super.c

linux 内核源代码

	if (sbi->s_frags_per_group > sb->s_blocksize * 8) {
		printk ("EXT2-fs: #fragments per group too big: %lu\n",
			sbi->s_frags_per_group);
		goto failed_mount;
	}
	if (sbi->s_inodes_per_group > sb->s_blocksize * 8) {
		printk ("EXT2-fs: #inodes per group too big: %lu\n",
			sbi->s_inodes_per_group);
		goto failed_mount;
	}

	if (EXT2_BLOCKS_PER_GROUP(sb) == 0)
		goto cantfind_ext2;
 	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
 				le32_to_cpu(es->s_first_data_block) - 1)
 					/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
	db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
		   EXT2_DESC_PER_BLOCK(sb);
	sbi->s_group_desc = kmalloc (db_count * sizeof (struct buffer_head *), GFP_KERNEL);
	if (sbi->s_group_desc == NULL) {
		printk ("EXT2-fs: not enough memory\n");
		goto failed_mount;
	}
	bgl_lock_init(&sbi->s_blockgroup_lock);
	sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL);
	if (!sbi->s_debts) {
		printk ("EXT2-fs: not enough memory\n");
		goto failed_mount_group_desc;
	}
	for (i = 0; i < db_count; i++) {
		block = descriptor_loc(sb, logic_sb_block, i);
		sbi->s_group_desc[i] = sb_bread(sb, block);
		if (!sbi->s_group_desc[i]) {
			for (j = 0; j < i; j++)
				brelse (sbi->s_group_desc[j]);
			printk ("EXT2-fs: unable to read group descriptors\n");
			goto failed_mount_group_desc;
		}
	}
	if (!ext2_check_descriptors (sb)) {
		printk ("EXT2-fs: group descriptors corrupted!\n");
		goto failed_mount2;
	}
	sbi->s_gdb_count = db_count;
	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
	spin_lock_init(&sbi->s_next_gen_lock);

	/* per fileystem reservation list head & lock */
	spin_lock_init(&sbi->s_rsv_window_lock);
	sbi->s_rsv_window_root = RB_ROOT;
	/*
	 * Add a single, static dummy reservation to the start of the
	 * reservation window list --- it gives us a placeholder for
	 * append-at-start-of-list which makes the allocation logic
	 * _much_ simpler.
	 */
	sbi->s_rsv_window_head.rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_alloc_hit = 0;
	sbi->s_rsv_window_head.rsv_goal_size = 0;
	ext2_rsv_window_add(sb, &sbi->s_rsv_window_head);

	err = percpu_counter_init(&sbi->s_freeblocks_counter,
				ext2_count_free_blocks(sb));
	if (!err) {
		err = percpu_counter_init(&sbi->s_freeinodes_counter,
				ext2_count_free_inodes(sb));
	}
	if (!err) {
		err = percpu_counter_init(&sbi->s_dirs_counter,
				ext2_count_dirs(sb));
	}
	if (err) {
		printk(KERN_ERR "EXT2-fs: insufficient memory\n");
		goto failed_mount3;
	}
	/*
	 * set up enough so that it can read an inode
	 */
	sb->s_op = &ext2_sops;
	sb->s_export_op = &ext2_export_ops;
	sb->s_xattr = ext2_xattr_handlers;
	root = iget(sb, EXT2_ROOT_INO);
	sb->s_root = d_alloc_root(root);
	if (!sb->s_root) {
		iput(root);
		printk(KERN_ERR "EXT2-fs: get root inode failed\n");
		goto failed_mount3;
	}
	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
		dput(sb->s_root);
		sb->s_root = NULL;
		printk(KERN_ERR "EXT2-fs: corrupt root inode, run e2fsck\n");
		goto failed_mount3;
	}
	if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL))
		ext2_warning(sb, __FUNCTION__,
			"mounting ext3 filesystem as ext2");
	ext2_setup_super (sb, es, sb->s_flags & MS_RDONLY);
	return 0;

cantfind_ext2:
	if (!silent)
		printk("VFS: Can't find an ext2 filesystem on dev %s.\n",
		       sb->s_id);
	goto failed_mount;
failed_mount3:
	percpu_counter_destroy(&sbi->s_freeblocks_counter);
	percpu_counter_destroy(&sbi->s_freeinodes_counter);
	percpu_counter_destroy(&sbi->s_dirs_counter);
failed_mount2:
	for (i = 0; i < db_count; i++)
		brelse(sbi->s_group_desc[i]);
failed_mount_group_desc:
	kfree(sbi->s_group_desc);
	kfree(sbi->s_debts);
failed_mount:
	brelse(bh);
failed_sbi:
	sb->s_fs_info = NULL;
	kfree(sbi);
	return -EINVAL;
}

static void ext2_commit_super (struct super_block * sb,
			       struct ext2_super_block * es)
{
	es->s_wtime = cpu_to_le32(get_seconds());
	mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
	sb->s_dirt = 0;
}

static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es)
{
	es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
	es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
	es->s_wtime = cpu_to_le32(get_seconds());
	mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
	sync_dirty_buffer(EXT2_SB(sb)->s_sbh);
	sb->s_dirt = 0;
}

