/* * super.c - NTFS kernel super block handling. Part of the Linux-NTFS project. * * Copyright (c) 2001-2006 Anton Altaparmakov * 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 #include #include #include #include #include /* For bdev_hardsect_size(). */ #include #include #include #include #include #include "sysctl.h" #include "logfile.h" #include "quota.h" #include "usnjrnl.h" #include "dir.h" #include "debug.h" #include "index.h" #include "aops.h" #include "layout.h" #include "malloc.h" #include "ntfs.h" /* Number of mounted filesystems which have compression enabled. */ static unsigned long ntfs_nr_compression_users; /* A global default upcase table and a corresponding reference count. */ static ntfschar *default_upcase = NULL; static unsigned long ntfs_nr_upcase_users = 0; /* Error constants/strings used in inode.c::ntfs_show_options(). */ typedef enum { /* One of these must be present, default is ON_ERRORS_CONTINUE. */ ON_ERRORS_PANIC = 0x01, ON_ERRORS_REMOUNT_RO = 0x02, ON_ERRORS_CONTINUE = 0x04, /* Optional, can be combined with any of the above. */ ON_ERRORS_RECOVER = 0x10, } ON_ERRORS_ACTIONS; const option_t on_errors_arr[] = { { ON_ERRORS_PANIC, "panic" }, { ON_ERRORS_REMOUNT_RO, "remount-ro", }, { ON_ERRORS_CONTINUE, "continue", }, { ON_ERRORS_RECOVER, "recover" }, { 0, NULL } }; /** * simple_getbool - * * Copied from old ntfs driver (which copied from vfat driver). */ static int simple_getbool(char *s, BOOL *setval) { if (s) { if (!strcmp(s, "1") || !strcmp(s, "yes") || !strcmp(s, "true")) *setval = TRUE; else if (!strcmp(s, "0") || !strcmp(s, "no") || !strcmp(s, "false")) *setval = FALSE; else return 0; } else *setval = TRUE; return 1; } /** * parse_options - parse the (re)mount options * @vol: ntfs volume * @opt: string containing the (re)mount options * * Parse the recognized options in @opt for the ntfs volume described by @vol. */ static BOOL parse_options(ntfs_volume *vol, char *opt) { char *p, *v, *ov; static char *utf8 = "utf8"; int errors = 0, sloppy = 0; uid_t uid = (uid_t)-1; gid_t gid = (gid_t)-1; mode_t fmask = (mode_t)-1, dmask = (mode_t)-1; int mft_zone_multiplier = -1, on_errors = -1; int show_sys_files = -1, case_sensitive = -1, disable_sparse = -1; struct nls_table *nls_map = NULL, *old_nls; /* I am lazy... (-8 */ #define NTFS_GETOPT_WITH_DEFAULT(option, variable, default_value) \ if (!strcmp(p, option)) { \ if (!v || !*v) \ variable = default_value; \ else { \ variable = simple_strtoul(ov = v, &v, 0); \ if (*v) \ goto needs_val; \ } \ } #define NTFS_GETOPT(option, variable) \ if (!strcmp(p, option)) { \ if (!v || !*v) \ goto needs_arg; \ variable = simple_strtoul(ov = v, &v, 0); \ if (*v) \ goto needs_val; \ } #define NTFS_GETOPT_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; \ } #define NTFS_GETOPT_BOOL(option, variable) \ if (!strcmp(p, option)) { \ BOOL val; \ if (!simple_getbool(v, &val)) \ goto needs_bool; \ variable = val; \ } #define NTFS_GETOPT_OPTIONS_ARRAY(option, variable, opt_array) \ if (!strcmp(p, option)) { \ int _i; \ if (!v || !*v) \ goto needs_arg; \ ov = v; \ if (variable == -1) \ variable = 0; \ for (_i = 0; opt_array[_i].str && *opt_array[_i].str; _i++) \ if (!strcmp(opt_array[_i].str, v)) { \ variable |= opt_array[_i].val; \ break; \ } \ if (!opt_array[_i].str || !*opt_array[_i].str) \ goto needs_val; \ } if (!opt || !*opt) goto no_mount_options; ntfs_debug("Entering with mount options string: %s", opt); while ((p = strsep(&opt, ","))) { if ((v = strchr(p, '='))) *v++ = 0; NTFS_GETOPT("uid", uid) else NTFS_GETOPT("gid", gid) else NTFS_GETOPT_OCTAL("umask", fmask = dmask) else NTFS_GETOPT_OCTAL("fmask", fmask) else NTFS_GETOPT_OCTAL("dmask", dmask) else NTFS_GETOPT("mft_zone_multiplier", mft_zone_multiplier) else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, TRUE) else NTFS_GETOPT_BOOL("show_sys_files", show_sys_files) else NTFS_GETOPT_BOOL("case_sensitive", case_sensitive) else NTFS_GETOPT_BOOL("disable_sparse", disable_sparse) 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= in " "the future."); if (!v || !*v) goto needs_arg; use_utf8: old_nls = nls_map; nls_map = load_nls(v); if (!nls_map) { if (!old_nls) { ntfs_error(vol->sb, "NLS character set " "%s not found.", v); return FALSE; } ntfs_error(vol->sb, "NLS character set %s not " "found. Using previous one %s.", v, old_nls->charset); nls_map = old_nls; } else /* nls_map */ { if (old_nls) unload_nls(old_nls); } } else if (!strcmp(p, "utf8")) { BOOL val = FALSE; ntfs_warning(vol->sb, "Option utf8 is no longer " "supported, using option nls=utf8. Please " "use option nls=utf8 in the future and " "make sure utf8 is compiled either as a " "module or into the kernel."); if (!v || !*v) val = TRUE; else if (!simple_getbool(v, &val)) goto needs_bool; if (val) { v = utf8; goto use_utf8; } } else { ntfs_error(vol->sb, "Unrecognized mount option %s.", p); if (errors < INT_MAX) errors++; } #undef NTFS_GETOPT_OPTIONS_ARRAY #undef NTFS_GETOPT_BOOL #undef NTFS_GETOPT #undef NTFS_GETOPT_WITH_DEFAULT } no_mount_options: if (errors && !sloppy) return FALSE; if (sloppy) ntfs_warning(vol->sb, "Sloppy option given. Ignoring " "unrecognized mount option(s) and continuing."); /* Keep this first! */ if (on_errors != -1) { if (!on_errors) { ntfs_error(vol->sb, "Invalid errors option argument " "or bug in options parser."); return FALSE; } } if (nls_map) { if (vol->nls_map && vol->nls_map != nls_map) { ntfs_error(vol->sb, "Cannot change NLS character set " "on remount."); return FALSE; } /* else (!vol->nls_map) */ ntfs_debug("Using NLS character set %s.", nls_map->charset); vol->nls_map = nls_map; } else /* (!nls_map) */ { if (!vol->nls_map) { vol->nls_map = load_nls_default(); if (!vol->nls_map) { ntfs_error(vol->sb, "Failed to load default " "NLS character set."); return FALSE; } ntfs_debug("Using default NLS character set (%s).", vol->nls_map->charset); } } if (mft_zone_multiplier != -1) { if (vol->mft_zone_multiplier && vol->mft_zone_multiplier != mft_zone_multiplier) { ntfs_error(vol->sb, "Cannot change mft_zone_multiplier " "on remount."); return FALSE; } if (mft_zone_multiplier < 1 || mft_zone_multiplier > 4) { ntfs_error(vol->sb, "Invalid mft_zone_multiplier. " "Using default value, i.e. 1."); mft_zone_multiplier = 1; } vol->mft_zone_multiplier = mft_zone_multiplier; } if (!vol->mft_zone_multiplier) vol->mft_zone_multiplier = 1; if (on_errors != -1) vol->on_errors = on_errors; if (!vol->on_errors || vol->on_errors == ON_ERRORS_RECOVER) vol->on_errors |= ON_ERRORS_CONTINUE; if (uid != (uid_t)-1) vol->uid = uid; if (gid != (gid_t)-1) vol->gid = gid; if (fmask != (mode_t)-1) vol->fmask = fmask; if (dmask != (mode_t)-1) vol->dmask = dmask; if (show_sys_files != -1) { if (show_sys_files) NVolSetShowSystemFiles(vol); else NVolClearShowSystemFiles(vol); } if (case_sensitive != -1) { if (case_sensitive) NVolSetCaseSensitive(vol); else NVolClearCaseSensitive(vol); } 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); } } return TRUE; needs_arg: ntfs_error(vol->sb, "The %s option requires an argument.", p); return FALSE; needs_bool: ntfs_error(vol->sb, "The %s option requires a boolean argument.", p); return FALSE; needs_val: ntfs_error(vol->sb, "Invalid %s option argument: %s", p, ov); return FALSE; } #ifdef NTFS_RW /** * ntfs_write_volume_flags - write new flags to the volume information flags * @vol: ntfs volume on which to modify the flags * @flags: new flags value for the volume information flags * * Internal function. You probably want to use ntfs_{set,clear}_volume_flags() * instead (see below). * * Replace the volume information flags on the volume @vol with the value * supplied in @flags. Note, this overwrites the volume information flags, so * make sure to combine the flags you want to modify with the old flags and use * the result when calling ntfs_write_volume_flags(). * * Return 0 on success and -errno on error. */ static int ntfs_write_volume_flags(ntfs_volume *vol, const VOLUME_FLAGS flags) { ntfs_inode *ni = NTFS_I(vol->vol_ino); MFT_RECORD *m; VOLUME_INFORMATION *vi; ntfs_attr_search_ctx *ctx; int err; ntfs_debug("Entering, old flags = 0x%x, new flags = 0x%x.", le16_to_cpu(vol->vol_flags), le16_to_cpu(flags)); if (vol->vol_flags == flags) goto done; BUG_ON(!ni); m = map_mft_record(ni); if (IS_ERR(m)) { err = PTR_ERR(m); goto err_out; } ctx = ntfs_attr_get_search_ctx(ni, m); if (!ctx) { err = -ENOMEM; goto put_unm_err_out; } err = ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0, ctx); if (err) goto put_unm_err_out; vi = (VOLUME_INFORMATION*)((u8*)ctx->attr + le16_to_cpu(ctx->attr->data.resident.value_offset)); vol->vol_flags = vi->flags = flags; flush_dcache_mft_record_page(ctx->ntfs_ino); mark_mft_record_dirty(ctx->ntfs_ino); ntfs_attr_put_search_ctx(ctx); unmap_mft_record(ni); done: ntfs_debug("Done."); return 0; put_unm_err_out: if (ctx) ntfs_attr_put_search_ctx(ctx); unmap_mft_record(ni); err_out: ntfs_error(vol->sb, "Failed with error code %i.", -err); return err; } /** * ntfs_set_volume_flags - set bits in the volume information flags * @vol: ntfs volume on which to modify the flags * @flags: flags to set on the volume * * Set the bits in @flags in the volume information flags on the volume @vol. * * Return 0 on success and -errno on error. */ static inline int ntfs_set_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags) { flags &= VOLUME_FLAGS_MASK; return ntfs_write_volume_flags(vol, vol->vol_flags | flags); } /** * ntfs_clear_volume_flags - clear bits in the volume information flags * @vol: ntfs volume on which to modify the flags * @flags: flags to clear on the volume * * Clear the bits in @flags in the volume information flags on the volume @vol. * * Return 0 on success and -errno on error. */ static inline int ntfs_clear_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags) { flags &= VOLUME_FLAGS_MASK; flags = vol->vol_flags & cpu_to_le16(~le16_to_cpu(flags)); return ntfs_write_volume_flags(vol, flags); } #endif /* NTFS_RW */ /** * ntfs_remount - change the mount options of a mounted ntfs filesystem * @sb: superblock of mounted ntfs filesystem * @flags: remount flags * @opt: remount options string * * Change the mount options of an already mounted ntfs filesystem. * * NOTE: The VFS sets the @sb->s_flags remount flags to @flags after * ntfs_remount() returns successfully (i.e. returns 0). Otherwise, * @sb->s_flags are not changed. */ static int ntfs_remount(struct super_block *sb, int *flags, char *opt) { ntfs_volume *vol = NTFS_SB(sb); ntfs_debug("Entering with remount options string: %s", opt); #ifndef NTFS_RW /* For read-only compiled driver, enforce read-only flag. */ *flags |= MS_RDONLY; #else /* NTFS_RW */ /* * For the read-write compiled driver, if we are remounting read-write, * make sure there are no volume errors and that no unsupported volume * flags are set. Also, empty the logfile journal as it would become * stale as soon as something is written to the volume and mark the * volume dirty so that chkdsk is run if the volume is not umounted * cleanly. Finally, mark the quotas out of date so Windows rescans * the volume on boot and updates them. * * When remounting read-only, mark the volume clean if no volume errors * have occured. */ if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) { static const char *es = ". Cannot remount read-write."; /* Remounting read-write. */ if (NVolErrors(vol)) { ntfs_error(sb, "Volume has errors and is read-only%s", es); return -EROFS; } if (vol->vol_flags & VOLUME_IS_DIRTY) { ntfs_error(sb, "Volume is dirty and read-only%s", es); return -EROFS; } if (vol->vol_flags & VOLUME_MODIFIED_BY_CHKDSK) { ntfs_error(sb, "Volume has been modified by chkdsk " "and is read-only%s", es); return -EROFS; } if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) { ntfs_error(sb, "Volume has unsupported flags set " "(0x%x) and is read-only%s", (unsigned)le16_to_cpu(vol->vol_flags), es); return -EROFS; } if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) { ntfs_error(sb, "Failed to set dirty bit in volume " "information flags%s", es); return -EROFS; } #if 0 // TODO: Enable this code once we start modifying anything that // is different between NTFS 1.2 and 3.x... /* Set NT4 compatibility flag on newer NTFS version volumes. */ if ((vol->major_ver > 1)) { if (ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) { ntfs_error(sb, "Failed to set NT4 " "compatibility flag%s", es); NVolSetErrors(vol); return -EROFS; } } #endif if (!ntfs_empty_logfile(vol->logfile_ino)) { ntfs_error(sb, "Failed to empty journal $LogFile%s", es); NVolSetErrors(vol); return -EROFS; } if (!ntfs_mark_quotas_out_of_date(vol)) { ntfs_error(sb, "Failed to mark quotas out of date%s", es); NVolSetErrors(vol); return -EROFS; } if (!ntfs_stamp_usnjrnl(vol)) { ntfs_error(sb, "Failed to stamp transation log " "($UsnJrnl)%s", es); NVolSetErrors(vol); return -EROFS; } } else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) { /* Remounting read-only. */ if (!NVolErrors(vol)) { if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY)) ntfs_warning(sb, "Failed to clear dirty bit " "in volume information " "flags. Run chkdsk."); } } #endif /* NTFS_RW */ // TODO: Deal with *flags. if (!parse_options(vol, opt)) return -EINVAL; ntfs_debug("Done."); return 0; } /** * is_boot_sector_ntfs - check whether a boot sector is a valid NTFS boot sector * @sb: Super block of the device to which @b belongs. * @b: Boot sector of device @sb to check. * @silent: If TRUE, all output will be silenced. * * is_boot_sector_ntfs() checks whether the boot sector @b is a valid NTFS boot * sector. Returns TRUE if it is valid and FALSE if not. * * @sb is only needed for warning/error output, i.e. it can be NULL when silent * is TRUE. */ static BOOL is_boot_sector_ntfs(const struct super_block *sb, const NTFS_BOOT_SECTOR *b, const BOOL silent) { /* * Check that checksum == sum of u32 values from b to the checksum * field. If checksum is zero, no checking is done. 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. */ if ((void*)b < (void*)&b->checksum && b->checksum && !silent) { 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) ntfs_warning(sb, "Invalid boot sector checksum."); } /* Check OEMidentifier is "NTFS " */ if (b->oem_id != magicNTFS) goto not_ntfs; /* Check bytes per sector value is between 256 and 4096. */ if (le16_to_cpu(b->bpb.bytes_per_sector) < 0x100 || le16_to_cpu(b->bpb.bytes_per_sector) > 0x1000) goto not_ntfs; /* Check sectors per cluster value is valid. */ switch (b->bpb.sectors_per_cluster) { case 1: case 2: case 4: case 8: case 16: case 32: case 64: case 128: break; default: goto not_ntfs; } /* Check the cluster size is not above the maximum (64kiB). */ if ((u32)le16_to_cpu(b->bpb.bytes_per_sector) * b->bpb.sectors_per_cluster > NTFS_MAX_CLUSTER_SIZE) goto not_ntfs; /* Check reserved/unused fields are really zero. */ if (le16_to_cpu(b->bpb.reserved_sectors) || le16_to_cpu(b->bpb.root_entries) || le16_to_cpu(b->bpb.sectors) || le16_to_cpu(b->bpb.sectors_per_fat) || le32_to_cpu(b->bpb.large_sectors) || b->bpb.fats) goto not_ntfs; /* Check clusters per file mft record value is valid. */ if ((u8)b->clusters_per_mft_record < 0xe1 || (u8)b->clusters_per_mft_record > 0xf7) switch (b->clusters_per_mft_record) { case 1: case 2: case 4: case 8: case 16: case 32: case 64: break; default: goto not_ntfs; } /* Check clusters per index block value is valid. */ if ((u8)b->clusters_per_index_record < 0xe1 || (u8)b->clusters_per_index_record > 0xf7) switch (b->clusters_per_index_record) { case 1: case 2: case 4: case 8: case 16: case 32: case 64: break; default: goto not_ntfs; } /* * Check for valid end of sector marker. We will work without it, but * many BIOSes will refuse to boot from a bootsector if the magic is * incorrect, so we emit a warning. */ if (!silent && b->end_of_sector_marker != const_cpu_to_le16(0xaa55)) ntfs_warning(sb, "Invalid end of sector marker."); return TRUE; not_ntfs: return FALSE; } /** * read_ntfs_boot_sector - read the NTFS boot sector of a device * @sb: super block of device to read the boot sector from * @silent: if true, suppress all output * * Reads the boot sector from the device and validates it. If that fails, tries * to read the backup boot sector, first from the end of the device a-la NT4 and * later and then from the middle of the device a-la NT3.51 and before. * * If a valid boot sector is found but it is not the primary boot sector, we * repair the primary boot sector silently (unless the device is read-only or * the primary boot sector is not accessible). * * NOTE: To call this function, @sb must have the fields s_dev, the ntfs super * block (u.ntfs_sb), nr_blocks and the device flags (s_flags) initialized * to their respective values. * * Return the unlocked buffer head containing the boot sector or NULL on error. */ static struct buffer_head *read_ntfs_boot_sector(struct super_block *sb, const int silent) { const char *read_err_str = "Unable to read %s boot sector."; struct buffer_head *bh_primary, *bh_backup; sector_t nr_blocks = NTFS_SB(sb)->nr_blocks; /* Try to read primary boot sector. */ if ((bh_primary = sb_bread(sb, 0))) { if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*) bh_primary->b_data, silent)) return bh_primary; if (!silent) ntfs_error(sb, "Primary boot sector is invalid."); } else if (!silent) ntfs_error(sb, read_err_str, "primary"); if (!