super.c

linux 内核源代码

	sbi->s_itb_per_group = sbi->s_inodes_per_group /
					sbi->s_inodes_per_block;
	sbi->s_desc_per_block = blocksize / EXT4_DESC_SIZE(sb);
	sbi->s_sbh = bh;
	sbi->s_mount_state = le16_to_cpu(es->s_state);
	sbi->s_addr_per_block_bits = ilog2(EXT4_ADDR_PER_BLOCK(sb));
	sbi->s_desc_per_block_bits = ilog2(EXT4_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
			"EXT4-fs: #blocks per group too big: %lu\n",
			sbi->s_blocks_per_group);
		goto failed_mount;
	}
	if (sbi->s_inodes_per_group > blocksize * 8) {
		printk (KERN_ERR
			"EXT4-fs: #inodes per group too big: %lu\n",
			sbi->s_inodes_per_group);
		goto failed_mount;
	}

	if (ext4_blocks_count(es) >
		    (sector_t)(~0ULL) >> (sb->s_blocksize_bits - 9)) {
		printk(KERN_ERR "EXT4-fs: filesystem on %s:"
			" too large to mount safely\n", sb->s_id);
		if (sizeof(sector_t) < 8)
			printk(KERN_WARNING "EXT4-fs: CONFIG_LBD not "
					"enabled\n");
		goto failed_mount;
	}

	if (EXT4_BLOCKS_PER_GROUP(sb) == 0)
		goto cantfind_ext4;
	blocks_count = (ext4_blocks_count(es) -
			le32_to_cpu(es->s_first_data_block) +
			EXT4_BLOCKS_PER_GROUP(sb) - 1);
	do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
	sbi->s_groups_count = blocks_count;
	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
		   EXT4_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 "EXT4-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, logical_sb_block, i);
		sbi->s_group_desc[i] = sb_bread(sb, block);
		if (!sbi->s_group_desc[i]) {
			printk (KERN_ERR "EXT4-fs: "
				"can't read group descriptor %d\n", i);
			db_count = i;
			goto failed_mount2;
		}
	}
	if (!ext4_check_descriptors (sb)) {
		printk(KERN_ERR "EXT4-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,
			ext4_count_free_blocks(sb));
	if (!err) {
		err = percpu_counter_init(&sbi->s_freeinodes_counter,
				ext4_count_free_inodes(sb));
	}
	if (!err) {
		err = percpu_counter_init(&sbi->s_dirs_counter,
				ext4_count_dirs(sb));
	}
	if (err) {
		printk(KERN_ERR "EXT4-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 = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_end = EXT4_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_alloc_hit = 0;
	sbi->s_rsv_window_head.rsv_goal_size = 0;
	ext4_rsv_window_add(sb, &sbi->s_rsv_window_head);

	/*
	 * set up enough so that it can read an inode
	 */
	sb->s_op = &ext4_sops;
	sb->s_export_op = &ext4_export_ops;
	sb->s_xattr = ext4_xattr_handlers;
#ifdef CONFIG_QUOTA
	sb->s_qcop = &ext4_qctl_operations;
	sb->dq_op = &ext4_quota_operations;
#endif
	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */

	sb->s_root = NULL;

	needs_recovery = (es->s_last_orphan != 0 ||
			  EXT4_HAS_INCOMPAT_FEATURE(sb,
				    EXT4_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) &&
	    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_HAS_JOURNAL)) {
		if (ext4_load_journal(sb, es, journal_devnum))
			goto failed_mount3;
	} else if (journal_inum) {
		if (ext4_create_journal(sb, es, journal_inum))
			goto failed_mount3;
	} else {
		if (!silent)
			printk (KERN_ERR
				"ext4: No journal on filesystem on %s\n",
				sb->s_id);
		goto failed_mount3;
	}

	if (ext4_blocks_count(es) > 0xffffffffULL &&
	    !jbd2_journal_set_features(EXT4_SB(sb)->s_journal, 0, 0,
				       JBD2_FEATURE_INCOMPAT_64BIT)) {
		printk(KERN_ERR "ext4: Failed to set 64-bit journal feature\n");
		goto failed_mount4;
	}

