Beispiel #1
0
/**
 * ext4_get_group_desc() -- load group descriptor from disk
 * @sb:			super block
 * @block_group:	given block group
 * @bh:			pointer to the buffer head to store the block
 *			group descriptor
 */
struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb,
					     ext4_group_t block_group,
					     struct buffer_head **bh)
{
	unsigned int group_desc;
	unsigned int offset;
	ext4_group_t ngroups = ext4_get_groups_count(sb);
	struct ext4_group_desc *desc;
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	if (block_group >= ngroups) {
		ext4_error(sb, "block_group >= groups_count - block_group = %u,"
			   " groups_count = %u", block_group, ngroups);

		return NULL;
	}

	group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
	offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
	if (!sbi->s_group_desc[group_desc]) {
		ext4_error(sb, "Group descriptor not loaded - "
			   "block_group = %u, group_desc = %u, desc = %u",
			   block_group, group_desc, offset);
		return NULL;
	}

	desc = (struct ext4_group_desc *)(
		(__u8 *)sbi->s_group_desc[group_desc]->b_data +
		offset * EXT4_DESC_SIZE(sb));
	if (bh)
		*bh = sbi->s_group_desc[group_desc];
	return desc;
}
Beispiel #2
0
static int ext4_valid_block_bitmap(struct super_block *sb,
					struct ext4_group_desc *desc,
					unsigned int block_group,
					struct buffer_head *bh)
{
	ext4_grpblk_t offset;
	ext4_grpblk_t next_zero_bit;
	ext4_fsblk_t bitmap_blk;
	ext4_fsblk_t group_first_block;

	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) {
		/* with FLEX_BG, the inode/block bitmaps and itable
		 * blocks may not be in the group at all
		 * so the bitmap validation will be skipped for those groups
		 * or it has to also read the block group where the bitmaps
		 * are located to verify they are set.
		 */
		return 1;
	}
	group_first_block = ext4_group_first_block_no(sb, block_group);

	/* check whether block bitmap block number is set */
	bitmap_blk = ext4_block_bitmap(sb, desc);
	offset = bitmap_blk - group_first_block;
	if (!ext4_test_bit(offset, bh->b_data))
		/* bad block bitmap */
		goto err_out;

	/* check whether the inode bitmap block number is set */
	bitmap_blk = ext4_inode_bitmap(sb, desc);
	offset = bitmap_blk - group_first_block;
	if (!ext4_test_bit(offset, bh->b_data))
		/* bad block bitmap */
		goto err_out;

	/* check whether the inode table block number is set */
	bitmap_blk = ext4_inode_table(sb, desc);
	offset = bitmap_blk - group_first_block;
	next_zero_bit = ext4_find_next_zero_bit(bh->b_data,
				offset + EXT4_SB(sb)->s_itb_per_group,
				offset);
	if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group)
		/* good bitmap for inode tables */
		return 1;

err_out:
	ext4_error(sb, __func__,
			"Invalid block bitmap - "
			"block_group = %d, block = %llu",
			block_group, bitmap_blk);
	return 0;
}
Beispiel #3
0
/*
 * Read the inode allocation bitmap for a given block_group, reading
 * into the specified slot in the superblock's bitmap cache.
 *
 * Return buffer_head of bitmap on success or NULL.
 */
static struct buffer_head *
read_inode_bitmap(struct super_block * sb, unsigned long block_group)
{
	struct ext4_group_desc *desc;
	struct buffer_head *bh = NULL;

	desc = ext4_get_group_desc(sb, block_group, NULL);
	if (!desc)
		goto error_out;

	bh = sb_bread(sb, ext4_inode_bitmap(sb, desc));
	if (!bh)
		ext4_error(sb, "read_inode_bitmap",
			    "Cannot read inode bitmap - "
			    "block_group = %lu, inode_bitmap = %llu",
			    block_group, ext4_inode_bitmap(sb, desc));
error_out:
	return bh;
}
Beispiel #4
0
/* Initializes an uninitialized block bitmap if given, and returns the
 * number of blocks free in the group. */
unsigned ext4_init_block_bitmap(struct super_block *sb, struct buffer_head *bh,
		 ext4_group_t block_group, struct ext4_group_desc *gdp)
{
	int bit, bit_max;
	ext4_group_t ngroups = ext4_get_groups_count(sb);
	unsigned free_blocks, group_blocks;
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	if (bh) {
		J_ASSERT_BH(bh, buffer_locked(bh));