/*
 * In the second extended file system, it is not necessary to
 * write the super block since we use a mapping of the
 * disk super block in a buffer.
 *
 * However, this function is still used to set the fs valid
 * flags to 0.  We need to set this flag to 0 since the fs
 * may have been checked while mounted and e2fsck may have
 * set s_state to EXT2_VALID_FS after some corrections.
 */

void ext2_write_super (struct super_block * sb)
{
	struct ext2_super_block * es;
	lock_kernel();
	if (!(sb->s_flags & MS_RDONLY)) {
		es = EXT2_SB(sb)->s_es;

		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS) {
			ext2_debug ("setting valid to 0\n");
			es->s_state = cpu_to_le16(le16_to_cpu(es->s_state) &
						  ~EXT2_VALID_FS);
			es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
			es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
			es->s_mtime = cpu_to_le32(get_seconds());
			ext2_sync_super(sb, es);
		} else
			ext2_commit_super (sb, es);
	}
	sb->s_dirt = 0;
	unlock_kernel();
}

static int ext2_remount (struct super_block * sb, int * flags, char * data)
{
	struct ext2_sb_info * sbi = EXT2_SB(sb);
	struct ext2_super_block * es;
	unsigned long old_mount_opt = sbi->s_mount_opt;
	struct ext2_mount_options old_opts;
	unsigned long old_sb_flags;
	int err;

	/* Store the old options */
	old_sb_flags = sb->s_flags;
	old_opts.s_mount_opt = sbi->s_mount_opt;
	old_opts.s_resuid = sbi->s_resuid;
	old_opts.s_resgid = sbi->s_resgid;

	/*
	 * Allow the "check" option to be passed as a remount option.
	 */
	if (!parse_options (data, sbi)) {
		err = -EINVAL;
		goto restore_opts;
	}

	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);

	ext2_xip_verify_sb(sb); /* see if bdev supports xip, unset
				    EXT2_MOUNT_XIP if not */

	if ((ext2_use_xip(sb)) && (sb->s_blocksize != PAGE_SIZE)) {
		printk("XIP: Unsupported blocksize\n");
		err = -EINVAL;
		goto restore_opts;
	}

	es = sbi->s_es;
	if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) !=
	    (old_mount_opt & EXT2_MOUNT_XIP)) &&
	    invalidate_inodes(sb))
		ext2_warning(sb, __FUNCTION__, "busy inodes while remounting "\
			     "xip remain in cache (no functional problem)");
	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
		return 0;
	if (*flags & MS_RDONLY) {
		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS ||
		    !(sbi->s_mount_state & EXT2_VALID_FS))
			return 0;
		/*
		 * OK, we are remounting a valid rw partition rdonly, so set
		 * the rdonly flag and then mark the partition as valid again.
		 */
		es->s_state = cpu_to_le16(sbi->s_mount_state);
		es->s_mtime = cpu_to_le32(get_seconds());
	} else {
		__le32 ret = EXT2_HAS_RO_COMPAT_FEATURE(sb,
					       ~EXT2_FEATURE_RO_COMPAT_SUPP);
		if (ret) {
			printk("EXT2-fs: %s: couldn't remount RDWR because of "
			       "unsupported optional features (%x).\n",
			       sb->s_id, le32_to_cpu(ret));
			err = -EROFS;
			goto restore_opts;
		}
		/*
		 * Mounting a RDONLY partition read-write, so reread and
		 * store the current valid flag.  (It may have been changed
		 * by e2fsck since we originally mounted the partition.)
		 */
		sbi->s_mount_state = le16_to_cpu(es->s_state);
		if (!ext2_setup_super (sb, es, 0))
			sb->s_flags &= ~MS_RDONLY;
	}
	ext2_sync_super(sb, es);
	return 0;
restore_opts:
	sbi->s_mount_opt = old_opts.s_mount_opt;
	sbi->s_resuid = old_opts.s_resuid;
	sbi->s_resgid = old_opts.s_resgid;
	sb->s_flags = old_sb_flags;
	return err;
}

static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
{
	struct super_block *sb = dentry->d_sb;
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	struct ext2_super_block *es = sbi->s_es;
	u64 fsid;

	if (test_opt (sb, MINIX_DF))
		sbi->s_overhead_last = 0;
	else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
		unsigned long i, overhead = 0;
		smp_rmb();

		/*
		 * Compute the overhead (FS structures). This is constant
		 * for a given filesystem unless the number of block groups
		 * changes so we cache the previous value until it does.
		 */

		/*
		 * All of the blocks before first_data_block are
		 * overhead
		 */
		overhead = le32_to_cpu(es->s_first_data_block);

		/*
		 * Add the overhead attributed to the superblock and
		 * block group descriptors.  If the sparse superblocks
		 * feature is turned on, then not all groups have this.
		 */
		for (i = 0; i < sbi->s_groups_count; i++)
			overhead += ext2_bg_has_super(sb, i) +
				ext2_bg_num_gdb(sb, i);

