super.c 101.7 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3
/*
 * super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.
 *
4
 * Copyright (c) 2001-2007 Anton Altaparmakov
L
Linus Torvalds 已提交
5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24
 * 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>
25
#include <linux/slab.h>
L
Linus Torvalds 已提交
26 27
#include <linux/string.h>
#include <linux/spinlock.h>
28
#include <linux/blkdev.h>	/* For bdev_logical_block_size(). */
L
Linus Torvalds 已提交
29 30 31 32 33 34 35 36 37
#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"
38
#include "usnjrnl.h"
L
Linus Torvalds 已提交
39 40 41 42
#include "dir.h"
#include "debug.h"
#include "index.h"
#include "aops.h"
43
#include "layout.h"
L
Linus Torvalds 已提交
44 45 46
#include "malloc.h"
#include "ntfs.h"

47
/* Number of mounted filesystems which have compression enabled. */
L
Linus Torvalds 已提交
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
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).
 */
77
static int simple_getbool(char *s, bool *setval)
L
Linus Torvalds 已提交
78 79 80
{
	if (s) {
		if (!strcmp(s, "1") || !strcmp(s, "yes") || !strcmp(s, "true"))
81
			*setval = true;
L
Linus Torvalds 已提交
82 83
		else if (!strcmp(s, "0") || !strcmp(s, "no") ||
							!strcmp(s, "false"))
84
			*setval = false;
L
Linus Torvalds 已提交
85 86 87
		else
			return 0;
	} else
88
		*setval = true;
L
Linus Torvalds 已提交
89 90 91 92 93 94 95 96 97 98
	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.
 */
99
static bool parse_options(ntfs_volume *vol, char *opt)
L
Linus Torvalds 已提交
100 101 102 103 104 105 106 107
{
	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;
108
	int show_sys_files = -1, case_sensitive = -1, disable_sparse = -1;
L
Linus Torvalds 已提交
109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129
	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;					\
	}
130 131 132 133 134 135 136 137
#define NTFS_GETOPT_OCTAL(option, variable)				\
	if (!strcmp(p, option)) {					\
		if (!v || !*v)						\
			goto needs_arg;					\
		variable = simple_strtoul(ov = v, &v, 8);		\
		if (*v)							\
			goto needs_val;					\
	}
L
Linus Torvalds 已提交
138 139
#define NTFS_GETOPT_BOOL(option, variable)				\
	if (!strcmp(p, option)) {					\
140
		bool val;						\
L
Linus Torvalds 已提交
141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168
		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)
169 170 171
		else NTFS_GETOPT_OCTAL("umask", fmask = dmask)
		else NTFS_GETOPT_OCTAL("fmask", fmask)
		else NTFS_GETOPT_OCTAL("dmask", dmask)
L
Linus Torvalds 已提交
172
		else NTFS_GETOPT("mft_zone_multiplier", mft_zone_multiplier)
173
		else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, true)
L
Linus Torvalds 已提交
174 175
		else NTFS_GETOPT_BOOL("show_sys_files", show_sys_files)
		else NTFS_GETOPT_BOOL("case_sensitive", case_sensitive)
176
		else NTFS_GETOPT_BOOL("disable_sparse", disable_sparse)
L
Linus Torvalds 已提交
177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196
		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);
197
					return false;
L
Linus Torvalds 已提交
198 199 200 201 202 203 204 205 206 207
				}
				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")) {
208
			bool val = false;
L
Linus Torvalds 已提交
209 210 211 212 213 214
			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)
215
				val = true;
L
Linus Torvalds 已提交
216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233
			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)
234
		return false;
L
Linus Torvalds 已提交
235 236 237 238 239 240 241 242
	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.");
243
			return false;
L
Linus Torvalds 已提交
244 245 246 247 248 249
		}
	}
	if (nls_map) {
		if (vol->nls_map && vol->nls_map != nls_map) {
			ntfs_error(vol->sb, "Cannot change NLS character set "
					"on remount.");
250
			return false;
L
Linus Torvalds 已提交
251 252 253 254 255 256 257 258 259
		} /* 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.");
260
				return false;
L
Linus Torvalds 已提交
261 262 263 264 265 266 267 268 269 270
			}
			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.");
271
			return false;
L
Linus Torvalds 已提交
272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305
		}
		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);
	}
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320
	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);
		}
	}
321
	return true;
L
Linus Torvalds 已提交
322 323
needs_arg:
	ntfs_error(vol->sb, "The %s option requires an argument.", p);
324
	return false;
L
Linus Torvalds 已提交
325 326
needs_bool:
	ntfs_error(vol->sb, "The %s option requires a boolean argument.", p);
327
	return false;
L
Linus Torvalds 已提交
328 329
needs_val:
	ntfs_error(vol->sb, "Invalid %s option argument: %s", p, ov);
330
	return false;
L
Linus Torvalds 已提交
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
}

#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
447 448
	/* For read-only compiled driver, enforce read-only flag. */
	*flags |= MS_RDONLY;
L
Linus Torvalds 已提交
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
#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;
		}
475 476 477 478 479
		if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
			ntfs_error(sb, "Volume has been modified by chkdsk "
					"and is read-only%s", es);
			return -EROFS;
		}
L
Linus Torvalds 已提交
480
		if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
481 482 483 484
			ntfs_error(sb, "Volume has unsupported flags set "
					"(0x%x) and is read-only%s",
					(unsigned)le16_to_cpu(vol->vol_flags),
					es);
L
Linus Torvalds 已提交
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
			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 $LogFile%s",
					es);
			NVolSetErrors(vol);
			return -EROFS;
		}
		if (!ntfs_mark_quotas_out_of_date(vol)) {
			ntfs_error(sb, "Failed to mark quotas out of date%s",
					es);
			NVolSetErrors(vol);
			return -EROFS;
		}
517 518 519 520 521 522
		if (!ntfs_stamp_usnjrnl(vol)) {
			ntfs_error(sb, "Failed to stamp transation log "
					"($UsnJrnl)%s", es);
			NVolSetErrors(vol);
			return -EROFS;
		}
L
Linus Torvalds 已提交
523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545
	} 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.
546
 * @silent:	If 'true', all output will be silenced.
L
Linus Torvalds 已提交
547 548
 *
 * is_boot_sector_ntfs() checks whether the boot sector @b is a valid NTFS boot
549
 * sector. Returns 'true' if it is valid and 'false' if not.
L
Linus Torvalds 已提交
550 551
 *
 * @sb is only needed for warning/error output, i.e. it can be NULL when silent
552
 * is 'true'.
L
Linus Torvalds 已提交
553
 */
554 555
static bool is_boot_sector_ntfs(const struct super_block *sb,
		const NTFS_BOOT_SECTOR *b, const bool silent)
L
Linus Torvalds 已提交
556 557 558
{
	/*
	 * Check that checksum == sum of u32 values from b to the checksum
559 560 561 562
	 * field.  If checksum is zero, no checking is done.  We will work when
	 * the checksum test fails, since some utilities update the boot sector
	 * ignoring the checksum which leaves the checksum out-of-date.  We
	 * report a warning if this is the case.
L
Linus Torvalds 已提交
563
	 */
564
	if ((void*)b < (void*)&b->checksum && b->checksum && !silent) {
L
Linus Torvalds 已提交
565 566 567 568 569 570
		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)
571
			ntfs_warning(sb, "Invalid boot sector checksum.");
L
Linus Torvalds 已提交
572 573 574 575 576 577 578 579 580 581 582 583 584 585 586
	}
	/* 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;
	}
587
	/* Check the cluster size is not above the maximum (64kiB). */
L
Linus Torvalds 已提交
588
	if ((u32)le16_to_cpu(b->bpb.bytes_per_sector) *
589
			b->bpb.sectors_per_cluster > NTFS_MAX_CLUSTER_SIZE)
L
Linus Torvalds 已提交
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
		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.
	 */
621
	if (!silent && b->end_of_sector_marker != cpu_to_le16(0xaa55))
L
Linus Torvalds 已提交
622
		ntfs_warning(sb, "Invalid end of sector marker.");
623
	return true;
L
Linus Torvalds 已提交
624
not_ntfs:
625
	return false;
L
Linus Torvalds 已提交
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
}

/**
 * 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;
652
	sector_t nr_blocks = NTFS_SB(sb)->nr_blocks;
L
Linus Torvalds 已提交
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

