super.c

linux 内核源代码

/* Called at mount-time, super-block is locked */
static int ext4_check_descriptors (struct super_block * sb)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
	ext4_fsblk_t last_block;
	ext4_fsblk_t block_bitmap;
	ext4_fsblk_t inode_bitmap;
	ext4_fsblk_t inode_table;
	struct ext4_group_desc * gdp = NULL;
	int desc_block = 0;
	int flexbg_flag = 0;
	int i;

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

	ext4_debug ("Checking group descriptors");

	for (i = 0; i < sbi->s_groups_count; i++)
	{
		if (i == sbi->s_groups_count - 1 || flexbg_flag)
			last_block = ext4_blocks_count(sbi->s_es) - 1;
		else
			last_block = first_block +
				(EXT4_BLOCKS_PER_GROUP(sb) - 1);

		if ((i % EXT4_DESC_PER_BLOCK(sb)) == 0)
			gdp = (struct ext4_group_desc *)
					sbi->s_group_desc[desc_block++]->b_data;
		block_bitmap = ext4_block_bitmap(sb, gdp);
		if (block_bitmap < first_block || block_bitmap > last_block)
		{
			ext4_error (sb, "ext4_check_descriptors",
				    "Block bitmap for group %d"
				    " not in group (block %llu)!",
				    i, block_bitmap);
			return 0;
		}
		inode_bitmap = ext4_inode_bitmap(sb, gdp);
		if (inode_bitmap < first_block || inode_bitmap > last_block)
		{
			ext4_error (sb, "ext4_check_descriptors",
				    "Inode bitmap for group %d"
				    " not in group (block %llu)!",
				    i, inode_bitmap);
			return 0;
		}
		inode_table = ext4_inode_table(sb, gdp);
		if (inode_table < first_block ||
		    inode_table + sbi->s_itb_per_group - 1 > last_block)
		{
			ext4_error (sb, "ext4_check_descriptors",
				    "Inode table for group %d"
				    " not in group (block %llu)!",
				    i, inode_table);
			return 0;
		}
		if (!ext4_group_desc_csum_verify(sbi, i, gdp)) {
			ext4_error(sb, __FUNCTION__,
				   "Checksum for group %d failed (%u!=%u)\n", i,
				   le16_to_cpu(ext4_group_desc_csum(sbi, i,
								    gdp)),
				   le16_to_cpu(gdp->bg_checksum));
			return 0;
		}
		if (!flexbg_flag)
			first_block += EXT4_BLOCKS_PER_GROUP(sb);
		gdp = (struct ext4_group_desc *)
			((__u8 *)gdp + EXT4_DESC_SIZE(sb));
	}

	ext4_free_blocks_count_set(sbi->s_es, ext4_count_free_blocks(sb));
	sbi->s_es->s_free_inodes_count=cpu_to_le32(ext4_count_free_inodes(sb));
	return 1;
}


/* ext4_orphan_cleanup() walks a singly-linked list of inodes (starting at
 * the superblock) which were deleted from all directories, but held open by
 * a process at the time of a crash.  We walk the list and try to delete these
 * inodes at recovery time (only with a read-write filesystem).
 *
 * In order to keep the orphan inode chain consistent during traversal (in
 * case of crash during recovery), we link each inode into the superblock
 * orphan list_head and handle it the same way as an inode deletion during
 * normal operation (which journals the operations for us).
 *
 * We only do an iget() and an iput() on each inode, which is very safe if we
 * accidentally point at an in-use or already deleted inode.  The worst that
 * can happen in this case is that we get a "bit already cleared" message from
 * ext4_free_inode().  The only reason we would point at a wrong inode is if
 * e2fsck was run on this filesystem, and it must have already done the orphan
 * inode cleanup for us, so we can safely abort without any further action.
 */
static void ext4_orphan_cleanup (struct super_block * sb,
				 struct ext4_super_block * es)
{
	unsigned int s_flags = sb->s_flags;
	int nr_orphans = 0, nr_truncates = 0;
#ifdef CONFIG_QUOTA
	int i;
#endif
	if (!es->s_last_orphan) {
		jbd_debug(4, "no orphan inodes to clean up\n");
		return;
	}

	if (bdev_read_only(sb->s_bdev)) {
		printk(KERN_ERR "EXT4-fs: write access "
			"unavailable, skipping orphan cleanup.\n");
		return;
	}

