Merge tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/tytso/ext4

Pull ext4 fixes from Ted Ts'o:
 "Bug fixes and regressions for ext4, the most serious of which is a
  potential deadlock during directory renames that was introduced during
  the merge window discovered by a combination of syzbot and lockdep"

* tag 'ext4_for_linus_stable' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4:
  ext4: zero i_disksize when initializing the bootloader inode
  ext4: make sure fs error flag setted before clear journal error
  ext4: commit super block if fs record error when journal record without error
  ext4, jbd2: add an optimized bmap for the journal inode
  ext4: fix WARNING in ext4_update_inline_data
  ext4: move where set the MAY_INLINE_DATA flag is set
  ext4: Fix deadlock during directory rename
  ext4: Fix comment about the 64BIT feature
  docs: ext4: modify the group desc size to 64
  ext4: fix another off-by-one fsmap error on 1k block filesystems
  ext4: fix RENAME_WHITEOUT handling for inline directories
  ext4: make kobj_type structures constant
  ext4: fix cgroup writeback accounting with fs-layer encryption

Documentation/filesystems/ext4/blockgroup.rst

@@ -105,9 +105,9 @@ descriptors. Instead, the superblock and a single block group descriptor
 block is placed at the beginning of the first, second, and last block
 groups in a meta-block group. A meta-block group is a collection of
 block groups which can be described by a single block group descriptor
-block. Since the size of the block group descriptor structure is 32
-bytes, a meta-block group contains 32 block groups for filesystems with
-a 1KB block size, and 128 block groups for filesystems with a 4KB
+block. Since the size of the block group descriptor structure is 64
+bytes, a meta-block group contains 16 block groups for filesystems with
+a 1KB block size, and 64 block groups for filesystems with a 4KB
 blocksize. Filesystems can either be created using this new block group
 descriptor layout, or existing filesystems can be resized on-line, and
 the field s_first_meta_bg in the superblock will indicate the first

fs/ext4/ext4.h

@@ -1387,7 +1387,7 @@ struct ext4_super_block {
 	__le32	s_first_meta_bg;	/* First metablock block group */
 	__le32	s_mkfs_time;		/* When the filesystem was created */
 	__le32	s_jnl_blocks[17];	/* Backup of the journal inode */
-	/* 64bit support valid if EXT4_FEATURE_COMPAT_64BIT */
+	/* 64bit support valid if EXT4_FEATURE_INCOMPAT_64BIT */
 /*150*/	__le32	s_blocks_count_hi;	/* Blocks count */
 	__le32	s_r_blocks_count_hi;	/* Reserved blocks count */
 	__le32	s_free_blocks_count_hi;	/* Free blocks count */

fs/ext4/fsmap.c

@@ -486,6 +486,8 @@ static int ext4_getfsmap_datadev(struct super_block *sb,
 		keys[0].fmr_physical = bofs;
 	if (keys[1].fmr_physical >= eofs)
 		keys[1].fmr_physical = eofs - 1;
+	if (keys[1].fmr_physical < keys[0].fmr_physical)
+		return 0;
 	start_fsb = keys[0].fmr_physical;
 	end_fsb = keys[1].fmr_physical;
 

fs/ext4/inline.c

@@ -159,7 +159,6 @@ int ext4_find_inline_data_nolock(struct inode *inode)
 					(void *)ext4_raw_inode(&is.iloc));
 		EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE +
 				le32_to_cpu(is.s.here->e_value_size);
-		ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
 	}
 out:
 	brelse(is.iloc.bh);

fs/ext4/inode.c

@@ -4797,8 +4797,13 @@ static inline int ext4_iget_extra_inode(struct inode *inode,
 
 	if (EXT4_INODE_HAS_XATTR_SPACE(inode)  &&
 	    *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
+		int err;
+
 		ext4_set_inode_state(inode, EXT4_STATE_XATTR);
-		return ext4_find_inline_data_nolock(inode);
+		err = ext4_find_inline_data_nolock(inode);
+		if (!err && ext4_has_inline_data(inode))
+			ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
+		return err;
 	} else
 		EXT4_I(inode)->i_inline_off = 0;
 	return 0;

fs/ext4/ioctl.c

@@ -431,6 +431,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
 		ei_bl->i_flags = 0;
 		inode_set_iversion(inode_bl, 1);
 		i_size_write(inode_bl, 0);
+		EXT4_I(inode_bl)->i_disksize = inode_bl->i_size;
 		inode_bl->i_mode = S_IFREG;
 		if (ext4_has_feature_extents(sb)) {
 			ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);

