xattr.c

linux 内核源代码

{
	handle_t *handle;
	int error, retries = 0;

retry:
	handle = ext4_journal_start(inode, EXT4_DATA_TRANS_BLOCKS(inode->i_sb));
	if (IS_ERR(handle)) {
		error = PTR_ERR(handle);
	} else {
		int error2;

		error = ext4_xattr_set_handle(handle, inode, name_index, name,
					      value, value_len, flags);
		error2 = ext4_journal_stop(handle);
		if (error == -ENOSPC &&
		    ext4_should_retry_alloc(inode->i_sb, &retries))
			goto retry;
		if (error == 0)
			error = error2;
	}

	return error;
}

/*
 * Shift the EA entries in the inode to create space for the increased
 * i_extra_isize.
 */
static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry,
				     int value_offs_shift, void *to,
				     void *from, size_t n, int blocksize)
{
	struct ext4_xattr_entry *last = entry;
	int new_offs;

	/* Adjust the value offsets of the entries */
	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
		if (!last->e_value_block && last->e_value_size) {
			new_offs = le16_to_cpu(last->e_value_offs) +
							value_offs_shift;
			BUG_ON(new_offs + le32_to_cpu(last->e_value_size)
				 > blocksize);
			last->e_value_offs = cpu_to_le16(new_offs);
		}
	}
	/* Shift the entries by n bytes */
	memmove(to, from, n);
}

/*
 * Expand an inode by new_extra_isize bytes when EAs are present.
 * Returns 0 on success or negative error number on failure.
 */
int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
			       struct ext4_inode *raw_inode, handle_t *handle)
{
	struct ext4_xattr_ibody_header *header;
	struct ext4_xattr_entry *entry, *last, *first;
	struct buffer_head *bh = NULL;
	struct ext4_xattr_ibody_find *is = NULL;
	struct ext4_xattr_block_find *bs = NULL;
	char *buffer = NULL, *b_entry_name = NULL;
	size_t min_offs, free;
	int total_ino, total_blk;
	void *base, *start, *end;
	int extra_isize = 0, error = 0, tried_min_extra_isize = 0;
	int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);

	down_write(&EXT4_I(inode)->xattr_sem);
retry:
	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) {
		up_write(&EXT4_I(inode)->xattr_sem);
		return 0;
	}

	header = IHDR(inode, raw_inode);
	entry = IFIRST(header);

	/*
	 * Check if enough free space is available in the inode to shift the
	 * entries ahead by new_extra_isize.
	 */

	base = start = entry;
	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
	min_offs = end - base;
	last = entry;
	total_ino = sizeof(struct ext4_xattr_ibody_header);

	free = ext4_xattr_free_space(last, &min_offs, base, &total_ino);
	if (free >= new_extra_isize) {
		entry = IFIRST(header);
		ext4_xattr_shift_entries(entry,	EXT4_I(inode)->i_extra_isize
				- new_extra_isize, (void *)raw_inode +
				EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize,
				(void *)header, total_ino,
				inode->i_sb->s_blocksize);
		EXT4_I(inode)->i_extra_isize = new_extra_isize;
		error = 0;
		goto cleanup;
	}

	/*
	 * Enough free space isn't available in the inode, check if
	 * EA block can hold new_extra_isize bytes.
	 */
	if (EXT4_I(inode)->i_file_acl) {
		bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
		error = -EIO;
		if (!bh)
			goto cleanup;
		if (ext4_xattr_check_block(bh)) {
			ext4_error(inode->i_sb, __FUNCTION__,
				"inode %lu: bad block %llu", inode->i_ino,
				EXT4_I(inode)->i_file_acl);
			error = -EIO;
			goto cleanup;
		}
		base = BHDR(bh);
		first = BFIRST(bh);
		end = bh->b_data + bh->b_size;
		min_offs = end - base;
		free = ext4_xattr_free_space(first, &min_offs, base,
					     &total_blk);
		if (free < new_extra_isize) {
			if (!tried_min_extra_isize && s_min_extra_isize) {
				tried_min_extra_isize++;
				new_extra_isize = s_min_extra_isize;
				brelse(bh);
				goto retry;
			}
			error = -1;
			goto cleanup;
		}
	} else {
		free = inode->i_sb->s_blocksize;
	}