	/* 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
699 700 701 702 703 704
		 * primary boot sector.  Note we only copy the actual boot
		 * sector structure, not the actual whole device sector as that
		 * may be bigger and would potentially damage the $Boot system
		 * file (FIXME: Would be nice to know if the backup boot sector
		 * on a large sector device contains the whole boot loader or
		 * just the first 512 bytes).
L
Linus Torvalds 已提交
705 706 707 708 709
		 */
		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,
710
					NTFS_BLOCK_SIZE);
L
Linus Torvalds 已提交
711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734
			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
735
 * the ntfs super block @vol.  Return 'true' on success and 'false' on error.
L
Linus Torvalds 已提交
736
 */
737
static bool parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
L
Linus Torvalds 已提交
738 739 740 741 742 743 744 745 746 747 748
{
	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);
749 750 751 752 753
	if (vol->sector_size < vol->sb->s_blocksize) {
		ntfs_error(vol->sb, "Sector size (%i) is smaller than the "
				"device block size (%lu).  This is not "
				"supported.  Sorry.", vol->sector_size,
				vol->sb->s_blocksize);
754
		return false;
755
	}
L
Linus Torvalds 已提交
756 757 758 759 760 761 762 763 764 765 766 767
	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);
768 769 770 771 772
	ntfs_debug("vol->cluster_size_bits = %i", vol->cluster_size_bits);
	if (vol->cluster_size < vol->sector_size) {
		ntfs_error(vol->sb, "Cluster size (%i) is smaller than the "
				"sector size (%i).  This is not supported.  "
				"Sorry.", vol->cluster_size, vol->sector_size);
773
		return false;
L
Linus Torvalds 已提交
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
	}
	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) {
801 802
		ntfs_error(vol->sb, "Mft record size (%i) exceeds the "
				"PAGE_CACHE_SIZE on your system (%lu).  "
L
Linus Torvalds 已提交
803
				"This is not supported.  Sorry.",
804
				vol->mft_record_size, PAGE_CACHE_SIZE);
805
		return false;
806 807 808 809 810 811 812
	}
	/* We cannot support mft record sizes below the sector size. */
	if (vol->mft_record_size < vol->sector_size) {
		ntfs_error(vol->sb, "Mft record size (%i) is smaller than the "
				"sector size (%i).  This is not supported.  "
				"Sorry.", vol->mft_record_size,
				vol->sector_size);
813
		return false;
L
Linus Torvalds 已提交
814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837
	}
	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);
838 839 840 841 842 843
	/* We cannot support index record sizes below the sector size. */
	if (vol->index_record_size < vol->sector_size) {
		ntfs_error(vol->sb, "Index record size (%i) is smaller than "
				"the sector size (%i).  This is not "
				"supported.  Sorry.", vol->index_record_size,
				vol->sector_size);
844
		return false;
845
	}
L
Linus Torvalds 已提交
846 847 848 849 850 851 852 853
	/*
	 * 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.");
854
		return false;
L
Linus Torvalds 已提交
855 856 857 858 859 860 861 862 863 864 865 866 867 868 869
	}
	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));
870
			return false;
L
Linus Torvalds 已提交
871 872 873 874
		}
	}
	ll = sle64_to_cpu(b->mft_lcn);
	if (ll >= vol->nr_clusters) {
875 876 877
		ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of "
				"volume.  Weird.", (unsigned long long)ll,
				(unsigned long long)ll);
878
		return false;
L
Linus Torvalds 已提交
879 880 881 882 883
	}
	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) {
884 885 886
		ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end "
				"of volume.  Weird.", (unsigned long long)ll,
				(unsigned long long)ll);
887
		return false;
L
Linus Torvalds 已提交
888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909
	}
	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);
910
	return true;
L
Linus Torvalds 已提交
911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002
}

/**
 * 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
 *
1003
 * Return 'true' on success or 'false' on error.
L
Linus Torvalds 已提交
1004
 */
1005
static bool load_and_init_mft_mirror(ntfs_volume *vol)
L
Linus Torvalds 已提交
1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016
{
	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. */
1017
		return false;
L
Linus Torvalds 已提交
1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034
	}
	/*
	 * 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);
1035
	NInoSetSparseDisabled(tmp_ni);
L
Linus Torvalds 已提交
1036 1037 1038 1039 1040 1041 1042 1043
	/*
	 * 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.");
1044
	return true;
L
Linus Torvalds 已提交
1045 1046 1047 1048 1049 1050
}

/**
 * check_mft_mirror - compare contents of the mft mirror with the mft
 * @vol:	ntfs super block describing device whose mft mirror to check
 *
1051
 * Return 'true' on success or 'false' on error.
L
Linus Torvalds 已提交
1052 1053 1054 1055 1056
 *
 * 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.
 */
1057
static bool check_mft_mirror(ntfs_volume *vol)
L
Linus Torvalds 已提交
1058 1059 1060 1061 1062 1063
{
	struct super_block *sb = vol->sb;
	ntfs_inode *mirr_ni;
	struct page *mft_page, *mirr_page;
	u8 *kmft, *kmirr;
	runlist_element *rl, rl2[2];
1064
	pgoff_t index;
L
Linus Torvalds 已提交
1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088
	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.");
1089
				return false;
L
Linus Torvalds 已提交
1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101
			}
			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 $MFTMirr.");
				goto mft_unmap_out;
			}
			kmirr = page_address(mirr_page);
			++index;
		}
1102 1103 1104 1105 1106 1107 1108
		/* Do not check the record if it is not in use. */
		if (((MFT_RECORD*)kmft)->flags & MFT_RECORD_IN_USE) {
			/* Make sure the record is ok. */
			if (ntfs_is_baad_recordp((le32*)kmft)) {
				ntfs_error(sb, "Incomplete multi sector "
						"transfer detected in mft "
						"record %i.", i);
L
Linus Torvalds 已提交
1109
mm_unmap_out:
1110
				ntfs_unmap_page(mirr_page);
L
Linus Torvalds 已提交
1111
mft_unmap_out:
1112
				ntfs_unmap_page(mft_page);
1113
				return false;
1114
			}
L
Linus Torvalds 已提交
1115
		}
1116 1117 1118 1119 1120 1121 1122 1123
		/* Do not check the mirror record if it is not in use. */
		if (((MFT_RECORD*)kmirr)->flags & MFT_RECORD_IN_USE) {
			if (ntfs_is_baad_recordp((le32*)kmirr)) {
				ntfs_error(sb, "Incomplete multi sector "
						"transfer detected in mft "
						"mirror record %i.", i);
				goto mm_unmap_out;
			}
L
Linus Torvalds 已提交
1124 1125 1126
		}
		/* Get the amount of data in the current record. */
		bytes = le32_to_cpu(((MFT_RECORD*)kmft)->bytes_in_use);
1127 1128 1129
		if (bytes < sizeof(MFT_RECORD_OLD) ||
				bytes > vol->mft_record_size ||
				ntfs_is_baad_recordp((le32*)kmft)) {
L
Linus Torvalds 已提交
1130
			bytes = le32_to_cpu(((MFT_RECORD*)kmirr)->bytes_in_use);
1131 1132 1133
			if (bytes < sizeof(MFT_RECORD_OLD) ||
					bytes > vol->mft_record_size ||
					ntfs_is_baad_recordp((le32*)kmirr))
L
Linus Torvalds 已提交
1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171
				bytes = vol->mft_record_size;
		}
		/* Compare the two records. */
		if (memcmp(kmft, kmirr, bytes)) {
			ntfs_error(sb, "$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);
1172
			return false;
L
Linus Torvalds 已提交
1173 1174 1175 1176
		}
	} while (rl2[i++].length);
	up_read(&mirr_ni->runlist.lock);
	ntfs_debug("Done.");
1177
	return true;
L
Linus Torvalds 已提交
1178 1179 1180 1181 1182 1183
}

/**
 * load_and_check_logfile - load and check the logfile inode for a volume
 * @vol:	ntfs super block describing device whose logfile to load
 *
1184
 * Return 'true' on success or 'false' on error.
L
Linus Torvalds 已提交
1185
 */
1186
static bool load_and_check_logfile(ntfs_volume *vol,
1187
		RESTART_PAGE_HEADER **rp)
L
Linus Torvalds 已提交
1188 1189 1190 1191 1192 1193 1194 1195 1196
{
	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. */
1197
		return false;
L
Linus Torvalds 已提交
1198
	}
1199
	if (!ntfs_check_logfile(tmp_ino, rp)) {
L
Linus Torvalds 已提交
1200 1201
		iput(tmp_ino);
		/* ntfs_check_logfile() will have displayed error output. */
1202
		return false;
L
Linus Torvalds 已提交
1203
	}
1204
	NInoSetSparseDisabled(NTFS_I(tmp_ino));
L
Linus Torvalds 已提交
1205 1206
	vol->logfile_ino = tmp_ino;
	ntfs_debug("Done.");
1207
	return true;
L
Linus Torvalds 已提交
1208 1209
}

1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244
#define NTFS_HIBERFIL_HEADER_SIZE	4096

