super.c

linux 内核源代码

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

	case EXT3_MOUNT_ORDERED_DATA:
	case EXT3_MOUNT_WRITEBACK_DATA:
		if (!journal_check_available_features
		    (sbi->s_journal, 0, 0, JFS_FEATURE_INCOMPAT_REVOKE)) {
			printk(KERN_ERR "EXT3-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) == EXT3_MOUNT_WRITEBACK_DATA)) {
			printk(KERN_WARNING "EXT3-fs: Ignoring nobh option - "
				"its supported only with writeback mode\n");
			clear_opt(sbi->s_mount_opt, NOBH);
		}
	}
	/*
	 * The journal_load will have done any necessary log recovery,
	 * so we can safely mount the rest of the filesystem now.
	 */

	root = iget(sb, EXT3_ROOT_INO);
	sb->s_root = d_alloc_root(root);
	if (!sb->s_root) {
		printk(KERN_ERR "EXT3-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 "EXT3-fs: corrupt root inode, run e2fsck\n");
		goto failed_mount4;
	}

	ext3_setup_super (sb, es, sb->s_flags & MS_RDONLY);
	/*
	 * 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.
	 */
	EXT3_SB(sb)->s_mount_state |= EXT3_ORPHAN_FS;
	ext3_orphan_cleanup(sb, es);
	EXT3_SB(sb)->s_mount_state &= ~EXT3_ORPHAN_FS;
	if (needs_recovery)
		printk (KERN_INFO "EXT3-fs: recovery complete.\n");
	ext3_mark_recovery_complete(sb, es);
	printk (KERN_INFO "EXT3-fs: mounted filesystem with %s data mode.\n",
		test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA ? "journal":
		test_opt(sb,DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA ? "ordered":
		"writeback");

	lock_kernel();
	return 0;

cantfind_ext3:
	if (!silent)
		printk(KERN_ERR "VFS: Can't find ext3 filesystem on dev %s.\n",
		       sb->s_id);
	goto failed_mount;

failed_mount4:
	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
	ext3_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 ext3_init_journal_params(struct super_block *sb, journal_t *journal)
{
	struct ext3_sb_info *sbi = EXT3_SB(sb);

	if (sbi->s_commit_interval)
		journal->j_commit_interval = sbi->s_commit_interval;
	/* We could also set up an ext3-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 |= JFS_BARRIER;
	else
		journal->j_flags &= ~JFS_BARRIER;
	spin_unlock(&journal->j_state_lock);
}

static journal_t *ext3_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 "EXT3-fs: no journal found.\n");
		return NULL;
	}
	if (!journal_inode->i_nlink) {
		make_bad_inode(journal_inode);
		iput(journal_inode);
		printk(KERN_ERR "EXT3-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 "EXT3-fs: invalid journal inode.\n");
		iput(journal_inode);
		return NULL;
	}

	journal = journal_init_inode(journal_inode);
	if (!journal) {
		printk(KERN_ERR "EXT3-fs: Could not load journal inode\n");
		iput(journal_inode);
		return NULL;
	}
	journal->j_private = sb;
	ext3_init_journal_params(sb, journal);
	return journal;
}

static journal_t *ext3_get_dev_journal(struct super_block *sb,
				       dev_t j_dev)
{
	struct buffer_head * bh;
	journal_t *journal;
	ext3_fsblk_t start;
	ext3_fsblk_t len;
	int hblock, blocksize;
	ext3_fsblk_t sb_block;
	unsigned long offset;
	struct ext3_super_block * es;
	struct block_device *bdev;

	bdev = ext3_blkdev_get(j_dev);
	if (bdev == NULL)
		return NULL;

	if (bd_claim(bdev, sb)) {
		printk(KERN_ERR
		        "EXT3: 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
			"EXT3-fs: blocksize too small for journal device.\n");
		goto out_bdev;
	}