	while (new_extra_isize > 0) {
		size_t offs, size, entry_size;
		struct ext4_xattr_entry *small_entry = NULL;
		struct ext4_xattr_info i = {
			.value = NULL,
			.value_len = 0,
		};
		unsigned int total_size;  /* EA entry size + value size */
		unsigned int shift_bytes; /* No. of bytes to shift EAs by? */
		unsigned int min_total_size = ~0U;

		is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
		bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS);
		if (!is || !bs) {
			error = -ENOMEM;
			goto cleanup;
		}

		is->s.not_found = -ENODATA;
		bs->s.not_found = -ENODATA;
		is->iloc.bh = NULL;
		bs->bh = NULL;

		last = IFIRST(header);
		/* Find the entry best suited to be pushed into EA block */
		entry = NULL;
		for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
			total_size =
			EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
					EXT4_XATTR_LEN(last->e_name_len);
			if (total_size <= free && total_size < min_total_size) {
				if (total_size < new_extra_isize) {
					small_entry = last;
				} else {
					entry = last;
					min_total_size = total_size;
				}
			}
		}

		if (entry == NULL) {
			if (small_entry) {
				entry = small_entry;
			} else {
				if (!tried_min_extra_isize &&
				    s_min_extra_isize) {
					tried_min_extra_isize++;
					new_extra_isize = s_min_extra_isize;
					goto retry;
				}
				error = -1;
				goto cleanup;
			}
		}
		offs = le16_to_cpu(entry->e_value_offs);
		size = le32_to_cpu(entry->e_value_size);
		entry_size = EXT4_XATTR_LEN(entry->e_name_len);
		i.name_index = entry->e_name_index,
		buffer = kmalloc(EXT4_XATTR_SIZE(size), GFP_NOFS);
		b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS);
		if (!buffer || !b_entry_name) {
			error = -ENOMEM;
			goto cleanup;
		}
		/* Save the entry name and the entry value */
		memcpy(buffer, (void *)IFIRST(header) + offs,
		       EXT4_XATTR_SIZE(size));
		memcpy(b_entry_name, entry->e_name, entry->e_name_len);
		b_entry_name[entry->e_name_len] = '\0';
		i.name = b_entry_name;

		error = ext4_get_inode_loc(inode, &is->iloc);
		if (error)
			goto cleanup;

		error = ext4_xattr_ibody_find(inode, &i, is);
		if (error)
			goto cleanup;

		/* Remove the chosen entry from the inode */
		error = ext4_xattr_ibody_set(handle, inode, &i, is);

		entry = IFIRST(header);
		if (entry_size + EXT4_XATTR_SIZE(size) >= new_extra_isize)
			shift_bytes = new_extra_isize;
		else
			shift_bytes = entry_size + size;
		/* Adjust the offsets and shift the remaining entries ahead */
		ext4_xattr_shift_entries(entry, EXT4_I(inode)->i_extra_isize -
			shift_bytes, (void *)raw_inode +
			EXT4_GOOD_OLD_INODE_SIZE + extra_isize + shift_bytes,
			(void *)header, total_ino - entry_size,
			inode->i_sb->s_blocksize);

		extra_isize += shift_bytes;
		new_extra_isize -= shift_bytes;
		EXT4_I(inode)->i_extra_isize = extra_isize;

		i.name = b_entry_name;
		i.value = buffer;
		i.value_len = size;
		error = ext4_xattr_block_find(inode, &i, bs);
		if (error)
			goto cleanup;

		/* Add entry which was removed from the inode into the block */
		error = ext4_xattr_block_set(handle, inode, &i, bs);
		if (error)
			goto cleanup;
		kfree(b_entry_name);
		kfree(buffer);
		brelse(is->iloc.bh);
		kfree(is);
		kfree(bs);
	}
	brelse(bh);
	up_write(&EXT4_I(inode)->xattr_sem);
	return 0;

cleanup:
	kfree(b_entry_name);
	kfree(buffer);
	if (is)
		brelse(is->iloc.bh);
	kfree(is);
	kfree(bs);
	brelse(bh);
	up_write(&EXT4_I(inode)->xattr_sem);
	return error;
}