		/* If checksum is bad mark all blocks used to prevent allocation
		 * essentially implementing a per-group read-only flag. */
		if (!ext4_group_desc_csum_verify(sbi, block_group, gdp)) {
			ext4_error(sb, __func__,
				  "Checksum bad for group %u", block_group);
			ext4_free_blks_set(sb, gdp, 0);
			ext4_free_inodes_set(sb, gdp, 0);
			ext4_itable_unused_set(sb, gdp, 0);
			memset(bh->b_data, 0xff, sb->s_blocksize);
			return 0;
		}
		memset(bh->b_data, 0, sb->s_blocksize);
	}

	/* Check for superblock and gdt backups in this group */
	bit_max = ext4_bg_has_super(sb, block_group);

	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
	    block_group < le32_to_cpu(sbi->s_es->s_first_meta_bg) *
			  sbi->s_desc_per_block) {
		if (bit_max) {
			bit_max += ext4_bg_num_gdb(sb, block_group);
			bit_max +=
				le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
		}
	} else { /* For META_BG_BLOCK_GROUPS */
		bit_max += ext4_bg_num_gdb(sb, block_group);
	}

	if (block_group == ngroups - 1) {
		/*
		 * Even though mke2fs always initialize first and last group
		 * if some other tool enabled the EXT4_BG_BLOCK_UNINIT we need
		 * to make sure we calculate the right free blocks
		 */
		group_blocks = ext4_blocks_count(sbi->s_es) -
			le32_to_cpu(sbi->s_es->s_first_data_block) -
			(EXT4_BLOCKS_PER_GROUP(sb) * (ngroups - 1));
	} else {
		group_blocks = EXT4_BLOCKS_PER_GROUP(sb);
	}

	free_blocks = group_blocks - bit_max;

	if (bh) {
		ext4_fsblk_t start, tmp;
		int flex_bg = 0;

		for (bit = 0; bit < bit_max; bit++)
			ext4_set_bit(bit, bh->b_data);

		start = ext4_group_first_block_no(sb, block_group);

		if (EXT4_HAS_INCOMPAT_FEATURE(sb,
					      EXT4_FEATURE_INCOMPAT_FLEX_BG))
			flex_bg = 1;

		/* Set bits for block and inode bitmaps, and inode table */
		tmp = ext4_block_bitmap(sb, gdp);
		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
			ext4_set_bit(tmp - start, bh->b_data);

		tmp = ext4_inode_bitmap(sb, gdp);
		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
			ext4_set_bit(tmp - start, bh->b_data);

		tmp = ext4_inode_table(sb, gdp);
		for (; tmp < ext4_inode_table(sb, gdp) +
				sbi->s_itb_per_group; tmp++) {
			if (!flex_bg ||
				ext4_block_in_group(sb, tmp, block_group))
				ext4_set_bit(tmp - start, bh->b_data);
		}
		/*
		 * Also if the number of blocks within the group is
		 * less than the blocksize * 8 ( which is the size
		 * of bitmap ), set rest of the block bitmap to 1
		 */
		mark_bitmap_end(group_blocks, sb->s_blocksize * 8, bh->b_data);
	}
	return free_blocks - ext4_group_used_meta_blocks(sb, block_group, gdp);
}
Beispiel #5
0
/**
 * ext4_add_groupblocks() -- Add given blocks to an existing group
 * @handle:			handle to this transaction
 * @sb:				super block
 * @block:			start physcial block to add to the block group
 * @count:			number of blocks to free
 *
 * This marks the blocks as free in the bitmap. We ask the
 * mballoc to reload the buddy after this by setting group
 * EXT4_GROUP_INFO_NEED_INIT_BIT flag
 */
void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
			 ext4_fsblk_t block, unsigned long count)
{
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *gd_bh;
	ext4_group_t block_group;
	ext4_grpblk_t bit;
	unsigned int i;
	struct ext4_group_desc *desc;
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	int err = 0, ret, blk_free_count;
	ext4_grpblk_t blocks_freed;
	struct ext4_group_info *grp;

	ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);

	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
	grp = ext4_get_group_info(sb, block_group);
	/*
	 * Check to see if we are freeing blocks across a group
	 * boundary.
	 */
	if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
		goto error_return;
	}
	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
	if (!bitmap_bh)
		goto error_return;
	desc = ext4_get_group_desc(sb, block_group, &gd_bh);
	if (!desc)
		goto error_return;

	if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
	    in_range(ext4_inode_bitmap(sb, desc), block, count) ||
	    in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
	    in_range(block + count - 1, ext4_inode_table(sb, desc),
		     sbi->s_itb_per_group)) {
		ext4_error(sb, __func__,
			   "Adding blocks in system zones - "
			   "Block = %llu, count = %lu",
			   block, count);
		goto error_return;
	}

	/*
	 * We are about to add blocks to the bitmap,
	 * so we need undo access.
	 */
	BUFFER_TRACE(bitmap_bh, "getting undo access");
	err = ext4_journal_get_undo_access(handle, bitmap_bh);
	if (err)
		goto error_return;

	/*
	 * We are about to modify some metadata.  Call the journal APIs
	 * to unshare ->b_data if a currently-committing transaction is
	 * using it
	 */
	BUFFER_TRACE(gd_bh, "get_write_access");
	err = ext4_journal_get_write_access(handle, gd_bh);
	if (err)
		goto error_return;
	/*
	 * make sure we don't allow a parallel init on other groups in the
	 * same buddy cache
	 */
	down_write(&grp->alloc_sem);
	for (i = 0, blocks_freed = 0; i < count; i++) {
		BUFFER_TRACE(bitmap_bh, "clear bit");
		if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
						bit + i, bitmap_bh->b_data)) {
			ext4_error(sb, __func__,
				   "bit already cleared for block %llu",
				   (ext4_fsblk_t)(block + i));
			BUFFER_TRACE(bitmap_bh, "bit already cleared");
		} else {
			blocks_freed++;
		}
	}
	ext4_lock_group(sb, block_group);
	blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
	ext4_free_blks_set(sb, desc, blk_free_count);
	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
	ext4_unlock_group(sb, block_group);
	percpu_counter_mod(&sbi->s_freeblocks_counter, blocks_freed);

	if (sbi->s_log_groups_per_flex) {
		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
		atomic_add(blocks_freed,
			   &sbi->s_flex_groups[flex_group].free_blocks);
	}
	/*
	 * request to reload the buddy with the
	 * new bitmap information
	 */
	set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
	grp->bb_free += blocks_freed;
	up_write(&grp->alloc_sem);

	/* We dirtied the bitmap block */
	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);

	/* And the group descriptor block */
	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
	ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
	if (!err)
		err = ret;

error_return:
	brelse(bitmap_bh);
	ext4_std_error(sb, err);
	return;
}
Beispiel #6
0
/**
 * ext4_read_block_bitmap()
 * @sb:			super block
 * @block_group:	given block group
 *
 * Read the bitmap for a given block_group,and validate the
 * bits for block/inode/inode tables are set in the bitmaps
 *
 * Return buffer_head on success or NULL in case of failure.
 */
struct buffer_head *
ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
{
	struct ext4_group_desc *desc;
	struct buffer_head *bh = NULL;
	ext4_fsblk_t bitmap_blk;

	desc = ext4_get_group_desc(sb, block_group, NULL);
	if (!desc)
		return NULL;
	bitmap_blk = ext4_block_bitmap(sb, desc);
	bh = sb_getblk(sb, bitmap_blk);
	if (unlikely(!bh)) {
		ext4_error(sb, __func__,
			    "Cannot read block bitmap - "
			    "block_group = %u, block_bitmap = %llu",
			    block_group, bitmap_blk);
		return NULL;
	}

	if (bitmap_uptodate(bh))
		return bh;

