Linux-2.6.12-rc2

Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.

Let it rip!

1 files changed, 2771 insertions, 0 deletions

diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c
new file mode 100644
index 000000000000..212a3d0f2073
--- /dev/null
+++ b/fs/ntfs/super.c
@@ -0,0 +1,2771 @@
+/*
+ * super.c - NTFS kernel super block handling. Part of the Linux-NTFS project.
+ *
+ * Copyright (c) 2001-2004 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 <linux/stddef.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/spinlock.h>
+#include <linux/blkdev.h>	/* For bdev_hardsect_size(). */
+#include <linux/backing-dev.h>
+#include <linux/buffer_head.h>
+#include <linux/vfs.h>
+#include <linux/moduleparam.h>
+#include <linux/smp_lock.h>
+
+#include "sysctl.h"
+#include "logfile.h"
+#include "quota.h"
+#include "dir.h"
+#include "debug.h"
+#include "index.h"
+#include "aops.h"
+#include "malloc.h"
+#include "ntfs.h"
+
+/* Number of mounted file systems 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;
+	struct nls_table *nls_map = NULL, *old_nls;
+
+	/* I am lazy... (-8 */
+#define NTFS_GETOPT_WITH_DEFAULT(option, variable, default_value)	\
+	if (!strcmp(p, option)) {					\
+		if (!v || !*v)						\
+			variable = default_value;			\
+		else {							\
+			variable = simple_strtoul(ov = v, &v, 0);	\
+			if (*v)						\
+				goto needs_val;				\
+		}							\
+	}
+#define NTFS_GETOPT(option, variable)					\
+	if (!strcmp(p, option)) {					\
+		if (!v || !*v)						\
+			goto needs_arg;					\
+		variable = simple_strtoul(ov = v, &v, 0);		\
+		if (*v)							\
+			goto needs_val;					\
+	}
+#define NTFS_GETOPT_BOOL(option, variable)				\
+	if (!strcmp(p, option)) {					\
+		BOOL val;						\
+		if (!simple_getbool(v, &val))				\
+			goto needs_bool;				\
+		variable = val;						\
+	}
+#define NTFS_GETOPT_OPTIONS_ARRAY(option, variable, opt_array)		\
+	if (!strcmp(p, option)) {					\
+		int _i;							\
+		if (!v || !*v)						\
+			goto needs_arg;					\
+		ov = v;							\
+		if (variable == -1)					\
+			variable = 0;					\
+		for (_i = 0; opt_array[_i].str && *opt_array[_i].str; _i++) \
+			if (!strcmp(opt_array[_i].str, v)) {		\
+				variable |= opt_array[_i].val;		\
+				break;					\
+			}						\
+		if (!opt_array[_i].str || !*opt_array[_i].str)		\
+			goto needs_val;					\
+	}
+	if (!opt || !*opt)
+		goto no_mount_options;
+	ntfs_debug("Entering with mount options string: %s", opt);
+	while ((p = strsep(&opt, ","))) {
+		if ((v = strchr(p, '=')))
+			*v++ = 0;
+		NTFS_GETOPT("uid", uid)
+		else NTFS_GETOPT("gid", gid)
+		else NTFS_GETOPT("umask", fmask = dmask)
+		else NTFS_GETOPT("fmask", fmask)
+		else NTFS_GETOPT("dmask", dmask)
+		else NTFS_GETOPT("mft_zone_multiplier", mft_zone_multiplier)
+		else NTFS_GETOPT_WITH_DEFAULT("sloppy", sloppy, TRUE)
+		else NTFS_GETOPT_BOOL("show_sys_files", show_sys_files)
+		else NTFS_GETOPT_BOOL("case_sensitive", case_sensitive)
+		else NTFS_GETOPT_OPTIONS_ARRAY("errors", on_errors,
+				on_errors_arr)
+		else if (!strcmp(p, "posix") || !strcmp(p, "show_inodes"))
+			ntfs_warning(vol->sb, "Ignoring obsolete option %s.",
+					p);
+		else if (!strcmp(p, "nls") || !strcmp(p, "iocharset")) {
+			if (!strcmp(p, "iocharset"))
+				ntfs_warning(vol->sb, "Option iocharset is "
+						"deprecated. Please use "
+						"option nls=<charsetname> in "
+						"the future.");
+			if (!v || !*v)
+				goto needs_arg;
+use_utf8:
+			old_nls = nls_map;
+			nls_map = load_nls(v);
+			if (!nls_map) {
+				if (!old_nls) {
+					ntfs_error(vol->sb, "NLS character set "
+							"%s not found.", v);
+					return FALSE;
+				}
+				ntfs_error(vol->sb, "NLS character set %s not "
+						"found. Using previous one %s.",
+						v, old_nls->charset);
+				nls_map = old_nls;
+			} else /* nls_map */ {
+				if (old_nls)