		/*
		 * Every block group has an inode bitmap, a block
		 * bitmap, and an inode table.
		 */
		overhead += (sbi->s_groups_count *
			     (2 + sbi->s_itb_per_group));
		sbi->s_overhead_last = overhead;
		smp_wmb();
		sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
	}

	buf->f_type = EXT2_SUPER_MAGIC;
	buf->f_bsize = sb->s_blocksize;
	buf->f_blocks = le32_to_cpu(es->s_blocks_count) - sbi->s_overhead_last;
	buf->f_bfree = ext2_count_free_blocks(sb);
	es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
	buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count);
	if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count))
		buf->f_bavail = 0;
	buf->f_files = le32_to_cpu(es->s_inodes_count);
	buf->f_ffree = ext2_count_free_inodes(sb);
	es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
	buf->f_namelen = EXT2_NAME_LEN;
	fsid = le64_to_cpup((void *)es->s_uuid) ^
	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
	return 0;
}

static int ext2_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
	return get_sb_bdev(fs_type, flags, dev_name, data, ext2_fill_super, mnt);
}

#ifdef CONFIG_QUOTA

/* Read data from quotafile - avoid pagecache and such because we cannot afford
 * acquiring the locks... As quota files are never truncated and quota code
 * itself serializes the operations (and noone else should touch the files)
 * we don't have to be afraid of races */
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data,
			       size_t len, loff_t off)
{
	struct inode *inode = sb_dqopt(sb)->files[type];
	sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb);
	int err = 0;
	int offset = off & (sb->s_blocksize - 1);
	int tocopy;
	size_t toread;
	struct buffer_head tmp_bh;
	struct buffer_head *bh;
	loff_t i_size = i_size_read(inode);

	if (off > i_size)
		return 0;
	if (off+len > i_size)
		len = i_size-off;
	toread = len;
	while (toread > 0) {
		tocopy = sb->s_blocksize - offset < toread ?
				sb->s_blocksize - offset : toread;

		tmp_bh.b_state = 0;
		err = ext2_get_block(inode, blk, &tmp_bh, 0);
		if (err < 0)
			return err;
		if (!buffer_mapped(&tmp_bh))	/* A hole? */
			memset(data, 0, tocopy);
		else {
			bh = sb_bread(sb, tmp_bh.b_blocknr);
			if (!bh)
				return -EIO;
			memcpy(data, bh->b_data+offset, tocopy);
			brelse(bh);
		}
		offset = 0;
		toread -= tocopy;
		data += tocopy;
		blk++;
	}
	return len;
}

/* Write to quotafile */
static ssize_t ext2_quota_write(struct super_block *sb, int type,
				const char *data, size_t len, loff_t off)
{
	struct inode *inode = sb_dqopt(sb)->files[type];
	sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb);
	int err = 0;
	int offset = off & (sb->s_blocksize - 1);
	int tocopy;
	size_t towrite = len;
	struct buffer_head tmp_bh;
	struct buffer_head *bh;

	mutex_lock_nested(&inode->i_mutex, I_MUTEX_QUOTA);
	while (towrite > 0) {
		tocopy = sb->s_blocksize - offset < towrite ?
				sb->s_blocksize - offset : towrite;

		tmp_bh.b_state = 0;
		err = ext2_get_block(inode, blk, &tmp_bh, 1);
		if (err < 0)
			goto out;
		if (offset || tocopy != EXT2_BLOCK_SIZE(sb))
			bh = sb_bread(sb, tmp_bh.b_blocknr);
		else
			bh = sb_getblk(sb, tmp_bh.b_blocknr);
		if (!bh) {
			err = -EIO;
			goto out;
		}
		lock_buffer(bh);
		memcpy(bh->b_data+offset, data, tocopy);
		flush_dcache_page(bh->b_page);
		set_buffer_uptodate(bh);
		mark_buffer_dirty(bh);
		unlock_buffer(bh);
		brelse(bh);
		offset = 0;
		towrite -= tocopy;
		data += tocopy;
		blk++;
	}
out:
	if (len == towrite)
		return err;
	if (inode->i_size < off+len-towrite)
		i_size_write(inode, off+len-towrite);
	inode->i_version++;
	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	mark_inode_dirty(inode);
	mutex_unlock(&inode->i_mutex);
	return len - towrite;
}

#endif

static struct file_system_type ext2_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "ext2",
	.get_sb		= ext2_get_sb,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};

static int __init init_ext2_fs(void)
{
	int err = init_ext2_xattr();
	if (err)
		return err;
	err = init_inodecache();
	if (err)
		goto out1;
        err = register_filesystem(&ext2_fs_type);
	if (err)
		goto out;
	return 0;
out:
	destroy_inodecache();
out1:
	exit_ext2_xattr();
	return err;
}

static void __exit exit_ext2_fs(void)
{
	unregister_filesystem(&ext2_fs_type);
	destroy_inodecache();
	exit_ext2_xattr();
}

module_init(init_ext2_fs)
module_exit(exit_ext2_fs)