	lock_buffer(bh);
	if (bitmap_uptodate(bh)) {
		unlock_buffer(bh);
		return bh;
	}
	ext4_lock_group(sb, block_group);
	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
		ext4_init_block_bitmap(sb, bh, block_group, desc);
		set_bitmap_uptodate(bh);
		set_buffer_uptodate(bh);
		ext4_unlock_group(sb, block_group);
		unlock_buffer(bh);
		return bh;
	}
	ext4_unlock_group(sb, block_group);
	if (buffer_uptodate(bh)) {
		/*
		 * if not uninit if bh is uptodate,
		 * bitmap is also uptodate
		 */
		set_bitmap_uptodate(bh);
		unlock_buffer(bh);
		return bh;
	}
	/*
	 * submit the buffer_head for read. We can
	 * safely mark the bitmap as uptodate now.
	 * We do it here so the bitmap uptodate bit
	 * get set with buffer lock held.
	 */
	set_bitmap_uptodate(bh);
	if (bh_submit_read(bh) < 0) {
		put_bh(bh);
		ext4_error(sb, __func__,
			    "Cannot read block bitmap - "
			    "block_group = %u, block_bitmap = %llu",
			    block_group, bitmap_blk);
		return NULL;
	}
	ext4_valid_block_bitmap(sb, desc, block_group, bh);
	/*
	 * file system mounted not to panic on error,
	 * continue with corrupt bitmap
	 */
	return bh;
}
Beispiel #7
0
/*
 * kmmpd will update the MMP sequence every s_mmp_update_interval seconds
 */
static int kmmpd(void *data)
{
	struct super_block *sb = ((struct mmpd_data *) data)->sb;
	struct buffer_head *bh = ((struct mmpd_data *) data)->bh;
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
	struct mmp_struct *mmp;
	ext4_fsblk_t mmp_block;
	u32 seq = 0;
	unsigned long failed_writes = 0;
	int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval);
	unsigned mmp_check_interval;
	unsigned long last_update_time;
	unsigned long diff;
	int retval;

	mmp_block = le64_to_cpu(es->s_mmp_block);
	mmp = (struct mmp_struct *)(bh->b_data);
	mmp->mmp_time = cpu_to_le64(get_seconds());
	/*
	 * Start with the higher mmp_check_interval and reduce it if
	 * the MMP block is being updated on time.
	 */
	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
				 EXT4_MMP_MIN_CHECK_INTERVAL);
	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
	bdevname(bh->b_bdev, mmp->mmp_bdevname);

	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
	       sizeof(mmp->mmp_nodename));

	while (!kthread_should_stop()) {
		if (++seq > EXT4_MMP_SEQ_MAX)
			seq = 1;

		mmp->mmp_seq = cpu_to_le32(seq);
		mmp->mmp_time = cpu_to_le64(get_seconds());
		last_update_time = jiffies;

		retval = write_mmp_block(sb, bh);
		/*
		 * Don't spew too many error messages. Print one every
		 * (s_mmp_update_interval * 60) seconds.
		 */
		if (retval) {
			if ((failed_writes % 60) == 0)
				ext4_error(sb, "Error writing to MMP block");
			failed_writes++;
		}

		if (!(le32_to_cpu(es->s_feature_incompat) &
		    EXT4_FEATURE_INCOMPAT_MMP)) {
			ext4_warning(sb, "kmmpd being stopped since MMP feature"
				     " has been disabled.");
			EXT4_SB(sb)->s_mmp_tsk = NULL;
			goto failed;
		}

		if (sb->s_flags & MS_RDONLY) {
			ext4_warning(sb, "kmmpd being stopped since filesystem "
				     "has been remounted as readonly.");
			EXT4_SB(sb)->s_mmp_tsk = NULL;
			goto failed;
		}

		diff = jiffies - last_update_time;
		if (diff < mmp_update_interval * HZ)
			schedule_timeout_interruptible(mmp_update_interval *
						       HZ - diff);

