super.c

linux 内核源代码

	for (i = 0; i < MAXQUOTAS; i++) {
		if (EXT3_SB(sb)->s_qf_names[i]) {
			int ret = ext3_quota_on_mount(sb, i);
			if (ret < 0)
				printk(KERN_ERR
					"EXT3-fs: Cannot turn on journalled "
					"quota: error %d\n", ret);
		}
	}
#endif

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

		if (!(inode =
		      ext3_orphan_get(sb, le32_to_cpu(es->s_last_orphan)))) {
			es->s_last_orphan = 0;
			break;
		}

		list_add(&EXT3_I(inode)->i_orphan, &EXT3_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);
			ext3_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 "EXT3-fs: %s: %d orphan inode%s deleted\n",
		       sb->s_id, PLURAL(nr_orphans));
	if (nr_truncates)
		printk(KERN_INFO "EXT3-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 ext3_max_size(int bits)
{
	loff_t res = EXT3_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 ext3_fsblk_t descriptor_loc(struct super_block *sb,
				    ext3_fsblk_t logic_sb_block,
				    int nr)
{
	struct ext3_sb_info *sbi = EXT3_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 (!EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_META_BG) ||
	    nr < first_meta_bg)
		return (logic_sb_block + nr + 1);
	bg = sbi->s_desc_per_block * nr;
	if (ext3_bg_has_super(sb, bg))
		has_super = 1;
	return (has_super + ext3_group_first_block_no(sb, bg));
}


static int ext3_fill_super (struct super_block *sb, void *data, int silent)
{
	struct buffer_head * bh;
	struct ext3_super_block *es = NULL;
	struct ext3_sb_info *sbi;
	ext3_fsblk_t block;
	ext3_fsblk_t sb_block = get_sb_block(&data);
	ext3_fsblk_t logic_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;
	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 = EXT3_DEF_RESUID;
	sbi->s_resgid = EXT3_DEF_RESGID;
	sbi->s_sb_block = sb_block;

	unlock_kernel();

	blocksize = sb_min_blocksize(sb, EXT3_MIN_BLOCK_SIZE);
	if (!blocksize) {
		printk(KERN_ERR "EXT3-fs: unable to set blocksize\n");
		goto out_fail;
	}

	/*
	 * The ext3 superblock will not be buffer aligned for other than 1kB
	 * block sizes.  We need to calculate the offset from buffer start.
	 */
	if (blocksize != EXT3_MIN_BLOCK_SIZE) {
		logic_sb_block = (sb_block * EXT3_MIN_BLOCK_SIZE) / blocksize;
		offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize;
	} else {
		logic_sb_block = sb_block;
	}

	if (!(bh = sb_bread(sb, logic_sb_block))) {
		printk (KERN_ERR "EXT3-fs: unable to read superblock\n");
		goto out_fail;
	}
	/*
	 * Note: s_es must be initialized as soon as possible because
	 *       some ext3 macro-instructions depend on its value
	 */
	es = (struct ext3_super_block *) (((char *)bh->b_data) + offset);
	sbi->s_es = es;
	sb->s_magic = le16_to_cpu(es->s_magic);
	if (sb->s_magic != EXT3_SUPER_MAGIC)
		goto cantfind_ext3;

	/* Set defaults before we parse the mount options */
	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
	if (def_mount_opts & EXT3_DEFM_DEBUG)
		set_opt(sbi->s_mount_opt, DEBUG);
	if (def_mount_opts & EXT3_DEFM_BSDGROUPS)
		set_opt(sbi->s_mount_opt, GRPID);
	if (def_mount_opts & EXT3_DEFM_UID16)
		set_opt(sbi->s_mount_opt, NO_UID32);
#ifdef CONFIG_EXT3_FS_XATTR
	if (def_mount_opts & EXT3_DEFM_XATTR_USER)
		set_opt(sbi->s_mount_opt, XATTR_USER);
#endif
#ifdef CONFIG_EXT3_FS_POSIX_ACL
	if (def_mount_opts & EXT3_DEFM_ACL)
		set_opt(sbi->s_mount_opt, POSIX_ACL);
#endif
	if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_DATA)
		sbi->s_mount_opt |= EXT3_MOUNT_JOURNAL_DATA;
	else if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_ORDERED)
		sbi->s_mount_opt |= EXT3_MOUNT_ORDERED_DATA;
	else if ((def_mount_opts & EXT3_DEFM_JMODE) == EXT3_DEFM_JMODE_WBACK)
		sbi->s_mount_opt |= EXT3_MOUNT_WRITEBACK_DATA;

	if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_ERRORS_PANIC)
		set_opt(sbi->s_mount_opt, ERRORS_PANIC);
	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT3_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);

