A lot of miscellaneous ext4 bug fixes and cleanups this cycle, most

notably in the journaling code, bufered I/O, and compiler warning
 cleanups.
 -----BEGIN PGP SIGNATURE-----
 
 iQEzBAABCAAdFiEEK2m5VNv+CHkogTfJ8vlZVpUNgaMFAmc7NN4ACgkQ8vlZVpUN
 gaMJRAf+Oc3Tn/ZvuX0amkaBQI+ZNIeYD/U0WBSvarKb00bo1X39mM/0LovqV6ec
 c51iRgt8U6uDZDUm6zJtppkIUiqkHRj+TmTInueFtmUqhIg8jgfZIpxCn0QkFKnQ
 jI5EKCkvUqM0B347axH/s+dlOE9JBSlQNKgjkvCYOGknQ1PH6X8oMDt5QAqGEk3P
 Nsa4QChIxt2yujFvydgFT+RAbjvY3sNvrZ7D3B+KL3VSJpILChVZK/UdFrraSXxq
 mLO5j4txjtnr/OLgujCTHOfPsTiQReHHXErrSbKhnFhrTXLD0mZSUgJ6irpaxRQ5
 wQHQzmsrVwqFfqPU3Hkl8FGeCR0owQ==
 =26/E
 -----END PGP SIGNATURE-----

Merge tag 'ext4_for_linus-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "A lot of miscellaneous ext4 bug fixes and cleanups this cycle, most
  notably in the journaling code, bufered I/O, and compiler warning
  cleanups"

* tag 'ext4_for_linus-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (33 commits)
  jbd2: Fix comment describing journal_init_common()
  ext4: prevent an infinite loop in the lazyinit thread
  ext4: use struct_size() to improve ext4_htree_store_dirent()
  ext4: annotate struct fname with __counted_by()
  jbd2: avoid dozens of -Wflex-array-member-not-at-end warnings
  ext4: use str_yes_no() helper function
  ext4: prevent delalloc to nodelalloc on remount
  jbd2: make b_frozen_data allocation always succeed
  ext4: cleanup variable name in ext4_fc_del()
  ext4: use string choices helpers
  jbd2: remove the 'success' parameter from the jbd2_do_replay() function
  jbd2: remove useless 'block_error' variable
  jbd2: factor out jbd2_do_replay()
  jbd2: refactor JBD2_COMMIT_BLOCK process in do_one_pass()
  jbd2: unified release of buffer_head in do_one_pass()
  jbd2: remove redundant judgments for check v1 checksum
  ext4: use ERR_CAST to return an error-valued pointer
  mm: zero range of eof folio exposed by inode size extension
  ext4: partial zero eof block on unaligned inode size extension
  ext4: disambiguate the return value of ext4_dio_write_end_io()
  ...

fs/ext4/balloc.c

@@ -550,7 +550,8 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group,
 	trace_ext4_read_block_bitmap_load(sb, block_group, ignore_locked);
 	ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO |
 			    (ignore_locked ? REQ_RAHEAD : 0),
-			    ext4_end_bitmap_read);
+			    ext4_end_bitmap_read,
+			    ext4_simulate_fail(sb, EXT4_SIM_BBITMAP_EIO));
 	return bh;
 verify:
 	err = ext4_validate_block_bitmap(sb, desc, block_group, bh);
@@ -577,7 +578,6 @@ int ext4_wait_block_bitmap(struct super_block *sb, ext4_group_t block_group,
 	if (!desc)
 		return -EFSCORRUPTED;
 	wait_on_buffer(bh);
-	ext4_simulate_fail_bh(sb, bh, EXT4_SIM_BBITMAP_EIO);
 	if (!buffer_uptodate(bh)) {
 		ext4_error_err(sb, EIO, "Cannot read block bitmap - "
 			       "block_group = %u, block_bitmap = %llu",

fs/ext4/dir.c

@@ -418,7 +418,7 @@ struct fname {
 	__u32		inode;
 	__u8		name_len;
 	__u8		file_type;
-	char		name[];
+	char		name[] __counted_by(name_len);
 };
 
 /*
@@ -471,14 +471,13 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash,
 	struct rb_node **p, *parent = NULL;
 	struct fname *fname, *new_fn;
 	struct dir_private_info *info;
-	int len;
 
 	info = dir_file->private_data;
 	p = &info->root.rb_node;
 