/**
 * check_windows_hibernation_status - check if Windows is suspended on a volume
 * @vol:	ntfs super block of device to check
 *
 * Check if Windows is hibernated on the ntfs volume @vol.  This is done by
 * looking for the file hiberfil.sys in the root directory of the volume.  If
 * the file is not present Windows is definitely not suspended.
 *
 * If hiberfil.sys exists and is less than 4kiB in size it means Windows is
 * definitely suspended (this volume is not the system volume).  Caveat:  on a
 * system with many volumes it is possible that the < 4kiB check is bogus but
 * for now this should do fine.
 *
 * If hiberfil.sys exists and is larger than 4kiB in size, we need to read the
 * hiberfil header (which is the first 4kiB).  If this begins with "hibr",
 * Windows is definitely suspended.  If it is completely full of zeroes,
 * Windows is definitely not hibernated.  Any other case is treated as if
 * Windows is suspended.  This caters for the above mentioned caveat of a
 * system with many volumes where no "hibr" magic would be present and there is
 * no zero header.
 *
 * Return 0 if Windows is not hibernated on the volume, >0 if Windows is
 * hibernated on the volume, and -errno on error.
 */
static int check_windows_hibernation_status(ntfs_volume *vol)
{
	MFT_REF mref;
	struct inode *vi;
	ntfs_inode *ni;
	struct page *page;
	u32 *kaddr, *kend;
	ntfs_name *name = NULL;
	int ret = 1;
1245 1246 1247 1248 1249 1250 1251
	static const ntfschar hiberfil[13] = { cpu_to_le16('h'),
			cpu_to_le16('i'), cpu_to_le16('b'),
			cpu_to_le16('e'), cpu_to_le16('r'),
			cpu_to_le16('f'), cpu_to_le16('i'),
			cpu_to_le16('l'), cpu_to_le16('.'),
			cpu_to_le16('s'), cpu_to_le16('y'),
			cpu_to_le16('s'), 0 };
1252 1253 1254 1255 1256 1257

	ntfs_debug("Entering.");
	/*
	 * Find the inode number for the hibernation file by looking up the
	 * filename hiberfil.sys in the root directory.
	 */
1258
	mutex_lock(&vol->root_ino->i_mutex);
1259 1260
	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->root_ino), hiberfil, 12,
			&name);
1261
	mutex_unlock(&vol->root_ino->i_mutex);
1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298
	if (IS_ERR_MREF(mref)) {
		ret = MREF_ERR(mref);
		/* If the file does not exist, Windows is not hibernated. */
		if (ret == -ENOENT) {
			ntfs_debug("hiberfil.sys not present.  Windows is not "
					"hibernated on the volume.");
			return 0;
		}
		/* A real error occured. */
		ntfs_error(vol->sb, "Failed to find inode number for "
				"hiberfil.sys.");
		return ret;
	}
	/* We do not care for the type of match that was found. */
	kfree(name);
	/* Get the inode. */
	vi = ntfs_iget(vol->sb, MREF(mref));
	if (IS_ERR(vi) || is_bad_inode(vi)) {
		if (!IS_ERR(vi))
			iput(vi);
		ntfs_error(vol->sb, "Failed to load hiberfil.sys.");
		return IS_ERR(vi) ? PTR_ERR(vi) : -EIO;
	}
	if (unlikely(i_size_read(vi) < NTFS_HIBERFIL_HEADER_SIZE)) {
		ntfs_debug("hiberfil.sys is smaller than 4kiB (0x%llx).  "
				"Windows is hibernated on the volume.  This "
				"is not the system volume.", i_size_read(vi));
		goto iput_out;
	}
	ni = NTFS_I(vi);
	page = ntfs_map_page(vi->i_mapping, 0);
	if (IS_ERR(page)) {
		ntfs_error(vol->sb, "Failed to read from hiberfil.sys.");
		ret = PTR_ERR(page);
		goto iput_out;
	}
	kaddr = (u32*)page_address(page);
1299
	if (*(le32*)kaddr == cpu_to_le32(0x72626968)/*'hibr'*/) {
1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327
		ntfs_debug("Magic \"hibr\" found in hiberfil.sys.  Windows is "
				"hibernated on the volume.  This is the "
				"system volume.");
		goto unm_iput_out;
	}
	kend = kaddr + NTFS_HIBERFIL_HEADER_SIZE/sizeof(*kaddr);
	do {
		if (unlikely(*kaddr)) {
			ntfs_debug("hiberfil.sys is larger than 4kiB "
					"(0x%llx), does not contain the "
					"\"hibr\" magic, and does not have a "
					"zero header.  Windows is hibernated "
					"on the volume.  This is not the "
					"system volume.", i_size_read(vi));
			goto unm_iput_out;
		}
	} while (++kaddr < kend);
	ntfs_debug("hiberfil.sys contains a zero header.  Windows is not "
			"hibernated on the volume.  This is the system "
			"volume.");
	ret = 0;
unm_iput_out:
	ntfs_unmap_page(page);
iput_out:
	iput(vi);
	return ret;
}

L
Linus Torvalds 已提交
1328 1329 1330 1331
/**
 * 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
 *
1332
 * Return 'true' on success or 'false' on error.  If $Quota is not present, we
L
Linus Torvalds 已提交
1333 1334
 * leave vol->quota_ino as NULL and return success.
 */
1335
static bool load_and_init_quota(ntfs_volume *vol)
L
Linus Torvalds 已提交
1336 1337 1338 1339
{
	MFT_REF mref;
	struct inode *tmp_ino;
	ntfs_name *name = NULL;
1340 1341 1342 1343 1344 1345
	static const ntfschar Quota[7] = { cpu_to_le16('$'),
			cpu_to_le16('Q'), cpu_to_le16('u'),
			cpu_to_le16('o'), cpu_to_le16('t'),
			cpu_to_le16('a'), 0 };
	static ntfschar Q[3] = { cpu_to_le16('$'),
			cpu_to_le16('Q'), 0 };
L
Linus Torvalds 已提交
1346 1347 1348 1349 1350 1351

	ntfs_debug("Entering.");
	/*
	 * Find the inode number for the quota file by looking up the filename
	 * $Quota in the extended system files directory $Extend.
	 */
1352
	mutex_lock(&vol->extend_ino->i_mutex);
L
Linus Torvalds 已提交
1353 1354
	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), Quota, 6,
			&name);
1355
	mutex_unlock(&vol->extend_ino->i_mutex);
L
Linus Torvalds 已提交
1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368
	if (IS_ERR_MREF(mref)) {
		/*
		 * If the file does not exist, quotas are disabled and have
		 * never been enabled on this volume, just return success.
		 */
		if (MREF_ERR(mref) == -ENOENT) {
			ntfs_debug("$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);
1369
			return true;
L
Linus Torvalds 已提交
1370 1371 1372
		}
		/* A real error occured. */
		ntfs_error(vol->sb, "Failed to find inode number for $Quota.");
1373
		return false;
L
Linus Torvalds 已提交
1374 1375
	}
	/* We do not care for the type of match that was found. */
1376
	kfree(name);
L
Linus Torvalds 已提交
1377 1378 1379 1380 1381 1382
	/* 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.");
1383
		return false;
L
Linus Torvalds 已提交
1384 1385 1386 1387 1388 1389
	}
	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.");
1390
		return false;
L
Linus Torvalds 已提交
1391 1392 1393
	}
	vol->quota_q_ino = tmp_ino;
	ntfs_debug("Done.");
1394
	return true;
L
Linus Torvalds 已提交
1395 1396
}

1397 1398 1399 1400
/**
 * load_and_init_usnjrnl - load and setup the transaction log if present
 * @vol:	ntfs super block describing device whose usnjrnl file to load
 *
1401
 * Return 'true' on success or 'false' on error.
1402 1403 1404 1405 1406 1407 1408 1409 1410
 *
 * If $UsnJrnl is not present or in the process of being disabled, we set
 * NVolUsnJrnlStamped() and return success.
 *
 * If the $UsnJrnl $DATA/$J attribute has a size equal to the lowest valid usn,
 * i.e. transaction logging has only just been enabled or the journal has been
 * stamped and nothing has been logged since, we also set NVolUsnJrnlStamped()
 * and return success.
 */
1411
static bool load_and_init_usnjrnl(ntfs_volume *vol)
1412 1413 1414 1415 1416 1417 1418
{
	MFT_REF mref;
	struct inode *tmp_ino;
	ntfs_inode *tmp_ni;
	struct page *page;
	ntfs_name *name = NULL;
	USN_HEADER *uh;
1419 1420 1421 1422 1423 1424 1425 1426 1427 1428
	static const ntfschar UsnJrnl[9] = { cpu_to_le16('$'),
			cpu_to_le16('U'), cpu_to_le16('s'),
			cpu_to_le16('n'), cpu_to_le16('J'),
			cpu_to_le16('r'), cpu_to_le16('n'),
			cpu_to_le16('l'), 0 };
	static ntfschar Max[5] = { cpu_to_le16('$'),
			cpu_to_le16('M'), cpu_to_le16('a'),
			cpu_to_le16('x'), 0 };
	static ntfschar J[3] = { cpu_to_le16('$'),
			cpu_to_le16('J'), 0 };
1429 1430 1431 1432 1433 1434

