super.c

嵌入式系统设计与实例开发源码

	loff_t res = EXT3_NDIR_BLOCKS;
	res += 1LL << (bits-2);
	res += 1LL << (2*(bits-2));
	res += 1LL << (3*(bits-2));
	res <<= bits;
	if (res > (512LL << 32) - (1 << bits))
		res = (512LL << 32) - (1 << bits);
	return res;
}

struct super_block * ext3_read_super (struct super_block * sb, void * data,
				      int silent)
{
	struct buffer_head * bh;
	struct ext3_super_block *es = 0;
	struct ext3_sb_info *sbi = EXT3_SB(sb);
	unsigned long sb_block = 1;
	unsigned long logic_sb_block = 1;
	unsigned long offset = 0;
	unsigned long journal_inum = 0;
	kdev_t dev = sb->s_dev;
	int blocksize;
	int hblock;
	int db_count;
	int i;
	int needs_recovery;

#ifdef CONFIG_JBD_DEBUG
	ext3_ro_after = 0;
#endif
	/*
	 * See what the current blocksize for the device is, and
	 * use that as the blocksize.  Otherwise (or if the blocksize
	 * is smaller than the default) use the default.
	 * This is important for devices that have a hardware
	 * sectorsize that is larger than the default.
	 */
	blocksize = EXT3_MIN_BLOCK_SIZE;
	hblock = get_hardsect_size(dev);
	if (blocksize < hblock)
		blocksize = hblock;

	sbi->s_mount_opt = 0;
	sbi->s_resuid = EXT3_DEF_RESUID;
	sbi->s_resgid = EXT3_DEF_RESGID;
	if (!parse_options ((char *) data, &sb_block, sbi, &journal_inum, 0)) {
		sb->s_dev = 0;
		goto out_fail;
	}

	sb->s_blocksize = blocksize;
	set_blocksize (dev, blocksize);

	/*
	 * 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;
	}

	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) {
		if (!silent)
			printk(KERN_ERR 
			       "VFS: Can't find ext3 filesystem on dev %s.\n",
			       bdevname(dev));
		goto failed_mount;
	}
	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.
	 */
	if ((i = EXT3_HAS_INCOMPAT_FEATURE(sb, ~EXT3_FEATURE_INCOMPAT_SUPP))) {
		printk(KERN_ERR "EXT3-fs: %s: couldn't mount because of "
		       "unsupported optional features (%x).\n",
		       bdevname(dev), i);
		goto failed_mount;
	}
	if (!(sb->s_flags & MS_RDONLY) &&
	    (i = EXT3_HAS_RO_COMPAT_FEATURE(sb, ~EXT3_FEATURE_RO_COMPAT_SUPP))){
		printk(KERN_ERR "EXT3-fs: %s: couldn't mount RDWR because of "
		       "unsupported optional features (%x).\n",
		       bdevname(dev), i);
		goto failed_mount;
	}
	sb->s_blocksize_bits = le32_to_cpu(es->s_log_block_size) + 10;
	sb->s_blocksize = 1 << sb->s_blocksize_bits;

	if (sb->s_blocksize < EXT3_MIN_BLOCK_SIZE ||
	    sb->s_blocksize > EXT3_MAX_BLOCK_SIZE) {
		printk(KERN_ERR 
		       "EXT3-fs: Unsupported filesystem blocksize %d on %s.\n",
		       blocksize, bdevname(dev));
		goto failed_mount;
	}

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

	if (sb->s_blocksize != blocksize) {
		blocksize = sb->s_blocksize;

		/*
		 * Make sure the blocksize for the filesystem is larger
		 * than the hardware sectorsize for the machine.
		 */
		if (sb->s_blocksize < hblock) {
			printk(KERN_ERR "EXT3-fs: blocksize %d too small for "
			       "device blocksize %d.\n", blocksize, hblock);
			goto failed_mount;
		}

		brelse (bh);
		set_blocksize (dev, sb->s_blocksize);
		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");
			return NULL;
		}
		es = (struct ext3_super_block *)(((char *)bh->b_data) + offset);
		sbi->s_es = es;
		if (es->s_magic != le16_to_cpu(EXT3_SUPER_MAGIC)) {
			printk (KERN_ERR 
				"EXT3-fs: Magic mismatch, very weird !\n");
			goto failed_mount;
		}
	}