(NTFS_SB(sb)->on_errors & ON_ERRORS_RECOVER)) { if (bh_primary) brelse(bh_primary); if (!silent) ntfs_error(sb, "Mount option errors=recover not used. " "Aborting without trying to recover."); return NULL; } /* Try to read NT4+ backup boot sector. */ if ((bh_backup = sb_bread(sb, nr_blocks - 1))) { if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*) bh_backup->b_data, silent)) goto hotfix_primary_boot_sector; brelse(bh_backup); } else if (!silent) ntfs_error(sb, read_err_str, "backup"); /* Try to read NT3.51- backup boot sector. */ if ((bh_backup = sb_bread(sb, nr_blocks >> 1))) { if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*) bh_backup->b_data, silent)) goto hotfix_primary_boot_sector; if (!silent) ntfs_error(sb, "Could not find a valid backup boot " "sector."); brelse(bh_backup); } else if (!silent) ntfs_error(sb, read_err_str, "backup"); /* We failed. Cleanup and return. */ if (bh_primary) brelse(bh_primary); return NULL; hotfix_primary_boot_sector: if (bh_primary) { /* * If we managed to read sector zero and the volume is not * read-only, copy the found, valid backup boot sector to the * primary boot sector. 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). */ 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, NTFS_BLOCK_SIZE); mark_buffer_dirty(bh_primary); sync_dirty_buffer(bh_primary); if (buffer_uptodate(bh_primary)) { brelse(bh_backup); return bh_primary; } ntfs_error(sb, "Hot-fix: Device write error while " "recovering primary boot sector."); } else { ntfs_warning(sb, "Hot-fix: Recovery of primary boot " "sector failed: Read-only mount."); } brelse(bh_primary); } ntfs_warning(sb, "Using backup boot sector."); return bh_backup; } /** * parse_ntfs_boot_sector - parse the boot sector and store the data in @vol * @vol: volume structure to initialise with data from boot sector * @b: boot sector to parse * * Parse the ntfs boot sector @b and store all imporant information therein in * the ntfs super block @vol. Return TRUE on success and FALSE on error. */ static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b) { unsigned int sectors_per_cluster_bits, nr_hidden_sects; int clusters_per_mft_record, clusters_per_index_record; s64 ll; vol->sector_size = le16_to_cpu(b->bpb.bytes_per_sector); vol->sector_size_bits = ffs(vol->sector_size) - 1; ntfs_debug("vol->sector_size = %i (0x%x)", vol->sector_size, vol->sector_size); ntfs_debug("vol->sector_size_bits = %i (0x%x)", vol->sector_size_bits, vol->sector_size_bits); if (vol->sector_size < vol->sb->s_blocksize) { ntfs_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); return FALSE; } ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster); sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1; ntfs_debug("sectors_per_cluster_bits = 0x%x", sectors_per_cluster_bits); nr_hidden_sects = le32_to_cpu(b->bpb.hidden_sectors); ntfs_debug("number of hidden sectors = 0x%x", nr_hidden_sects); vol->cluster_size = vol->sector_size << sectors_per_cluster_bits; vol->cluster_size_mask = vol->cluster_size - 1; vol->cluster_size_bits = ffs(vol->cluster_size) - 1; ntfs_debug("vol->cluster_size = %i (0x%x)", vol->cluster_size, vol->cluster_size); ntfs_debug("vol->cluster_size_mask = 0x%x", vol->cluster_size_mask); ntfs_debug("vol->cluster_size_bits = %i", 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); return FALSE; } clusters_per_mft_record = b->clusters_per_mft_record; ntfs_debug("clusters_per_mft_record = %i (0x%x)", clusters_per_mft_record, clusters_per_mft_record); if (clusters_per_mft_record > 0) vol->mft_record_size = vol->cluster_size << (ffs(clusters_per_mft_record) - 1); else /* * When mft_record_size < cluster_size, clusters_per_mft_record * = -log2(mft_record_size) bytes. mft_record_size normaly is * 1024 bytes, which is encoded as 0xF6 (-10 in decimal). */ vol->mft_record_size = 1 << -clusters_per_mft_record; vol->mft_record_size_mask = vol->mft_record_size - 1; vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1; ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size, vol->mft_record_size); ntfs_debug("vol->mft_record_size_mask = 0x%x", vol->mft_record_size_mask); ntfs_debug("vol->mft_record_size_bits = %i (0x%x)", vol->mft_record_size_bits, vol->mft_record_size_bits); /* * We cannot support mft record sizes above the PAGE_CACHE_SIZE since * we store $MFT/$DATA, the table of mft records in the page cache. */ if (vol->mft_record_size > PAGE_CACHE_SIZE) { ntfs_error(vol->sb, "Mft record size (%i) exceeds the " "PAGE_CACHE_SIZE on your system (%lu). " "This is not supported. Sorry.", vol->mft_record_size, PAGE_CACHE_SIZE); return FALSE; } /* 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); return FALSE; } clusters_per_index_record = b->clusters_per_index_record; ntfs_debug("clusters_per_index_record = %i (0x%x)", clusters_per_index_record, clusters_per_index_record); if (clusters_per_index_record > 0) vol->index_record_size = vol->cluster_size << (ffs(clusters_per_index_record) - 1); else /* * When index_record_size < cluster_size, * clusters_per_index_record = -log2(index_record_size) bytes. * index_record_size normaly equals 4096 bytes, which is * encoded as 0xF4 (-12 in decimal). */ vol->index_record_size = 1 << -clusters_per_index_record; vol->index_record_size_mask = vol->index_record_size - 1; vol->index_record_size_bits = ffs(vol->index_record_size) - 1; ntfs_debug("vol->index_record_size = %i (0x%x)", vol->index_record_size, vol->index_record_size); ntfs_debug("vol->index_record_size_mask = 0x%x", vol->index_record_size_mask); ntfs_debug("vol->index_record_size_bits = %i (0x%x)", vol->index_record_size_bits, vol->index_record_size_bits); /* 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); return FALSE; } /* * Get the size of the volume in clusters and check for 64-bit-ness. * Windows currently only uses 32 bits to save the clusters so we do * the same as it is much faster on 32-bit CPUs. */ ll = sle64_to_cpu(b->number_of_sectors) >> sectors_per_cluster_bits; if ((u64)ll >= 1ULL << 32) { ntfs_error(vol->sb, "Cannot handle 64-bit clusters. Sorry."); return FALSE; } vol->nr_clusters = ll; ntfs_debug("vol->nr_clusters = 0x%llx", (long long)vol->nr_clusters); /* * On an architecture where unsigned long is 32-bits, we restrict the * volume size to 2TiB (2^41). On a 64-bit architecture, the compiler * will hopefully optimize the whole check away. */ if (sizeof(unsigned long) < 8) { if ((ll << vol->cluster_size_bits) >= (1ULL << 41)) { ntfs_error(vol->sb, "Volume size (%lluTiB) is too " "large for this architecture. " "Maximum supported is 2TiB. Sorry.", (unsigned long long)ll >> (40 - vol->cluster_size_bits)); return FALSE; } } ll = sle64_to_cpu(b->mft_lcn); if (ll >= vol->nr_clusters) { ntfs_error(vol->sb, "MFT LCN (%lli, 0x%llx) is beyond end of " "volume. Weird.", (unsigned long long)ll, (unsigned long long)ll); return FALSE; } vol->mft_lcn = ll; ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn); ll = sle64_to_cpu(b->mftmirr_lcn); if (ll >= vol->nr_clusters) { ntfs_error(vol->sb, "MFTMirr LCN (%lli, 0x%llx) is beyond end " "of volume. Weird.", (unsigned long long)ll, (unsigned long long)ll); return FALSE; } vol->mftmirr_lcn = ll; ntfs_debug("vol->mftmirr_lcn = 0x%llx", (long long)vol->mftmirr_lcn); #ifdef NTFS_RW /* * Work out the size of the mft mirror in number of mft records. If the * cluster size is less than or equal to the size taken by four mft * records, the mft mirror stores the first four mft records. If the * cluster size is bigger than the size taken by four mft records, the * mft mirror contains as many mft records as will fit into one * cluster. */ if (vol->cluster_size <= (4 << vol->mft_record_size_bits)) vol->mftmirr_size = 4; else vol->mftmirr_size = vol->cluster_size >> vol->mft_record_size_bits; ntfs_debug("vol->mftmirr_size = %i", vol->mftmirr_size); #endif /* NTFS_RW */ vol->serial_no = le64_to_cpu(b->volume_serial_number); ntfs_debug("vol->serial_no = 0x%llx", (unsigned long long)vol->serial_no); return TRUE; } /** * ntfs_setup_allocators - initialize the cluster and mft allocators * @vol: volume structure for which to setup the allocators * * Setup the cluster (lcn) and mft allocators to the starting values. */ static void ntfs_setup_allocators(ntfs_volume *vol) { #ifdef NTFS_RW LCN mft_zone_size, mft_lcn; #endif /* NTFS_RW */ ntfs_debug("vol->mft_zone_multiplier = 0x%x", vol->mft_zone_multiplier); #ifdef NTFS_RW /* Determine the size of the MFT zone. */ mft_zone_size = vol->nr_clusters; switch (vol->mft_zone_multiplier) { /* % of volume size in clusters */ case 4: mft_zone_size >>= 1; /* 50% */ break; case 3: mft_zone_size = (mft_zone_size + (mft_zone_size >> 1)) >> 2; /* 37.5% */ break; case 2: mft_zone_size >>= 2; /* 25% */ break; /* case 1: */ default: mft_zone_size >>= 3; /* 12.5% */ break; } /* Setup the mft zone. */ vol->mft_zone_start = vol->mft_zone_pos = vol->mft_lcn; ntfs_debug("vol->mft_zone_pos = 0x%llx", (unsigned long long)vol->mft_zone_pos); /* * Calculate the mft_lcn for an unmodified NTFS volume (see mkntfs * source) and if the actual mft_lcn is in the expected place or even * further to the front of the volume, extend the mft_zone to cover the * beginning of the volume as well. This is in order to protect the * area reserved for the mft bitmap as well within the mft_zone itself. * On non-standard volumes we do not protect it as the overhead would * be higher than the speed increase we would get by doing it. */ mft_lcn = (8192 + 2 * vol->cluster_size - 1) / vol->cluster_size; if (mft_lcn * vol->cluster_size < 16 * 1024) mft_lcn = (16 * 1024 + vol->cluster_size - 1) / vol->cluster_size; if (vol->mft_zone_start <= mft_lcn) vol->mft_zone_start = 0; ntfs_debug("vol->mft_zone_start = 0x%llx", (unsigned long long)vol->mft_zone_start); /* * Need to cap the mft zone on non-standard volumes so that it does * not point outside the boundaries of the volume. We do this by * halving the zone size until we are inside the volume. */ vol->mft_zone_end = vol->mft_lcn + mft_zone_size; while (vol->mft_zone_end >= vol->nr_clusters) { mft_zone_size >>= 1; vol->mft_zone_end = vol->mft_lcn + mft_zone_size; } ntfs_debug("vol->mft_zone_end = 0x%llx", (unsigned long long)vol->mft_zone_end); /* * Set the current position within each data zone to the start of the * respective zone. */ vol->data1_zone_pos = vol->mft_zone_end; ntfs_debug("vol->data1_zone_pos = 0x%llx", (unsigned long long)vol->data1_zone_pos); vol->data2_zone_pos = 0; ntfs_debug("vol->data2_zone_pos = 0x%llx", (unsigned long long)vol->data2_zone_pos); /* Set the mft data allocation position to mft record 24. */ vol->mft_data_pos = 24; ntfs_debug("vol->mft_data_pos = 0x%llx", (unsigned long long)vol->mft_data_pos); #endif /* NTFS_RW */ } #ifdef NTFS_RW /** * load_and_init_mft_mirror - load and setup the mft mirror inode for a volume * @vol: ntfs super block describing device whose mft mirror to load * * Return TRUE on success or FALSE on error. */ static BOOL load_and_init_mft_mirror(ntfs_volume *vol) { struct inode *tmp_ino; ntfs_inode *tmp_ni; ntfs_debug("Entering."); /* Get mft mirror inode. */ tmp_ino = ntfs_iget(vol->sb, FILE_MFTMirr); if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) { if (!IS_ERR(tmp_ino)) iput(tmp_ino); /* Caller will display error message. */ return FALSE; } /* * Re-initialize some specifics about $MFTMirr's inode as * ntfs_read_inode() will have set up the default ones. */ /* Set uid and gid to root. */ tmp_ino->i_uid = tmp_ino->i_gid = 0; /* Regular file. No access for anyone. */ tmp_ino->i_mode = S_IFREG; /* No VFS initiated operations allowed for $MFTMirr. */ tmp_ino->i_op = &ntfs_empty_inode_ops; tmp_ino->i_fop = &ntfs_empty_file_ops; /* Put in our special address space operations. */ tmp_ino->i_mapping->a_ops = &ntfs_mst_aops; tmp_ni = NTFS_I(tmp_ino); /* The $MFTMirr, like the $MFT is multi sector transfer protected. */ NInoSetMstProtected(tmp_ni); NInoSetSparseDisabled(tmp_ni); /* * Set up our little cheat allowing us to reuse the async read io * completion handler for directories. */ tmp_ni->itype.index.block_size = vol->mft_record_size; tmp_ni->itype.index.block_size_bits = vol->mft_record_size_bits; vol->mftmirr_ino = tmp_ino; ntfs_debug("Done."); return TRUE; } /** * check_mft_mirror - compare contents of the mft mirror with the mft * @vol: ntfs super block describing device whose mft mirror to check * * Return TRUE on success or FALSE on error. * * Note, this function also results in the mft mirror runlist being completely * mapped into memory. The mft mirror write code requires this and will BUG() * should it find an unmapped runlist element. */ static BOOL check_mft_mirror(ntfs_volume *vol) { struct super_block *sb = vol->sb; ntfs_inode *mirr_ni; struct page *mft_page, *mirr_page; u8 *kmft, *kmirr; runlist_element *rl, rl2[2]; pgoff_t index; int mrecs_per_page, i; ntfs_debug("Entering."); /* Compare contents of $MFT and $MFTMirr. */ mrecs_per_page = PAGE_CACHE_SIZE / vol->mft_record_size; BUG_ON(!mrecs_per_page); BUG_ON(!vol->mftmirr_size); mft_page = mirr_page = NULL; kmft = kmirr = NULL; index = i = 0; do { u32 bytes; /* Switch pages if necessary. */ if (!