	ntfs_debug("Entering.");
	/*
	 * Find the inode number for the transaction log file by looking up the
	 * filename $UsnJrnl in the extended system files directory $Extend.
	 */
1435
	mutex_lock(&vol->extend_ino->i_mutex);
1436 1437
	mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), UsnJrnl, 8,
			&name);
1438
	mutex_unlock(&vol->extend_ino->i_mutex);
1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452
	if (IS_ERR_MREF(mref)) {
		/*
		 * If the file does not exist, transaction logging is disabled,
		 * just return success.
		 */
		if (MREF_ERR(mref) == -ENOENT) {
			ntfs_debug("$UsnJrnl not present.  Volume does not "
					"have transaction logging enabled.");
not_enabled:
			/*
			 * No need to try to stamp the transaction log if
			 * transaction logging is not enabled.
			 */
			NVolSetUsnJrnlStamped(vol);
1453
			return true;
1454 1455 1456 1457
		}
		/* A real error occured. */
		ntfs_error(vol->sb, "Failed to find inode number for "
				"$UsnJrnl.");
1458
		return false;
1459 1460 1461 1462 1463 1464 1465 1466 1467
	}
	/* We do not care for the type of match that was found. */
	kfree(name);
	/* Get the inode. */
	tmp_ino = ntfs_iget(vol->sb, MREF(mref));
	if (unlikely(IS_ERR(tmp_ino) || is_bad_inode(tmp_ino))) {
		if (!IS_ERR(tmp_ino))
			iput(tmp_ino);
		ntfs_error(vol->sb, "Failed to load $UsnJrnl.");
1468
		return false;
1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485
	}
	vol->usnjrnl_ino = tmp_ino;
	/*
	 * If the transaction log is in the process of being deleted, we can
	 * ignore it.
	 */
	if (unlikely(vol->vol_flags & VOLUME_DELETE_USN_UNDERWAY)) {
		ntfs_debug("$UsnJrnl in the process of being disabled.  "
				"Volume does not have transaction logging "
				"enabled.");
		goto not_enabled;
	}
	/* Get the $DATA/$Max attribute. */
	tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, Max, 4);
	if (IS_ERR(tmp_ino)) {
		ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$Max "
				"attribute.");
1486
		return false;
1487 1488 1489 1490 1491
	}
	vol->usnjrnl_max_ino = tmp_ino;
	if (unlikely(i_size_read(tmp_ino) < sizeof(USN_HEADER))) {
		ntfs_error(vol->sb, "Found corrupt $UsnJrnl/$DATA/$Max "
				"attribute (size is 0x%llx but should be at "
1492
				"least 0x%zx bytes).", i_size_read(tmp_ino),
1493
				sizeof(USN_HEADER));
1494
		return false;
1495 1496 1497 1498 1499 1500
	}
	/* Get the $DATA/$J attribute. */
	tmp_ino = ntfs_attr_iget(vol->usnjrnl_ino, AT_DATA, J, 2);
	if (IS_ERR(tmp_ino)) {
		ntfs_error(vol->sb, "Failed to load $UsnJrnl/$DATA/$J "
				"attribute.");
1501
		return false;
1502 1503 1504 1505 1506 1507 1508
	}
	vol->usnjrnl_j_ino = tmp_ino;
	/* Verify $J is non-resident and sparse. */
	tmp_ni = NTFS_I(vol->usnjrnl_j_ino);
	if (unlikely(!NInoNonResident(tmp_ni) || !NInoSparse(tmp_ni))) {
		ntfs_error(vol->sb, "$UsnJrnl/$DATA/$J attribute is resident "
				"and/or not sparse.");
1509
		return false;
1510 1511 1512 1513 1514 1515
	}
	/* Read the USN_HEADER from $DATA/$Max. */
	page = ntfs_map_page(vol->usnjrnl_max_ino->i_mapping, 0);
	if (IS_ERR(page)) {
		ntfs_error(vol->sb, "Failed to read from $UsnJrnl/$DATA/$Max "
				"attribute.");
1516
		return false;
1517 1518 1519 1520 1521 1522 1523 1524 1525 1526
	}
	uh = (USN_HEADER*)page_address(page);
	/* Sanity check the $Max. */
	if (unlikely(sle64_to_cpu(uh->allocation_delta) >
			sle64_to_cpu(uh->maximum_size))) {
		ntfs_error(vol->sb, "Allocation delta (0x%llx) exceeds "
				"maximum size (0x%llx).  $UsnJrnl is corrupt.",
				(long long)sle64_to_cpu(uh->allocation_delta),
				(long long)sle64_to_cpu(uh->maximum_size));
		ntfs_unmap_page(page);
1527
		return false;
1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550
	}
	/*
	 * If the transaction log has been stamped and nothing has been written
	 * to it since, we do not need to stamp it.
	 */
	if (unlikely(sle64_to_cpu(uh->lowest_valid_usn) >=
			i_size_read(vol->usnjrnl_j_ino))) {
		if (likely(sle64_to_cpu(uh->lowest_valid_usn) ==
				i_size_read(vol->usnjrnl_j_ino))) {
			ntfs_unmap_page(page);
			ntfs_debug("$UsnJrnl is enabled but nothing has been "
					"logged since it was last stamped.  "
					"Treating this as if the volume does "
					"not have transaction logging "
					"enabled.");
			goto not_enabled;
		}
		ntfs_error(vol->sb, "$UsnJrnl has lowest valid usn (0x%llx) "
				"which is out of bounds (0x%llx).  $UsnJrnl "
				"is corrupt.",
				(long long)sle64_to_cpu(uh->lowest_valid_usn),
				i_size_read(vol->usnjrnl_j_ino));
		ntfs_unmap_page(page);
1551
		return false;
1552 1553 1554
	}
	ntfs_unmap_page(page);
	ntfs_debug("Done.");
1555
	return true;
1556 1557
}

L
Linus Torvalds 已提交
1558 1559 1560 1561
/**
 * load_and_init_attrdef - load the attribute definitions table for a volume
 * @vol:	ntfs super block describing device whose attrdef to load
 *
1562
 * Return 'true' on success or 'false' on error.
L
Linus Torvalds 已提交
1563
 */
1564
static bool load_and_init_attrdef(ntfs_volume *vol)
L
Linus Torvalds 已提交
1565
{
1566
	loff_t i_size;
L
Linus Torvalds 已提交
1567 1568 1569
	struct super_block *sb = vol->sb;
	struct inode *ino;
	struct page *page;
1570
	pgoff_t index, max_index;
L
Linus Torvalds 已提交
1571 1572 1573 1574 1575 1576 1577 1578 1579 1580
	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;
	}
1581
	NInoSetSparseDisabled(NTFS_I(ino));
L
Linus Torvalds 已提交
1582
	/* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */
1583 1584
	i_size = i_size_read(ino);
	if (i_size <= 0 || i_size > 0x7fffffff)
L
Linus Torvalds 已提交
1585
		goto iput_failed;
1586
	vol->attrdef = (ATTR_DEF*)ntfs_malloc_nofs(i_size);
L
Linus Torvalds 已提交
1587 1588 1589
	if (!vol->attrdef)
		goto iput_failed;
	index = 0;
1590
	max_index = i_size >> PAGE_CACHE_SHIFT;
L
Linus Torvalds 已提交
1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602
	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) {
1603
		size = i_size & ~PAGE_CACHE_MASK;
L
Linus Torvalds 已提交
1604 1605 1606
		if (size)
			goto read_partial_attrdef_page;
	}
1607 1608
	vol->attrdef_size = i_size;
	ntfs_debug("Read %llu bytes from $AttrDef.", i_size);
L
Linus Torvalds 已提交
1609
	iput(ino);
1610
	return true;
L
Linus Torvalds 已提交
1611 1612 1613 1614 1615 1616 1617
free_iput_failed:
	ntfs_free(vol->attrdef);
	vol->attrdef = NULL;
iput_failed:
	iput(ino);
failed:
	ntfs_error(sb, "Failed to initialize attribute definition table.");
1618
	return false;
L
Linus Torvalds 已提交
1619 1620 1621 1622 1623 1624 1625 1626
}