 	/* Create and allocate the fname structure */
-	len = sizeof(struct fname) + ent_name->len + 1;
+	new_fn = kzalloc(struct_size(new_fn, name, ent_name->len + 1),
-	new_fn = kzalloc(len, GFP_KERNEL);
+			 GFP_KERNEL);
 	if (!new_fn)
 		return -ENOMEM;
 	new_fn->hash = hash;

fs/ext4/ext4.h

@@ -1869,14 +1869,6 @@ static inline bool ext4_simulate_fail(struct super_block *sb,
 	return false;
 }
 
-static inline void ext4_simulate_fail_bh(struct super_block *sb,
-					 struct buffer_head *bh,
-					 unsigned long code)
-{
-	if (!IS_ERR(bh) && ext4_simulate_fail(sb, code))
-		clear_buffer_uptodate(bh);
-}
-
 /*
  * Error number codes for s_{first,last}_error_errno
  *
@@ -3104,9 +3096,9 @@ extern struct buffer_head *ext4_sb_bread(struct super_block *sb,
 extern struct buffer_head *ext4_sb_bread_unmovable(struct super_block *sb,
 						   sector_t block);
 extern void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
-				bh_end_io_t *end_io);
+				bh_end_io_t *end_io, bool simu_fail);
 extern int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
-			bh_end_io_t *end_io);
+			bh_end_io_t *end_io, bool simu_fail);
 extern int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
 extern void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block);
 extern int ext4_seq_options_show(struct seq_file *seq, void *offset);

fs/ext4/extents.c

@@ -568,7 +568,7 @@ __read_extent_tree_block(const char *function, unsigned int line,
 
 	if (!bh_uptodate_or_lock(bh)) {
 		trace_ext4_ext_load_extent(inode, pblk, _RET_IP_);
-		err = ext4_read_bh(bh, 0, NULL);
+		err = ext4_read_bh(bh, 0, NULL, false);
 		if (err < 0)
 			goto errout;
 	}
@@ -3138,7 +3138,7 @@ static void ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
 		return;
 
 	ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
-			      EXTENT_STATUS_WRITTEN, 0);
+			      EXTENT_STATUS_WRITTEN, false);
 }
 
 /* FIXME!! we need to try to merge to left or right after zero-out  */
@@ -4158,7 +4158,7 @@ insert_hole:
 	/* Put just found gap into cache to speed up subsequent requests */
 	ext_debug(inode, " -> %u:%u\n", hole_start, len);
 	ext4_es_insert_extent(inode, hole_start, len, ~0,
-			      EXTENT_STATUS_HOLE, 0);
+			      EXTENT_STATUS_HOLE, false);
 
 	/* Update hole_len to reflect hole size after lblk */
 	if (hole_start != lblk)
@@ -4482,7 +4482,7 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 	int depth = 0;
 	struct ext4_map_blocks map;
 	unsigned int credits;
-	loff_t epos;
+	loff_t epos, old_size = i_size_read(inode);
 
 	BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS));
 	map.m_lblk = offset;
@@ -4541,6 +4541,11 @@ retry:
 			if (ext4_update_inode_size(inode, epos) & 0x1)
 				inode_set_mtime_to_ts(inode,
 						      inode_get_ctime(inode));
+			if (epos > old_size) {
+				pagecache_isize_extended(inode, old_size, epos);
+				ext4_zero_partial_blocks(handle, inode,
+						     old_size, epos - old_size);
+			}
 		}
 		ret2 = ext4_mark_inode_dirty(handle, inode);
 		ext4_update_inode_fsync_trans(handle, inode, 1);

fs/ext4/extents_status.c

@@ -848,7 +848,7 @@ out:
  */
 void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 			   ext4_lblk_t len, ext4_fsblk_t pblk,
-			   unsigned int status, int flags)
+			   unsigned int status, bool delalloc_reserve_used)
 {
 	struct extent_status newes;
 	ext4_lblk_t end = lblk + len - 1;
@@ -863,8 +863,8 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 	if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
 		return;
 
-	es_debug("add [%u/%u) %llu %x %x to extent status tree of inode %lu\n",
+	es_debug("add [%u/%u) %llu %x %d to extent status tree of inode %lu\n",
-		 lblk, len, pblk, status, flags, inode->i_ino);
+		 lblk, len, pblk, status, delalloc_reserve_used, inode->i_ino);
 
 	if (!len)
 		return;
@@ -945,7 +945,7 @@ error:
 	resv_used += pending;
 	if (resv_used)
 		ext4_da_update_reserve_space(inode, resv_used,
-				flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE);
+					     delalloc_reserve_used);
 
 	if (err1 || err2 || err3 < 0)
 		goto retry;

fs/ext4/extents_status.h

@@ -135,7 +135,8 @@ extern void ext4_es_init_tree(struct ext4_es_tree *tree);
 
