ext4: Expand extra_inodes space per the s_{want,min}_extra_isize fields

We need to make sure that existing ext3 filesystems can also avail the
new fields that have been added to the ext4 inode. We use
s_want_extra_isize and s_min_extra_isize to decide by how much we should
expand the inode. If EXT4_FEATURE_RO_COMPAT_EXTRA_ISIZE feature is set
then we expand the inode by max(s_want_extra_isize, s_min_extra_isize ,
sizeof(ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE) bytes. Actually it is
still an open question about whether users should be able to set
s_*_extra_isize smaller than the known fields or not.

This patch also adds the functionality to expand inodes to include the
newly added fields. We start by trying to expand by s_want_extra_isize
bytes and if its fails we try to expand by s_min_extra_isize bytes. This
is done by changing the i_extra_isize if enough space is available in
the inode and no EAs are present. If EAs are present and there is enough
space in the inode then the EAs in the inode are shifted to make space.
If enough space is not available in the inode due to the EAs then 1 or
more EAs are shifted to the external EA block. In the worst case when
even the external EA block does not have enough space we inform the user
that some EA would need to be deleted or s_min_extra_isize would have to
be reduced.

Signed-off-by: Andreas Dilger <adilger@clusterfs.com>
Signed-off-by: Kalpak Shah <kalpak@clusterfs.com>
Signed-off-by: Mingming Cao <cmm@us.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

fs/ext4/inode.c

@@ -3105,6 +3105,39 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 	return err;
 }
 
+/*
+ * Expand an inode by new_extra_isize bytes.
+ * Returns 0 on success or negative error number on failure.
+ */
+int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize,
+			struct ext4_iloc iloc, handle_t *handle)
+{
+	struct ext4_inode *raw_inode;
+	struct ext4_xattr_ibody_header *header;
+	struct ext4_xattr_entry *entry;
+
+	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
+		return 0;
+
+	raw_inode = ext4_raw_inode(&iloc);
+
+	header = IHDR(inode, raw_inode);
+	entry = IFIRST(header);
+
+	/* No extended attributes present */
+	if (!(EXT4_I(inode)->i_state & EXT4_STATE_XATTR) ||
+		header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
+		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
+			new_extra_isize);
+		EXT4_I(inode)->i_extra_isize = new_extra_isize;
+		return 0;
+	}
+
+	/* try to expand with EAs present */
+	return ext4_expand_extra_isize_ea(inode, new_extra_isize,
+					  raw_inode, handle);
+}
+
 /*
  * What we do here is to mark the in-core inode as clean with respect to inode
  * dirtiness (it may still be data-dirty).
@@ -3129,10 +3162,38 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
 {
 	struct ext4_iloc iloc;
-	int err;
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	static unsigned int mnt_count;
+	int err, ret;
 
 	might_sleep();
 	err = ext4_reserve_inode_write(handle, inode, &iloc);
+	if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize &&
+	    !(EXT4_I(inode)->i_state & EXT4_STATE_NO_EXPAND)) {
+		/*
+		 * We need extra buffer credits since we may write into EA block
+		 * with this same handle. If journal_extend fails, then it will
+		 * only result in a minor loss of functionality for that inode.
+		 * If this is felt to be critical, then e2fsck should be run to
+		 * force a large enough s_min_extra_isize.
+		 */
+		if ((jbd2_journal_extend(handle,
+			     EXT4_DATA_TRANS_BLOCKS(inode->i_sb))) == 0) {
+			ret = ext4_expand_extra_isize(inode,
+						      sbi->s_want_extra_isize,
+						      iloc, handle);
+			if (ret) {
+				EXT4_I(inode)->i_state |= EXT4_STATE_NO_EXPAND;
+				if (mnt_count != sbi->s_es->s_mnt_count) {
+					ext4_warning(inode->i_sb, __FUNCTION__,
+					"Unable to expand inode %lu. Delete"
+					" some EAs or run e2fsck.",
+					inode->i_ino);
+					mnt_count = sbi->s_es->s_mnt_count;
+				}
+			}
+		}
+	}
 	if (!err)
 		err = ext4_mark_iloc_dirty(handle, inode, &iloc);
 	return err;

fs/ext4/xattr.c

@@ -66,13 +66,6 @@
 #define BFIRST(bh) ENTRY(BHDR(bh)+1)
 #define IS_LAST_ENTRY(entry) (*(__u32 *)(entry) == 0)
 