+					unload_nls(old_nls);
+			}
+		} else if (!strcmp(p, "utf8")) {
+			BOOL val = FALSE;
+			ntfs_warning(vol->sb, "Option utf8 is no longer "
+				   "supported, using option nls=utf8. Please "
+				   "use option nls=utf8 in the future and "
+				   "make sure utf8 is compiled either as a "
+				   "module or into the kernel.");
+			if (!v || !*v)
+				val = TRUE;
+			else if (!simple_getbool(v, &val))
+				goto needs_bool;
+			if (val) {
+				v = utf8;
+				goto use_utf8;
+			}
+		} else {
+			ntfs_error(vol->sb, "Unrecognized mount option %s.", p);
+			if (errors < INT_MAX)
+				errors++;
+		}
+#undef NTFS_GETOPT_OPTIONS_ARRAY
+#undef NTFS_GETOPT_BOOL
+#undef NTFS_GETOPT
+#undef NTFS_GETOPT_WITH_DEFAULT
+	}
+no_mount_options:
+	if (errors && !sloppy)
+		return FALSE;
+	if (sloppy)
+		ntfs_warning(vol->sb, "Sloppy option given. Ignoring "
+				"unrecognized mount option(s) and continuing.");
+	/* Keep this first! */
+	if (on_errors != -1) {
+		if (!on_errors) {
+			ntfs_error(vol->sb, "Invalid errors option argument "
+					"or bug in options parser.");
+			return FALSE;
+		}
+	}
+	if (nls_map) {
+		if (vol->nls_map && vol->nls_map != nls_map) {
+			ntfs_error(vol->sb, "Cannot change NLS character set "
+					"on remount.");
+			return FALSE;
+		} /* else (!vol->nls_map) */
+		ntfs_debug("Using NLS character set %s.", nls_map->charset);
+		vol->nls_map = nls_map;
+	} else /* (!nls_map) */ {
+		if (!vol->nls_map) {
+			vol->nls_map = load_nls_default();
+			if (!vol->nls_map) {
+				ntfs_error(vol->sb, "Failed to load default "
+						"NLS character set.");
+				return FALSE;
+			}
+			ntfs_debug("Using default NLS character set (%s).",
+					vol->nls_map->charset);
+		}
+	}
+	if (mft_zone_multiplier != -1) {
+		if (vol->mft_zone_multiplier && vol->mft_zone_multiplier !=
+				mft_zone_multiplier) {
+			ntfs_error(vol->sb, "Cannot change mft_zone_multiplier "
+					"on remount.");
+			return FALSE;
+		}
+		if (mft_zone_multiplier < 1 || mft_zone_multiplier > 4) {
+			ntfs_error(vol->sb, "Invalid mft_zone_multiplier. "
+					"Using default value, i.e. 1.");
+			mft_zone_multiplier = 1;
+		}
+		vol->mft_zone_multiplier = mft_zone_multiplier;
+	}
+	if (!vol->mft_zone_multiplier)
+		vol->mft_zone_multiplier = 1;
+	if (on_errors != -1)
+		vol->on_errors = on_errors;
+	if (!vol->on_errors || vol->on_errors == ON_ERRORS_RECOVER)
+		vol->on_errors |= ON_ERRORS_CONTINUE;
+	if (uid != (uid_t)-1)
+		vol->uid = uid;
+	if (gid != (gid_t)-1)
+		vol->gid = gid;
+	if (fmask != (mode_t)-1)
+		vol->fmask = fmask;
+	if (dmask != (mode_t)-1)
+		vol->dmask = dmask;
+	if (show_sys_files != -1) {
+		if (show_sys_files)
+			NVolSetShowSystemFiles(vol);
+		else
+			NVolClearShowSystemFiles(vol);
+	}
+	if (case_sensitive != -1) {
+		if (case_sensitive)
+			NVolSetCaseSensitive(vol);
+		else
+			NVolClearCaseSensitive(vol);
+	}
+	return TRUE;
+needs_arg:
+	ntfs_error(vol->sb, "The %s option requires an argument.", p);
+	return FALSE;
+needs_bool:
+	ntfs_error(vol->sb, "The %s option requires a boolean argument.", p);
+	return FALSE;
+needs_val:
+	ntfs_error(vol->sb, "Invalid %s option argument: %s", p, ov);
+	return FALSE;
+}
+
+#ifdef NTFS_RW
+
+/**
+ * ntfs_write_volume_flags - write new flags to the volume information flags
+ * @vol:	ntfs volume on which to modify the flags
+ * @flags:	new flags value for the volume information flags
+ *
+ * Internal function.  You probably want to use ntfs_{set,clear}_volume_flags()
+ * instead (see below).
+ *
+ * Replace the volume information flags on the volume @vol with the value
+ * supplied in @flags.  Note, this overwrites the volume information flags, so
+ * make sure to combine the flags you want to modify with the old flags and use
+ * the result when calling ntfs_write_volume_flags().
+ *
+ * Return 0 on success and -errno on error.