(i % mrecs_per_page)) { if (index) { ntfs_unmap_page(mft_page); ntfs_unmap_page(mirr_page); } /* Get the $MFT page. */ mft_page = ntfs_map_page(vol->mft_ino->i_mapping, index); if (IS_ERR(mft_page)) { ntfs_error(sb, "Failed to read $MFT."); return FALSE; } kmft = page_address(mft_page); /* Get the $MFTMirr page. */ mirr_page = ntfs_map_page(vol->mftmirr_ino->i_mapping, index); if (IS_ERR(mirr_page)) { ntfs_error(sb, "Failed to read $MFTMirr."); goto mft_unmap_out; } kmirr = page_address(mirr_page); ++index; } /* Do not check the record if it is not in use. */ if (((MFT_RECORD*)kmft)->flags & MFT_RECORD_IN_USE) { /* Make sure the record is ok. */ if (ntfs_is_baad_recordp((le32*)kmft)) { ntfs_error(sb, "Incomplete multi sector " "transfer detected in mft " "record %i.", i); mm_unmap_out: ntfs_unmap_page(mirr_page); mft_unmap_out: ntfs_unmap_page(mft_page); return FALSE; } } /* Do not check the mirror record if it is not in use. */ if (((MFT_RECORD*)kmirr)->flags & MFT_RECORD_IN_USE) { if (ntfs_is_baad_recordp((le32*)kmirr)) { ntfs_error(sb, "Incomplete multi sector " "transfer detected in mft " "mirror record %i.", i); goto mm_unmap_out; } } /* Get the amount of data in the current record. */ bytes = le32_to_cpu(((MFT_RECORD*)kmft)->bytes_in_use); if (bytes < sizeof(MFT_RECORD_OLD) || bytes > vol->mft_record_size || ntfs_is_baad_recordp((le32*)kmft)) { bytes = le32_to_cpu(((MFT_RECORD*)kmirr)->bytes_in_use); if (bytes < sizeof(MFT_RECORD_OLD) || bytes > vol->mft_record_size || ntfs_is_baad_recordp((le32*)kmirr)) bytes = vol->mft_record_size; } /* Compare the two records. */ if (memcmp(kmft, kmirr, bytes)) { ntfs_error(sb, "$MFT and $MFTMirr (record %i) do not " "match. Run ntfsfix or chkdsk.", i); goto mm_unmap_out; } kmft += vol->mft_record_size; kmirr += vol->mft_record_size; } while (++i < vol->mftmirr_size); /* Release the last pages. */ ntfs_unmap_page(mft_page); ntfs_unmap_page(mirr_page); /* Construct the mft mirror runlist by hand. */ rl2[0].vcn = 0; rl2[0].lcn = vol->mftmirr_lcn; rl2[0].length = (vol->mftmirr_size * vol->mft_record_size + vol->cluster_size - 1) / vol->cluster_size; rl2[1].vcn = rl2[0].length; rl2[1].lcn = LCN_ENOENT; rl2[1].length = 0; /* * Because we have just read all of the mft mirror, we know we have * mapped the full runlist for it. */ mirr_ni = NTFS_I(vol->mftmirr_ino); down_read(&mirr_ni->runlist.lock); rl = mirr_ni->runlist.rl; /* Compare the two runlists. They must be identical. */ i = 0; do { if (rl2[i].vcn != rl[i].vcn || rl2[i].lcn != rl[i].lcn || rl2[i].length != rl[i].length) { ntfs_error(sb, "$MFTMirr location mismatch. " "Run chkdsk."); up_read(&mirr_ni->runlist.lock); return FALSE; } } while (rl2[i++].length); up_read(&mirr_ni->runlist.lock); ntfs_debug("Done."); return TRUE; } /** * load_and_check_logfile - load and check the logfile inode for a volume * @vol: ntfs super block describing device whose logfile to load * * Return TRUE on success or FALSE on error. */ static BOOL load_and_check_logfile(ntfs_volume *vol, RESTART_PAGE_HEADER **rp) { struct inode *tmp_ino; ntfs_debug("Entering."); tmp_ino = ntfs_iget(vol->sb, FILE_LogFile); if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) { if (!IS_ERR(tmp_ino)) iput(tmp_ino); /* Caller will display error message. */ return FALSE; } if (!ntfs_check_logfile(tmp_ino, rp)) { iput(tmp_ino); /* ntfs_check_logfile() will have displayed error output. */ return FALSE; } NInoSetSparseDisabled(NTFS_I(tmp_ino)); vol->logfile_ino = tmp_ino; ntfs_debug("Done."); return TRUE; } #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; static const ntfschar hiberfil[13] = { const_cpu_to_le16('h'), const_cpu_to_le16('i'), const_cpu_to_le16('b'), const_cpu_to_le16('e'), const_cpu_to_le16('r'), const_cpu_to_le16('f'), const_cpu_to_le16('i'), const_cpu_to_le16('l'), const_cpu_to_le16('.'), const_cpu_to_le16('s'), const_cpu_to_le16('y'), const_cpu_to_le16('s'), 0 }; ntfs_debug("Entering."); /* * Find the inode number for the hibernation file by looking up the * filename hiberfil.sys in the root directory. */ mutex_lock(&vol->root_ino->i_mutex); mref = ntfs_lookup_inode_by_name(NTFS_I(vol->root_ino), hiberfil, 12, &name); mutex_unlock(&vol->root_ino->i_mutex); 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); if (*(le32*)kaddr == const_cpu_to_le32(0x72626968)/*'hibr'*/) { 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; } /** * load_and_init_quota - load and setup the quota file for a volume if present * @vol: ntfs super block describing device whose quota file to load * * Return TRUE on success or FALSE on error. If $Quota is not present, we * leave vol->quota_ino as NULL and return success. */ static BOOL load_and_init_quota(ntfs_volume *vol) { MFT_REF mref; struct inode *tmp_ino; ntfs_name *name = NULL; static const ntfschar Quota[7] = { const_cpu_to_le16('$'), const_cpu_to_le16('Q'), const_cpu_to_le16('u'), const_cpu_to_le16('o'), const_cpu_to_le16('t'), const_cpu_to_le16('a'), 0 }; static ntfschar Q[3] = { const_cpu_to_le16('$'), const_cpu_to_le16('Q'), 0 }; ntfs_debug("Entering."); /* * Find the inode number for the quota file by looking up the filename * $Quota in the extended system files directory $Extend. */ mutex_lock(&vol->extend_ino->i_mutex); mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), Quota, 