	sb_block = EXT3_MIN_BLOCK_SIZE / blocksize;
	offset = EXT3_MIN_BLOCK_SIZE % blocksize;
	set_blocksize(bdev, blocksize);
	if (!(bh = __bread(bdev, sb_block, blocksize))) {
		printk(KERN_ERR "EXT3-fs: couldn't read superblock of "
		       "external journal\n");
		goto out_bdev;
	}

	es = (struct ext3_super_block *) (((char *)bh->b_data) + offset);
	if ((le16_to_cpu(es->s_magic) != EXT3_SUPER_MAGIC) ||
	    !(le32_to_cpu(es->s_feature_incompat) &
	      EXT3_FEATURE_INCOMPAT_JOURNAL_DEV)) {
		printk(KERN_ERR "EXT3-fs: external journal has "
					"bad superblock\n");
		brelse(bh);
		goto out_bdev;
	}

	if (memcmp(EXT3_SB(sb)->s_es->s_journal_uuid, es->s_uuid, 16)) {
		printk(KERN_ERR "EXT3-fs: journal UUID does not match\n");
		brelse(bh);
		goto out_bdev;
	}

	len = le32_to_cpu(es->s_blocks_count);
	start = sb_block + 1;
	brelse(bh);	/* we're done with the superblock */

	journal = journal_init_dev(bdev, sb->s_bdev,
					start, len, blocksize);
	if (!journal) {
		printk(KERN_ERR "EXT3-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 "EXT3-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 "EXT3-fs: External journal has more than one "
					"user (unsupported) - %d\n",
			be32_to_cpu(journal->j_superblock->s_nr_users));
		goto out_journal;
	}
	EXT3_SB(sb)->journal_bdev = bdev;
	ext3_init_journal_params(sb, journal);
	return journal;
out_journal:
	journal_destroy(journal);
out_bdev:
	ext3_blkdev_put(bdev);
	return NULL;
}

static int ext3_load_journal(struct super_block *sb,
			     struct ext3_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 "EXT3-fs: external journal device major/minor "
			"numbers have changed\n");
		journal_dev = new_decode_dev(journal_devnum);
	} else
		journal_dev = new_decode_dev(le32_to_cpu(es->s_journal_dev));

	really_read_only = bdev_read_only(sb->s_bdev);

	/*
	 * Are we loading a blank journal or performing recovery after a
	 * crash?  For recovery, we need to check in advance whether we
	 * can get read-write access to the device.
	 */

	if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER)) {
		if (sb->s_flags & MS_RDONLY) {
			printk(KERN_INFO "EXT3-fs: INFO: recovery "
					"required on readonly filesystem.\n");
			if (really_read_only) {
				printk(KERN_ERR "EXT3-fs: write access "
					"unavailable, cannot proceed.\n");
				return -EROFS;
			}
			printk (KERN_INFO "EXT3-fs: write access will "
					"be enabled during recovery.\n");
		}
	}

	if (journal_inum && journal_dev) {
		printk(KERN_ERR "EXT3-fs: filesystem has both journal "
		       "and inode journals!\n");
		return -EINVAL;
	}

	if (journal_inum) {
		if (!(journal = ext3_get_journal(sb, journal_inum)))
			return -EINVAL;
	} else {
		if (!(journal = ext3_get_dev_journal(sb, journal_dev)))
			return -EINVAL;
	}

	if (!really_read_only && test_opt(sb, UPDATE_JOURNAL)) {
		err = journal_update_format(journal);
		if (err)  {
			printk(KERN_ERR "EXT3-fs: error updating journal.\n");
			journal_destroy(journal);
			return err;
		}
	}

	if (!EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER))
		err = journal_wipe(journal, !really_read_only);
	if (!err)
		err = journal_load(journal);

	if (err) {
		printk(KERN_ERR "EXT3-fs: error loading journal.\n");
		journal_destroy(journal);
		return err;
	}