 extern void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 				  ext4_lblk_t len, ext4_fsblk_t pblk,
-				  unsigned int status, int flags);
+				  unsigned int status,
+				  bool delalloc_reserve_used);
 extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
 				 ext4_lblk_t len, ext4_fsblk_t pblk,
 				 unsigned int status);

fs/ext4/fast_commit.c

@@ -291,9 +291,9 @@ void ext4_fc_del(struct inode *inode)
 		return;
 
 restart:
-	spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+	spin_lock(&sbi->s_fc_lock);
 	if (list_empty(&ei->i_fc_list) && list_empty(&ei->i_fc_dilist)) {
-		spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
+		spin_unlock(&sbi->s_fc_lock);
 		return;
 	}
 
@@ -357,9 +357,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl
 	}
 	spin_lock(&sbi->s_fc_lock);
 	is_ineligible = ext4_test_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
-	if (has_transaction &&
+	if (has_transaction && (!is_ineligible || tid_gt(tid, sbi->s_fc_ineligible_tid)))
-	    (!is_ineligible ||
-	     (is_ineligible && tid_gt(tid, sbi->s_fc_ineligible_tid))))
 		sbi->s_fc_ineligible_tid = tid;
 	ext4_set_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
 	spin_unlock(&sbi->s_fc_lock);

fs/ext4/file.c

@@ -392,8 +392,9 @@ static int ext4_dio_write_end_io(struct kiocb *iocb, ssize_t size,
 	 */
 	if (pos + size <= READ_ONCE(EXT4_I(inode)->i_disksize) &&
 	    pos + size <= i_size_read(inode))
-		return size;
+		return 0;
-	return ext4_handle_inode_extension(inode, pos, size, size);
+	error = ext4_handle_inode_extension(inode, pos, size, size);
+	return error < 0 ? error : 0;
 }
 
 static const struct iomap_dio_ops ext4_dio_write_ops = {
@@ -564,12 +565,9 @@ static ssize_t ext4_dio_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		}
 
 		ret = ext4_orphan_add(handle, inode);
-		if (ret) {
-			ext4_journal_stop(handle);
-			goto out;
-		}
-
 		ext4_journal_stop(handle);
+		if (ret)
+			goto out;
 	}
 
 	if (ilock_shared && !unwritten)

fs/ext4/fsmap.c

@@ -185,6 +185,56 @@ static inline ext4_fsblk_t ext4_fsmap_next_pblk(struct ext4_fsmap *fmr)
 	return fmr->fmr_physical + fmr->fmr_length;
 }
 
+static int ext4_getfsmap_meta_helper(struct super_block *sb,
+				     ext4_group_t agno, ext4_grpblk_t start,
+				     ext4_grpblk_t len, void *priv)
+{
+	struct ext4_getfsmap_info *info = priv;
+	struct ext4_fsmap *p;
+	struct ext4_fsmap *tmp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t fsb, fs_start, fs_end;
+	int error;
+
+	fs_start = fsb = (EXT4_C2B(sbi, start) +
+			  ext4_group_first_block_no(sb, agno));
+	fs_end = fs_start + EXT4_C2B(sbi, len);
+
+	/* Return relevant extents from the meta_list */
+	list_for_each_entry_safe(p, tmp, &info->gfi_meta_list, fmr_list) {
+		if (p->fmr_physical < info->gfi_next_fsblk) {
+			list_del(&p->fmr_list);
+			kfree(p);
+			continue;
+		}
+		if (p->fmr_physical <= fs_start ||
+		    p->fmr_physical + p->fmr_length <= fs_end) {
+			/* Emit the retained free extent record if present */
+			if (info->gfi_lastfree.fmr_owner) {
+				error = ext4_getfsmap_helper(sb, info,
+							&info->gfi_lastfree);
+				if (error)
+					return error;
+				info->gfi_lastfree.fmr_owner = 0;
+			}
+			error = ext4_getfsmap_helper(sb, info, p);
+			if (error)
+				return error;
+			fsb = p->fmr_physical + p->fmr_length;
+			if (info->gfi_next_fsblk < fsb)
+				info->gfi_next_fsblk = fsb;
+			list_del(&p->fmr_list);
+			kfree(p);
+			continue;
+		}
+	}
+	if (info->gfi_next_fsblk < fsb)
+		info->gfi_next_fsblk = fsb;
+
+	return 0;
+}
+
+
 /* Transform a blockgroup's free record into a fsmap */
 static int ext4_getfsmap_datadev_helper(struct super_block *sb,
 					ext4_group_t agno, ext4_grpblk_t start,
@@ -539,6 +589,7 @@ static int ext4_getfsmap_datadev(struct super_block *sb,
 		error = ext4_mballoc_query_range(sb, info->gfi_agno,
 				EXT4_B2C(sbi, info->gfi_low.fmr_physical),
 				EXT4_B2C(sbi, info->gfi_high.fmr_physical),
+				ext4_getfsmap_meta_helper,
 				ext4_getfsmap_datadev_helper, info);
 		if (error)
 			goto err;
@@ -560,7 +611,8 @@ static int ext4_getfsmap_datadev(struct super_block *sb,
 
