mft.c

LINUX下读写NTFS分区的工具。 已经集成了通过LIBCONV库支持中文的代码。

	/* Sync MFT to minimize data loss if there won't be clean unmount. */
	if (ntfs_inode_sync(mft_na->ni))
		goto undo_data_init;
	
	ret = 0;
out:	
	ntfs_log_leave("\n");
	return ret;
	
undo_data_init:
	mft_na->initialized_size = old_data_initialized;
	mft_na->data_size = old_data_size;
	goto out;
}

/**
 * ntfs_mft_record_alloc - allocate an mft record on an ntfs volume
 * @vol:	volume on which to allocate the mft record
 * @base_ni:	open base inode if allocating an extent mft record or NULL
 *
 * Allocate an mft record in $MFT/$DATA of an open ntfs volume @vol.
 *
 * If @base_ni is NULL make the mft record a base mft record and allocate it at
 * the default allocator position.
 *
 * If @base_ni is not NULL make the allocated mft record an extent record,
 * allocate it starting at the mft record after the base mft record and attach
 * the allocated and opened ntfs inode to the base inode @base_ni.
 *
 * On success return the now opened ntfs (extent) inode of the mft record.
 *
 * On error return NULL with errno set to the error code.
 *
 * To find a free mft record, we scan the mft bitmap for a zero bit.  To
 * optimize this we start scanning at the place specified by @base_ni or if
 * @base_ni is NULL we start where we last stopped and we perform wrap around
 * when we reach the end.  Note, we do not try to allocate mft records below
 * number 24 because numbers 0 to 15 are the defined system files anyway and 16
 * to 24 are special in that they are used for storing extension mft records
 * for the $DATA attribute of $MFT.  This is required to avoid the possibility
 * of creating a run list with a circular dependence which once written to disk
 * can never be read in again.  Windows will only use records 16 to 24 for
 * normal files if the volume is completely out of space.  We never use them
 * which means that when the volume is really out of space we cannot create any
 * more files while Windows can still create up to 8 small files.  We can start
 * doing this at some later time, it does not matter much for now.
 *
 * When scanning the mft bitmap, we only search up to the last allocated mft
 * record.  If there are no free records left in the range 24 to number of
 * allocated mft records, then we extend the $MFT/$DATA attribute in order to
 * create free mft records.  We extend the allocated size of $MFT/$DATA by 16
 * records at a time or one cluster, if cluster size is above 16kiB.  If there
 * is not sufficient space to do this, we try to extend by a single mft record
 * or one cluster, if cluster size is above the mft record size, but we only do
 * this if there is enough free space, which we know from the values returned
 * by the failed cluster allocation function when we tried to do the first
 * allocation.
 *
 * No matter how many mft records we allocate, we initialize only the first
 * allocated mft record, incrementing mft data size and initialized size
 * accordingly, open an ntfs_inode for it and return it to the caller, unless
 * there are less than 24 mft records, in which case we allocate and initialize
 * mft records until we reach record 24 which we consider as the first free mft
 * record for use by normal files.
 *
 * If during any stage we overflow the initialized data in the mft bitmap, we
 * extend the initialized size (and data size) by 8 bytes, allocating another
 * cluster if required.  The bitmap data size has to be at least equal to the
 * number of mft records in the mft, but it can be bigger, in which case the
 * superfluous bits are padded with zeroes.
 *
 * Thus, when we return successfully (return value non-zero), we will have:
 *	- initialized / extended the mft bitmap if necessary,
 *	- initialized / extended the mft data if necessary,
 *	- set the bit corresponding to the mft record being allocated in the
 *	  mft bitmap,
 *	- open an ntfs_inode for the allocated mft record, and we will
 *	- return the ntfs_inode.
 *
 * On error (return value zero), nothing will have changed.  If we had changed
 * anything before the error occurred, we will have reverted back to the
 * starting state before returning to the caller.  Thus, except for bugs, we
 * should always leave the volume in a consistent state when returning from
 * this function.
 *
 * Note, this function cannot make use of most of the normal functions, like
 * for example for attribute resizing, etc, because when the run list overflows
 * the base mft record and an attribute list is used, it is very important that
 * the extension mft records used to store the $DATA attribute of $MFT can be
 * reached without having to read the information contained inside them, as
 * this would make it impossible to find them in the first place after the
 * volume is dismounted.  $MFT/$BITMAP probably does not need to follow this
 * rule because the bitmap is not essential for finding the mft records, but on
 * the other hand, handling the bitmap in this special way would make life
 * easier because otherwise there might be circular invocations of functions
 * when reading the bitmap but if we are careful, we should be able to avoid
 * all problems.
 */
ntfs_inode *ntfs_mft_record_alloc(ntfs_volume *vol, ntfs_inode *base_ni)
{
	s64 ll, bit;
	ntfs_attr *mft_na, *mftbmp_na;
	MFT_RECORD *m;
	ntfs_inode *ni = NULL;
	int err;
	u16 seq_no, usn;