fs/ext4/namei.c

@@ -1595,11 +1595,10 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir,
 		int has_inline_data = 1;
 		ret = ext4_find_inline_entry(dir, fname, res_dir,
 					     &has_inline_data);
-		if (has_inline_data) {
-			if (inlined)
-				*inlined = 1;
+		if (inlined)
+			*inlined = has_inline_data;
+		if (has_inline_data)
 			goto cleanup_and_exit;
-		}
 	}
 
 	if ((namelen <= 2) && (name[0] == '.') &&
@@ -3646,7 +3645,8 @@ static void ext4_resetent(handle_t *handle, struct ext4_renament *ent,
 	 * so the old->de may no longer valid and need to find it again
 	 * before reset old inode info.
 	 */
-	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
+	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de,
+				 &old.inlined);
 	if (IS_ERR(old.bh))
 		retval = PTR_ERR(old.bh);
 	if (!old.bh)
@@ -3813,9 +3813,20 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 			return retval;
 	}
 
-	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de, NULL);
-	if (IS_ERR(old.bh))
-		return PTR_ERR(old.bh);
+	/*
+	 * We need to protect against old.inode directory getting converted
+	 * from inline directory format into a normal one.
+	 */
+	if (S_ISDIR(old.inode->i_mode))
+		inode_lock_nested(old.inode, I_MUTEX_NONDIR2);
+
+	old.bh = ext4_find_entry(old.dir, &old.dentry->d_name, &old.de,
+				 &old.inlined);
+	if (IS_ERR(old.bh)) {
+		retval = PTR_ERR(old.bh);
+		goto unlock_moved_dir;
+	}
+
 	/*
 	 *  Check for inode number is _not_ due to possible IO errors.
 	 *  We might rmdir the source, keep it as pwd of some process
@@ -3872,11 +3883,6 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 			if (new.dir != old.dir && EXT4_DIR_LINK_MAX(new.dir))
 				goto end_rename;
 		}
-		/*
-		 * We need to protect against old.inode directory getting
-		 * converted from inline directory format into a normal one.
-		 */
-		inode_lock_nested(old.inode, I_MUTEX_NONDIR2);
 		retval = ext4_rename_dir_prepare(handle, &old);
 		if (retval) {
 			inode_unlock(old.inode);
@@ -4013,12 +4019,15 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 	} else {
 		ext4_journal_stop(handle);
 	}
-	if (old.dir_bh)
-		inode_unlock(old.inode);
 release_bh:
 	brelse(old.dir_bh);
 	brelse(old.bh);
 	brelse(new.bh);
+
+unlock_moved_dir:
+	if (S_ISDIR(old.inode->i_mode))
+		inode_unlock(old.inode);
+
 	return retval;
 }
 

fs/ext4/page-io.c

@@ -409,7 +409,8 @@ static void io_submit_init_bio(struct ext4_io_submit *io,
 
 static void io_submit_add_bh(struct ext4_io_submit *io,
 			     struct inode *inode,
-			     struct page *page,
+			     struct page *pagecache_page,
+			     struct page *bounce_page,
 			     struct buffer_head *bh)
 {
 	int ret;
@@ -421,10 +422,11 @@ static void io_submit_add_bh(struct ext4_io_submit *io,
 	}
 	if (io->io_bio == NULL)
 		io_submit_init_bio(io, bh);
-	ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh));
+	ret = bio_add_page(io->io_bio, bounce_page ?: pagecache_page,
+			   bh->b_size, bh_offset(bh));
 	if (ret != bh->b_size)
 		goto submit_and_retry;
-	wbc_account_cgroup_owner(io->io_wbc, page, bh->b_size);
+	wbc_account_cgroup_owner(io->io_wbc, pagecache_page, bh->b_size);
 	io->io_next_block++;
 }
 
@@ -561,8 +563,7 @@ int ext4_bio_write_page(struct ext4_io_submit *io,
 	do {
 		if (!buffer_async_write(bh))
 			continue;
-		io_submit_add_bh(io, inode,
-				 bounce_page ? bounce_page : page, bh);
+		io_submit_add_bh(io, inode, page, bounce_page, bh);
 	} while ((bh = bh->b_this_page) != head);
 unlock:
 	unlock_page(page);

fs/ext4/super.c

@@ -5726,6 +5726,28 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb,
 	return journal_inode;
 }
 