		/*
		 * We need to make sure that more than mmp_check_interval
		 * seconds have not passed since writing. If that has happened
		 * we need to check if the MMP block is as we left it.
		 */
		diff = jiffies - last_update_time;
		if (diff > mmp_check_interval * HZ) {
			struct buffer_head *bh_check = NULL;
			struct mmp_struct *mmp_check;

			retval = read_mmp_block(sb, &bh_check, mmp_block);
			if (retval) {
				ext4_error(sb, "error reading MMP data: %d",
					   retval);

				EXT4_SB(sb)->s_mmp_tsk = NULL;
				goto failed;
			}

			mmp_check = (struct mmp_struct *)(bh_check->b_data);
			if (mmp->mmp_seq != mmp_check->mmp_seq ||
			    memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename,
				   sizeof(mmp->mmp_nodename))) {
				dump_mmp_msg(sb, mmp_check,
					     "Error while updating MMP info. "
					     "The filesystem seems to have been"
					     " multiply mounted.");
				ext4_error(sb, "abort");
				goto failed;
			}
			put_bh(bh_check);
		}

		 /*
		 * Adjust the mmp_check_interval depending on how much time
		 * it took for the MMP block to be written.
		 */
		mmp_check_interval = max(min(EXT4_MMP_CHECK_MULT * diff / HZ,
					     EXT4_MMP_MAX_CHECK_INTERVAL),
					 EXT4_MMP_MIN_CHECK_INTERVAL);
		mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
	}

	/*
	 * Unmount seems to be clean.
	 */
	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
	mmp->mmp_time = cpu_to_le64(get_seconds());

	retval = write_mmp_block(sb, bh);

failed:
	kfree(data);
	brelse(bh);
	return retval;
}
Beispiel #8
0
/*
 * NOTE! When we get the inode, we're the only people
 * that have access to it, and as such there are no
 * race conditions we have to worry about. The inode
 * is not on the hash-lists, and it cannot be reached
 * through the filesystem because the directory entry
 * has been deleted earlier.
 *
 * HOWEVER: we must make sure that we get no aliases,
 * which means that we have to call "clear_inode()"
 * _before_ we mark the inode not in use in the inode
 * bitmaps. Otherwise a newly created file might use
 * the same inode number (not actually the same pointer
 * though), and then we'd have two inodes sharing the
 * same inode number and space on the harddisk.
 */
void ext4_free_inode (handle_t *handle, struct inode * inode)
{
	struct super_block * sb = inode->i_sb;
	int is_directory;
	unsigned long ino;
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *bh2;
	unsigned long block_group;
	unsigned long bit;
	struct ext4_group_desc * gdp;
	struct ext4_super_block * es;
	struct ext4_sb_info *sbi;
	int fatal = 0, err;

	if (atomic_read(&inode->i_count) > 1) {
		printk ("ext4_free_inode: inode has count=%d\n",
					atomic_read(&inode->i_count));
		return;
	}
	if (inode->i_nlink) {
		printk ("ext4_free_inode: inode has nlink=%d\n",
			inode->i_nlink);
		return;
	}
	if (!sb) {
		printk("ext4_free_inode: inode on nonexistent device\n");
		return;
	}
	sbi = EXT4_SB(sb);

	ino = inode->i_ino;
	ext4_debug ("freeing inode %lu\n", ino);

	/*
	 * Note: we must free any quota before locking the superblock,
	 * as writing the quota to disk may need the lock as well.
	 */
	DQUOT_INIT(inode);
	ext4_xattr_delete_inode(handle, inode);
	DQUOT_FREE_INODE(inode);
	DQUOT_DROP(inode);

	is_directory = S_ISDIR(inode->i_mode);

	/* Do this BEFORE marking the inode not in use or returning an error */
	clear_inode (inode);

	es = EXT4_SB(sb)->s_es;
	if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
		ext4_error (sb, "ext4_free_inode",
			    "reserved or nonexistent inode %lu", ino);
		goto error_return;
	}
	block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
	bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
	bitmap_bh = read_inode_bitmap(sb, block_group);
	if (!bitmap_bh)
		goto error_return;

	BUFFER_TRACE(bitmap_bh, "get_write_access");
	fatal = ext4_journal_get_write_access(handle, bitmap_bh);
	if (fatal)
		goto error_return;