+ */
+static int ntfs_write_volume_flags(ntfs_volume *vol, const VOLUME_FLAGS flags)
+{
+	ntfs_inode *ni = NTFS_I(vol->vol_ino);
+	MFT_RECORD *m;
+	VOLUME_INFORMATION *vi;
+	ntfs_attr_search_ctx *ctx;
+	int err;
+
+	ntfs_debug("Entering, old flags = 0x%x, new flags = 0x%x.",
+			le16_to_cpu(vol->vol_flags), le16_to_cpu(flags));
+	if (vol->vol_flags == flags)
+		goto done;
+	BUG_ON(!ni);
+	m = map_mft_record(ni);
+	if (IS_ERR(m)) {
+		err = PTR_ERR(m);
+		goto err_out;
+	}
+	ctx = ntfs_attr_get_search_ctx(ni, m);
+	if (!ctx) {
+		err = -ENOMEM;
+		goto put_unm_err_out;
+	}
+	err = ntfs_attr_lookup(AT_VOLUME_INFORMATION, NULL, 0, 0, 0, NULL, 0,
+			ctx);
+	if (err)
+		goto put_unm_err_out;
+	vi = (VOLUME_INFORMATION*)((u8*)ctx->attr +
+			le16_to_cpu(ctx->attr->data.resident.value_offset));
+	vol->vol_flags = vi->flags = flags;
+	flush_dcache_mft_record_page(ctx->ntfs_ino);
+	mark_mft_record_dirty(ctx->ntfs_ino);
+	ntfs_attr_put_search_ctx(ctx);
+	unmap_mft_record(ni);
+done:
+	ntfs_debug("Done.");
+	return 0;
+put_unm_err_out:
+	if (ctx)
+		ntfs_attr_put_search_ctx(ctx);
+	unmap_mft_record(ni);
+err_out:
+	ntfs_error(vol->sb, "Failed with error code %i.", -err);
+	return err;
+}
+
+/**
+ * ntfs_set_volume_flags - set bits in the volume information flags
+ * @vol:	ntfs volume on which to modify the flags
+ * @flags:	flags to set on the volume
+ *
+ * Set the bits in @flags in the volume information flags on the volume @vol.
+ *
+ * Return 0 on success and -errno on error.
+ */
+static inline int ntfs_set_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)
+{
+	flags &= VOLUME_FLAGS_MASK;
+	return ntfs_write_volume_flags(vol, vol->vol_flags | flags);
+}
+
+/**
+ * ntfs_clear_volume_flags - clear bits in the volume information flags
+ * @vol:	ntfs volume on which to modify the flags
+ * @flags:	flags to clear on the volume
+ *
+ * Clear the bits in @flags in the volume information flags on the volume @vol.
+ *
+ * Return 0 on success and -errno on error.
+ */
+static inline int ntfs_clear_volume_flags(ntfs_volume *vol, VOLUME_FLAGS flags)
+{
+	flags &= VOLUME_FLAGS_MASK;
+	flags = vol->vol_flags & cpu_to_le16(~le16_to_cpu(flags));
+	return ntfs_write_volume_flags(vol, flags);
+}
+
+#endif /* NTFS_RW */
+
+/**
+ * ntfs_remount - change the mount options of a mounted ntfs filesystem
+ * @sb:		superblock of mounted ntfs filesystem
+ * @flags:	remount flags
+ * @opt:	remount options string
+ *
+ * Change the mount options of an already mounted ntfs filesystem.
+ *
+ * NOTE:  The VFS sets the @sb->s_flags remount flags to @flags after
+ * ntfs_remount() returns successfully (i.e. returns 0).  Otherwise,
+ * @sb->s_flags are not changed.
+ */
+static int ntfs_remount(struct super_block *sb, int *flags, char *opt)
+{
+	ntfs_volume *vol = NTFS_SB(sb);
+
+	ntfs_debug("Entering with remount options string: %s", opt);
+#ifndef NTFS_RW
+	/* For read-only compiled driver, enforce all read-only flags. */
+	*flags |= MS_RDONLY | MS_NOATIME | MS_NODIRATIME;
+#else /* NTFS_RW */
+	/*
+	 * For the read-write compiled driver, if we are remounting read-write,
+	 * make sure there are no volume errors and that no unsupported volume
+	 * flags are set.  Also, empty the logfile journal as it would become
+	 * stale as soon as something is written to the volume and mark the
+	 * volume dirty so that chkdsk is run if the volume is not umounted
+	 * cleanly.  Finally, mark the quotas out of date so Windows rescans
+	 * the volume on boot and updates them.
+	 *
+	 * When remounting read-only, mark the volume clean if no volume errors
+	 * have occured.
+	 */
+	if ((sb->s_flags & MS_RDONLY) && !(*flags & MS_RDONLY)) {
+		static const char *es = ".  Cannot remount read-write.";
+
+		/* Remounting read-write. */
+		if (NVolErrors(vol)) {
+			ntfs_error(sb, "Volume has errors and is read-only%s",
+					es);
+			return -EROFS;
+		}
+		if (vol->vol_flags & VOLUME_IS_DIRTY) {
+			ntfs_error(sb, "Volume is dirty and read-only%s", es);
+			return -EROFS;
+		}
+		if (vol->vol_flags & VOLUME_MUST_MOUNT_RO_MASK) {
+			ntfs_error(sb, "Volume has unsupported flags set and "
+					"is read-only%s", es);
+			return -EROFS;
+		}
+		if (ntfs_set_volume_flags(vol, VOLUME_IS_DIRTY)) {
+			ntfs_error(sb, "Failed to set dirty bit in volume "
+					"information flags%s", es);
+			return -EROFS;
+		}
+#if 0
+		// TODO: Enable this code once we start modifying anything that
+		//	 is different between NTFS 1.2 and 3.x...