	if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
		if (es->s_last_orphan)
			jbd_debug(1, "Errors on filesystem, "
				  "clearing orphan list.\n");
		es->s_last_orphan = 0;
		jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
		return;
	}

	if (s_flags & MS_RDONLY) {
		printk(KERN_INFO "EXT4-fs: %s: orphan cleanup on readonly fs\n",
		       sb->s_id);
		sb->s_flags &= ~MS_RDONLY;
	}
#ifdef CONFIG_QUOTA
	/* Needed for iput() to work correctly and not trash data */
	sb->s_flags |= MS_ACTIVE;
	/* Turn on quotas so that they are updated correctly */
	for (i = 0; i < MAXQUOTAS; i++) {
		if (EXT4_SB(sb)->s_qf_names[i]) {
			int ret = ext4_quota_on_mount(sb, i);
			if (ret < 0)
				printk(KERN_ERR
					"EXT4-fs: Cannot turn on journalled "
					"quota: error %d\n", ret);
		}
	}
#endif

	while (es->s_last_orphan) {
		struct inode *inode;

		if (!(inode =
		      ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan)))) {
			es->s_last_orphan = 0;
			break;
		}

		list_add(&EXT4_I(inode)->i_orphan, &EXT4_SB(sb)->s_orphan);
		DQUOT_INIT(inode);
		if (inode->i_nlink) {
			printk(KERN_DEBUG
				"%s: truncating inode %lu to %Ld bytes\n",
				__FUNCTION__, inode->i_ino, inode->i_size);
			jbd_debug(2, "truncating inode %lu to %Ld bytes\n",
				  inode->i_ino, inode->i_size);
			ext4_truncate(inode);
			nr_truncates++;
		} else {
			printk(KERN_DEBUG
				"%s: deleting unreferenced inode %lu\n",
				__FUNCTION__, inode->i_ino);
			jbd_debug(2, "deleting unreferenced inode %lu\n",
				  inode->i_ino);
			nr_orphans++;
		}
		iput(inode);  /* The delete magic happens here! */
	}

#define PLURAL(x) (x), ((x)==1) ? "" : "s"

	if (nr_orphans)
		printk(KERN_INFO "EXT4-fs: %s: %d orphan inode%s deleted\n",
		       sb->s_id, PLURAL(nr_orphans));
	if (nr_truncates)
		printk(KERN_INFO "EXT4-fs: %s: %d truncate%s cleaned up\n",
		       sb->s_id, PLURAL(nr_truncates));
#ifdef CONFIG_QUOTA
	/* Turn quotas off */
	for (i = 0; i < MAXQUOTAS; i++) {
		if (sb_dqopt(sb)->files[i])
			vfs_quota_off(sb, i);
	}
#endif
	sb->s_flags = s_flags; /* Restore MS_RDONLY status */
}

/*
 * Maximal file size.  There is a direct, and {,double-,triple-}indirect
 * block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks.
 * We need to be 1 filesystem block less than the 2^32 sector limit.
 */
static loff_t ext4_max_size(int bits)
{
	loff_t res = EXT4_NDIR_BLOCKS;
	/* This constant is calculated to be the largest file size for a
	 * dense, 4k-blocksize file such that the total number of
	 * sectors in the file, including data and all indirect blocks,
	 * does not exceed 2^32. */
	const loff_t upper_limit = 0x1ff7fffd000LL;

	res += 1LL << (bits-2);
	res += 1LL << (2*(bits-2));
	res += 1LL << (3*(bits-2));
	res <<= bits;
	if (res > upper_limit)
		res = upper_limit;
	return res;
}

static ext4_fsblk_t descriptor_loc(struct super_block *sb,
				ext4_fsblk_t logical_sb_block, int nr)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);
	unsigned long bg, first_meta_bg;
	int has_super = 0;

	first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);

	if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_META_BG) ||
	    nr < first_meta_bg)
		return logical_sb_block + nr + 1;
	bg = sbi->s_desc_per_block * nr;
	if (ext4_bg_has_super(sb, bg))
		has_super = 1;
	return (has_super + ext4_group_first_block_no(sb, bg));
}


static int ext4_fill_super (struct super_block *sb, void *data, int silent)
{
	struct buffer_head * bh;
	struct ext4_super_block *es = NULL;
	struct ext4_sb_info *sbi;
	ext4_fsblk_t block;
	ext4_fsblk_t sb_block = get_sb_block(&data);
	ext4_fsblk_t logical_sb_block;
	unsigned long offset = 0;
	unsigned int journal_inum = 0;
	unsigned long journal_devnum = 0;
	unsigned long def_mount_opts;
	struct inode *root;
	int blocksize;
	int hblock;
	int db_count;
	int i;
	int needs_recovery;
	__le32 features;
	__u64 blocks_count;
	int err;