	if (base_ni)
		ntfs_log_enter("Entering (allocating an extent mft record for "
			       "base mft record %lld).\n", 
			       (long long)base_ni->mft_no);
	else
		ntfs_log_enter("Entering (allocating a base mft record)\n");
	if (!vol || !vol->mft_na || !vol->mftbmp_na) {
		errno = EINVAL;
		goto out;
	}
	
	mft_na = vol->mft_na;
	mftbmp_na = vol->mftbmp_na;
retry:	
	bit = ntfs_mft_bitmap_find_free_rec(vol, base_ni);
	if (bit >= 0) {
		ntfs_log_debug("found free record (#1) at %lld\n",
				(long long)bit);
		goto found_free_rec;
	}
	if (errno != ENOSPC)
		goto out;
	/*
	 * No free mft records left.  If the mft bitmap already covers more
	 * than the currently used mft records, the next records are all free,
	 * so we can simply allocate the first unused mft record.
	 * Note: We also have to make sure that the mft bitmap at least covers
	 * the first 24 mft records as they are special and whilst they may not
	 * be in use, we do not allocate from them.
	 */
	ll = mft_na->initialized_size >> vol->mft_record_size_bits;
	if (mftbmp_na->initialized_size << 3 > ll &&
			mftbmp_na->initialized_size > 3) {
		bit = ll;
		if (bit < 24)
			bit = 24;
		ntfs_log_debug("found free record (#2) at %lld\n",
				(long long)bit);
		goto found_free_rec;
	}
	/*
	 * The mft bitmap needs to be expanded until it covers the first unused
	 * mft record that we can allocate.
	 * Note: The smallest mft record we allocate is mft record 24.
	 */
	ntfs_log_debug("Status of mftbmp before extension: allocated_size 0x%llx, "
			"data_size 0x%llx, initialized_size 0x%llx.\n",
			(long long)mftbmp_na->allocated_size,
			(long long)mftbmp_na->data_size,
			(long long)mftbmp_na->initialized_size);
	if (mftbmp_na->initialized_size + 8 > mftbmp_na->allocated_size) {
		/* Need to extend bitmap by one more cluster. */
		ntfs_log_debug("mftbmp: initialized_size + 8 > allocated_size.\n");
		if (ntfs_mft_bitmap_extend_allocation(vol))
			goto err_out;
		ntfs_log_debug("Status of mftbmp after allocation extension: "
				"allocated_size 0x%llx, data_size 0x%llx, "
				"initialized_size 0x%llx.\n",
				(long long)mftbmp_na->allocated_size,
				(long long)mftbmp_na->data_size,
				(long long)mftbmp_na->initialized_size);
	}
	/*
	 * We now have sufficient allocated space, extend the initialized_size
	 * as well as the data_size if necessary and fill the new space with
	 * zeroes.
	 */
	bit = mftbmp_na->initialized_size << 3;
	if (ntfs_mft_bitmap_extend_initialized(vol))
		goto err_out;
	ntfs_log_debug("Status of mftbmp after initialized extension: "
			"allocated_size 0x%llx, data_size 0x%llx, "
			"initialized_size 0x%llx.\n",
			(long long)mftbmp_na->allocated_size,
			(long long)mftbmp_na->data_size,
			(long long)mftbmp_na->initialized_size);
	ntfs_log_debug("found free record (#3) at %lld\n", (long long)bit);
found_free_rec:
	/* @bit is the found free mft record, allocate it in the mft bitmap. */
	if (ntfs_bitmap_set_bit(mftbmp_na, bit)) {
		ntfs_log_error("Failed to allocate bit in mft bitmap.\n");
		goto err_out;
	}
	