#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
 *
1627
 * Return 'true' on success or 'false' on error.
L
Linus Torvalds 已提交
1628
 */
1629
static bool load_and_init_upcase(ntfs_volume *vol)
L
Linus Torvalds 已提交
1630
{
1631
	loff_t i_size;
L
Linus Torvalds 已提交
1632 1633 1634
	struct super_block *sb = vol->sb;
	struct inode *ino;
	struct page *page;
1635
	pgoff_t index, max_index;
L
Linus Torvalds 已提交
1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650
	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).
	 */
1651 1652 1653
	i_size = i_size_read(ino);
	if (!i_size || i_size & (sizeof(ntfschar) - 1) ||
			i_size > 64ULL * 1024 * sizeof(ntfschar))
L
Linus Torvalds 已提交
1654
		goto iput_upcase_failed;
1655
	vol->upcase = (ntfschar*)ntfs_malloc_nofs(i_size);
L
Linus Torvalds 已提交
1656 1657 1658
	if (!vol->upcase)
		goto iput_upcase_failed;
	index = 0;
1659
	max_index = i_size >> PAGE_CACHE_SHIFT;
L
Linus Torvalds 已提交
1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671
	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) {
1672
		size = i_size & ~PAGE_CACHE_MASK;
L
Linus Torvalds 已提交
1673 1674 1675
		if (size)
			goto read_partial_upcase_page;
	}
1676
	vol->upcase_len = i_size >> UCHAR_T_SIZE_BITS;
L
Linus Torvalds 已提交
1677
	ntfs_debug("Read %llu bytes from $UpCase (expected %zu bytes).",
1678
			i_size, 64 * 1024 * sizeof(ntfschar));
L
Linus Torvalds 已提交
1679
	iput(ino);
1680
	mutex_lock(&ntfs_lock);
L
Linus Torvalds 已提交
1681 1682 1683
	if (!default_upcase) {
		ntfs_debug("Using volume specified $UpCase since default is "
				"not present.");
1684
		mutex_unlock(&ntfs_lock);
1685
		return true;
L
Linus Torvalds 已提交
1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697
	}
	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++;
1698
		mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
1699 1700
		ntfs_debug("Volume specified $UpCase matches default. Using "
				"default.");
1701
		return true;
L
Linus Torvalds 已提交
1702
	}
1703
	mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
1704 1705
	ntfs_debug("Using volume specified $UpCase since it does not match "
			"the default.");
1706
	return true;
L
Linus Torvalds 已提交
1707 1708 1709 1710 1711
iput_upcase_failed:
	iput(ino);
	ntfs_free(vol->upcase);
	vol->upcase = NULL;
upcase_failed:
1712
	mutex_lock(&ntfs_lock);
L
Linus Torvalds 已提交
1713 1714 1715 1716
	if (default_upcase) {
		vol->upcase = default_upcase;
		vol->upcase_len = default_upcase_len;
		ntfs_nr_upcase_users++;
1717
		mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
1718 1719
		ntfs_error(sb, "Failed to load $UpCase from the volume. Using "
				"default.");
1720
		return true;
L
Linus Torvalds 已提交
1721
	}
1722
	mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
1723
	ntfs_error(sb, "Failed to initialize upcase table.");
1724
	return false;
L
Linus Torvalds 已提交
1725 1726
}

1727 1728 1729 1730 1731 1732 1733 1734
/*
 * The lcn and mft bitmap inodes are NTFS-internal inodes with
 * their own special locking rules:
 */
static struct lock_class_key
	lcnbmp_runlist_lock_key, lcnbmp_mrec_lock_key,
	mftbmp_runlist_lock_key, mftbmp_mrec_lock_key;

L
Linus Torvalds 已提交
1735 1736 1737 1738 1739 1740 1741
/**
 * 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.
 *
1742
 * Return 'true' on success or 'false' on error.
L
Linus Torvalds 已提交
1743
 */
1744
static bool load_system_files(ntfs_volume *vol)
L
Linus Torvalds 已提交
1745 1746 1747 1748 1749
{
	struct super_block *sb = vol->sb;
	MFT_RECORD *m;
	VOLUME_INFORMATION *vi;
	ntfs_attr_search_ctx *ctx;
1750
#ifdef NTFS_RW
1751
	RESTART_PAGE_HEADER *rp;
1752 1753
	int err;
#endif /* NTFS_RW */
L
Linus Torvalds 已提交
1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773

	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;
			}
1774
			sb->s_flags |= MS_RDONLY;
L
Linus Torvalds 已提交
1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790
			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;
	}
1791 1792 1793 1794
	lockdep_set_class(&NTFS_I(vol->mftbmp_ino)->runlist.lock,
			   &mftbmp_runlist_lock_key);
	lockdep_set_class(&NTFS_I(vol->mftbmp_ino)->mrec_lock,
			   &mftbmp_mrec_lock_key);
L
Linus Torvalds 已提交
1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816
	/* 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;
	}
1817 1818 1819 1820 1821
	lockdep_set_class(&NTFS_I(vol->lcnbmp_ino)->runlist.lock,
			   &lcnbmp_runlist_lock_key);
	lockdep_set_class(&NTFS_I(vol->lcnbmp_ino)->mrec_lock,
			   &lcnbmp_mrec_lock_key);

1822
	NInoSetSparseDisabled(NTFS_I(vol->lcnbmp_ino));
1823
	if ((vol->nr_clusters + 7) >> 3 > i_size_read(vol->lcnbmp_ino)) {
L
Linus Torvalds 已提交
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
		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);
1874 1875 1876 1877 1878 1879
	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);
	}
L
Linus Torvalds 已提交
1880 1881 1882 1883
#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";
1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901
		static const char *es1b = "Volume has been modified by chkdsk";
		static const char *es1c = "Volume has unsupported flags set";
		static const char *es2a = ".  Run chkdsk and mount in Windows.";
		static const char *es2b = ".  Mount in Windows.";
		const char *es1, *es2;

		es2 = es2a;
		if (vol->vol_flags & VOLUME_IS_DIRTY)
			es1 = es1a;
		else if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) {
			es1 = es1b;
			es2 = es2b;
		} else {
			es1 = es1c;
			ntfs_warning(sb, "Unsupported volume flags 0x%x "
					"encountered.",
					(unsigned)le16_to_cpu(vol->vol_flags));
		}
L
Linus Torvalds 已提交
1902 1903 1904 1905 1906 1907 1908 1909 1910 1911
		/* 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;
			}
1912
			sb->s_flags |= MS_RDONLY;
L
Linus Torvalds 已提交
1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925
			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.
	 */
1926 1927 1928
	rp = NULL;
	if (!load_and_check_logfile(vol, &rp) ||
			!ntfs_is_logfile_clean(vol->logfile_ino, rp)) {
L
Linus Torvalds 已提交
1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942
		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);
1943 1944 1945 1946
				if (vol->logfile_ino) {
					BUG_ON(!rp);
					ntfs_free(rp);
				}
L
Linus Torvalds 已提交
1947 1948
				goto iput_logfile_err_out;
			}
1949
			sb->s_flags |= MS_RDONLY;
L
Linus Torvalds 已提交
1950 1951 1952 1953 1954 1955 1956
			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);
	}
1957
	ntfs_free(rp);
1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993
#endif /* NTFS_RW */
	/* Get the root directory inode so we can do path lookups. */
	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;
	}
#ifdef NTFS_RW
	/*
	 * Check if Windows is suspended to disk on the target volume.  If it
	 * is hibernated, we must not write *anything* to the disk so set
	 * NVolErrors() without setting the dirty volume flag and mount
	 * read-only.  This will prevent read-write remounting and it will also
	 * prevent all writes.
	 */
	err = check_windows_hibernation_status(vol);
	if (unlikely(err)) {
		static const char *es1a = "Failed to determine if Windows is "
				"hibernated";
		static const char *es1b = "Windows is hibernated";
		static const char *es2 = ".  Run chkdsk.";
		const char *es1;

		es1 = err < 0 ? 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_root_err_out;
			}
1994
			sb->s_flags |= MS_RDONLY;
1995 1996 1997 1998 1999 2000 2001
			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);
	}
L
Linus Torvalds 已提交
2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014
	/* 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);
2015
			goto iput_root_err_out;
L
Linus Torvalds 已提交
2016 2017
		}
		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
2018
		sb->s_flags |= MS_RDONLY;
L
Linus Torvalds 已提交
2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041
		/*
		 * 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);
2042
			goto iput_root_err_out;
L
Linus Torvalds 已提交
2043 2044
		}
		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
2045
		sb->s_flags |= MS_RDONLY;
L
Linus Torvalds 已提交
2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060
		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);
2061
			goto iput_root_err_out;
L
Linus Torvalds 已提交
2062 2063
		}
		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
2064
		sb->s_flags |= MS_RDONLY;
L
Linus Torvalds 已提交
2065 2066 2067 2068
		NVolSetErrors(vol);
	}
#endif /* NTFS_RW */
	/* If on NTFS versions before 3.0, we are done. */
2069
	if (unlikely(vol->major_ver < 3))
2070
		return true;
L
Linus Torvalds 已提交
2071 2072 2073 2074 2075 2076 2077 2078 2079
	/* 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;
	}
2080
	// TODO: Initialize security.
L
Linus Torvalds 已提交
2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104
	/* 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;
			}
2105
			sb->s_flags |= MS_RDONLY;
L
Linus Torvalds 已提交
2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127
			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);
2128
		sb->s_flags |= MS_RDONLY;
L
Linus Torvalds 已提交
2129 2130
		NVolSetErrors(vol);
	}
2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148
	/*
	 * Find the transaction log file ($UsnJrnl), load it if present, check
	 * it, and set it up.
	 */
	if (!load_and_init_usnjrnl(vol)) {
		static const char *es1 = "Failed to load $UsnJrnl";
		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_usnjrnl_err_out;
			}
2149
			sb->s_flags |= MS_RDONLY;
2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171
			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, stamp the transaction log. */
	if (!(sb->s_flags & MS_RDONLY) && !ntfs_stamp_usnjrnl(vol)) {
		static const char *es1 = "Failed to stamp transaction log "
				"($UsnJrnl)";
		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_usnjrnl_err_out;
		}
		ntfs_error(sb, "%s.  Mounting read-only%s", es1, es2);
2172
		sb->s_flags |= MS_RDONLY;
2173 2174
		NVolSetErrors(vol);
	}
L
Linus Torvalds 已提交
2175
#endif /* NTFS_RW */
2176
	return true;
L
Linus Torvalds 已提交
2177
#ifdef NTFS_RW
2178 2179 2180 2181 2182 2183 2184
iput_usnjrnl_err_out:
	if (vol->usnjrnl_j_ino)
		iput(vol->usnjrnl_j_ino);
	if (vol->usnjrnl_max_ino)
		iput(vol->usnjrnl_max_ino);
	if (vol->usnjrnl_ino)
		iput(vol->usnjrnl_ino);
L
Linus Torvalds 已提交
2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214
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;
2215
	mutex_lock(&ntfs_lock);
L
Linus Torvalds 已提交
2216 2217 2218 2219
	if (vol->upcase == default_upcase) {
		ntfs_nr_upcase_users--;
		vol->upcase = NULL;
	}
2220
	mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231
	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 */
2232
	return false;
L
Linus Torvalds 已提交
2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248
}