	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) {
			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);
	sbi->s_inodes_per_block = blocksize / EXT3_INODE_SIZE(sb);
	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;
	if (sbi->s_resuid == EXT3_DEF_RESUID)
		sbi->s_resuid = le16_to_cpu(es->s_def_resuid);
	if (sbi->s_resgid == EXT3_DEF_RESGID)
		sbi->s_resgid = le16_to_cpu(es->s_def_resgid);
	sbi->s_mount_state = le16_to_cpu(es->s_state);
	sbi->s_addr_per_block_bits = log2(EXT3_ADDR_PER_BLOCK(sb));
	sbi->s_desc_per_block_bits = log2(EXT3_DESC_PER_BLOCK(sb));

	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;
	}

	sbi->s_groups_count = (le32_to_cpu(es->s_blocks_count) -
			       le32_to_cpu(es->s_first_data_block) +
			       EXT3_BLOCKS_PER_GROUP(sb) - 1) /
			      EXT3_BLOCKS_PER_GROUP(sb);
	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;
	}
	for (i = 0; i < db_count; i++) {
		sbi->s_group_desc[i] = sb_bread(sb, logic_sb_block + i + 1);
		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;
	}
	for (i = 0; i < EXT3_MAX_GROUP_LOADED; i++) {
		sbi->s_inode_bitmap_number[i] = 0;
		sbi->s_inode_bitmap[i] = NULL;
		sbi->s_block_bitmap_number[i] = 0;
		sbi->s_block_bitmap[i] = NULL;
	}
	sbi->s_loaded_inode_bitmaps = 0;
	sbi->s_loaded_block_bitmaps = 0;
	sbi->s_gdb_count = db_count;
	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
	/*
	 * set up enough so that it can read an inode
	 */
	sb->s_op = &ext3_sops;
	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */

	sb->s_root = 0;

	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))
			goto failed_mount2;
	} else if (journal_inum) {
		if (ext3_create_journal(sb, es, journal_inum))
			goto failed_mount2;
	} else {
		if (!silent)
			printk (KERN_ERR
				"ext3: No journal on filesystem on %s\n",
				bdevname(dev));
		goto failed_mount2;
	}

	/* 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 (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_mount3;
		}
	default:
		break;
	}

	/*
	 * The journal_load will have done any necessary log recovery,
	 * so we can safely mount the rest of the filesystem now.
	 */

	sb->s_root = d_alloc_root(iget(sb, EXT3_ROOT_INO));
	if (!sb->s_root || !S_ISDIR(sb->s_root->d_inode->i_mode) ||
	    !sb->s_root->d_inode->i_blocks || !sb->s_root->d_inode->i_size) {
		if (sb->s_root) {
			dput(sb->s_root);
			sb->s_root = NULL;
			printk(KERN_ERR
			       "EXT3-fs: corrupt root inode, run e2fsck\n");
		} else
			printk(KERN_ERR "EXT3-fs: get root inode failed\n");
		goto failed_mount3;
	}

	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;
	unlock_super(sb);	/* akpm: sigh */
	ext3_orphan_cleanup(sb, es);
	lock_super(sb);
	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");

	return sb;

failed_mount3:
	journal_destroy(sbi->s_journal);
failed_mount2:
	for (i = 0; i < db_count; i++)
		brelse(sbi->s_group_desc[i]);
	kfree(sbi->s_group_desc);
failed_mount:
	ext3_blkdev_remove(sbi);
	brelse(bh);
out_fail:
	return NULL;
}

static journal_t *ext3_get_journal(struct super_block *sb, 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 journal;
}

static journal_t *ext3_get_dev_journal(struct super_block *sb,
				       int dev)
{
	struct buffer_head * bh;
	journal_t *journal;
	int start;
	int len;
	int hblock, blocksize;
	unsigned long sb_block;
	unsigned long offset;
	kdev_t journal_dev = to_kdev_t(dev);
	struct ext3_super_block * es;
	struct block_device *bdev;

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

	blocksize = sb->s_blocksize;
	hblock = get_hardsect_size(journal_dev);
	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(dev, blocksize);
	if (!(bh = bread(dev, 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);