	/* 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
		 * cope, else JOURNAL_DATA
		 */
		if (jbd2_journal_check_available_features
		    (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE))
			set_opt(sbi->s_mount_opt, ORDERED_DATA);
		else
			set_opt(sbi->s_mount_opt, JOURNAL_DATA);
		break;

	case EXT4_MOUNT_ORDERED_DATA:
	case EXT4_MOUNT_WRITEBACK_DATA:
		if (!jbd2_journal_check_available_features
		    (sbi->s_journal, 0, 0, JBD2_FEATURE_INCOMPAT_REVOKE)) {
			printk(KERN_ERR "EXT4-fs: Journal does not support "
			       "requested data journaling mode\n");
			goto failed_mount4;
		}
	default:
		break;
	}

	if (test_opt(sb, NOBH)) {
		if (!(test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)) {
			printk(KERN_WARNING "EXT4-fs: Ignoring nobh option - "
				"its supported only with writeback mode\n");
			clear_opt(sbi->s_mount_opt, NOBH);
		}
	}
	/*
	 * The jbd2_journal_load will have done any necessary log recovery,
	 * so we can safely mount the rest of the filesystem now.
	 */

	root = iget(sb, EXT4_ROOT_INO);
	sb->s_root = d_alloc_root(root);
	if (!sb->s_root) {
		printk(KERN_ERR "EXT4-fs: get root inode failed\n");
		iput(root);
		goto failed_mount4;
	}
	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
		dput(sb->s_root);
		sb->s_root = NULL;
		printk(KERN_ERR "EXT4-fs: corrupt root inode, run e2fsck\n");
		goto failed_mount4;
	}

	ext4_setup_super (sb, es, sb->s_flags & MS_RDONLY);

	/* determine the minimum size of new large inodes, if present */
	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
						     EXT4_GOOD_OLD_INODE_SIZE;
		if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
				       EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE)) {
			if (sbi->s_want_extra_isize <
			    le16_to_cpu(es->s_want_extra_isize))
				sbi->s_want_extra_isize =
					le16_to_cpu(es->s_want_extra_isize);
			if (sbi->s_want_extra_isize <
			    le16_to_cpu(es->s_min_extra_isize))
				sbi->s_want_extra_isize =
					le16_to_cpu(es->s_min_extra_isize);
		}
	}
	/* Check if enough inode space is available */
	if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
							sbi->s_inode_size) {
		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
						       EXT4_GOOD_OLD_INODE_SIZE;
		printk(KERN_INFO "EXT4-fs: required extra inode space not"
			"available.\n");
	}

	/*
	 * akpm: core read_super() calls in here with the superblock locked.
	 * That deadlocks, because orphan cleanup needs to lock the superblock
	 * in numerous places.  Here we just pop the lock - it's relatively
	 * harmless, because we are now ready to accept write_super() requests,
	 * and aviro says that's the only reason for hanging onto the
	 * superblock lock.
	 */
	EXT4_SB(sb)->s_mount_state |= EXT4_ORPHAN_FS;
	ext4_orphan_cleanup(sb, es);
	EXT4_SB(sb)->s_mount_state &= ~EXT4_ORPHAN_FS;
	if (needs_recovery)
		printk (KERN_INFO "EXT4-fs: recovery complete.\n");
	ext4_mark_recovery_complete(sb, es);
	printk (KERN_INFO "EXT4-fs: mounted filesystem with %s data mode.\n",
		test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ? "journal":
		test_opt(sb,DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA ? "ordered":
		"writeback");

	ext4_ext_init(sb);

	lock_kernel();
	return 0;

cantfind_ext4:
	if (!silent)
		printk(KERN_ERR "VFS: Can't find ext4 filesystem on dev %s.\n",
		       sb->s_id);
	goto failed_mount;

failed_mount4:
	jbd2_journal_destroy(sbi->s_journal);
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]);
	kfree(sbi->s_group_desc);
failed_mount:
#ifdef CONFIG_QUOTA
	for (i = 0; i < MAXQUOTAS; i++)
		kfree(sbi->s_qf_names[i]);
#endif
	ext4_blkdev_remove(sbi);
	brelse(bh);
out_fail:
	sb->s_fs_info = NULL;
	kfree(sbi);
	lock_kernel();
	return -EINVAL;
}

/*
 * Setup any per-fs journal parameters now.  We'll do this both on
 * initial mount, once the journal has been initialised but before we've
 * done any recovery; and again on any subsequent remount.
 */
static void ext4_init_journal_params(struct super_block *sb, journal_t *journal)
{
	struct ext4_sb_info *sbi = EXT4_SB(sb);

	if (sbi->s_commit_interval)
		journal->j_commit_interval = sbi->s_commit_interval;
	/* We could also set up an ext4-specific default for the commit
	 * interval here, but for now we'll just fall back to the jbd
	 * default. */

	spin_lock(&journal->j_state_lock);
	if (test_opt(sb, BARRIER))
		journal->j_flags |= JBD2_BARRIER;
	else
		journal->j_flags &= ~JBD2_BARRIER;
	spin_unlock(&journal->j_state_lock);
}

static journal_t *ext4_get_journal(struct super_block *sb,
				   unsigned int journal_inum)
{
	struct inode *journal_inode;
	journal_t *journal;

