avatar
Linus Torvalds committed
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
 *
 * Calculate the number of free mft records (inodes) on the mounted NTFS
 * volume @vol. We actually calculate the number of mft records in use instead
 * because this allows us to not care about partial pages as these will be just
 * zero filled and hence not be counted as allocated mft record.
 *
 * If any pages cannot be read we assume all mft records in the erroring pages
 * are in use. This means we return an underestimate on errors which is better
 * than an overestimate.
 *
 * NOTE: Caller must hold mftbmp_lock rw_semaphore for reading or writing.
 */
2076
2077
static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,
		s64 nr_free, const pgoff_t max_index)
Linus Torvalds's avatar
Linus Torvalds committed
2078
2079
2080
2081
2082
{
	u32 *kaddr;
	struct address_space *mapping = vol->mftbmp_ino->i_mapping;
	filler_t *readpage = (filler_t*)mapping->a_ops->readpage;
	struct page *page;
2083
	pgoff_t index;
Linus Torvalds's avatar
Linus Torvalds committed
2084
2085

	ntfs_debug("Entering.");
2086
	/* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */
Linus Torvalds's avatar
Linus Torvalds committed
2087
	ntfs_debug("Reading $MFT/$BITMAP, max_index = 0x%lx, max_size = "
2088
2089
			"0x%lx.", max_index, PAGE_CACHE_SIZE / 4);
	for (index = 0; index < max_index; index++) {
Linus Torvalds's avatar
Linus Torvalds committed
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
		unsigned int i;
		/*
		 * Read the page from page cache, getting it from backing store
		 * if necessary, and increment the use count.
		 */
		page = read_cache_page(mapping, index, (filler_t*)readpage,
				NULL);
		/* Ignore pages which errored synchronously. */
		if (IS_ERR(page)) {
			ntfs_debug("Sync read_cache_page() error. Skipping "
					"page (index 0x%lx).", index);
			nr_free -= PAGE_CACHE_SIZE * 8;
			continue;
		}
		wait_on_page_locked(page);
		/* Ignore pages which errored asynchronously. */
		if (!PageUptodate(page)) {
			ntfs_debug("Async read_cache_page() error. Skipping "
					"page (index 0x%lx).", index);
			page_cache_release(page);
			nr_free -= PAGE_CACHE_SIZE * 8;
			continue;
		}
		kaddr = (u32*)kmap_atomic(page, KM_USER0);
		/*
		 * For each 4 bytes, subtract the number of set bits. If this
		 * is the last page and it is partial we don't really care as
		 * it just means we do a little extra work but it won't affect
		 * the result as all out of range bytes are set to zero by
		 * ntfs_readpage().
		 */
2121
	  	for (i = 0; i < PAGE_CACHE_SIZE / 4; i++)
Linus Torvalds's avatar
Linus Torvalds committed
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
			nr_free -= (s64)hweight32(kaddr[i]);
		kunmap_atomic(kaddr, KM_USER0);
		page_cache_release(page);
	}
	ntfs_debug("Finished reading $MFT/$BITMAP, last index = 0x%lx.",
			index - 1);
	/* If errors occured we may well have gone below zero, fix this. */
	if (nr_free < 0)
		nr_free = 0;
	ntfs_debug("Exiting.");
	return nr_free;
}

/**
 * ntfs_statfs - return information about mounted NTFS volume
 * @sb:		super block of mounted volume
 * @sfs:	statfs structure in which to return the information
 *
 * Return information about the mounted NTFS volume @sb in the statfs structure
 * pointed to by @sfs (this is initialized with zeros before ntfs_statfs is
 * called). We interpret the values to be correct of the moment in time at
 * which we are called. Most values are variable otherwise and this isn't just
 * the free values but the totals as well. For example we can increase the
 * total number of file nodes if we run out and we can keep doing this until
 * there is no more space on the volume left at all.
 *
 * Called from vfs_statfs which is used to handle the statfs, fstatfs, and
 * ustat system calls.
 *
 * Return 0 on success or -errno on error.
 */
static int ntfs_statfs(struct super_block *sb, struct kstatfs *sfs)
{
	s64 size;
2156
2157
2158
2159
	ntfs_volume *vol = NTFS_SB(sb);
	ntfs_inode *mft_ni = NTFS_I(vol->mft_ino);
	pgoff_t max_index;
	unsigned long flags;
Linus Torvalds's avatar
Linus Torvalds committed
2160
2161
2162
2163
2164
2165
2166