	/* Ok, now we can actually update the inode bitmaps.. */
	if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
					bit, bitmap_bh->b_data))
		ext4_error (sb, "ext4_free_inode",
			      "bit already cleared for inode %lu", ino);
	else {
		gdp = ext4_get_group_desc (sb, block_group, &bh2);

		BUFFER_TRACE(bh2, "get_write_access");
		fatal = ext4_journal_get_write_access(handle, bh2);
		if (fatal) goto error_return;

		if (gdp) {
			spin_lock(sb_bgl_lock(sbi, block_group));
			gdp->bg_free_inodes_count = cpu_to_le16(
				le16_to_cpu(gdp->bg_free_inodes_count) + 1);
			if (is_directory)
				gdp->bg_used_dirs_count = cpu_to_le16(
				  le16_to_cpu(gdp->bg_used_dirs_count) - 1);
			spin_unlock(sb_bgl_lock(sbi, block_group));
			percpu_counter_inc(&sbi->s_freeinodes_counter);
			if (is_directory)
				percpu_counter_dec(&sbi->s_dirs_counter);

		}
		BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
		err = ext4_journal_dirty_metadata(handle, bh2);
		if (!fatal) fatal = err;
	}
	BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata");
	err = ext4_journal_dirty_metadata(handle, bitmap_bh);
	if (!fatal)
		fatal = err;
	sb->s_dirt = 1;
error_return:
	brelse(bitmap_bh);
	ext4_std_error(sb, fatal);
}
Beispiel #9
0
/*
 * There are two policies for allocating an inode.  If the new inode is
 * a directory, then a forward search is made for a block group with both
 * free space and a low directory-to-inode ratio; if that fails, then of
 * the groups with above-average free space, that group with the fewest
 * directories already is chosen.
 *
 * For other inodes, search forward from the parent directory's block
 * group to find a free inode.
 */
struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
{
	struct super_block *sb;
	struct buffer_head *bitmap_bh = NULL;
	struct buffer_head *bh2;
	int group;
	unsigned long ino = 0;
	struct inode * inode;
	struct ext4_group_desc * gdp = NULL;
	struct ext4_super_block * es;
	struct ext4_inode_info *ei;
	struct ext4_sb_info *sbi;
	int err = 0;
	struct inode *ret;
	int i;

	/* Cannot create files in a deleted directory */
	if (!dir || !dir->i_nlink)
		return ERR_PTR(-EPERM);

	sb = dir->i_sb;
	inode = new_inode(sb);
	if (!inode)
		return ERR_PTR(-ENOMEM);
	ei = EXT4_I(inode);

	sbi = EXT4_SB(sb);
	es = sbi->s_es;
	if (S_ISDIR(mode)) {
		if (test_opt (sb, OLDALLOC))
			group = find_group_dir(sb, dir);
		else
			group = find_group_orlov(sb, dir);
	} else
		group = find_group_other(sb, dir);

	err = -ENOSPC;
	if (group == -1)
		goto out;

	for (i = 0; i < sbi->s_groups_count; i++) {
		err = -EIO;

		gdp = ext4_get_group_desc(sb, group, &bh2);
		if (!gdp)
			goto fail;

		brelse(bitmap_bh);
		bitmap_bh = read_inode_bitmap(sb, group);
		if (!bitmap_bh)
			goto fail;

		ino = 0;

repeat_in_this_group:
		ino = ext4_find_next_zero_bit((unsigned long *)
				bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino);
		if (ino < EXT4_INODES_PER_GROUP(sb)) {