+		/* Set NT4 compatibility flag on newer NTFS version volumes. */
+		if ((vol->major_ver > 1)) {
+			if (ntfs_set_volume_flags(vol, VOLUME_MOUNTED_ON_NT4)) {
+				ntfs_error(sb, "Failed to set NT4 "
+						"compatibility flag%s", es);
+				NVolSetErrors(vol);
+				return -EROFS;
+			}
+		}
+#endif
+		if (!ntfs_empty_logfile(vol->logfile_ino)) {
+			ntfs_error(sb, "Failed to empty journal $LogFile%s",
+					es);
+			NVolSetErrors(vol);
+			return -EROFS;
+		}
+		if (!ntfs_mark_quotas_out_of_date(vol)) {
+			ntfs_error(sb, "Failed to mark quotas out of date%s",
+					es);
+			NVolSetErrors(vol);
+			return -EROFS;
+		}
+	} else if (!(sb->s_flags & MS_RDONLY) && (*flags & MS_RDONLY)) {
+		/* Remounting read-only. */
+		if (!NVolErrors(vol)) {
+			if (ntfs_clear_volume_flags(vol, VOLUME_IS_DIRTY))
+				ntfs_warning(sb, "Failed to clear dirty bit "
+						"in volume information "
+						"flags.  Run chkdsk.");
+		}
+	}
+#endif /* NTFS_RW */
+
+	// TODO: Deal with *flags.
+
+	if (!parse_options(vol, opt))
+		return -EINVAL;
+	ntfs_debug("Done.");
+	return 0;
+}
+
+/**
+ * is_boot_sector_ntfs - check whether a boot sector is a valid NTFS boot sector
+ * @sb:		Super block of the device to which @b belongs.
+ * @b:		Boot sector of device @sb to check.
+ * @silent:	If TRUE, all output will be silenced.
+ *
+ * is_boot_sector_ntfs() checks whether the boot sector @b is a valid NTFS boot
+ * sector. Returns TRUE if it is valid and FALSE if not.
+ *
+ * @sb is only needed for warning/error output, i.e. it can be NULL when silent
+ * is TRUE.
+ */
+static BOOL is_boot_sector_ntfs(const struct super_block *sb,
+		const NTFS_BOOT_SECTOR *b, const BOOL silent)
+{
+	/*
+	 * Check that checksum == sum of u32 values from b to the checksum
+	 * field. If checksum is zero, no checking is done.
+	 */
+	if ((void*)b < (void*)&b->checksum && b->checksum) {
+		le32 *u;
+		u32 i;
+
+		for (i = 0, u = (le32*)b; u < (le32*)(&b->checksum); ++u)
+			i += le32_to_cpup(u);
+		if (le32_to_cpu(b->checksum) != i)
+			goto not_ntfs;
+	}
+	/* Check OEMidentifier is "NTFS    " */
+	if (b->oem_id != magicNTFS)
+		goto not_ntfs;
+	/* Check bytes per sector value is between 256 and 4096. */
+	if (le16_to_cpu(b->bpb.bytes_per_sector) < 0x100 ||
+			le16_to_cpu(b->bpb.bytes_per_sector) > 0x1000)
+		goto not_ntfs;
+	/* Check sectors per cluster value is valid. */
+	switch (b->bpb.sectors_per_cluster) {
+	case 1: case 2: case 4: case 8: case 16: case 32: case 64: case 128:
+		break;
+	default:
+		goto not_ntfs;
+	}
+	/* Check the cluster size is not above 65536 bytes. */
+	if ((u32)le16_to_cpu(b->bpb.bytes_per_sector) *
+			b->bpb.sectors_per_cluster > 0x10000)
+		goto not_ntfs;
+	/* Check reserved/unused fields are really zero. */
+	if (le16_to_cpu(b->bpb.reserved_sectors) ||
+			le16_to_cpu(b->bpb.root_entries) ||
+			le16_to_cpu(b->bpb.sectors) ||
+			le16_to_cpu(b->bpb.sectors_per_fat) ||
+			le32_to_cpu(b->bpb.large_sectors) || b->bpb.fats)
+		goto not_ntfs;
+	/* Check clusters per file mft record value is valid. */
+	if ((u8)b->clusters_per_mft_record < 0xe1 ||
+			(u8)b->clusters_per_mft_record > 0xf7)
+		switch (b->clusters_per_mft_record) {
+		case 1: case 2: case 4: case 8: case 16: case 32: case 64:
+			break;
+		default:
+			goto not_ntfs;
+		}
+	/* Check clusters per index block value is valid. */
+	if ((u8)b->clusters_per_index_record < 0xe1 ||
+			(u8)b->clusters_per_index_record > 0xf7)
+		switch (b->clusters_per_index_record) {
+		case 1: case 2: case 4: case 8: case 16: case 32: case 64:
+			break;
+		default:
+			goto not_ntfs;
+		}
+	/*
+	 * Check for valid end of sector marker. We will work without it, but
+	 * many BIOSes will refuse to boot from a bootsector if the magic is
+	 * incorrect, so we emit a warning.