	ntfs_debug("Entering.");
	/* Type of filesystem. */
	sfs->f_type   = NTFS_SB_MAGIC;
	/* Optimal transfer block size. */
	sfs->f_bsize  = PAGE_CACHE_SIZE;
	/*
2167
	 * Total data blocks in filesystem in units of f_bsize and since
Linus Torvalds's avatar
Linus Torvalds committed
2168
2169
2170
2171
2172
	 * inodes are also stored in data blocs ($MFT is a file) this is just
	 * the total clusters.
	 */
	sfs->f_blocks = vol->nr_clusters << vol->cluster_size_bits >>
				PAGE_CACHE_SHIFT;
2173
	/* Free data blocks in filesystem in units of f_bsize. */
Linus Torvalds's avatar
Linus Torvalds committed
2174
2175
2176
2177
2178
2179
2180
2181
	size	      = get_nr_free_clusters(vol) << vol->cluster_size_bits >>
				PAGE_CACHE_SHIFT;
	if (size < 0LL)
		size = 0LL;
	/* Free blocks avail to non-superuser, same as above on NTFS. */
	sfs->f_bavail = sfs->f_bfree = size;
	/* Serialize accesses to the inode bitmap. */
	down_read(&vol->mftbmp_lock);
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
	read_lock_irqsave(&mft_ni->size_lock, flags);
	size = i_size_read(vol->mft_ino) >> vol->mft_record_size_bits;
	/*
	 * Convert the maximum number of set bits into bytes rounded up, then
	 * convert into multiples of PAGE_CACHE_SIZE, rounding up so that if we
	 * have one full and one partial page max_index = 2.
	 */
	max_index = ((((mft_ni->initialized_size >> vol->mft_record_size_bits)
			+ 7) >> 3) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	read_unlock_irqrestore(&mft_ni->size_lock, flags);
2192
	/* Number of inodes in filesystem (at this point in time). */
2193
	sfs->f_files = size;
Linus Torvalds's avatar
Linus Torvalds committed
2194
	/* Free inodes in fs (based on current total count). */
2195
	sfs->f_ffree = __get_nr_free_mft_records(vol, size, max_index);
Linus Torvalds's avatar
Linus Torvalds committed
2196
2197
2198
2199
2200
	up_read(&vol->mftbmp_lock);
	/*
	 * File system id. This is extremely *nix flavour dependent and even
	 * within Linux itself all fs do their own thing. I interpret this to
	 * mean a unique id associated with the mounted fs and not the id
2201
2202
	 * associated with the filesystem driver, the latter is already given
	 * by the filesystem type in sfs->f_type. Thus we use the 64-bit
Linus Torvalds's avatar
Linus Torvalds committed
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
	 * volume serial number splitting it into two 32-bit parts. We enter
	 * the least significant 32-bits in f_fsid[0] and the most significant
	 * 32-bits in f_fsid[1].
	 */
	sfs->f_fsid.val[0] = vol->serial_no & 0xffffffff;
	sfs->f_fsid.val[1] = (vol->serial_no >> 32) & 0xffffffff;
	/* Maximum length of filenames. */
	sfs->f_namelen	   = NTFS_MAX_NAME_LEN;
	return 0;
}

/**
 * The complete super operations.
 */
static struct super_operations ntfs_sops = {
	.alloc_inode	= ntfs_alloc_big_inode,	  /* VFS: Allocate new inode. */
	.destroy_inode	= ntfs_destroy_big_inode, /* VFS: Deallocate inode. */
	.put_inode	= ntfs_put_inode,	  /* VFS: Called just before
						     the inode reference count
						     is decreased. */
#ifdef NTFS_RW
	//.dirty_inode	= NULL,			/* VFS: Called from
	//					   __mark_inode_dirty(). */
	.write_inode	= ntfs_write_inode,	/* VFS: Write dirty inode to
						   disk. */
	//.drop_inode	= NULL,			/* VFS: Called just after the
	//					   inode reference count has
	//					   been decreased to zero.
	//					   NOTE: The inode lock is
	//					   held. See fs/inode.c::
	//					   generic_drop_inode(). */
	//.delete_inode	= NULL,			/* VFS: Delete inode from disk.
	//					   Called when i_count becomes
	//					   0 and i_nlink is also 0. */
	//.write_super	= NULL,			/* Flush dirty super block to
	//					   disk. */
	//.sync_fs	= NULL,			/* ? */
	//.write_super_lockfs	= NULL,		/* ? */
	//.unlockfs	= NULL,			/* ? */
#endif /* NTFS_RW */
	.put_super	= ntfs_put_super,	/* Syscall: umount. */
	.statfs		= ntfs_statfs,		/* Syscall: statfs */
	.remount_fs	= ntfs_remount,		/* Syscall: mount -o remount. */
	.clear_inode	= ntfs_clear_big_inode,	/* VFS: Called when an inode is
						   removed from memory. */
	//.umount_begin	= NULL,			/* Forced umount. */
	.show_options	= ntfs_show_options,	/* Show mount options in
						   proc. */
};