			BUFFER_TRACE(bitmap_bh, "get_write_access");
			err = ext4_journal_get_write_access(handle, bitmap_bh);
			if (err)
				goto fail;

			if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group),
						ino, bitmap_bh->b_data)) {
				/* we won it */
				BUFFER_TRACE(bitmap_bh,
					"call ext4_journal_dirty_metadata");
				err = ext4_journal_dirty_metadata(handle,
								bitmap_bh);
				if (err)
					goto fail;
				goto got;
			}
			/* we lost it */
			jbd2_journal_release_buffer(handle, bitmap_bh);

			if (++ino < EXT4_INODES_PER_GROUP(sb))
				goto repeat_in_this_group;
		}

		/*
		 * This case is possible in concurrent environment.  It is very
		 * rare.  We cannot repeat the find_group_xxx() call because
		 * that will simply return the same blockgroup, because the
		 * group descriptor metadata has not yet been updated.
		 * So we just go onto the next blockgroup.
		 */
		if (++group == sbi->s_groups_count)
			group = 0;
	}
	err = -ENOSPC;
	goto out;

got:
	ino += group * EXT4_INODES_PER_GROUP(sb) + 1;
	if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
		ext4_error (sb, "ext4_new_inode",
			    "reserved inode or inode > inodes count - "
			    "block_group = %d, inode=%lu", group, ino);
		err = -EIO;
		goto fail;
	}

	BUFFER_TRACE(bh2, "get_write_access");
	err = ext4_journal_get_write_access(handle, bh2);
	if (err) goto fail;
	spin_lock(sb_bgl_lock(sbi, group));
	gdp->bg_free_inodes_count =
		cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
	if (S_ISDIR(mode)) {
		gdp->bg_used_dirs_count =
			cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
	}
	spin_unlock(sb_bgl_lock(sbi, group));
	BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
	err = ext4_journal_dirty_metadata(handle, bh2);
	if (err) goto fail;

	percpu_counter_dec(&sbi->s_freeinodes_counter);
	if (S_ISDIR(mode))
		percpu_counter_inc(&sbi->s_dirs_counter);
	sb->s_dirt = 1;

	inode->i_uid = current->fsuid;
	if (test_opt (sb, GRPID))
		inode->i_gid = dir->i_gid;
	else if (dir->i_mode & S_ISGID) {
		inode->i_gid = dir->i_gid;
		if (S_ISDIR(mode))
			mode |= S_ISGID;
	} else
		inode->i_gid = current->fsgid;
	inode->i_mode = mode;

	inode->i_ino = ino;
	/* This is the optimal IO size (for stat), not the fs block size */
	inode->i_blocks = 0;
	inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
						       ext4_current_time(inode);

	memset(ei->i_data, 0, sizeof(ei->i_data));
	ei->i_dir_start_lookup = 0;
	ei->i_disksize = 0;

	ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL;
	if (S_ISLNK(mode))
		ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL);
	/* dirsync only applies to directories */
	if (!S_ISDIR(mode))
		ei->i_flags &= ~EXT4_DIRSYNC_FL;
#ifdef EXT4_FRAGMENTS
	ei->i_faddr = 0;
	ei->i_frag_no = 0;
	ei->i_frag_size = 0;
#endif
	ei->i_file_acl = 0;
	ei->i_dir_acl = 0;
	ei->i_dtime = 0;
	ei->i_block_alloc_info = NULL;
	ei->i_block_group = group;

	ext4_set_inode_flags(inode);
	if (IS_DIRSYNC(inode))
		handle->h_sync = 1;
	insert_inode_hash(inode);
	spin_lock(&sbi->s_next_gen_lock);
	inode->i_generation = sbi->s_next_generation++;
	spin_unlock(&sbi->s_next_gen_lock);

	ei->i_state = EXT4_STATE_NEW;

	ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;

	ret = inode;
	if(DQUOT_ALLOC_INODE(inode)) {
		err = -EDQUOT;
		goto fail_drop;
	}

	err = ext4_init_acl(handle, inode, dir);
	if (err)
		goto fail_free_drop;

	err = ext4_init_security(handle,inode, dir);
	if (err)
		goto fail_free_drop;

	err = ext4_mark_inode_dirty(handle, inode);
	if (err) {
		ext4_std_error(sb, err);
		goto fail_free_drop;
	}
	if (test_opt(sb, EXTENTS)) {
		EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
		ext4_ext_tree_init(handle, inode);
		if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
			err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
			if (err) goto fail;
			EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS);
			BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata");
			err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
		}
	}