+	 */
+	if (!silent && b->end_of_sector_marker != cpu_to_le16(0xaa55))
+		ntfs_warning(sb, "Invalid end of sector marker.");
+	return TRUE;
+not_ntfs:
+	return FALSE;
+}
+
+/**
+ * read_ntfs_boot_sector - read the NTFS boot sector of a device
+ * @sb:		super block of device to read the boot sector from
+ * @silent:	if true, suppress all output
+ *
+ * Reads the boot sector from the device and validates it. If that fails, tries
+ * to read the backup boot sector, first from the end of the device a-la NT4 and
+ * later and then from the middle of the device a-la NT3.51 and before.
+ *
+ * If a valid boot sector is found but it is not the primary boot sector, we
+ * repair the primary boot sector silently (unless the device is read-only or
+ * the primary boot sector is not accessible).
+ *
+ * NOTE: To call this function, @sb must have the fields s_dev, the ntfs super
+ * block (u.ntfs_sb), nr_blocks and the device flags (s_flags) initialized
+ * to their respective values.
+ *
+ * Return the unlocked buffer head containing the boot sector or NULL on error.
+ */
+static struct buffer_head *read_ntfs_boot_sector(struct super_block *sb,
+		const int silent)
+{
+	const char *read_err_str = "Unable to read %s boot sector.";
+	struct buffer_head *bh_primary, *bh_backup;
+	long nr_blocks = NTFS_SB(sb)->nr_blocks;
+
+	/* Try to read primary boot sector. */
+	if ((bh_primary = sb_bread(sb, 0))) {
+		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
+				bh_primary->b_data, silent))
+			return bh_primary;
+		if (!silent)
+			ntfs_error(sb, "Primary boot sector is invalid.");
+	} else if (!silent)
+		ntfs_error(sb, read_err_str, "primary");
+	if (!(NTFS_SB(sb)->on_errors & ON_ERRORS_RECOVER)) {
+		if (bh_primary)
+			brelse(bh_primary);
+		if (!silent)
+			ntfs_error(sb, "Mount option errors=recover not used. "
+					"Aborting without trying to recover.");
+		return NULL;
+	}
+	/* Try to read NT4+ backup boot sector. */
+	if ((bh_backup = sb_bread(sb, nr_blocks - 1))) {
+		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
+				bh_backup->b_data, silent))
+			goto hotfix_primary_boot_sector;
+		brelse(bh_backup);
+	} else if (!silent)
+		ntfs_error(sb, read_err_str, "backup");
+	/* Try to read NT3.51- backup boot sector. */
+	if ((bh_backup = sb_bread(sb, nr_blocks >> 1))) {
+		if (is_boot_sector_ntfs(sb, (NTFS_BOOT_SECTOR*)
+				bh_backup->b_data, silent))
+			goto hotfix_primary_boot_sector;
+		if (!silent)
+			ntfs_error(sb, "Could not find a valid backup boot "
+					"sector.");
+		brelse(bh_backup);
+	} else if (!silent)
+		ntfs_error(sb, read_err_str, "backup");
+	/* We failed. Cleanup and return. */
+	if (bh_primary)
+		brelse(bh_primary);
+	return NULL;
+hotfix_primary_boot_sector:
+	if (bh_primary) {
+		/*
+		 * If we managed to read sector zero and the volume is not
+		 * read-only, copy the found, valid backup boot sector to the
+		 * primary boot sector.
+		 */
+		if (!(sb->s_flags & MS_RDONLY)) {
+			ntfs_warning(sb, "Hot-fix: Recovering invalid primary "
+					"boot sector from backup copy.");
+			memcpy(bh_primary->b_data, bh_backup->b_data,
+					sb->s_blocksize);
+			mark_buffer_dirty(bh_primary);
+			sync_dirty_buffer(bh_primary);
+			if (buffer_uptodate(bh_primary)) {
+				brelse(bh_backup);
+				return bh_primary;
+			}
+			ntfs_error(sb, "Hot-fix: Device write error while "
+					"recovering primary boot sector.");
+		} else {
+			ntfs_warning(sb, "Hot-fix: Recovery of primary boot "
+					"sector failed: Read-only mount.");
+		}
+		brelse(bh_primary);
+	}
+	ntfs_warning(sb, "Using backup boot sector.");
+	return bh_backup;
+}
+
+/**
+ * parse_ntfs_boot_sector - parse the boot sector and store the data in @vol
+ * @vol:	volume structure to initialise with data from boot sector
+ * @b:		boot sector to parse
+ *
+ * Parse the ntfs boot sector @b and store all imporant information therein in
+ * the ntfs super block @vol.  Return TRUE on success and FALSE on error.