	/* The mft bitmap is now uptodate.  Deal with mft data attribute now. */
	ll = (bit + 1) << vol->mft_record_size_bits;
	if (ll > mft_na->initialized_size)
		if (ntfs_mft_record_init(vol, ll) < 0)
			goto undo_mftbmp_alloc;

	/*
	 * We now have allocated and initialized the mft record.  Need to read
	 * it from disk and re-format it, preserving the sequence number if it
	 * is not zero as well as the update sequence number if it is not zero
	 * or -1 (0xffff).
	 */
	m = ntfs_malloc(vol->mft_record_size);
	if (!m)
		goto undo_mftbmp_alloc;
	
	if (ntfs_mft_record_read(vol, bit, m)) {
		ntfs_log_perror("Error reading mft %lld", (long long)bit);
		free(m);
		goto undo_mftbmp_alloc;
	}
	/* Sanity check that the mft record is really not in use. */
	if (ntfs_is_file_record(m->magic) && (m->flags & MFT_RECORD_IN_USE)) {
		ntfs_log_error("Inode %lld is used but it wasn't marked in "
			       "$MFT bitmap. Fixed.\n", (long long)bit);
		free(m);
		goto retry;
	}
	seq_no = m->sequence_number;
	usn = *(u16*)((u8*)m + le16_to_cpu(m->usa_ofs));
	if (ntfs_mft_record_layout(vol, bit, m)) {
		ntfs_log_error("Failed to re-format mft record.\n");
		free(m);
		goto undo_mftbmp_alloc;
	}
	if (le16_to_cpu(seq_no))
		m->sequence_number = seq_no;
	seq_no = le16_to_cpu(usn);
	if (seq_no && seq_no != 0xffff)
		*(u16*)((u8*)m + le16_to_cpu(m->usa_ofs)) = usn;
	/* Set the mft record itself in use. */
	m->flags |= MFT_RECORD_IN_USE;
	/* Now need to open an ntfs inode for the mft record. */
	ni = ntfs_inode_allocate(vol);
	if (!ni) {
		ntfs_log_error("Failed to allocate buffer for inode.\n");
		free(m);
		goto undo_mftbmp_alloc;
	}
	ni->mft_no = bit;
	ni->mrec = m;
	/*
	 * If we are allocating an extent mft record, make the opened inode an
	 * extent inode and attach it to the base inode.  Also, set the base
	 * mft record reference in the extent inode.
	 */
	if (base_ni) {
		ni->nr_extents = -1;
		ni->base_ni = base_ni;
		m->base_mft_record = MK_LE_MREF(base_ni->mft_no,
				le16_to_cpu(base_ni->mrec->sequence_number));
		/*
		 * Attach the extent inode to the base inode, reallocating
		 * memory if needed.
		 */
		if (!(base_ni->nr_extents & 3)) {
			ntfs_inode **extent_nis;
			int i;

			i = (base_ni->nr_extents + 4) * sizeof(ntfs_inode *);
			extent_nis = ntfs_malloc(i);
			if (!extent_nis) {
				free(m);
				free(ni);
				goto undo_mftbmp_alloc;
			}
			if (base_ni->extent_nis) {
				memcpy(extent_nis, base_ni->extent_nis,
						i - 4 * sizeof(ntfs_inode *));
				free(base_ni->extent_nis);
			}
			base_ni->extent_nis = extent_nis;
		}
		base_ni->extent_nis[base_ni->nr_extents++] = ni;
	}
	/* Make sure the allocated inode is written out to disk later. */
	ntfs_inode_mark_dirty(ni);
	/* Initialize time, allocated and data size in ntfs_inode struct. */
	ni->data_size = ni->allocated_size = 0;
	ni->flags = 0;
	ni->creation_time = ni->last_data_change_time =
			ni->last_mft_change_time =
			ni->last_access_time = time(NULL);
	/* Update the default mft allocation position if it was used. */
	if (!base_ni)
		vol->mft_data_pos = bit + 1;
	/* Return the opened, allocated inode of the allocated mft record. */
	ntfs_log_debug("allocated %sinode 0x%llx.\n",
			base_ni ? "extent " : "", (long long)bit);
	vol->free_mft_records--; 
out:
	ntfs_log_leave("\n");	
	return ni;