	/* First, test for the existence of a valid inode on disk.  Bad
	 * things happen if we iget() an unused inode, as the subsequent
	 * iput() will try to delete it. */

	journal_inode = iget(sb, journal_inum);
	if (!journal_inode) {
		printk(KERN_ERR "EXT4-fs: no journal found.\n");
		return NULL;
	}
	if (!journal_inode->i_nlink) {
		make_bad_inode(journal_inode);
		iput(journal_inode);
		printk(KERN_ERR "EXT4-fs: journal inode is deleted.\n");
		return NULL;
	}

	jbd_debug(2, "Journal inode found at %p: %Ld bytes\n",
		  journal_inode, journal_inode->i_size);
	if (is_bad_inode(journal_inode) || !S_ISREG(journal_inode->i_mode)) {
		printk(KERN_ERR "EXT4-fs: invalid journal inode.\n");
		iput(journal_inode);
		return NULL;
	}

	journal = jbd2_journal_init_inode(journal_inode);
	if (!journal) {
		printk(KERN_ERR "EXT4-fs: Could not load journal inode\n");
		iput(journal_inode);
		return NULL;
	}
	journal->j_private = sb;
	ext4_init_journal_params(sb, journal);
	return journal;
}

static journal_t *ext4_get_dev_journal(struct super_block *sb,
				       dev_t j_dev)
{
	struct buffer_head * bh;
	journal_t *journal;
	ext4_fsblk_t start;
	ext4_fsblk_t len;
	int hblock, blocksize;
	ext4_fsblk_t sb_block;
	unsigned long offset;
	struct ext4_super_block * es;
	struct block_device *bdev;

	bdev = ext4_blkdev_get(j_dev);
	if (bdev == NULL)
		return NULL;

	if (bd_claim(bdev, sb)) {
		printk(KERN_ERR
			"EXT4: failed to claim external journal device.\n");
		blkdev_put(bdev);
		return NULL;
	}

	blocksize = sb->s_blocksize;
	hblock = bdev_hardsect_size(bdev);
	if (blocksize < hblock) {
		printk(KERN_ERR
			"EXT4-fs: blocksize too small for journal device.\n");
		goto out_bdev;
	}

	sb_block = EXT4_MIN_BLOCK_SIZE / blocksize;
	offset = EXT4_MIN_BLOCK_SIZE % blocksize;
	set_blocksize(bdev, blocksize);
	if (!(bh = __bread(bdev, sb_block, blocksize))) {
		printk(KERN_ERR "EXT4-fs: couldn't read superblock of "
		       "external journal\n");
		goto out_bdev;
	}

	es = (struct ext4_super_block *) (((char *)bh->b_data) + offset);
	if ((le16_to_cpu(es->s_magic) != EXT4_SUPER_MAGIC) ||
	    !(le32_to_cpu(es->s_feature_incompat) &
	      EXT4_FEATURE_INCOMPAT_JOURNAL_DEV)) {
		printk(KERN_ERR "EXT4-fs: external journal has "
					"bad superblock\n");
		brelse(bh);
		goto out_bdev;
	}

	if (memcmp(EXT4_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
		printk(KERN_ERR "EXT4-fs: journal UUID does not match\n");
		brelse(bh);
		goto out_bdev;
	}

	len = ext4_blocks_count(es);
	start = sb_block + 1;
	brelse(bh);	/* we're done with the superblock */

	journal = jbd2_journal_init_dev(bdev, sb->s_bdev,
					start, len, blocksize);
	if (!journal) {
		printk(KERN_ERR "EXT4-fs: failed to create device journal\n");
		goto out_bdev;
	}
	journal->j_private = sb;
	ll_rw_block(READ, 1, &journal->j_sb_buffer);
	wait_on_buffer(journal->j_sb_buffer);
	if (!buffer_uptodate(journal->j_sb_buffer)) {
		printk(KERN_ERR "EXT4-fs: I/O error on journal device\n");
		goto out_journal;
	}
	if (be32_to_cpu(journal->j_superblock->s_nr_users) != 1) {
		printk(KERN_ERR "EXT4-fs: External journal has more than one "
					"user (unsupported) - %d\n",
			be32_to_cpu(journal->j_superblock->s_nr_users));
		goto out_journal;
	}
	EXT4_SB(sb)->journal_bdev = bdev;
	ext4_init_journal_params(sb, journal);
	return journal;
out_journal:
	jbd2_journal_destroy(journal);
out_bdev:
	ext4_blkdev_put(bdev);
	return NULL;
}

static int ext4_load_journal(struct super_block *sb,
			     struct ext4_super_block *es,
			     unsigned long journal_devnum)
{
	journal_t *journal;
	unsigned int journal_inum = le32_to_cpu(es->s_journal_inum);
	dev_t journal_dev;
	int err = 0;
	int really_read_only;

	if (journal_devnum &&
	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
		printk(KERN_INFO "EXT4-fs: external journal device major/minor "
			"numbers have changed\n");
		journal_dev = new_decode_dev(journal_devnum);
	} else
		journal_dev = new_decode_d