+ */
+static BOOL parse_ntfs_boot_sector(ntfs_volume *vol, const NTFS_BOOT_SECTOR *b)
+{
+	unsigned int sectors_per_cluster_bits, nr_hidden_sects;
+	int clusters_per_mft_record, clusters_per_index_record;
+	s64 ll;
+
+	vol->sector_size = le16_to_cpu(b->bpb.bytes_per_sector);
+	vol->sector_size_bits = ffs(vol->sector_size) - 1;
+	ntfs_debug("vol->sector_size = %i (0x%x)", vol->sector_size,
+			vol->sector_size);
+	ntfs_debug("vol->sector_size_bits = %i (0x%x)", vol->sector_size_bits,
+			vol->sector_size_bits);
+	if (vol->sector_size != vol->sb->s_blocksize)
+		ntfs_warning(vol->sb, "The boot sector indicates a sector size "
+				"different from the device sector size.");
+	ntfs_debug("sectors_per_cluster = 0x%x", b->bpb.sectors_per_cluster);
+	sectors_per_cluster_bits = ffs(b->bpb.sectors_per_cluster) - 1;
+	ntfs_debug("sectors_per_cluster_bits = 0x%x",
+			sectors_per_cluster_bits);
+	nr_hidden_sects = le32_to_cpu(b->bpb.hidden_sectors);
+	ntfs_debug("number of hidden sectors = 0x%x", nr_hidden_sects);
+	vol->cluster_size = vol->sector_size << sectors_per_cluster_bits;
+	vol->cluster_size_mask = vol->cluster_size - 1;
+	vol->cluster_size_bits = ffs(vol->cluster_size) - 1;
+	ntfs_debug("vol->cluster_size = %i (0x%x)", vol->cluster_size,
+			vol->cluster_size);
+	ntfs_debug("vol->cluster_size_mask = 0x%x", vol->cluster_size_mask);
+	ntfs_debug("vol->cluster_size_bits = %i (0x%x)",
+			vol->cluster_size_bits, vol->cluster_size_bits);
+	if (vol->sector_size > vol->cluster_size) {
+		ntfs_error(vol->sb, "Sector sizes above the cluster size are "
+				"not supported.  Sorry.");
+		return FALSE;
+	}
+	if (vol->sb->s_blocksize > vol->cluster_size) {
+		ntfs_error(vol->sb, "Cluster sizes smaller than the device "
+				"sector size are not supported.  Sorry.");
+		return FALSE;
+	}
+	clusters_per_mft_record = b->clusters_per_mft_record;
+	ntfs_debug("clusters_per_mft_record = %i (0x%x)",
+			clusters_per_mft_record, clusters_per_mft_record);
+	if (clusters_per_mft_record > 0)
+		vol->mft_record_size = vol->cluster_size <<
+				(ffs(clusters_per_mft_record) - 1);
+	else
+		/*
+		 * When mft_record_size < cluster_size, clusters_per_mft_record
+		 * = -log2(mft_record_size) bytes. mft_record_size normaly is
+		 * 1024 bytes, which is encoded as 0xF6 (-10 in decimal).
+		 */
+		vol->mft_record_size = 1 << -clusters_per_mft_record;
+	vol->mft_record_size_mask = vol->mft_record_size - 1;
+	vol->mft_record_size_bits = ffs(vol->mft_record_size) - 1;
+	ntfs_debug("vol->mft_record_size = %i (0x%x)", vol->mft_record_size,
+			vol->mft_record_size);
+	ntfs_debug("vol->mft_record_size_mask = 0x%x",
+			vol->mft_record_size_mask);
+	ntfs_debug("vol->mft_record_size_bits = %i (0x%x)",
+			vol->mft_record_size_bits, vol->mft_record_size_bits);
+	/*
+	 * We cannot support mft record sizes above the PAGE_CACHE_SIZE since
+	 * we store $MFT/$DATA, the table of mft records in the page cache.
+	 */
+	if (vol->mft_record_size > PAGE_CACHE_SIZE) {
+		ntfs_error(vol->sb, "Mft record size %i (0x%x) exceeds the "
+				"page cache size on your system %lu (0x%lx).  "
+				"This is not supported.  Sorry.",
+				vol->mft_record_size, vol->mft_record_size,
+				PAGE_CACHE_SIZE, PAGE_CACHE_SIZE);
+		return FALSE;
+	}
+	clusters_per_index_record = b->clusters_per_index_record;
+	ntfs_debug("clusters_per_index_record = %i (0x%x)",
+			clusters_per_index_record, clusters_per_index_record);
+	if (clusters_per_index_record > 0)
+		vol->index_record_size = vol->cluster_size <<
+				(ffs(clusters_per_index_record) - 1);
+	else
+		/*
+		 * When index_record_size < cluster_size,
+		 * clusters_per_index_record = -log2(index_record_size) bytes.
+		 * index_record_size normaly equals 4096 bytes, which is
+		 * encoded as 0xF4 (-12 in decimal).
+		 */
+		vol->index_record_size = 1 << -clusters_per_index_record;
+	vol->index_record_size_mask = vol->index_record_size - 1;
+	vol->index_record_size_bits = ffs(vol->index_record_size) - 1;
+	ntfs_debug("vol->index_record_size = %i (0x%x)",
+			vol->index_record_size, vol->index_record_size);
+	ntfs_debug("vol->index_record_size_mask = 0x%x",
+			vol->index_record_size_mask);
+	ntfs_debug("vol->index_record_size_bits = %i (0x%x)",
+			vol->index_record_size_bits,
+			vol->index_record_size_bits);
+	/*
+	 * Get the size of the volume in clusters and check for 64-bit-ness.