undo_mftbmp_alloc:
	err = errno;
	if (ntfs_bitmap_clear_bit(mftbmp_na, bit))
		ntfs_log_error("Failed to clear bit in mft bitmap.%s\n", es);
	errno = err;
err_out:
	if (!errno)
		errno = EIO;
	ni = NULL;
	goto out;	
}

/**
 * ntfs_mft_record_free - free an mft record on an ntfs volume
 * @vol:	volume on which to free the mft record
 * @ni:		open ntfs inode of the mft record to free
 *
 * Free the mft record of the open inode @ni on the mounted ntfs volume @vol.
 * Note that this function calls ntfs_inode_close() internally and hence you
 * cannot use the pointer @ni any more after this function returns success.
 *
 * On success return 0 and on error return -1 with errno set to the error code.
 */
int ntfs_mft_record_free(ntfs_volume *vol, ntfs_inode *ni)
{
	u64 mft_no;
	int err;
	u16 seq_no, old_seq_no;

	ntfs_log_trace("Entering for inode 0x%llx.\n", (long long) ni->mft_no);

	if (!vol || !vol->mftbmp_na || !ni) {
		errno = EINVAL;
		return -1;
	}

	/* Cache the mft reference for later. */
	mft_no = ni->mft_no;

	/* Mark the mft record as not in use. */
	ni->mrec->flags &= ~MFT_RECORD_IN_USE;

	/* Increment the sequence number, skipping zero, if it is not zero. */
	old_seq_no = ni->mrec->sequence_number;
	seq_no = le16_to_cpu(old_seq_no);
	if (seq_no == 0xffff)
		seq_no = 1;
	else if (seq_no)
		seq_no++;
	ni->mrec->sequence_number = cpu_to_le16(seq_no);

	/* Set the inode dirty and write it out. */
	ntfs_inode_mark_dirty(ni);
	if (ntfs_inode_sync(ni)) {
		err = errno;
		goto sync_rollback;
	}

	/* Clear the bit in the $MFT/$BITMAP corresponding to this record. */
	if (ntfs_bitmap_clear_bit(vol->mftbmp_na, mft_no)) {
		err = errno;
		// FIXME: If ntfs_bitmap_clear_run() guarantees rollback on
		//	  error, this could be changed to goto sync_rollback;
		goto bitmap_rollback;
	}

	/* Throw away the now freed inode. */
	if (!ntfs_inode_close(ni)) {
		vol->free_mft_records++; 
		return 0;
	}
	err = errno;

	/* Rollback what we did... */
bitmap_rollback:
	if (ntfs_bitmap_set_bit(vol->mftbmp_na, mft_no))
		ntfs_log_debug("Eeek! Rollback failed in ntfs_mft_record_free().  "
				"Leaving inconsistent metadata!\n");
sync_rollback:
	ni->mrec->flags |= MFT_RECORD_IN_USE;
	ni->mrec->sequence_number = old_seq_no;
	ntfs_inode_mark_dirty(ni);
	errno = err;
	return -1;
}

/**
 * ntfs_mft_usn_dec - Decrement USN by one
 * @mrec:	pointer to an mft record
 *
 * On success return 0 and on error return -1 with errno set.
 */
int ntfs_mft_usn_dec(MFT_RECORD *mrec)
{
	u16 usn, *usnp;

	if (!mrec) {
		errno = EINVAL;
		return -1;
	}
	usnp = (u16 *)((char *)mrec + le16_to_cpu(mrec->usa_ofs));
	usn = le16_to_cpup(usnp);
	if (usn-- <= 1)
		usn = 0xfffe;
	*usnp = cpu_to_le16(usn);

	return 0;
}