 	/* Report any gaps at the end of the bg */
 	info->gfi_last = true;
-	error = ext4_getfsmap_datadev_helper(sb, end_ag, last_cluster, 0, info);
+	error = ext4_getfsmap_datadev_helper(sb, end_ag, last_cluster + 1,
+					     0, info);
 	if (error)
 		goto err;
 

fs/ext4/ialloc.c

@@ -193,8 +193,9 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	 * submit the buffer_head for reading
 	 */
 	trace_ext4_load_inode_bitmap(sb, block_group);
-	ext4_read_bh(bh, REQ_META | REQ_PRIO, ext4_end_bitmap_read);
+	ext4_read_bh(bh, REQ_META | REQ_PRIO,
-	ext4_simulate_fail_bh(sb, bh, EXT4_SIM_IBITMAP_EIO);
+		     ext4_end_bitmap_read,
+		     ext4_simulate_fail(sb, EXT4_SIM_IBITMAP_EIO));
 	if (!buffer_uptodate(bh)) {
 		put_bh(bh);
 		ext4_error_err(sb, EIO, "Cannot read inode bitmap - "

fs/ext4/indirect.c

@@ -170,7 +170,7 @@ static Indirect *ext4_get_branch(struct inode *inode, int depth,
 		}
 
 		if (!bh_uptodate_or_lock(bh)) {
-			if (ext4_read_bh(bh, 0, NULL) < 0) {
+			if (ext4_read_bh(bh, 0, NULL, false) < 0) {
 				put_bh(bh);
 				goto failure;
 			}

fs/ext4/inode.c

@@ -483,7 +483,7 @@ static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
 	status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 			EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
 	ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
-			      map->m_pblk, status, 0);
+			      map->m_pblk, status, false);
 	return retval;
 }
 
@@ -563,8 +563,8 @@ static int ext4_map_create_blocks(handle_t *handle, struct inode *inode,
 
 	status = map->m_flags & EXT4_MAP_UNWRITTEN ?
 			EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
-	ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+	ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk,
-			      map->m_pblk, status, flags);
+			      status, flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE);
 
 	return retval;
 }
@@ -856,7 +856,14 @@ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
 	if (nowait)
 		return sb_find_get_block(inode->i_sb, map.m_pblk);
 
-	bh = sb_getblk(inode->i_sb, map.m_pblk);
+	/*
+	 * Since bh could introduce extra ref count such as referred by
+	 * journal_head etc. Try to avoid using __GFP_MOVABLE here
+	 * as it may fail the migration when journal_head remains.
+	 */
+	bh = getblk_unmovable(inode->i_sb->s_bdev, map.m_pblk,
+				inode->i_sb->s_blocksize);
+
 	if (unlikely(!bh))
 		return ERR_PTR(-ENOMEM);
 	if (map.m_flags & EXT4_MAP_NEW) {
@@ -1307,8 +1314,10 @@ static int ext4_write_end(struct file *file,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	if (old_size < pos && !verity)
+	if (old_size < pos && !verity) {
 		pagecache_isize_extended(inode, old_size, pos);
+		ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size);
+	}
 	/*
 	 * Don't mark the inode dirty under folio lock. First, it unnecessarily
 	 * makes the holding time of folio lock longer. Second, it forces lock
@@ -1423,8 +1432,10 @@ static int ext4_journalled_write_end(struct file *file,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	if (old_size < pos && !verity)
+	if (old_size < pos && !verity) {
 		pagecache_isize_extended(inode, old_size, pos);
+		ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size);
+	}
 
 	if (size_changed) {
 		ret2 = ext4_mark_inode_dirty(handle, inode);
@@ -2985,7 +2996,8 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	loff_t old_size = inode->i_size;
 	bool disksize_changed = false;
-	loff_t new_i_size;
+	loff_t new_i_size, zero_len = 0;
+	handle_t *handle;
 
 	if (unlikely(!folio_buffers(folio))) {
 		folio_unlock(folio);
@@ -3029,19 +3041,22 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	if (old_size < pos)
+	if (pos > old_size) {
 		pagecache_isize_extended(inode, old_size, pos);
-
+		zero_len = pos - old_size;
-	if (disksize_changed) {
-		handle_t *handle;
-
-		handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
-		if (IS_ERR(handle))
-			return PTR_ERR(handle);
-		ext4_mark_inode_dirty(handle, inode);
-		ext4_journal_stop(handle);
 	}
 