/**
 * 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.");
2249 2250 2251

	lock_kernel();

L
Linus Torvalds 已提交
2252 2253 2254 2255 2256 2257 2258 2259 2260
#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) {
2261 2262 2263 2264 2265 2266
		if (vol->usnjrnl_j_ino)
			ntfs_commit_inode(vol->usnjrnl_j_ino);
		if (vol->usnjrnl_max_ino)
			ntfs_commit_inode(vol->usnjrnl_max_ino);
		if (vol->usnjrnl_ino)
			ntfs_commit_inode(vol->usnjrnl_ino);
L
Linus Torvalds 已提交
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
		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
2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333
		if (vol->usnjrnl_j_ino) {
			iput(vol->usnjrnl_j_ino);
			vol->usnjrnl_j_ino = NULL;
		}
		if (vol->usnjrnl_max_ino) {
			iput(vol->usnjrnl_max_ino);
			vol->usnjrnl_max_ino = NULL;
		}
		if (vol->usnjrnl_ino) {
			iput(vol->usnjrnl_ino);
			vol->usnjrnl_ino = NULL;
		}
L
Linus Torvalds 已提交
2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 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
		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);
2387
	if (sb_has_dirty_inodes(sb)) {
L
Linus Torvalds 已提交
2388 2389
		const char *s1, *s2;

2390
		mutex_lock(&vol->mft_ino->i_mutex);
L
Linus Torvalds 已提交
2391
		truncate_inode_pages(vol->mft_ino->i_mapping, 0);
2392
		mutex_unlock(&vol->mft_ino->i_mutex);
L
Linus Torvalds 已提交
2393
		write_inode_now(vol->mft_ino, 1);
2394
		if (sb_has_dirty_inodes(sb)) {
L
Linus Torvalds 已提交
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
			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.
	 */
2428
	mutex_lock(&ntfs_lock);
L
Linus Torvalds 已提交
2429 2430 2431 2432 2433 2434 2435 2436 2437 2438
	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();
2439
	mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
2440 2441 2442 2443 2444 2445 2446 2447 2448 2449
	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);
2450 2451

	unlock_kernel();
L
Linus Torvalds 已提交
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
}

/**
 * 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;
	struct page *page;
2479
	pgoff_t index, max_index;
L
Linus Torvalds 已提交
2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490

	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;
2491 2492 2493 2494
	/* 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++) {
L
Linus Torvalds 已提交
2495 2496 2497 2498 2499
		unsigned int i;
		/*
		 * Read the page from page cache, getting it from backing store
		 * if necessary, and increment the use count.
		 */
2500
		page = read_mapping_page(mapping, index, NULL);
L
Linus Torvalds 已提交
2501 2502
		/* Ignore pages which errored synchronously. */
		if (IS_ERR(page)) {
2503
			ntfs_debug("read_mapping_page() error. Skipping "
L
Linus Torvalds 已提交
2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515
					"page (index 0x%lx).", index);
			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().
		 */
2516
	  	for (i = 0; i < PAGE_CACHE_SIZE / 4; i++)
L
Linus Torvalds 已提交
2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538
			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
2539
 * @nr_free:	number of mft records in filesystem
2540
 * @max_index:	maximum number of pages containing set bits
L
Linus Torvalds 已提交
2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552
 *
 * 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.
 */
2553 2554
static unsigned long __get_nr_free_mft_records(ntfs_volume *vol,
		s64 nr_free, const pgoff_t max_index)
L
Linus Torvalds 已提交
2555 2556 2557 2558
{
	u32 *kaddr;
	struct address_space *mapping = vol->mftbmp_ino->i_mapping;
	struct page *page;
2559
	pgoff_t index;
L
Linus Torvalds 已提交
2560 2561

	ntfs_debug("Entering.");
2562
	/* Use multiples of 4 bytes, thus max_size is PAGE_CACHE_SIZE / 4. */
L
Linus Torvalds 已提交
2563
	ntfs_debug("Reading $MFT/$BITMAP, max_index = 0x%lx, max_size = "
2564 2565
			"0x%lx.", max_index, PAGE_CACHE_SIZE / 4);
	for (index = 0; index < max_index; index++) {
L
Linus Torvalds 已提交
2566 2567 2568 2569 2570
		unsigned int i;
		/*
		 * Read the page from page cache, getting it from backing store
		 * if necessary, and increment the use count.
		 */
2571
		page = read_mapping_page(mapping, index, NULL);
L
Linus Torvalds 已提交
2572 2573
		/* Ignore pages which errored synchronously. */
		if (IS_ERR(page)) {
2574
			ntfs_debug("read_mapping_page() error. Skipping "
L
Linus Torvalds 已提交
2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586
					"page (index 0x%lx).", index);
			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().
		 */
2587
	  	for (i = 0; i < PAGE_CACHE_SIZE / 4; i++)
L
Linus Torvalds 已提交
2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602
			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
2603
 * @dentry:	dentry from mounted volume
L
Linus Torvalds 已提交
2604 2605
 * @sfs:	statfs structure in which to return the information
 *
2606
 * Return information about the mounted NTFS volume @dentry in the statfs structure
L
Linus Torvalds 已提交
2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618
 * 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.
 */
2619
static int ntfs_statfs(struct dentry *dentry, struct kstatfs *sfs)
L
Linus Torvalds 已提交
2620
{
2621
	struct super_block *sb = dentry->d_sb;
L
Linus Torvalds 已提交
2622
	s64 size;
2623 2624 2625 2626
	ntfs_volume *vol = NTFS_SB(sb);
	ntfs_inode *mft_ni = NTFS_I(vol->mft_ino);
	pgoff_t max_index;
	unsigned long flags;
L
Linus Torvalds 已提交
2627 2628 2629 2630 2631 2632 2633

	ntfs_debug("Entering.");
	/* Type of filesystem. */
	sfs->f_type   = NTFS_SB_MAGIC;
	/* Optimal transfer block size. */
	sfs->f_bsize  = PAGE_CACHE_SIZE;
	/*
2634
	 * Total data blocks in filesystem in units of f_bsize and since
L
Linus Torvalds 已提交
2635 2636 2637 2638 2639
	 * 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;
2640
	/* Free data blocks in filesystem in units of f_bsize. */
L
Linus Torvalds 已提交
2641 2642 2643 2644 2645 2646 2647 2648
	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);
2649 2650 2651 2652 2653 2654 2655 2656 2657 2658
	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);
2659
	/* Number of inodes in filesystem (at this point in time). */
2660
	sfs->f_files = size;
L
Linus Torvalds 已提交
2661
	/* Free inodes in fs (based on current total count). */
2662
	sfs->f_ffree = __get_nr_free_mft_records(vol, size, max_index);
L
Linus Torvalds 已提交
2663 2664 2665 2666 2667
	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
2668 2669
	 * associated with the filesystem driver, the latter is already given
	 * by the filesystem type in sfs->f_type. Thus we use the 64-bit
L
Linus Torvalds 已提交
2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683
	 * 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.
 */
2684
static const struct super_operations ntfs_sops = {
L
Linus Torvalds 已提交
2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717
	.alloc_inode	= ntfs_alloc_big_inode,	  /* VFS: Allocate new inode. */
	.destroy_inode	= ntfs_destroy_big_inode, /* VFS: Deallocate inode. */
#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. */
};

/**
2718 2719
 * ntfs_fill_super - mount an ntfs filesystem
 * @sb:		super block of ntfs filesystem to mount
L
Linus Torvalds 已提交
2720 2721 2722 2723
 * @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
2724
 * with the mount otions in @data with the NTFS filesystem.
L
Linus Torvalds 已提交
2725 2726
 *
 * If @silent is true, remain silent even if errors are detected. This is used
2727 2728 2729
 * 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
L
Linus Torvalds 已提交
2730 2731 2732 2733 2734 2735 2736 2737 2738 2739
 * 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;
2740
	int blocksize, result;
L
Linus Torvalds 已提交
2741