	EXT3_SB(sb)->s_journal = journal;
	ext3_clear_journal_err(sb, es);

	if (journal_devnum &&
	    journal_devnum != le32_to_cpu(es->s_journal_dev)) {
		es->s_journal_dev = cpu_to_le32(journal_devnum);
		sb->s_dirt = 1;

		/* Make sure we flush the recovery flag to disk. */
		ext3_commit_super(sb, es, 1);
	}

	return 0;
}

static int ext3_create_journal(struct super_block * sb,
			       struct ext3_super_block * es,
			       unsigned int journal_inum)
{
	journal_t *journal;
	int err;

	if (sb->s_flags & MS_RDONLY) {
		printk(KERN_ERR "EXT3-fs: readonly filesystem when trying to "
				"create journal.\n");
		return -EROFS;
	}

	journal = ext3_get_journal(sb, journal_inum);
	if (!journal)
		return -EINVAL;

	printk(KERN_INFO "EXT3-fs: creating new journal on inode %u\n",
	       journal_inum);

	err = journal_create(journal);
	if (err) {
		printk(KERN_ERR "EXT3-fs: error creating journal.\n");
		journal_destroy(journal);
		return -EIO;
	}

	EXT3_SB(sb)->s_journal = journal;

	ext3_update_dynamic_rev(sb);
	EXT3_SET_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
	EXT3_SET_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL);

	es->s_journal_inum = cpu_to_le32(journal_inum);
	sb->s_dirt = 1;

	/* Make sure we flush the recovery flag to disk. */
	ext3_commit_super(sb, es, 1);

	return 0;
}

static void ext3_commit_super (struct super_block * sb,
			       struct ext3_super_block * es,
			       int sync)
{
	struct buffer_head *sbh = EXT3_SB(sb)->s_sbh;

	if (!sbh)
		return;
	es->s_wtime = cpu_to_le32(get_seconds());
	es->s_free_blocks_count = cpu_to_le32(ext3_count_free_blocks(sb));
	es->s_free_inodes_count = cpu_to_le32(ext3_count_free_inodes(sb));
	BUFFER_TRACE(sbh, "marking dirty");
	mark_buffer_dirty(sbh);
	if (sync)
		sync_dirty_buffer(sbh);
}


/*
 * Have we just finished recovery?  If so, and if we are mounting (or
 * remounting) the filesystem readonly, then we will end up with a
 * consistent fs on disk.  Record that fact.
 */
static void ext3_mark_recovery_complete(struct super_block * sb,
					struct ext3_super_block * es)
{
	journal_t *journal = EXT3_SB(sb)->s_journal;

	journal_lock_updates(journal);
	journal_flush(journal);
	lock_super(sb);
	if (EXT3_HAS_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER) &&
	    sb->s_flags & MS_RDONLY) {
		EXT3_CLEAR_INCOMPAT_FEATURE(sb, EXT3_FEATURE_INCOMPAT_RECOVER);
		sb->s_dirt = 0;
		ext3_commit_super(sb, es, 1);
	}
	unlock_super(sb);
	journal_unlock_updates(journal);
}

/*
 * If we are mounting (or read-write remounting) a filesystem whose journal
 * has recorded an error from a previous lifetime, move that error to the
 * main filesystem now.
 */
static void ext3_clear_journal_err(struct super_block * sb,
				   struct ext3_super_block * es)
{
	journal_t *journal;
	int j_errno;
	const char *errstr;

	journal = EXT3_SB(sb)->s_journal;

	/*
	 * Now check for any error status which may have been recorded in the
	 * journal by a prior ext3_error() or ext3_abort()
	 */

	j_errno = journal_errno(journal);
	if (j_errno) {
		char nbuf[16];

		errstr = ext3_decode_error(sb, j_errno, nbuf);
		ext3_warning(sb, __FUNCTION__, "Filesystem error recorded "
			     "from previous mount: %s", errstr);
		ext3_warning(sb, __FUNCTION__, "Marking fs in need of "
			     "filesystem check.");

		EXT3_SB(sb)->s_mount_state