+static int ext4_journal_bmap(journal_t *journal, sector_t *block)
+{
+	struct ext4_map_blocks map;
+	int ret;
+
+	if (journal->j_inode == NULL)
+		return 0;
+
+	map.m_lblk = *block;
+	map.m_len = 1;
+	ret = ext4_map_blocks(NULL, journal->j_inode, &map, 0);
+	if (ret <= 0) {
+		ext4_msg(journal->j_inode->i_sb, KERN_CRIT,
+			 "journal bmap failed: block %llu ret %d\n",
+			 *block, ret);
+		jbd2_journal_abort(journal, ret ? ret : -EIO);
+		return ret;
+	}
+	*block = map.m_pblk;
+	return 0;
+}
+
 static journal_t *ext4_get_journal(struct super_block *sb,
 				   unsigned int journal_inum)
 {
@@ -5746,6 +5768,7 @@ static journal_t *ext4_get_journal(struct super_block *sb,
 		return NULL;
 	}
 	journal->j_private = sb;
+	journal->j_bmap = ext4_journal_bmap;
 	ext4_init_journal_params(sb, journal);
 	return journal;
 }
@@ -5920,6 +5943,7 @@ static int ext4_load_journal(struct super_block *sb,
 		err = jbd2_journal_wipe(journal, !really_read_only);
 	if (!err) {
 		char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL);
+
 		if (save)
 			memcpy(save, ((char *) es) +
 			       EXT4_S_ERR_START, EXT4_S_ERR_LEN);
@@ -5928,6 +5952,14 @@ static int ext4_load_journal(struct super_block *sb,
 			memcpy(((char *) es) + EXT4_S_ERR_START,
 			       save, EXT4_S_ERR_LEN);
 		kfree(save);
+		es->s_state |= cpu_to_le16(EXT4_SB(sb)->s_mount_state &
+					   EXT4_ERROR_FS);
+		/* Write out restored error information to the superblock */
+		if (!bdev_read_only(sb->s_bdev)) {
+			int err2;
+			err2 = ext4_commit_super(sb);
+			err = err ? : err2;
+		}
 	}
 
 	if (err) {
@@ -6157,11 +6189,13 @@ static int ext4_clear_journal_err(struct super_block *sb,
 		errstr = ext4_decode_error(sb, j_errno, nbuf);
 		ext4_warning(sb, "Filesystem error recorded "
 			     "from previous mount: %s", errstr);
-		ext4_warning(sb, "Marking fs in need of filesystem check.");
 
 		EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
 		es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-		ext4_commit_super(sb);
+		j_errno = ext4_commit_super(sb);
+		if (j_errno)
+			return j_errno;
+		ext4_warning(sb, "Marked fs in need of filesystem check.");
 
 		jbd2_journal_clear_err(journal);
 		jbd2_journal_update_sb_errno(journal);

fs/ext4/sysfs.c

@@ -501,13 +501,13 @@ static const struct sysfs_ops ext4_attr_ops = {
 	.store	= ext4_attr_store,
 };
 
-static struct kobj_type ext4_sb_ktype = {
+static const struct kobj_type ext4_sb_ktype = {
 	.default_groups = ext4_groups,
 	.sysfs_ops	= &ext4_attr_ops,
 	.release	= ext4_sb_release,
 };
 
-static struct kobj_type ext4_feat_ktype = {
+static const struct kobj_type ext4_feat_ktype = {
 	.default_groups = ext4_feat_groups,
 	.sysfs_ops	= &ext4_attr_ops,
 	.release	= ext4_feat_release,

fs/ext4/xattr.c

@@ -2852,6 +2852,9 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			(void *)header, total_ino);
 	EXT4_I(inode)->i_extra_isize = new_extra_isize;
 
+	if (ext4_has_inline_data(inode))
+		error = ext4_find_inline_data_nolock(inode);
+
 cleanup:
 	if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) {
 		ext4_warning(inode->i_sb, "Unable to expand inode %lu. Delete some EAs or run e2fsck.",

fs/jbd2/journal.c

@@ -969,10 +969,13 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
 {
 	int err = 0;
 	unsigned long long ret;
-	sector_t block = 0;
+	sector_t block = blocknr;
 
-	if (journal->j_inode) {
-		block = blocknr;
+	if (journal->j_bmap) {
+		err = journal->j_bmap(journal, &block);
+		if (err == 0)
+			*retp = block;
+	} else if (journal->j_inode) {
 		ret = bmap(journal->j_inode, &block);
 
 		if (ret || !block) {

include/linux/jbd2.h

@@ -1308,6 +1308,14 @@ struct journal_s
 				    struct buffer_head *bh,
 				    enum passtype pass, int off,
 				    tid_t expected_commit_id);
+
+	/**
+	 * @j_bmap:
+	 *
+	 * Bmap function that should be used instead of the generic
+	 * VFS bmap function.
+	 */
+	int (*j_bmap)(struct journal_s *journal, sector_t *block);
 };
 
 #define jbd2_might_wait_for_commit(j) \