2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752
	/*
	 * We do a pretty difficult piece of bootstrap by reading the
	 * MFT (and other metadata) from disk into memory. We'll only
	 * release this metadata during umount, so the locking patterns
	 * observed during bootstrap do not count. So turn off the
	 * observation of locking patterns (strictly for this context
	 * only) while mounting NTFS. [The validator is still active
	 * otherwise, even for this context: it will for example record
	 * lock class registrations.]
	 */
	lockdep_off();
L
Linus Torvalds 已提交
2753 2754
	ntfs_debug("Entering.");
#ifndef NTFS_RW
2755
	sb->s_flags |= MS_RDONLY;
L
Linus Torvalds 已提交
2756 2757 2758 2759 2760 2761 2762 2763
#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...");
2764
		lockdep_on();
L
Linus Torvalds 已提交
2765 2766 2767
		return -ENOMEM;
	}
	/* Initialize ntfs_volume structure. */
2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778
	*vol = (ntfs_volume) {
		.sb = sb,
		/*
		 * 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.
		 */
		.fmask = 0177,
		.dmask = 0077,
	};
L
Linus Torvalds 已提交
2779 2780 2781 2782 2783
	init_rwsem(&vol->mftbmp_lock);
	init_rwsem(&vol->lcnbmp_lock);

	unlock_kernel();

2784 2785 2786
	/* By default, enable sparse support. */
	NVolSetSparseEnabled(vol);

L
Linus Torvalds 已提交
2787 2788 2789 2790
	/* Important to get the mount options dealt with now. */
	if (!parse_options(vol, (char*)opt))
		goto err_out_now;

2791
	/* We support sector sizes up to the PAGE_CACHE_SIZE. */
2792
	if (bdev_logical_block_size(sb->s_bdev) > PAGE_CACHE_SIZE) {
2793 2794 2795 2796 2797
		if (!silent)
			ntfs_error(sb, "Device has unsupported sector size "
					"(%i).  The maximum supported sector "
					"size on this architecture is %lu "
					"bytes.",
2798
					bdev_logical_block_size(sb->s_bdev),
2799 2800 2801
					PAGE_CACHE_SIZE);
		goto err_out_now;
	}
L
Linus Torvalds 已提交
2802
	/*
2803 2804
	 * Setup the device access block size to NTFS_BLOCK_SIZE or the hard
	 * sector size, whichever is bigger.
L
Linus Torvalds 已提交
2805
	 */
2806 2807
	blocksize = sb_min_blocksize(sb, NTFS_BLOCK_SIZE);
	if (blocksize < NTFS_BLOCK_SIZE) {
L
Linus Torvalds 已提交
2808
		if (!silent)
2809
			ntfs_error(sb, "Unable to set device block size.");
L
Linus Torvalds 已提交
2810 2811
		goto err_out_now;
	}
2812 2813 2814 2815 2816
	BUG_ON(blocksize != sb->s_blocksize);
	ntfs_debug("Set device block size to %i bytes (block size bits %i).",
			blocksize, sb->s_blocksize_bits);
	/* Determine the size of the device in units of block_size bytes. */
	if (!i_size_read(sb->s_bdev->bd_inode)) {
L
Linus Torvalds 已提交
2817
		if (!silent)
2818
			ntfs_error(sb, "Unable to determine device size.");
L
Linus Torvalds 已提交
2819 2820
		goto err_out_now;
	}
2821
	vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
2822
			sb->s_blocksize_bits;
L
Linus Torvalds 已提交
2823 2824 2825 2826 2827 2828 2829
	/* 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;
	}
	/*
2830
	 * Extract the data from the boot sector and setup the ntfs volume
L
Linus Torvalds 已提交
2831 2832 2833 2834 2835 2836 2837 2838 2839 2840
	 * using it.
	 */
	result = parse_ntfs_boot_sector(vol, (NTFS_BOOT_SECTOR*)bh->b_data);
	brelse(bh);
	if (!result) {
		if (!silent)
			ntfs_error(sb, "Unsupported NTFS filesystem.");
		goto err_out_now;
	}
	/*
2841 2842 2843 2844 2845 2846 2847 2848
	 * If the boot sector indicates a sector size bigger than the current
	 * device block size, switch the device block size to the sector size.
	 * TODO: It may be possible to support this case even when the set
	 * below fails, we would just be breaking up the i/o for each sector
	 * into multiple blocks for i/o purposes but otherwise it should just
	 * work.  However it is safer to leave disabled until someone hits this
	 * error message and then we can get them to try it without the setting
	 * so we know for sure that it works.
L
Linus Torvalds 已提交
2849
	 */
2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867
	if (vol->sector_size > blocksize) {
		blocksize = sb_set_blocksize(sb, vol->sector_size);
		if (blocksize != vol->sector_size) {
			if (!silent)
				ntfs_error(sb, "Unable to set device block "
						"size to sector size (%i).",
						vol->sector_size);
			goto err_out_now;
		}
		BUG_ON(blocksize != sb->s_blocksize);
		vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >>
				sb->s_blocksize_bits;
		ntfs_debug("Changed device block size to %i bytes (block size "
				"bits %i) to match volume sector size.",
				blocksize, sb->s_blocksize_bits);
	}
	/* Initialize the cluster and mft allocators. */
	ntfs_setup_allocators(vol);
L
Linus Torvalds 已提交
2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878
	/* 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;
2879
	/* Ntfs measures time in 100ns intervals. */
L
Linus Torvalds 已提交
2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901
	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;
	}
2902
	mutex_lock(&ntfs_lock);
L
Linus Torvalds 已提交
2903 2904 2905 2906 2907 2908 2909 2910 2911 2912
	/*
	 * 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--;
2913
			mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924
			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++;
2925
	mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942
	/*
	 * 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;
	}
	if ((sb->s_root = d_alloc_root(vol->root_ino))) {
		/* We increment i_count simulating an ntfs_iget(). */
		atomic_inc(&vol->root_ino->i_count);
		ntfs_debug("Exiting, status successful.");
		/* Release the default upcase if it has no users. */
2943
		mutex_lock(&ntfs_lock);
L
Linus Torvalds 已提交
2944 2945 2946 2947
		if (!--ntfs_nr_upcase_users && default_upcase) {
			ntfs_free(default_upcase);
			default_upcase = NULL;
		}
2948
		mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
2949 2950
		sb->s_export_op = &ntfs_export_ops;
		lock_kernel();
2951
		lockdep_on();
L
Linus Torvalds 已提交
2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963
		return 0;
	}
	ntfs_error(sb, "Failed to allocate root directory.");
	/* Clean up after the successful load_system_files() call from above. */
	// TODO: Use ntfs_put_super() instead of repeating all this code...
	// FIXME: Should mark the volume clean as the error is most likely
	// 	  -ENOMEM.
	iput(vol->vol_ino);
	vol->vol_ino = NULL;
	/* NTFS 3.0+ specific clean up. */
	if (vol->major_ver >= 3) {
#ifdef NTFS_RW
2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975
		if (vol->usnjrnl_j_ino) {
			iput(vol->usnjrnl_j_ino);
			vol->usnjrnl_j_ino = NULL;
		}
		if (vol->usnjrnl_max_ino) {
			iput(vol->usnjrnl_max_ino);
			vol->usnjrnl_max_ino = NULL;
		}
		if (vol->usnjrnl_ino) {
			iput(vol->usnjrnl_ino);
			vol->usnjrnl_ino = NULL;
		}
L
Linus Torvalds 已提交
2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016
		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;
	iput(vol->lcnbmp_ino);
	vol->lcnbmp_ino = NULL;
	iput(vol->mftbmp_ino);
	vol->mftbmp_ino = NULL;
#ifdef NTFS_RW
	if (vol->logfile_ino) {
		iput(vol->logfile_ino);
		vol->logfile_ino = NULL;
	}
	if (vol->mftmirr_ino) {
		iput(vol->mftmirr_ino);
		vol->mftmirr_ino = NULL;
	}
#endif /* NTFS_RW */
	/* 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;
3017
	mutex_lock(&ntfs_lock);
L
Linus Torvalds 已提交
3018 3019 3020 3021
	if (vol->upcase == default_upcase) {
		ntfs_nr_upcase_users--;
		vol->upcase = NULL;
	}
3022
	mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036
	if (vol->upcase) {
		ntfs_free(vol->upcase);
		vol->upcase = NULL;
	}
	if (vol->nls_map) {
		unload_nls(vol->nls_map);
		vol->nls_map = NULL;
	}
	/* Error exit code path. */
unl_upcase_iput_tmp_ino_err_out_now:
	/*
	 * Decrease the number of upcase users and destroy the global default
	 * upcase table if necessary.
	 */
3037
	mutex_lock(&ntfs_lock);
L
Linus Torvalds 已提交
3038 3039 3040 3041 3042 3043
	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();
3044
	mutex_unlock(&ntfs_lock);
L
Linus Torvalds 已提交
3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070
iput_tmp_ino_err_out_now:
	iput(tmp_ino);
	if (vol->mft_ino && vol->mft_ino != tmp_ino)
		iput(vol->mft_ino);
	vol->mft_ino = NULL;
	/*
	 * This is needed to get ntfs_clear_extent_inode() called for each
	 * inode we have ever called ntfs_iget()/iput() on, otherwise we A)
	 * leak resources and B) a subsequent mount fails automatically due to
	 * ntfs_iget() never calling down into our ntfs_read_locked_inode()
	 * method again... FIXME: Do we need to do this twice now because of
	 * attribute inodes? I think not, so leave as is for now... (AIA)
	 */
	if (invalidate_inodes(sb)) {
		ntfs_error(sb, "Busy inodes left. This is most likely a NTFS "
				"driver bug.");
		/* Copied from fs/super.c. I just love this message. (-; */
		printk("NTFS: Busy inodes after umount. Self-destruct in 5 "
				"seconds.  Have a nice day...\n");
	}
	/* Errors at this stage are irrelevant. */
err_out_now:
	lock_kernel();
	sb->s_fs_info = NULL;
	kfree(vol);
	ntfs_debug("Failed, returning -EINVAL.");
3071
	lockdep_on();
L
Linus Torvalds 已提交
3072 3073 3074 3075 3076 3077 3078 3079
	return -EINVAL;
}