/**
2254
2255
 * ntfs_fill_super - mount an ntfs filesystem
 * @sb:		super block of ntfs filesystem to mount
Linus Torvalds's avatar
Linus Torvalds committed
2256
2257
2258
2259
 * @opt:	string containing the mount options
 * @silent:	silence error output
 *
 * ntfs_fill_super() is called by the VFS to mount the device described by @sb
2260
 * with the mount otions in @data with the NTFS filesystem.
Linus Torvalds's avatar
Linus Torvalds committed
2261
2262
 *
 * If @silent is true, remain silent even if errors are detected. This is used
2263
2264
2265
 * during bootup, when the kernel tries to mount the root filesystem with all
 * registered filesystems one after the other until one succeeds. This implies
 * that all filesystems except the correct one will quite correctly and
Linus Torvalds's avatar
Linus Torvalds committed
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
 * expectedly return an error, but nobody wants to see error messages when in
 * fact this is what is supposed to happen.
 *
 * NOTE: @sb->s_flags contains the mount options flags.
 */
static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent)
{
	ntfs_volume *vol;
	struct buffer_head *bh;
	struct inode *tmp_ino;
	int result;

	ntfs_debug("Entering.");
#ifndef NTFS_RW
	sb->s_flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
#endif /* ! NTFS_RW */
	/* Allocate a new ntfs_volume and place it in sb->s_fs_info. */
	sb->s_fs_info = kmalloc(sizeof(ntfs_volume), GFP_NOFS);
	vol = NTFS_SB(sb);
	if (!vol) {
		if (!silent)
			ntfs_error(sb, "Allocation of NTFS volume structure "
					"failed. Aborting mount...");
		return -ENOMEM;
	}
	/* Initialize ntfs_volume structure. */
	memset(vol, 0, sizeof(ntfs_volume));
	vol->sb = sb;
	vol->upcase = NULL;
	vol->attrdef = NULL;
	vol->mft_ino = NULL;
	vol->mftbmp_ino = NULL;
	init_rwsem(&vol->mftbmp_lock);
#ifdef NTFS_RW
	vol->mftmirr_ino = NULL;
	vol->logfile_ino = NULL;
#endif /* NTFS_RW */
	vol->lcnbmp_ino = NULL;
	init_rwsem(&vol->lcnbmp_lock);
	vol->vol_ino = NULL;
	vol->root_ino = NULL;
	vol->secure_ino = NULL;
	vol->extend_ino = NULL;
#ifdef NTFS_RW
	vol->quota_ino = NULL;
	vol->quota_q_ino = NULL;
#endif /* NTFS_RW */
	vol->nls_map = NULL;

	/*
	 * Default is group and other don't have any access to files or
	 * directories while owner has full access. Further, files by default
	 * are not executable but directories are of course browseable.
	 */
	vol->fmask = 0177;
	vol->dmask = 0077;

	unlock_kernel();

2325
2326
2327
	/* By default, enable sparse support. */
	NVolSetSparseEnabled(vol);

Linus Torvalds's avatar
Linus Torvalds committed
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
	/* Important to get the mount options dealt with now. */
	if (!parse_options(vol, (char*)opt))
		goto err_out_now;

	/*
	 * TODO: Fail safety check. In the future we should really be able to
	 * cope with this being the case, but for now just bail out.
	 */
	if (bdev_hardsect_size(sb->s_bdev) > NTFS_BLOCK_SIZE) {
		if (!silent)
			ntfs_error(sb, "Device has unsupported hardsect_size.");
		goto err_out_now;
	}