6, &name); mutex_unlock(&vol->extend_ino->i_mutex); if (IS_ERR_MREF(mref)) { /* * If the file does not exist, quotas are disabled and have * never been enabled on this volume, just return success. */ if (MREF_ERR(mref) == -ENOENT) { ntfs_debug("$Quota not present. Volume does not have " "quotas enabled."); /* * No need to try to set quotas out of date if they are * not enabled. */ NVolSetQuotaOutOfDate(vol); return TRUE; } /* A real error occured. */ ntfs_error(vol->sb, "Failed to find inode number for $Quota."); return FALSE; } /* We do not care for the type of match that was found. */ kfree(name); /* Get the inode. */ tmp_ino = ntfs_iget(vol->sb, MREF(mref)); if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) { if (!IS_ERR(tmp_ino)) iput(tmp_ino); ntfs_error(vol->sb, "Failed to load $Quota."); return FALSE; } vol->quota_ino = tmp_ino; /* Get the $Q index allocation attribute. */ tmp_ino = ntfs_index_iget(vol->quota_ino, Q, 2); if (IS_ERR(tmp_ino)) { ntfs_error(vol->sb, "Failed to load $Quota/$Q index."); return FALSE; } vol->quota_q_ino = tmp_ino; ntfs_debug("Done."); return TRUE; } /** * load_and_init_usnjrnl - load and setup the transaction log if present * @vol: ntfs super block describing device whose usnjrnl file to load * * Return TRUE on success or FALSE on error. * * 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. */ static BOOL load_and_init_usnjrnl(ntfs_volume *vol) { MFT_REF mref; struct inode *tmp_ino; ntfs_inode *tmp_ni; struct page *page; ntfs_name *name = NULL; USN_HEADER *uh; static const ntfschar UsnJrnl[9] = { const_cpu_to_le16('$'), const_cpu_to_le16('U'), const_cpu_to_le16('s'), const_cpu_to_le16('n'), const_cpu_to_le16('J'), const_cpu_to_le16('r'), const_cpu_to_le16('n'), const_cpu_to_le16('l'), 0 }; static ntfschar Max[5] = { const_cpu_to_le16('$'), const_cpu_to_le16('M'), const_cpu_to_le16('a'), const_cpu_to_le16('x'), 0 }; static ntfschar J[3] = { const_cpu_to_le16('$'), const_cpu_to_le16('J'), 0 }; ntfs_debug("Entering."); /* * Find the inode number for the transaction log file by looking up the * filename $UsnJrnl in the extended system files directory $Extend. */ mutex_lock(&vol->extend_ino->i_mutex); mref = ntfs_lookup_inode_by_name(NTFS_I(vol->extend_ino), UsnJrnl, 8, &name); mutex_unlock(&vol->extend_ino->i_mutex); if (IS_ERR_MREF(mref)) { /* * If the file does not exist, transaction logging is disabled, * just return success. */ if (MREF_ERR(mref) == -ENOENT) { ntfs_debug("$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); return TRUE; } /* A real error occured. */ ntfs_error(vol->sb, "Failed to find inode number for " "$UsnJrnl."); return FALSE; } /* 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 $UsnJrnl."); return FALSE; } vol->usnjrnl_ino = tmp_ino; /* * If the transaction log is in the process of being deleted, we can * ignore it. */ if (unlikely(vol->vol_flags & VOLUME_DELETE_USN_UNDERWAY)) { ntfs_debug("$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."); return FALSE; } 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 " "least 0x%zx bytes).", i_size_read(tmp_ino), sizeof(USN_HEADER)); return FALSE; } /* 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."); return FALSE; } 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."); return FALSE; } /* 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."); return FALSE; } 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). $UsnJrnl is corrupt.", (long long)sle64_to_cpu(uh->allocation_delta), (long long)sle64_to_cpu(uh->maximum_size)); ntfs_unmap_page(page); return FALSE; } /* * If the transaction log has been stamped and nothing has been written * to it since, we do not need to stamp it. */ if (unlikely(sle64_to_cpu(uh->lowest_valid_usn) >= i_size_read(vol->usnjrnl_j_ino))) { if (likely(sle64_to_cpu(uh->lowest_valid_usn) == i_size_read(vol->usnjrnl_j_ino))) { ntfs_unmap_page(page); ntfs_debug("$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); return FALSE; } ntfs_unmap_page(page); ntfs_debug("Done."); return TRUE; } /** * load_and_init_attrdef - load the attribute definitions table for a volume * @vol: ntfs super block describing device whose attrdef to load * * Return TRUE on success or FALSE on error. */ static BOOL load_and_init_attrdef(ntfs_volume *vol) { loff_t i_size; struct super_block *sb = vol->sb; struct inode *ino; struct page *page; pgoff_t index, max_index; 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; } NInoSetSparseDisabled(NTFS_I(ino)); /* The size of FILE_AttrDef must be above 0 and fit inside 31 bits. */ i_size = i_size_read(ino); if (i_size <= 0 || i_size > 0x7fffffff) goto iput_failed; vol->attrdef = (ATTR_DEF*)ntfs_malloc_nofs(i_size); if (!vol->attrdef) goto iput_failed; index = 0; max_index = i_size >> PAGE_CACHE_SHIFT; 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) { size = i_size & ~PAGE_CACHE_MASK; if (size) goto read_partial_attrdef_page; } vol->attrdef_size = i_size; ntfs_debug("Read %llu bytes from $AttrDef.", i_size); iput(ino); return TRUE; free_iput_failed: ntfs_free(vol->attrdef); vol->attrdef = NULL; iput_failed: iput(ino); failed: ntfs_error(sb, "Failed to initialize attribute definition table."); return FALSE; } #endif /* NTFS_RW */ /** * load_and_init_upcase - load the upcase table for an ntfs volume * @vol: ntfs super block describing device whose upcase to load * * Return TRUE on success or FALSE on error. */ static BOOL load_and_init_upcase(ntfs_volume *vol) { loff_t i_size; struct super_block *sb = vol->sb; struct inode *ino; struct page *page; pgoff_t index, max_index; 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). */ i_size = i_size_read(ino); if (!i_size || i_size & (sizeof(ntfschar) - 1) || i_size > 64ULL * 1024 * sizeof(ntfschar)) goto iput_upcase_failed; vol->upcase = (ntfschar*)ntfs_malloc_nofs(i_size); if (!vol->upcase) goto iput_upcase_failed; index = 0; max_index = i_size >> PAGE_CACHE_SHIFT; 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) { size = i_size & ~PAGE_CACHE_MASK; if (size) goto read_partial_upcase_page; } vol->upcase_len = i_size >> UCHAR_T_SIZE_BITS; ntfs_debug("Read %llu bytes from $UpCase (expected %zu bytes).", i_size, 64 * 1024 * sizeof(ntfschar)); iput(ino); mutex_lock(&ntfs_lock); if (!default_upcase) { ntfs_debug("Using volume specified $UpCase since default is " "not present."); mutex_unlock(&ntfs_lock); return TRUE; } max = default_upcase_len; if (max > vol->upcase_len) max = vol->upcase_len; for (i = 0; i < max; i++) if (vol->upcase[i] != default_upcase[i]) break; if (i == max) { ntfs_free(vol->upcase); vol->upcase = default_upcase; vol->upcase_len = max; ntfs_nr_upcase_users++; mutex_unlock(&ntfs_lock); ntfs_debug("Volume specified $UpCase matches default. Using " "default."); return TRUE; } mutex_unlock(&ntfs_lock); ntfs_debug("Using volume specified $UpCase since it does not match " "the default."); return TRUE; iput_upcase_failed: iput(ino); ntfs_free(vol->upcase); vol->upcase = NULL; upcase_failed: mutex_lock(&ntfs_lock); if (default_upcase) { vol->upcase = default_upcase; vol->upcase_len = default_upcase_len; ntfs_nr_upcase_users++; mutex_unlock(&ntfs_lock); ntfs_error(sb, "Failed to load $UpCase from the volume. Using " "default."); return TRUE; } mutex_unlock(&ntfs_lock); ntfs_error(sb, "Failed to initialize upcase table."); return FALSE; } /** * load_system_files - open the system files using normal functions * @vol: ntfs super block describing device whose system files to load * * Open the system files with normal access functions and complete setting up * the ntfs super block @vol. * * Return TRUE on success or FALSE on error. */ static BOOL load_system_files(ntfs_volume *vol) { struct super_block *sb = vol->sb; MFT_RECORD *m; VOLUME_INFORMATION *vi; ntfs_attr_search_ctx *ctx; #ifdef NTFS_RW RESTART_PAGE_HEADER *rp; int err; #endif /* NTFS_RW */ ntfs_debug("Entering."); #ifdef NTFS_RW /* Get mft mirror inode compare the contents of $MFT and $MFTMirr. */ if (!load_and_init_mft_mirror(vol) || !check_mft_mirror(vol)) { static const char *es1 = "Failed to load $MFTMirr"; static const char *es2 = "$MFTMirr does not match $MFT"; static const char *es3 = ". Run ntfsfix and/or chkdsk."; /* If a read-write mount, convert it to a read-only mount. */ if (!(sb->s_flags & MS_RDONLY)) { if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO | ON_ERRORS_CONTINUE))) { ntfs_error(sb, "%s and neither on_errors=" "continue nor on_errors=" "remount-ro was specified%s", !vol->mftmirr_ino ? es1 : es2, es3); goto iput_mirr_err_out; } sb->s_flags |= MS_RDONLY; ntfs_error(sb, "%s. Mounting read-only%s", !vol->mftmirr_ino ? es1 : es2, es3); } else ntfs_warning(sb, "%s. Will not be able to remount " "read-write%s", !vol->mftmirr_ino ? es1 : es2, es3); /* This will prevent a read-write remount. */ NVolSetErrors(vol); } #endif /* NTFS_RW */ /* Get mft bitmap attribute inode. */ vol->mftbmp_ino = ntfs_attr_iget(vol->mft_ino, AT_BITMAP, NULL, 0); if (IS_ERR(vol->mftbmp_ino)) { ntfs_error(sb, "Failed to load $MFT/$BITMAP attribute."); goto iput_mirr_err_out; } /* Read upcase table and setup @vol->upcase and @vol->upcase_len. */ if (!load_and_init_upcase(vol)) goto iput_mftbmp_err_out; #ifdef NTFS_RW /* * Read attribute definitions table and setup @vol->attrdef and * @vol->attrdef_size. */ if (!load_and_init_attrdef(vol)) goto iput_upcase_err_out; #endif /* NTFS_RW */ /* * Get the cluster allocation bitmap inode and verify the size, no * need for any locking at this stage as we are already running * exclusively as we are mount in progress task. */ vol->lcnbmp_ino = ntfs_iget(sb, FILE_Bitmap); if (IS_ERR(vol->lcnbmp_ino) || is_bad_inode(vol->lcnbmp_ino)) { if (!IS_ERR(vol->lcnbmp_ino)) iput(vol->lcnbmp_ino); goto bitmap_failed; } NInoSetSparseDisabled(NTFS_I(vol->lcnbmp_ino)); if ((vol->nr_clusters + 7) >> 3 > i_size_read(vol->lcnbmp_ino)) { 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); 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); } #ifdef NTFS_RW /* Make sure that no unsupported volume flags are set. */ if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) { static const char *es1a = "Volume is dirty"; static const char *es1b = "Volume has 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)); } /* If a read-write mount, convert it to a read-only mount. */ if (!(sb->s_flags & MS_RDONLY)) { if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO | ON_ERRORS_CONTINUE))) { ntfs_error(sb, "%s and neither on_errors=" "continue nor on_errors=" "remount-ro was specified%s", es1, es2); goto iput_vol_err_out; } sb->s_flags |= MS_RDONLY; 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. */ rp = NULL; if (!load_and_check_logfile(vol, &rp) || !ntfs_is_logfile_clean(vol->logfile_ino, rp)) { 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); if (vol->logfile_ino) { BUG_ON(!rp); ntfs_free(rp); } goto iput_logfile_err_out; } sb->s_flags |= MS_RDONLY; 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); } ntfs_free(rp); #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; } sb->s_flags |= MS_RDONLY; ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); } else ntfs_warning(sb, "%s. Will not be able to remount " "read-write%s", es1, es2); /* This will prevent a read-write remount. */ NVolSetErrors(vol); } /* If (still) a read-write mount, mark the volume dirty. */ if (!(sb->s_flags & MS_RDONLY) && ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) { static const char *es1 = "Failed to set dirty bit in volume " "information flags"; static const char *es2 = ". Run chkdsk."; /* Convert to a read-only mount. */ if (!(vol->on_errors & (ON_ERRORS_REMOUNT_RO | ON_ERRORS_CONTINUE))) { ntfs_error(sb, "%s and neither on_errors=continue nor " "on_errors=remount-ro was specified%s", es1, es2); goto iput_root_err_out; } ntfs_error(sb, "%s. Mounting read-only%s", es1, es2); sb->s_flags |= MS_RDONLY; /* * 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