/*
 * This is a slab cache to optimize allocations and deallocations of Unicode
 * strings of the maximum length allowed by NTFS, which is NTFS_MAX_NAME_LEN
 * (255) Unicode characters + a terminating NULL Unicode character.
 */
3080
struct kmem_cache *ntfs_name_cache;
L
Linus Torvalds 已提交
3081

3082
/* Slab caches for efficient allocation/deallocation of inodes. */
3083 3084
struct kmem_cache *ntfs_inode_cache;
struct kmem_cache *ntfs_big_inode_cache;
L
Linus Torvalds 已提交
3085 3086

/* Init once constructor for the inode slab cache. */
3087
static void ntfs_big_inode_init_once(void *foo)
L
Linus Torvalds 已提交
3088 3089 3090
{
	ntfs_inode *ni = (ntfs_inode *)foo;

C
Christoph Lameter 已提交
3091
	inode_init_once(VFS_I(ni));
L
Linus Torvalds 已提交
3092 3093 3094 3095 3096 3097
}

/*
 * Slab caches to optimize allocations and deallocations of attribute search
 * contexts and index contexts, respectively.
 */
3098 3099
struct kmem_cache *ntfs_attr_ctx_cache;
struct kmem_cache *ntfs_index_ctx_cache;
L
Linus Torvalds 已提交
3100

3101
/* Driver wide mutex. */
3102
DEFINE_MUTEX(ntfs_lock);
L
Linus Torvalds 已提交
3103

3104 3105
static int ntfs_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
L
Linus Torvalds 已提交
3106
{
3107 3108
	return get_sb_bdev(fs_type, flags, dev_name, data, ntfs_fill_super,
			   mnt);
L
Linus Torvalds 已提交
3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148
}

static struct file_system_type ntfs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "ntfs",
	.get_sb		= ntfs_get_sb,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};

/* Stable names for the slab caches. */
static const char ntfs_index_ctx_cache_name[] = "ntfs_index_ctx_cache";
static const char ntfs_attr_ctx_cache_name[] = "ntfs_attr_ctx_cache";
static const char ntfs_name_cache_name[] = "ntfs_name_cache";
static const char ntfs_inode_cache_name[] = "ntfs_inode_cache";
static const char ntfs_big_inode_cache_name[] = "ntfs_big_inode_cache";

static int __init init_ntfs_fs(void)
{
	int err = 0;

	/* This may be ugly but it results in pretty output so who cares. (-8 */
	printk(KERN_INFO "NTFS driver " NTFS_VERSION " [Flags: R/"
#ifdef NTFS_RW
			"W"
#else
			"O"
#endif
#ifdef DEBUG
			" DEBUG"
#endif
#ifdef MODULE
			" MODULE"
#endif
			"].\n");

	ntfs_debug("Debug messages are enabled.");

	ntfs_index_ctx_cache = kmem_cache_create(ntfs_index_ctx_cache_name,
			sizeof(ntfs_index_context), 0 /* offset */,
3149
			SLAB_HWCACHE_ALIGN, NULL /* ctor */);
L
Linus Torvalds 已提交
3150 3151 3152 3153 3154 3155 3156
	if (!ntfs_index_ctx_cache) {
		printk(KERN_CRIT "NTFS: Failed to create %s!\n",
				ntfs_index_ctx_cache_name);
		goto ictx_err_out;
	}
	ntfs_attr_ctx_cache = kmem_cache_create(ntfs_attr_ctx_cache_name,
			sizeof(ntfs_attr_search_ctx), 0 /* offset */,
3157
			SLAB_HWCACHE_ALIGN, NULL /* ctor */);
L
Linus Torvalds 已提交
3158 3159 3160 3161 3162 3163 3164 3165
	if (!ntfs_attr_ctx_cache) {
		printk(KERN_CRIT "NTFS: Failed to create %s!\n",
				ntfs_attr_ctx_cache_name);
		goto actx_err_out;
	}

	ntfs_name_cache = kmem_cache_create(ntfs_name_cache_name,
			(NTFS_MAX_NAME_LEN+1) * sizeof(ntfschar), 0,
3166
			SLAB_HWCACHE_ALIGN, NULL);
L
Linus Torvalds 已提交
3167 3168 3169 3170 3171 3172 3173 3174
	if (!ntfs_name_cache) {
		printk(KERN_CRIT "NTFS: Failed to create %s!\n",
				ntfs_name_cache_name);
		goto name_err_out;
	}

	ntfs_inode_cache = kmem_cache_create(ntfs_inode_cache_name,
			sizeof(ntfs_inode), 0,
3175
			SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, NULL);
L
Linus Torvalds 已提交
3176 3177 3178 3179 3180 3181 3182 3183
	if (!ntfs_inode_cache) {
		printk(KERN_CRIT "NTFS: Failed to create %s!\n",
				ntfs_inode_cache_name);
		goto inode_err_out;
	}

	ntfs_big_inode_cache = kmem_cache_create(ntfs_big_inode_cache_name,
			sizeof(big_ntfs_inode), 0,
3184
			SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD,
3185
			ntfs_big_inode_init_once);
L
Linus Torvalds 已提交
3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203
	if (!ntfs_big_inode_cache) {
		printk(KERN_CRIT "NTFS: Failed to create %s!\n",
				ntfs_big_inode_cache_name);
		goto big_inode_err_out;
	}

	/* Register the ntfs sysctls. */
	err = ntfs_sysctl(1);
	if (err) {
		printk(KERN_CRIT "NTFS: Failed to register NTFS sysctls!\n");
		goto sysctl_err_out;
	}

	err = register_filesystem(&ntfs_fs_type);
	if (!err) {
		ntfs_debug("NTFS driver registered successfully.");
		return 0; /* Success! */
	}
3204
	printk(KERN_CRIT "NTFS: Failed to register NTFS filesystem driver!\n");
L
Linus Torvalds 已提交
3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217

sysctl_err_out:
	kmem_cache_destroy(ntfs_big_inode_cache);
big_inode_err_out:
	kmem_cache_destroy(ntfs_inode_cache);
inode_err_out:
	kmem_cache_destroy(ntfs_name_cache);
name_err_out:
	kmem_cache_destroy(ntfs_attr_ctx_cache);
actx_err_out:
	kmem_cache_destroy(ntfs_index_ctx_cache);
ictx_err_out:
	if (!err) {
3218
		printk(KERN_CRIT "NTFS: Aborting NTFS filesystem driver "
L
Linus Torvalds 已提交
3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229
				"registration...\n");
		err = -ENOMEM;
	}
	return err;
}

static void __exit exit_ntfs_fs(void)
{
	ntfs_debug("Unregistering NTFS driver.");

	unregister_filesystem(&ntfs_fs_type);
3230 3231 3232 3233 3234
	kmem_cache_destroy(ntfs_big_inode_cache);
	kmem_cache_destroy(ntfs_inode_cache);
	kmem_cache_destroy(ntfs_name_cache);
	kmem_cache_destroy(ntfs_attr_ctx_cache);
	kmem_cache_destroy(ntfs_index_ctx_cache);
L
Linus Torvalds 已提交
3235 3236 3237 3238 3239
	/* Unregister the ntfs sysctls. */
	ntfs_sysctl(0);
}

MODULE_AUTHOR("Anton Altaparmakov <aia21@cantab.net>");
3240
MODULE_DESCRIPTION("NTFS 1.2/3.x driver - Copyright (c) 2001-2007 Anton Altaparmakov");
L
Linus Torvalds 已提交
3241 3242 3243 3244 3245 3246 3247 3248 3249
MODULE_VERSION(NTFS_VERSION);
MODULE_LICENSE("GPL");
#ifdef DEBUG
module_param(debug_msgs, bool, 0);
MODULE_PARM_DESC(debug_msgs, "Enable debug messages.");
#endif

module_init(init_ntfs_fs)
module_exit(exit_ntfs_fs)