	ext4_debug("allocating inode %lu\n", inode->i_ino);
	goto really_out;
fail:
	ext4_std_error(sb, err);
out:
	iput(inode);
	ret = ERR_PTR(err);
really_out:
	brelse(bitmap_bh);
	return ret;

fail_free_drop:
	DQUOT_FREE_INODE(inode);

fail_drop:
	DQUOT_DROP(inode);
	inode->i_flags |= S_NOQUOTA;
	inode->i_nlink = 0;
	iput(inode);
	brelse(bitmap_bh);
	return ERR_PTR(err);
}
Beispiel #10
0
static int kmmpd(void *data)
{
	struct super_block *sb = ((struct mmpd_data *) data)->sb;
	struct buffer_head *bh = ((struct mmpd_data *) data)->bh;
	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
	struct mmp_struct *mmp;
	ext4_fsblk_t mmp_block;
	u32 seq = 0;
	unsigned long failed_writes = 0;
	int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval);
	unsigned mmp_check_interval;
	unsigned long last_update_time;
	unsigned long diff;
	int retval;

	mmp_block = le64_to_cpu(es->s_mmp_block);
	mmp = (struct mmp_struct *)(bh->b_data);
	mmp->mmp_time = cpu_to_le64(get_seconds());
	mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
				 EXT4_MMP_MIN_CHECK_INTERVAL);
	mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
	bdevname(bh->b_bdev, mmp->mmp_bdevname);

	memcpy(mmp->mmp_nodename, init_utsname()->nodename,
	       sizeof(mmp->mmp_nodename));

	while (!kthread_should_stop()) {
		if (++seq > EXT4_MMP_SEQ_MAX)
			seq = 1;

		mmp->mmp_seq = cpu_to_le32(seq);
		mmp->mmp_time = cpu_to_le64(get_seconds());
		last_update_time = jiffies;

		retval = write_mmp_block(bh);
		if (retval) {
			if ((failed_writes % 60) == 0)
				ext4_error(sb, "Error writing to MMP block");
			failed_writes++;
		}

		if (!(le32_to_cpu(es->s_feature_incompat) &
		    EXT4_FEATURE_INCOMPAT_MMP)) {
			ext4_warning(sb, "kmmpd being stopped since MMP feature"
				     " has been disabled.");
			EXT4_SB(sb)->s_mmp_tsk = NULL;
			goto failed;
		}

		if (sb->s_flags & MS_RDONLY) {
			ext4_warning(sb, "kmmpd being stopped since filesystem "
				     "has been remounted as readonly.");
			EXT4_SB(sb)->s_mmp_tsk = NULL;
			goto failed;
		}

		diff = jiffies - last_update_time;
		if (diff < mmp_update_interval * HZ)
			schedule_timeout_interruptible(mmp_update_interval *
						       HZ - diff);

		diff = jiffies - last_update_time;
		if (diff > mmp_check_interval * HZ) {
			struct buffer_head *bh_check = NULL;
			struct mmp_struct *mmp_check;

			retval = read_mmp_block(sb, &bh_check, mmp_block);
			if (retval) {
				ext4_error(sb, "error reading MMP data: %d",
					   retval);

				EXT4_SB(sb)->s_mmp_tsk = NULL;
				goto failed;
			}

			mmp_check = (struct mmp_struct *)(bh_check->b_data);
			if (mmp->mmp_seq != mmp_check->mmp_seq ||
			    memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename,
				   sizeof(mmp->mmp_nodename))) {
				dump_mmp_msg(sb, mmp_check,
					     "Error while updating MMP info. "
					     "The filesystem seems to have been"
					     " multiply mounted.");
				ext4_error(sb, "abort");
				goto failed;
			}
			put_bh(bh_check);
		}

		mmp_check_interval = max(min(EXT4_MMP_CHECK_MULT * diff / HZ,
					     EXT4_MMP_MAX_CHECK_INTERVAL),
					 EXT4_MMP_MIN_CHECK_INTERVAL);
		mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
	}

	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
	mmp->mmp_time = cpu_to_le64(get_seconds());

	retval = write_mmp_block(bh);

failed:
	kfree(data);
	brelse(bh);
	return retval;
}