-#define IHDR(inode, raw_inode) \
-	((struct ext4_xattr_ibody_header *) \
-		((void *)raw_inode + \
-		 EXT4_GOOD_OLD_INODE_SIZE + \
-		 EXT4_I(inode)->i_extra_isize))
-#define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1))
-
 #ifdef EXT4_XATTR_DEBUG
 # define ea_idebug(inode, f...) do { \
 		printk(KERN_DEBUG "inode %s:%lu: ", \
@@ -508,6 +501,24 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 	return;
 }
 
+/*
+ * Find the available free space for EAs. This also returns the total number of
+ * bytes used by EA entries.
+ */
+static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last,
+				    size_t *min_offs, void *base, int *total)
+{
+	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+		*total += EXT4_XATTR_LEN(last->e_name_len);
+		if (!last->e_value_block && last->e_value_size) {
+			size_t offs = le16_to_cpu(last->e_value_offs);
+			if (offs < *min_offs)
+				*min_offs = offs;
+		}
+	}
+	return (*min_offs - ((void *)last - base) - sizeof(__u32));
+}
+
 struct ext4_xattr_info {
 	int name_index;
 	const char *name;
@@ -1014,6 +1025,8 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 	if (!error) {
 		ext4_xattr_update_super_block(handle, inode->i_sb);
 		inode->i_ctime = ext4_current_time(inode);
+		if (!value)
+			EXT4_I(inode)->i_state &= ~EXT4_STATE_NO_EXPAND;
 		error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
 		/*
 		 * The bh is consumed by ext4_mark_iloc_dirty, even with
@@ -1066,6 +1079,253 @@ ext4_xattr_set(struct inode *inode, int name_index, const char *name,
 	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 = 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 = cpu_to_le32(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()
  *

fs/ext4/xattr.h

@@ -56,6 +56,13 @@ struct ext4_xattr_entry {
 #define EXT4_XATTR_SIZE(size) \
 	(((size) + EXT4_XATTR_ROUND) & ~EXT4_XATTR_ROUND)
 
+#define IHDR(inode, raw_inode) \
+	((struct ext4_xattr_ibody_header *) \
+		((void *)raw_inode + \
+		EXT4_GOOD_OLD_INODE_SIZE + \
+		EXT4_I(inode)->i_extra_isize))
+#define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1))
+
 # ifdef CONFIG_EXT4DEV_FS_XATTR
 
 extern struct xattr_handler ext4_xattr_user_handler;
@@ -74,6 +81,9 @@ extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *,
 extern void ext4_xattr_delete_inode(handle_t *, struct inode *);
 extern void ext4_xattr_put_super(struct super_block *);
 
+extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
+			    struct ext4_inode *raw_inode, handle_t *handle);
+
 extern int init_ext4_xattr(void);
 extern void exit_ext4_xattr(void);
 
@@ -129,6 +139,13 @@ exit_ext4_xattr(void)
 {
 }
 
+static inline int
+ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
+			    struct ext4_inode *raw_inode, handle_t *handle)
+{
+	return -EOPNOTSUPP;
+}
+
 #define ext4_xattr_handlers	NULL
 
 # endif  /* CONFIG_EXT4DEV_FS_XATTR */

include/linux/ext4_fs.h

@@ -202,6 +202,7 @@ struct ext4_group_desc
 #define EXT4_STATE_JDATA		0x00000001 /* journaled data exists */
 #define EXT4_STATE_NEW			0x00000002 /* inode is newly created */
 #define EXT4_STATE_XATTR		0x00000004 /* has in-inode xattrs */
+#define EXT4_STATE_NO_EXPAND		0x00000008 /* No space for expansion */
 
 /* Used to pass group descriptor data when online resize is done */
 struct ext4_new_group_input {