	/* Setup the device access block size to NTFS_BLOCK_SIZE. */
	if (sb_set_blocksize(sb, NTFS_BLOCK_SIZE) != NTFS_BLOCK_SIZE) {
		if (!silent)
			ntfs_error(sb, "Unable to set block size.");
		goto err_out_now;
	}

	/* Get the size of the device in units of NTFS_BLOCK_SIZE bytes. */
2350
2351
	vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
			NTFS_BLOCK_SIZE_BITS;
Linus Torvalds's avatar
Linus Torvalds committed
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708

	/* Read the boot sector and return unlocked buffer head to it. */
	if (!(bh = read_ntfs_boot_sector(sb, silent))) {
		if (!silent)
			ntfs_error(sb, "Not an NTFS volume.");
		goto err_out_now;
	}

	/*
	 * Extract the data from the boot sector and setup the ntfs super block
	 * using it.
	 */
	result = parse_ntfs_boot_sector(vol, (NTFS_BOOT_SECTOR*)bh->b_data);

	/* Initialize the cluster and mft allocators. */
	ntfs_setup_allocators(vol);

	brelse(bh);

	if (!result) {
		if (!silent)
			ntfs_error(sb, "Unsupported NTFS filesystem.");
		goto err_out_now;
	}

	/*
	 * TODO: When we start coping with sector sizes different from
	 * NTFS_BLOCK_SIZE, we now probably need to set the blocksize of the
	 * device (probably to NTFS_BLOCK_SIZE).
	 */

	/* Setup remaining fields in the super block. */
	sb->s_magic = NTFS_SB_MAGIC;

	/*
	 * Ntfs allows 63 bits for the file size, i.e. correct would be:
	 *	sb->s_maxbytes = ~0ULL >> 1;
	 * But the kernel uses a long as the page cache page index which on
	 * 32-bit architectures is only 32-bits. MAX_LFS_FILESIZE is kernel
	 * defined to the maximum the page cache page index can cope with
	 * without overflowing the index or to 2^63 - 1, whichever is smaller.
	 */
	sb->s_maxbytes = MAX_LFS_FILESIZE;

	sb->s_time_gran = 100;

	/*
	 * Now load the metadata required for the page cache and our address
	 * space operations to function. We do this by setting up a specialised
	 * read_inode method and then just calling the normal iget() to obtain
	 * the inode for $MFT which is sufficient to allow our normal inode
	 * operations and associated address space operations to function.
	 */
	sb->s_op = &ntfs_sops;
	tmp_ino = new_inode(sb);
	if (!tmp_ino) {
		if (!silent)
			ntfs_error(sb, "Failed to load essential metadata.");
		goto err_out_now;
	}
	tmp_ino->i_ino = FILE_MFT;
	insert_inode_hash(tmp_ino);
	if (ntfs_read_inode_mount(tmp_ino) < 0) {
		if (!silent)
			ntfs_error(sb, "Failed to load essential metadata.");
		goto iput_tmp_ino_err_out_now;
	}
	down(&ntfs_lock);
	/*
	 * The current mount is a compression user if the cluster size is
	 * less than or equal 4kiB.
	 */
	if (vol->cluster_size <= 4096 && !ntfs_nr_compression_users++) {
		result = allocate_compression_buffers();
		if (result) {
			ntfs_error(NULL, "Failed to allocate buffers "
					"for compression engine.");
			ntfs_nr_compression_users--;
			up(&ntfs_lock);
			goto iput_tmp_ino_err_out_now;
		}
	}
	/*
	 * Generate the global default upcase table if necessary.  Also
	 * temporarily increment the number of upcase users to avoid race
	 * conditions with concurrent (u)mounts.
	 */
	if (!default_upcase)
		default_upcase = generate_default_upcase();
	ntfs_nr_upcase_users++;
	up(&ntfs_lock);
	/*
	 * From now on, ignore @silent parameter. If we fail below this line,
	 * it will be due to a corrupt fs or a system error, so we report it.
	 */
	/*
	 * Open the system files with normal access functions and complete
	 * setting up the ntfs super block.
	 */
	if (!load_system_files(vol)) {
		ntfs_error(sb, "Failed to load system files.");
		goto unl_upcase_iput_tmp_ino_err_out_now;