+	 * Windows currently only uses 32 bits to save the clusters so we do
+	 * the same as it is much faster on 32-bit CPUs.
+	 */
+	ll = sle64_to_cpu(b->number_of_sectors) >> sectors_per_cluster_bits;
+	if ((u64)ll >= 1ULL << 32) {
+		ntfs_error(vol->sb, "Cannot handle 64-bit clusters.  Sorry.");
+		return FALSE;
+	}
+	vol->nr_clusters = ll;
+	ntfs_debug("vol->nr_clusters = 0x%llx", (long long)vol->nr_clusters);
+	/*
+	 * On an architecture where unsigned long is 32-bits, we restrict the
+	 * volume size to 2TiB (2^41). On a 64-bit architecture, the compiler
+	 * will hopefully optimize the whole check away.
+	 */
+	if (sizeof(unsigned long) < 8) {
+		if ((ll << vol->cluster_size_bits) >= (1ULL << 41)) {
+			ntfs_error(vol->sb, "Volume size (%lluTiB) is too "
+					"large for this architecture.  "
+					"Maximum supported is 2TiB.  Sorry.",
+					(unsigned long long)ll >> (40 -
+					vol->cluster_size_bits));
+			return FALSE;
+		}
+	}
+	ll = sle64_to_cpu(b->mft_lcn);
+	if (ll >= vol->nr_clusters) {
+		ntfs_error(vol->sb, "MFT LCN is beyond end of volume.  Weird.");
+		return FALSE;
+	}
+	vol->mft_lcn = ll;
+	ntfs_debug("vol->mft_lcn = 0x%llx", (long long)vol->mft_lcn);
+	ll = sle64_to_cpu(b->mftmirr_lcn);
+	if (ll >= vol->nr_clusters) {
+		ntfs_error(vol->sb, "MFTMirr LCN is beyond end of volume.  "
+				"Weird.");
+		return FALSE;
+	}
+	vol->mftmirr_lcn = ll;
+	ntfs_debug("vol->mftmirr_lcn = 0x%llx", (long long)vol->mftmirr_lcn);
+#ifdef NTFS_RW
+	/*
+	 * Work out the size of the mft mirror in number of mft records. If the
+	 * cluster size is less than or equal to the size taken by four mft
+	 * records, the mft mirror stores the first four mft records. If the
+	 * cluster size is bigger than the size taken by four mft records, the
+	 * mft mirror contains as many mft records as will fit into one
+	 * cluster.
+	 */
+	if (vol->cluster_size <= (4 << vol->mft_record_size_bits))
+		vol->mftmirr_size = 4;
+	else
+		vol->mftmirr_size = vol->cluster_size >>
+				vol->mft_record_size_bits;
+	ntfs_debug("vol->mftmirr_size = %i", vol->mftmirr_size);
+#endif /* NTFS_RW */
+	vol->serial_no = le64_to_cpu(b->volume_serial_number);
+	ntfs_debug("vol->serial_no = 0x%llx",
+			(unsigned long long)vol->serial_no);
+	return TRUE;
+}
+
+/**
+ * ntfs_setup_allocators - initialize the cluster and mft allocators
+ * @vol:	volume structure for which to setup the allocators
+ *
+ * Setup the cluster (lcn) and mft allocators to the starting values.
+ */
+static void ntfs_setup_allocators(ntfs_volume *vol)
+{
+#ifdef NTFS_RW
+	LCN mft_zone_size, mft_lcn;
+#endif /* NTFS_RW */
+
+	ntfs_debug("vol->mft_zone_multiplier = 0x%x",
+			vol->mft_zone_multiplier);
+#ifdef NTFS_RW
+	/* Determine the size of the MFT zone. */
+	mft_zone_size = vol->nr_clusters;
+	switch (vol->mft_zone_multiplier) {  /* % of volume size in clusters */
+	case 4:
+		mft_zone_size >>= 1;			/* 50%   */
+		break;
+	case 3:
+		mft_zone_size = (mft_zone_size +
+				(mft_zone_size >> 1)) >> 2;	/* 37.5% */
+		break;
+	case 2:
+		mft_zone_size >>= 2;			/* 25%   */
+		break;
+	/* case 1: */
+	default:
+		mft_zone_size >>= 3;			/* 12.5% */
+		break;
+	}
+	/* Setup the mft zone. */
+	vol->mft_zone_start = vol->mft_zone_pos = vol->mft_lcn;
+	ntfs_debug("vol->mft_zone_pos = 0x%llx",
+			(unsigned long long)vol->mft_zone_pos);
+	/*
+	 * Calculate the mft_lcn for an unmodified NTFS volume (see mkntfs
+	 * source) and if the actual mft_lcn is in the expected place or even
+	 * further to the front of the volume, extend the mft_zone to cover the
+	 * beginning of the volume as well.  This is in order to protect the
+	 * area reserved for the mft bitmap as well within the mft_zone itself.
+	 * On non-standard volumes we do not protect it as the overhead would
+	 * be higher than the speed increase we would get by doing it.