+	if (!disksize_changed && !zero_len)
+		return copied;
+
+	handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+	if (IS_ERR(handle))
+		return PTR_ERR(handle);
+	if (zero_len)
+		ext4_zero_partial_blocks(handle, inode, old_size, zero_len);
+	ext4_mark_inode_dirty(handle, inode);
+	ext4_journal_stop(handle);
+
 	return copied;
 }
 
@@ -4514,10 +4529,10 @@ make_io:
 	 * Read the block from disk.
 	 */
 	trace_ext4_load_inode(sb, ino);
-	ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL);
+	ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL,
+			    ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO));
 	blk_finish_plug(&plug);
 	wait_on_buffer(bh);
-	ext4_simulate_fail_bh(sb, bh, EXT4_SIM_INODE_EIO);
 	if (!buffer_uptodate(bh)) {
 		if (ret_block)
 			*ret_block = block;
@@ -5443,6 +5458,14 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		}
 
 		if (attr->ia_size != inode->i_size) {
+			/* attach jbd2 jinode for EOF folio tail zeroing */
+			if (attr->ia_size & (inode->i_sb->s_blocksize - 1) ||
+			    oldsize & (inode->i_sb->s_blocksize - 1)) {
+				error = ext4_inode_attach_jinode(inode);
+				if (error)
+					goto err_out;
+			}
+
 			handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
 			if (IS_ERR(handle)) {
 				error = PTR_ERR(handle);
@@ -5453,12 +5476,17 @@ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 				orphan = 1;
 			}
 			/*
-			 * Update c/mtime on truncate up, ext4_truncate() will
+			 * Update c/mtime and tail zero the EOF folio on
-			 * update c/mtime in shrink case below
+			 * truncate up. ext4_truncate() handles the shrink case
+			 * below.
 			 */
-			if (!shrink)
+			if (!shrink) {
 				inode_set_mtime_to_ts(inode,
 						      inode_set_ctime_current(inode));
+				if (oldsize & (inode->i_sb->s_blocksize - 1))
+					ext4_block_truncate_page(handle,
+							inode->i_mapping, oldsize);
+			}
 
 			if (shrink)
 				ext4_fc_track_range(handle, inode,

fs/ext4/mballoc.c

@@ -5711,7 +5711,7 @@ static void ext4_mb_show_ac(struct ext4_allocation_context *ac)
 			(unsigned long)ac->ac_b_ex.fe_logical,
 			(int)ac->ac_criteria);
 	mb_debug(sb, "%u found", ac->ac_found);
-	mb_debug(sb, "used pa: %s, ", ac->ac_pa ? "yes" : "no");
+	mb_debug(sb, "used pa: %s, ", str_yes_no(ac->ac_pa));
 	if (ac->ac_pa)
 		mb_debug(sb, "pa_type %s\n", ac->ac_pa->pa_type == MB_GROUP_PA ?
 			 "group pa" : "inode pa");
@@ -6056,7 +6056,7 @@ static bool ext4_mb_discard_preallocations_should_retry(struct super_block *sb,
 	}
 
 out_dbg:
-	mb_debug(sb, "freed %d, retry ? %s\n", freed, ret ? "yes" : "no");
+	mb_debug(sb, "freed %d, retry ? %s\n", freed, str_yes_no(ret));
 	return ret;
 }
 
@@ -6999,13 +6999,14 @@ int
 ext4_mballoc_query_range(
 	struct super_block		*sb,
 	ext4_group_t			group,
-	ext4_grpblk_t			start,
+	ext4_grpblk_t			first,
 	ext4_grpblk_t			end,
+	ext4_mballoc_query_range_fn	meta_formatter,
 	ext4_mballoc_query_range_fn	formatter,
 	void				*priv)
 {
 	void				*bitmap;
-	ext4_grpblk_t			next;
+	ext4_grpblk_t			start, next;
 	struct ext4_buddy		e4b;
 	int				error;
 
@@ -7016,10 +7017,19 @@ ext4_mballoc_query_range(
 
 	ext4_lock_group(sb, group);
 