/*
 * ext4_xattr_delete_inode()
 *
 * Free extended attribute resources associated with this inode. This
 * is called immediately before an inode is freed. We have exclusive
 * access to the inode.
 */
void
ext4_xattr_delete_inode(handle_t *handle, struct inode *inode)
{
	struct buffer_head *bh = NULL;

	if (!EXT4_I(inode)->i_file_acl)
		goto cleanup;
	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
	if (!bh) {
		ext4_error(inode->i_sb, __FUNCTION__,
			"inode %lu: block %llu read error", inode->i_ino,
			EXT4_I(inode)->i_file_acl);
		goto cleanup;
	}
	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
	    BHDR(bh)->h_blocks != cpu_to_le32(1)) {
		ext4_error(inode->i_sb, __FUNCTION__,
			"inode %lu: bad block %llu", inode->i_ino,
			EXT4_I(inode)->i_file_acl);
		goto cleanup;
	}
	ext4_xattr_release_block(handle, inode, bh);
	EXT4_I(inode)->i_file_acl = 0;

cleanup:
	brelse(bh);
}

/*
 * ext4_xattr_put_super()
 *
 * This is called when a file system is unmounted.
 */
void
ext4_xattr_put_super(struct super_block *sb)
{
	mb_cache_shrink(sb->s_bdev);
}

/*
 * ext4_xattr_cache_insert()
 *
 * Create a new entry in the extended attribute cache, and insert
 * it unless such an entry is already in the cache.
 *
 * Returns 0, or a negative error number on failure.
 */
static void
ext4_xattr_cache_insert(struct buffer_head *bh)
{
	__u32 hash = le32_to_cpu(BHDR(bh)->h_hash);
	struct mb_cache_entry *ce;
	int error;

	ce = mb_cache_entry_alloc(ext4_xattr_cache);
	if (!ce) {
		ea_bdebug(bh, "out of memory");
		return;
	}
	error = mb_cache_entry_insert(ce, bh->b_bdev, bh->b_blocknr, &hash);
	if (error) {
		mb_cache_entry_free(ce);
		if (error == -EBUSY) {
			ea_bdebug(bh, "already in cache");
			error = 0;
		}
	} else {
		ea_bdebug(bh, "inserting [%x]", (int)hash);
		mb_cache_entry_release(ce);
	}
}

/*
 * ext4_xattr_cmp()
 *
 * Compare two extended attribute blocks for equality.
 *
 * Returns 0 if the blocks are equal, 1 if they differ, and
 * a negative error number on errors.
 */
static int
ext4_xattr_cmp(struct ext4_xattr_header *header1,
	       struct ext4_xattr_header *header2)
{
	struct ext4_xattr_entry *entry1, *entry2;

	entry1 = ENTRY(header1+1);
	entry2 = ENTRY(header2+1);
	while (!IS_LAST_ENTRY(entry1)) {
		if (IS_LAST_ENTRY(entry2))
			return 1;
		if (entry1->e_hash != entry2->e_hash ||
		    entry1->e_name_index != entry2->e_name_index ||
		    entry1->e_name_len != entry2->e_name_len ||
		    entry1->e_value_size != entry2->e_value_size ||
		    memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len))
			return 1;
		if (entry1->e_value_block != 0 || entry2->e_value_block != 0)
			return -EIO;
		if (memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs),
			   (char *)header2 + le16_to_cpu(entry2->e_value_offs),
			   le32_to_cpu(entry1->e_value_size)))
			return 1;

		entry1 = EXT4_XATTR_NEXT(entry1);
		entry2 = EXT4_XATTR_NEXT(entry2);
	}
	if (!IS_LAST_ENTRY(entry2))
		return 1;
	return 0;
}