+	 */
+	mft_lcn = (8192 + 2 * vol->cluster_size - 1) / vol->cluster_size;
+	if (mft_lcn * vol->cluster_size < 16 * 1024)
+		mft_lcn = (16 * 1024 + vol->cluster_size - 1) /
+				vol->cluster_size;
+	if (vol->mft_zone_start <= mft_lcn)
+		vol->mft_zone_start = 0;
+	ntfs_debug("vol->mft_zone_start = 0x%llx",
+			(unsigned long long)vol->mft_zone_start);
+	/*
+	 * Need to cap the mft zone on non-standard volumes so that it does
+	 * not point outside the boundaries of the volume.  We do this by
+	 * halving the zone size until we are inside the volume.
+	 */
+	vol->mft_zone_end = vol->mft_lcn + mft_zone_size;
+	while (vol->mft_zone_end >= vol->nr_clusters) {
+		mft_zone_size >>= 1;
+		vol->mft_zone_end = vol->mft_lcn + mft_zone_size;
+	}
+	ntfs_debug("vol->mft_zone_end = 0x%llx",
+			(unsigned long long)vol->mft_zone_end);
+	/*
+	 * Set the current position within each data zone to the start of the
+	 * respective zone.
+	 */
+	vol->data1_zone_pos = vol->mft_zone_end;
+	ntfs_debug("vol->data1_zone_pos = 0x%llx",
+			(unsigned long long)vol->data1_zone_pos);
+	vol->data2_zone_pos = 0;
+	ntfs_debug("vol->data2_zone_pos = 0x%llx",
+			(unsigned long long)vol->data2_zone_pos);
+
+	/* Set the mft data allocation position to mft record 24. */
+	vol->mft_data_pos = 24;
+	ntfs_debug("vol->mft_data_pos = 0x%llx",
+			(unsigned long long)vol->mft_data_pos);
+#endif /* NTFS_RW */
+}
+
+#ifdef NTFS_RW
+
+/**
+ * load_and_init_mft_mirror - load and setup the mft mirror inode for a volume
+ * @vol:	ntfs super block describing device whose mft mirror to load
+ *
+ * Return TRUE on success or FALSE on error.
+ */
+static BOOL load_and_init_mft_mirror(ntfs_volume *vol)
+{
+	struct inode *tmp_ino;
+	ntfs_inode *tmp_ni;
+
+	ntfs_debug("Entering.");
+	/* Get mft mirror inode. */
+	tmp_ino = ntfs_iget(vol->sb, FILE_MFTMirr);
+	if (IS_ERR(tmp_ino) || is_bad_inode(tmp_ino)) {
+		if (!IS_ERR(tmp_ino))
+			iput(tmp_ino);
+		/* Caller will display error message. */
+		return FALSE;
+	}
+	/*
+	 * Re-initialize some specifics about $MFTMirr's inode as
+	 * ntfs_read_inode() will have set up the default ones.
+	 */
+	/* Set uid and gid to root. */
+	tmp_ino->i_uid = tmp_ino->i_gid = 0;
+	/* Regular file.  No access for anyone. */
+	tmp_ino->i_mode = S_IFREG;
+	/* No VFS initiated operations allowed for $MFTMirr. */
+	tmp_ino->i_op = &ntfs_empty_inode_ops;
+	tmp_ino->i_fop = &ntfs_empty_file_ops;
+	/* Put in our special address space operations. */
+	tmp_ino->i_mapping->a_ops = &ntfs_mst_aops;
+	tmp_ni = NTFS_I(tmp_ino);
+	/* The $MFTMirr, like the $MFT is multi sector transfer protected. */
+	NInoSetMstProtected(tmp_ni);
+	/*
+	 * 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)
+{
+	unsigned long index;
+	struct super_block *sb = vol->sb;
+	ntfs_inode *mirr_ni;
+	struct page *mft_page, *mirr_page;
+	u8 *kmft, *kmirr;
+	runlist_element *rl, rl2[2];
+	int mrecs_per_page, i;
+
+	ntfs_debug("Entering.");
+	/* Compare contents of $MFT and $MFTMirr. */
+	mrecs_per_page = PAGE_CACHE_SIZE / vol->mft_record_size;
+	BUG_ON(!mrecs_per_page);
+	BUG_ON(!vol->mftmirr_size);
+	mft_page = mirr_page = NULL;
+	kmft = kmirr = NULL;
+	index = i = 0;
+	do {
+		u32 bytes;
+
+		/* Switch pages if necessary. */
+		if (!(i % mrecs_per_page)) {
+			if (index) {
+				ntfs_unmap_page(mft_page);
+				ntfs_unmap_page(mirr_page);
+			}
+			/* Get the $MFT page. */
+			mft_page = ntfs_map_page(vol->mft_ino->i_mapping,
+					index);
+			if (IS_ERR(mft_page)) {
+				ntfs_error(sb, "Failed to read $MFT.");
+				return FALSE;
+			}
+			kmft = page_address(mft_page);
+			/* Get the $MFTMirr page. */
+			mirr_page = ntfs_map_page(vol->mftmirr_ino->i_mapping,
+					index);
+			if (IS_ERR(mirr_page)) {
+				ntfs_error(sb, "Failed to read $MFTMirr.");
+				goto mft_unmap_out;
+			}
+			kmirr = page_address(mirr_page);
+			++index;
+		}
+		/* Make sure the record is ok. *