-	start = max(e4b.bd_info->bb_first_free, start);
+	start = max(e4b.bd_info->bb_first_free, first);
 	if (end >= EXT4_CLUSTERS_PER_GROUP(sb))
 		end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
-
+	if (meta_formatter && start != first) {
+		if (start > end)
+			start = end;
+		ext4_unlock_group(sb, group);
+		error = meta_formatter(sb, group, first, start - first,
+				       priv);
+		if (error)
+			goto out_unload;
+		ext4_lock_group(sb, group);
+	}
 	while (start <= end) {
 		start = mb_find_next_zero_bit(bitmap, end + 1, start);
 		if (start > end)

fs/ext4/mballoc.h

@@ -259,6 +259,7 @@ ext4_mballoc_query_range(
 	ext4_group_t			agno,
 	ext4_grpblk_t			start,
 	ext4_grpblk_t			end,
+	ext4_mballoc_query_range_fn	meta_formatter,
 	ext4_mballoc_query_range_fn	formatter,
 	void				*priv);
 

fs/ext4/mmp.c

@@ -94,7 +94,7 @@ static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
 	}
 
 	lock_buffer(*bh);
-	ret = ext4_read_bh(*bh, REQ_META | REQ_PRIO, NULL);
+	ret = ext4_read_bh(*bh, REQ_META | REQ_PRIO, NULL, false);
 	if (ret)
 		goto warn_exit;
 

fs/ext4/move_extent.c

@@ -213,7 +213,7 @@ static int mext_page_mkuptodate(struct folio *folio, size_t from, size_t to)
 			unlock_buffer(bh);
 			continue;
 		}
-		ext4_read_bh_nowait(bh, 0, NULL);
+		ext4_read_bh_nowait(bh, 0, NULL, false);
 		nr++;
 	} while (block++, (bh = bh->b_this_page) != head);
 

fs/ext4/namei.c

@@ -1747,7 +1747,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
 #endif
 	frame = dx_probe(fname, dir, NULL, frames);
 	if (IS_ERR(frame))
-		return (struct buffer_head *) frame;
+		return ERR_CAST(frame);
 	do {
 		block = dx_get_block(frame->at);
 		bh = ext4_read_dirblock(dir, block, DIRENT_HTREE);
@@ -1952,7 +1952,7 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	if (IS_ERR(bh2)) {
 		brelse(*bh);
 		*bh = NULL;
-		return (struct ext4_dir_entry_2 *) bh2;
+		return ERR_CAST(bh2);
 	}
 
 	BUFFER_TRACE(*bh, "get_write_access");
@@ -2000,8 +2000,17 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	else
 		split = count/2;
 
+	if (WARN_ON_ONCE(split == 0)) {
+		/* Should never happen, but avoid out-of-bounds access below */
+		ext4_error_inode_block(dir, (*bh)->b_blocknr, 0,
+			"bad indexed directory? hash=%08x:%08x count=%d move=%u",
+			hinfo->hash, hinfo->minor_hash, count, move);
+		err = -EFSCORRUPTED;
+		goto out;
+	}
+
 	hash2 = map[split].hash;
-	continued = split > 0 ? hash2 == map[split - 1].hash : 0;
+	continued = hash2 == map[split - 1].hash;
 	dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
 			(unsigned long)dx_get_block(frame->at),
 					hash2, split, count-split));
@@ -2043,10 +2052,11 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
 	return de;
 
 journal_error:
+	ext4_std_error(dir->i_sb, err);
+out:
 	brelse(*bh);
 	brelse(bh2);
 	*bh = NULL;
-	ext4_std_error(dir->i_sb, err);
 	return ERR_PTR(err);
 }
 

fs/ext4/page-io.c

@@ -417,8 +417,10 @@ static void io_submit_add_bh(struct ext4_io_submit *io,
 submit_and_retry:
 		ext4_io_submit(io);
 	}
-	if (io->io_bio == NULL)
+	if (io->io_bio == NULL) {
 		io_submit_init_bio(io, bh);
+		io->io_bio->bi_write_hint = inode->i_write_hint;
+	}
 	if (!bio_add_folio(io->io_bio, io_folio, bh->b_size, bh_offset(bh)))
 		goto submit_and_retry;
 	wbc_account_cgroup_owner(io->io_wbc, folio, bh->b_size);

fs/ext4/resize.c

@@ -1300,7 +1300,7 @@ static struct buffer_head *ext4_get_bitmap(struct super_block *sb, __u64 block)
 	if (unlikely(!bh))
 		return NULL;
 	if (!bh_uptodate_or_lock(bh)) {
-		if (ext4_read_bh(bh, 0, NULL) < 0) {
+		if (ext4_read_bh(bh, 0, NULL, false) < 0) {
 			brelse(bh);
 			return NULL;
 		}