	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 & EXT3_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);

	if (le32_to_cpu(es->s_rev_level) == EXT3_GOOD_OLD_REV &&
	    (EXT3_HAS_COMPAT_FEATURE(sb, ~0U) ||
	     EXT3_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
	     EXT3_HAS_INCOMPAT_FEATURE(sb, ~0U)))
		printk(KERN_WARNING
		       "EXT3-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 = EXT3_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP);
	if (features) {
		printk(KERN_ERR "EXT3-fs: %s: couldn't mount because of "
		       "unsupported optional features (%x).\n",
		       sb->s_id, le32_to_cpu(features));
		goto failed_mount;
	}
	features = EXT3_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP);
	if (!(sb->s_flags & MS_RDONLY) && features) {
		printk(KERN_ERR "EXT3-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 < EXT3_MIN_BLOCK_SIZE ||
	    blocksize > EXT3_MAX_BLOCK_SIZE) {
		printk(KERN_ERR
		       "EXT3-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 "EXT3-fs: blocksize %d too small for "
			       "device blocksize %d.\n", blocksize, hblock);
			goto failed_mount;
		}

		brelse (bh);
		if (!sb_set_blocksize(sb, blocksize)) {
			printk(KERN_ERR "EXT3-fs: bad blocksize %d.\n",
				blocksize);
			goto out_fail;
		}
		logic_sb_block = (sb_block * EXT3_MIN_BLOCK_SIZE) / blocksize;
		offset = (sb_block * EXT3_MIN_BLOCK_SIZE) % blocksize;
		bh = sb_bread(sb, logic_sb_block);
		if (!bh) {
			printk(KERN_ERR
			       "EXT3-fs: Can't read superblock on 2nd try.\n");
			goto failed_mount;
		}
		es = (struct ext3_super_block *)(((char *)bh->b_data) + offset);
		sbi->s_es = es;
		if (es->s_magic != cpu_to_le16(EXT3_SUPER_MAGIC)) {
			printk (KERN_ERR
				"EXT3-fs: Magic mismatch, very weird !\n");
			goto failed_mount;
		}
	}

	sb->s_maxbytes = ext3_max_size(sb->s_blocksize_bits);

	if (le32_to_cpu(es->s_rev_level) == EXT3_GOOD_OLD_REV) {
		sbi->s_inode_size = EXT3_GOOD_OLD_INODE_SIZE;
		sbi->s_first_ino = EXT3_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 < EXT3_GOOD_OLD_INODE_SIZE) ||
		    (!is_power_of_2(sbi->s_inode_size)) ||
		    (sbi->s_inode_size > blocksize)) {
			printk (KERN_ERR
				"EXT3-fs: unsupported inode size: %d\n",
				sbi->s_inode_size);
			goto failed_mount;
		}
	}
	sbi->s_frag_size = EXT3_MIN_FRAG_SIZE <<
				   le32_to_cpu(es->s_log_frag_size);
	if (blocksize != sbi->s_frag_size) {
		printk(KERN_ERR
		       "EXT3-fs: fragsize %lu != blocksize %u (unsupported)\n",
		       sbi->s_frag_size, blocksize);
		goto failed_mount;
	}
	sbi->s_frags_per_block = 1;
	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
	sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);
	if (EXT3_INODE_SIZE(sb) == 0 || EXT3_INODES_PER_GROUP(sb) == 0)
		goto cantfind_ext3;
	sbi->s_inodes_per_block = blocksize / EXT3_INODE_SIZE(sb);
	if (sbi->s_inodes_per_block == 0)
		goto cantfind_ext3;
	sbi->s_itb_per_group = sbi->s_inodes_per_group /
					sbi->s_inodes_per_block;
	sbi->s_desc_per_block = blocksize / sizeof(struct ext3_group_desc);
	sbi->s_sbh = bh;
	sbi->s_mount_state = le16_to_cpu(es->s_state);
	sbi->s_addr_per_block_bits = ilog2(EXT3_ADDR_PER_BLOCK(sb));
	sbi->s_desc_per_block_bits = ilog2(EXT3_DESC_PER_BLOCK(sb));
	for (i=0; i < 4; i++)
		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
	sbi->s_def_hash_version = es->s_def_hash_version;