	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;
	sb->s_fs_info = sbi;
	sbi->s_mount_opt = 0;
	sbi->s_resuid = EXT4_DEF_RESUID;
	sbi->s_resgid = EXT4_DEF_RESGID;
	sbi->s_sb_block = sb_block;

	unlock_kernel();

	blocksize = sb_min_blocksize(sb, EXT4_MIN_BLOCK_SIZE);
	if (!blocksize) {
		printk(KERN_ERR "EXT4-fs: unable to set blocksize\n");
		goto out_fail;
	}

	/*
	 * The ext4 superblock will not be buffer aligned for other than 1kB
	 * block sizes.  We need to calculate the offset from buffer start.
	 */
	if (blocksize != EXT4_MIN_BLOCK_SIZE) {
		logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
		offset = do_div(logical_sb_block, blocksize);
	} else {
		logical_sb_block = sb_block;
	}

	if (!(bh = sb_bread(sb, logical_sb_block))) {
		printk (KERN_ERR "EXT4-fs: unable to read superblock\n");
		goto out_fail;
	}
	/*
	 * Note: s_es must be initialized as soon as possible because
	 *       some ext4 macro-instructions depend on its value
	 */
	es = (struct ext4_super_block *) (((char *)bh->b_data) + offset);
	sbi->s_es = es;
	sb->s_magic = le16_to_cpu(es->s_magic);
	if (sb->s_magic != EXT4_SUPER_MAGIC)
		goto cantfind_ext4;

	/* Set defaults before we parse the mount options */
	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
	if (def_mount_opts & EXT4_DEFM_DEBUG)
		set_opt(sbi->s_mount_opt, DEBUG);
	if (def_mount_opts & EXT4_DEFM_BSDGROUPS)
		set_opt(sbi->s_mount_opt, GRPID);
	if (def_mount_opts & EXT4_DEFM_UID16)
		set_opt(sbi->s_mount_opt, NO_UID32);
#ifdef CONFIG_EXT4DEV_FS_XATTR
	if (def_mount_opts & EXT4_DEFM_XATTR_USER)
		set_opt(sbi->s_mount_opt, XATTR_USER);
#endif
#ifdef CONFIG_EXT4DEV_FS_POSIX_ACL
	if (def_mount_opts & EXT4_DEFM_ACL)
		set_opt(sbi->s_mount_opt, POSIX_ACL);
#endif
	if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_DATA)
		sbi->s_mount_opt |= EXT4_MOUNT_JOURNAL_DATA;
	else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_ORDERED)
		sbi->s_mount_opt |= EXT4_MOUNT_ORDERED_DATA;
	else if ((def_mount_opts & EXT4_DEFM_JMODE) == EXT4_DEFM_JMODE_WBACK)
		sbi->s_mount_opt |= EXT4_MOUNT_WRITEBACK_DATA;

	if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_PANIC)
		set_opt(sbi->s_mount_opt, ERRORS_PANIC);
	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT4_ERRORS_RO)
		set_opt(sbi->s_mount_opt, ERRORS_RO);
	else
		set_opt(sbi->s_mount_opt, ERRORS_CONT);

	sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
	sbi->s_resgid = le16_to_cpu(es->s_def_resgid);

	set_opt(sbi->s_mount_opt, RESERVATION);

	/*
	 * turn on extents feature by default in ext4 filesystem
	 * User -o noextents to turn it off
	 */
	set_opt(sbi->s_mount_opt, EXTENTS);

	if (!parse_options ((char *) data, sb, &journal_inum, &journal_devnum,
			    NULL, 0))
		goto failed_mount;

	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		((sbi->s_mount_opt & EXT4_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);