fs/ext4/super.c

@@ -161,8 +161,14 @@ MODULE_ALIAS("ext3");
 
 
 static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
-				  bh_end_io_t *end_io)
+				  bh_end_io_t *end_io, bool simu_fail)
 {
+	if (simu_fail) {
+		clear_buffer_uptodate(bh);
+		unlock_buffer(bh);
+		return;
+	}
+
 	/*
 	 * buffer's verified bit is no longer valid after reading from
 	 * disk again due to write out error, clear it to make sure we
@@ -176,7 +182,7 @@ static inline void __ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
 }
 
 void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
-			 bh_end_io_t *end_io)
+			 bh_end_io_t *end_io, bool simu_fail)
 {
 	BUG_ON(!buffer_locked(bh));
 
@@ -184,10 +190,11 @@ void ext4_read_bh_nowait(struct buffer_head *bh, blk_opf_t op_flags,
 		unlock_buffer(bh);
 		return;
 	}
-	__ext4_read_bh(bh, op_flags, end_io);
+	__ext4_read_bh(bh, op_flags, end_io, simu_fail);
 }
 
-int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io)
+int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags,
+		 bh_end_io_t *end_io, bool simu_fail)
 {
 	BUG_ON(!buffer_locked(bh));
 
@@ -196,7 +203,7 @@ int ext4_read_bh(struct buffer_head *bh, blk_opf_t op_flags, bh_end_io_t *end_io
 		return 0;
 	}
 
-	__ext4_read_bh(bh, op_flags, end_io);
+	__ext4_read_bh(bh, op_flags, end_io, simu_fail);
 
 	wait_on_buffer(bh);
 	if (buffer_uptodate(bh))
@@ -208,10 +215,10 @@ int ext4_read_bh_lock(struct buffer_head *bh, blk_opf_t op_flags, bool wait)
 {
 	lock_buffer(bh);
 	if (!wait) {
-		ext4_read_bh_nowait(bh, op_flags, NULL);
+		ext4_read_bh_nowait(bh, op_flags, NULL, false);
 		return 0;
 	}
-	return ext4_read_bh(bh, op_flags, NULL);
+	return ext4_read_bh(bh, op_flags, NULL, false);
 }
 
 /*
@@ -266,7 +273,7 @@ void ext4_sb_breadahead_unmovable(struct super_block *sb, sector_t block)
 
 	if (likely(bh)) {
 		if (trylock_buffer(bh))
-			ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL);
+			ext4_read_bh_nowait(bh, REQ_RAHEAD, NULL, false);
 		brelse(bh);
 	}
 }
@@ -346,9 +353,9 @@ __u32 ext4_free_group_clusters(struct super_block *sb,
 __u32 ext4_free_inodes_count(struct super_block *sb,
 			      struct ext4_group_desc *bg)
 {
-	return le16_to_cpu(bg->bg_free_inodes_count_lo) |
+	return le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_lo)) |
 		(EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT ?
-		 (__u32)le16_to_cpu(bg->bg_free_inodes_count_hi) << 16 : 0);
+		 (__u32)le16_to_cpu(READ_ONCE(bg->bg_free_inodes_count_hi)) << 16 : 0);
 }
 
 __u32 ext4_used_dirs_count(struct super_block *sb,
@@ -402,9 +409,9 @@ void ext4_free_group_clusters_set(struct super_block *sb,
 void ext4_free_inodes_set(struct super_block *sb,
 			  struct ext4_group_desc *bg, __u32 count)
 {
-	bg->bg_free_inodes_count_lo = cpu_to_le16((__u16)count);
+	WRITE_ONCE(bg->bg_free_inodes_count_lo, cpu_to_le16((__u16)count));
 	if (EXT4_DESC_SIZE(sb) >= EXT4_MIN_DESC_SIZE_64BIT)
-		bg->bg_free_inodes_count_hi = cpu_to_le16(count >> 16);
+		WRITE_ONCE(bg->bg_free_inodes_count_hi, cpu_to_le16(count >> 16));
 }
 
 void ext4_used_dirs_set(struct super_block *sb,
@@ -2096,16 +2103,16 @@ static int ext4_parse_test_dummy_encryption(const struct fs_parameter *param,
 }
 
 #define EXT4_SET_CTX(name)						\
-static inline void ctx_set_##name(struct ext4_fs_context *ctx,		\
+static inline __maybe_unused						\
-				  unsigned long flag)			\
+void ctx_set_##name(struct ext4_fs_context *ctx, unsigned long flag)	\
 {									\
 	ctx->mask_s_##name |= flag;					\
 	ctx->vals_s_##name |= flag;					\
 }
 