/*
 * ext4_xattr_cache_find()
 *
 * Find an identical extended attribute block.
 *
 * Returns a pointer to the block found, or NULL if such a block was
 * not found or an error occurred.
 */
static struct buffer_head *
ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
		      struct mb_cache_entry **pce)
{
	__u32 hash = le32_to_cpu(header->h_hash);
	struct mb_cache_entry *ce;

	if (!header->h_hash)
		return NULL;  /* never share */
	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
again:
	ce = mb_cache_entry_find_first(ext4_xattr_cache, 0,
				       inode->i_sb->s_bdev, hash);
	while (ce) {
		struct buffer_head *bh;

		if (IS_ERR(ce)) {
			if (PTR_ERR(ce) == -EAGAIN)
				goto again;
			break;
		}
		bh = sb_bread(inode->i_sb, ce->e_block);
		if (!bh) {
			ext4_error(inode->i_sb, __FUNCTION__,
				"inode %lu: block %lu read error",
				inode->i_ino, (unsigned long) ce->e_block);
		} else if (le32_to_cpu(BHDR(bh)->h_refcount) >=
				EXT4_XATTR_REFCOUNT_MAX) {
			ea_idebug(inode, "block %lu refcount %d>=%d",
				  (unsigned long) ce->e_block,
				  le32_to_cpu(BHDR(bh)->h_refcount),
					  EXT4_XATTR_REFCOUNT_MAX);
		} else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) {
			*pce = ce;
			return bh;
		}
		brelse(bh);
		ce = mb_cache_entry_find_next(ce, 0, inode->i_sb->s_bdev, hash);
	}
	return NULL;
}

#define NAME_HASH_SHIFT 5
#define VALUE_HASH_SHIFT 16

/*
 * ext4_xattr_hash_entry()
 *
 * Compute the hash of an extended attribute.
 */
static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
					 struct ext4_xattr_entry *entry)
{
	__u32 hash = 0;
	char *name = entry->e_name;
	int n;

	for (n=0; n < entry->e_name_len; n++) {
		hash = (hash << NAME_HASH_SHIFT) ^
		       (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
		       *name++;
	}

	if (entry->e_value_block == 0 && entry->e_value_size != 0) {
		__le32 *value = (__le32 *)((char *)header +
			le16_to_cpu(entry->e_value_offs));
		for (n = (le32_to_cpu(entry->e_value_size) +
		     EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) {
			hash = (hash << VALUE_HASH_SHIFT) ^
			       (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
			       le32_to_cpu(*value++);
		}
	}
	entry->e_hash = cpu_to_le32(hash);
}

#undef NAME_HASH_SHIFT
#undef VALUE_HASH_SHIFT

#define BLOCK_HASH_SHIFT 16

/*
 * ext4_xattr_rehash()
 *
 * Re-compute the extended attribute hash value after an entry has changed.
 */
static void ext4_xattr_rehash(struct ext4_xattr_header *header,
			      struct ext4_xattr_entry *entry)
{
	struct ext4_xattr_entry *here;
	__u32 hash = 0;

	ext4_xattr_hash_entry(header, entry);
	here = ENTRY(header+1);
	while (!IS_LAST_ENTRY(here)) {
		if (!here->e_hash) {
			/* Block is not shared if an entry's hash value == 0 */
			hash = 0;
			break;
		}
		hash = (hash << BLOCK_HASH_SHIFT) ^
		       (hash >> (8*sizeof(hash) - BLOCK_HASH_SHIFT)) ^
		       le32_to_cpu(here->e_hash);
		here = EXT4_XATTR_NEXT(here);
	}
	header->h_hash = cpu_to_le32(hash);
}

#undef BLOCK_HASH_SHIFT

int __init
init_ext4_xattr(void)
{
	ext4_xattr_cache = mb_cache_create("ext4_xattr", NULL,
		sizeof(struct mb_cache_entry) +
		sizeof(((struct mb_cache_entry *) 0)->e_indexes[0]), 1, 6);
	if (!ext4_xattr_cache)
		return -ENOMEM;
	return 0;
}

void
exit_ext4_xattr(void)
{
	if (ext4_xattr_cache)
		mb_cache_destroy(ext4_xattr_cache);
	ext4_xattr_cache = NULL;
}