	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV &&
	    (EXT4_HAS_COMPAT_FEATURE(sb, ~0U) ||
	     EXT4_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
	     EXT4_HAS_INCOMPAT_FEATURE(sb, ~0U)))
		printk(KERN_WARNING
		       "EXT4-fs warning: feature flags set on rev 0 fs, "
		       "running e2fsck is recommended\n");
	/*
	 * Check feature flags regardless of the revision level, since we
	 * previously didn't change the revision level when setting the flags,
	 * so there is a chance incompat flags are set on a rev 0 filesystem.
	 */
	features = EXT4_HAS_INCOMPAT_FEATURE(sb, ~EXT4_FEATURE_INCOMPAT_SUPP);
	if (features) {
		printk(KERN_ERR "EXT4-fs: %s: couldn't mount because of "
		       "unsupported optional features (%x).\n",
		       sb->s_id, le32_to_cpu(features));
		goto failed_mount;
	}
	features = EXT4_HAS_RO_COMPAT_FEATURE(sb, ~EXT4_FEATURE_RO_COMPAT_SUPP);
	if (!(sb->s_flags & MS_RDONLY) && features) {
		printk(KERN_ERR "EXT4-fs: %s: couldn't mount RDWR because of "
		       "unsupported optional features (%x).\n",
		       sb->s_id, le32_to_cpu(features));
		goto failed_mount;
	}
	blocksize = BLOCK_SIZE << le32_to_cpu(es->s_log_block_size);

	if (blocksize < EXT4_MIN_BLOCK_SIZE ||
	    blocksize > EXT4_MAX_BLOCK_SIZE) {
		printk(KERN_ERR
		       "EXT4-fs: Unsupported filesystem blocksize %d on %s.\n",
		       blocksize, sb->s_id);
		goto failed_mount;
	}

	hblock = bdev_hardsect_size(sb->s_bdev);
	if (sb->s_blocksize != blocksize) {
		/*
		 * Make sure the blocksize for the filesystem is larger
		 * than the hardware sectorsize for the machine.
		 */
		if (blocksize < hblock) {
			printk(KERN_ERR "EXT4-fs: blocksize %d too small for "
			       "device blocksize %d.\n", blocksize, hblock);
			goto failed_mount;
		}

		brelse (bh);
		sb_set_blocksize(sb, blocksize);
		logical_sb_block = sb_block * EXT4_MIN_BLOCK_SIZE;
		offset = do_div(logical_sb_block, blocksize);
		bh = sb_bread(sb, logical_sb_block);
		if (!bh) {
			printk(KERN_ERR
			       "EXT4-fs: Can't read superblock on 2nd try.\n");
			goto failed_mount;
		}
		es = (struct ext4_super_block *)(((char *)bh->b_data) + offset);
		sbi->s_es = es;
		if (es->s_magic != cpu_to_le16(EXT4_SUPER_MAGIC)) {
			printk (KERN_ERR
				"EXT4-fs: Magic mismatch, very weird !\n");
			goto failed_mount;
		}
	}

	sb->s_maxbytes = ext4_max_size(sb->s_blocksize_bits);

	if (le32_to_cpu(es->s_rev_level) == EXT4_GOOD_OLD_REV) {
		sbi->s_inode_size = EXT4_GOOD_OLD_INODE_SIZE;
		sbi->s_first_ino = EXT4_GOOD_OLD_FIRST_INO;
	} else {
		sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
		sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
		if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
		    (!is_power_of_2(sbi->s_inode_size)) ||
		    (sbi->s_inode_size > blocksize)) {
			printk (KERN_ERR
				"EXT4-fs: unsupported inode size: %d\n",
				sbi->s_inode_size);
			goto failed_mount;
		}
		if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE)
			sb->s_time_gran = 1 << (EXT4_EPOCH_BITS - 2);
	}
	sbi->s_desc_size = le16_to_cpu(es->s_desc_size);
	if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_64BIT)) {
		if (sbi->s_desc_size < EXT4_MIN_DESC_SIZE_64BIT ||
		    sbi->s_desc_size > EXT4_MAX_DESC_SIZE ||
		    !is_power_of_2(sbi->s_desc_size)) {
			printk(KERN_ERR
			       "EXT4-fs: unsupported descriptor size %lu\n",
			       sbi->s_desc_size);
			goto failed_mount;
		}
	} else
		sbi->s_desc_size = EXT4_MIN_DESC_SIZE;
	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
	if (EXT4_INODE_SIZE(sb) == 0 || EXT4_INODES_PER_GROUP(sb) == 0)
		goto cantfind_ext4;
	sbi->s_inodes_per_block = blocksize / EXT4_INODE_SIZE(sb);
	if (sbi->s_inodes_per_block == 0)
		goto cantfind_ext4;