	if (sbi->s_blocks_per_group > blocksize * 8) {
		printk (KERN_ERR
			"EXT3-fs: #blocks per group too big: %lu\n",
			sbi->s_blocks_per_group);
		goto failed_mount;
	}
	if (sbi->s_frags_per_group > blocksize * 8) {
		printk (KERN_ERR
			"EXT3-fs: #fragments per group too big: %lu\n",
			sbi->s_frags_per_group);
		goto failed_mount;
	}
	if (sbi->s_inodes_per_group > blocksize * 8) {
		printk (KERN_ERR
			"EXT3-fs: #inodes per group too big: %lu\n",
			sbi->s_inodes_per_group);
		goto failed_mount;
	}

	if (le32_to_cpu(es->s_blocks_count) >
		    (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
		printk(KERN_ERR "EXT3-fs: filesystem on %s:"
			" too large to mount safely\n", sb->s_id);
		if (sizeof(sector_t) < 8)
			printk(KERN_WARNING "EXT3-fs: CONFIG_LBD not "
					"enabled\n");
		goto failed_mount;
	}

	if (EXT3_BLOCKS_PER_GROUP(sb) == 0)
		goto cantfind_ext3;
	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
			       le32_to_cpu(es->s_first_data_block) - 1)
				       / EXT3_BLOCKS_PER_GROUP(sb)) + 1;
	db_count = (sbi->s_groups_count + EXT3_DESC_PER_BLOCK(sb) - 1) /
		   EXT3_DESC_PER_BLOCK(sb);
	sbi->s_group_desc = kmalloc(db_count * sizeof (struct buffer_head *),
				    GFP_KERNEL);
	if (sbi->s_group_desc == NULL) {
		printk (KERN_ERR "EXT3-fs: not enough memory\n");
		goto failed_mount;
	}

	bgl_lock_init(&sbi->s_blockgroup_lock);

	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]) {
			printk (KERN_ERR "EXT3-fs: "
				"can't read group descriptor %d\n", i);
			db_count = i;
			goto failed_mount2;
		}
	}
	if (!ext3_check_descriptors (sb)) {
		printk(KERN_ERR "EXT3-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);

	err = percpu_counter_init(&sbi->s_freeblocks_counter,
			ext3_count_free_blocks(sb));
	if (!err) {
		err = percpu_counter_init(&sbi->s_freeinodes_counter,
				ext3_count_free_inodes(sb));
	}
	if (!err) {
		err = percpu_counter_init(&sbi->s_dirs_counter,
				ext3_count_dirs(sb));
	}
	if (err) {
		printk(KERN_ERR "EXT3-fs: insufficient memory\n");
		goto failed_mount3;
	}

	/* 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 = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_end = EXT3_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_alloc_hit = 0;
	sbi->s_rsv_window_head.rsv_goal_size = 0;
	ext3_rsv_window_add(sb, &sbi->s_rsv_window_head);

	/*
	 * set up enough so that it can read an inode
	 */
	sb->s_op = &ext3_sops;
	sb->s_export_op = &ext3_export_ops;
	sb->s_xattr = ext3_xattr_handlers;
#ifdef CONFIG_QUOTA
	sb->s_qcop = &ext3_qctl_operations;
	sb->dq_op = &ext3_quota_operations;
#endif
	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */

	sb->s_root = NULL;

	needs_recovery = (es->s_last_orphan != 0 ||
			  EXT3_HAS_INCOMPAT_FEATURE(sb,
				    EXT3_FEATURE_INCOMPAT_RECOVER));

	/*
	 * The first inode we look at is the journal inode.  Don't try
	 * root first: it may be modified in the journal!
	 */
	if (!test_opt(sb, NOLOAD) &&
	    EXT3_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL)) {
		if (ext3_load_journal(sb, es, journal_devnum))
			goto failed_mount3;
	} else if (journal_inum) {
		if (ext3_create_journal(sb, es, journal_inum))
			goto failed_mount3;
	} else {
		if (!silent)
			printk (KERN_ERR
				"ext3: No journal on filesystem on %s\n",
				sb->s_id);
		goto failed_mount3;
	}

	/* We have now updated the journal if required, so we can
	 * validate the data journaling mode. */
	switch (test_opt(sb, DATA_FLAGS)) {
	case 0:
		/* No mode set, assume a default based on the journal
                   capabilities: ORDERED_DATA if the journal can