 #define EXT4_CLEAR_CTX(name)						\
-static inline void ctx_clear_##name(struct ext4_fs_context *ctx,	\
+static inline __maybe_unused						\
-				    unsigned long flag)			\
+void ctx_clear_##name(struct ext4_fs_context *ctx, unsigned long flag)	\
 {									\
 	ctx->mask_s_##name |= flag;					\
 	ctx->vals_s_##name &= ~flag;					\
@@ -3030,6 +3037,9 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb,
 		SEQ_OPTS_PUTS("mb_optimize_scan=1");
 	}
 
+	if (nodefs && !test_opt(sb, NO_PREFETCH_BLOCK_BITMAPS))
+		SEQ_OPTS_PUTS("prefetch_block_bitmaps");
+
 	ext4_show_quota_options(seq, sb);
 	return 0;
 }
@@ -3709,12 +3719,12 @@ static int ext4_run_li_request(struct ext4_li_request *elr)
 		ret = 1;
 
 	if (!ret) {
-		start_time = ktime_get_real_ns();
+		start_time = ktime_get_ns();
 		ret = ext4_init_inode_table(sb, group,
 					    elr->lr_timeout ? 0 : 1);
 		trace_ext4_lazy_itable_init(sb, group);
 		if (elr->lr_timeout == 0) {
-			elr->lr_timeout = nsecs_to_jiffies((ktime_get_real_ns() - start_time) *
+			elr->lr_timeout = nsecs_to_jiffies((ktime_get_ns() - start_time) *
 				EXT4_SB(elr->lr_super)->s_li_wait_mult);
 		}
 		elr->lr_next_sched = jiffies + elr->lr_timeout;
@@ -3774,8 +3784,9 @@ static int ext4_lazyinit_thread(void *arg)
 
 cont_thread:
 	while (true) {
-		next_wakeup = MAX_JIFFY_OFFSET;
+		bool next_wakeup_initialized = false;
 
+		next_wakeup = 0;
 		mutex_lock(&eli->li_list_mtx);
 		if (list_empty(&eli->li_request_list)) {
 			mutex_unlock(&eli->li_list_mtx);
@@ -3788,8 +3799,11 @@ cont_thread:
 					 lr_request);
 
 			if (time_before(jiffies, elr->lr_next_sched)) {
-				if (time_before(elr->lr_next_sched, next_wakeup))
+				if (!next_wakeup_initialized ||
+				    time_before(elr->lr_next_sched, next_wakeup)) {
 					next_wakeup = elr->lr_next_sched;
+					next_wakeup_initialized = true;
+				}
 				continue;
 			}
 			if (down_read_trylock(&elr->lr_super->s_umount)) {
@@ -3817,16 +3831,18 @@ cont_thread:
 				elr->lr_next_sched = jiffies +
 					get_random_u32_below(EXT4_DEF_LI_MAX_START_DELAY * HZ);
 			}
-			if (time_before(elr->lr_next_sched, next_wakeup))
+			if (!next_wakeup_initialized ||
+			    time_before(elr->lr_next_sched, next_wakeup)) {
 				next_wakeup = elr->lr_next_sched;
+				next_wakeup_initialized = true;
+			}
 		}
 		mutex_unlock(&eli->li_list_mtx);
 
 		try_to_freeze();
 
 		cur = jiffies;
-		if ((time_after_eq(cur, next_wakeup)) ||
+		if (!next_wakeup_initialized || time_after_eq(cur, next_wakeup)) {
-		    (MAX_JIFFY_OFFSET == next_wakeup)) {
 			cond_resched();
 			continue;
 		}
@@ -6332,7 +6348,7 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
 	if (unlikely(ext4_forced_shutdown(sb)))
-		return 0;
+		return -EIO;
 
 	trace_ext4_sync_fs(sb, wait);
 	flush_workqueue(sbi->rsv_conversion_wq);
@@ -6549,8 +6565,12 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 		goto restore_opts;
 	}
 
-	if (test_opt2(sb, ABORT))
+	if ((old_opts.s_mount_opt & EXT4_MOUNT_DELALLOC) &&
-		ext4_abort(sb, ESHUTDOWN, "Abort forced by user");
+	    !test_opt(sb, DELALLOC)) {
+		ext4_msg(sb, KERN_ERR, "can't disable delalloc during remount");
+		err = -EINVAL;
+		goto restore_opts;
+	}
 
 	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
 		(test_opt(sb, POSIX_ACL) ? SB_POSIXACL : 0);
@@ -6720,6 +6740,14 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
 	if (!ext4_has_feature_mmp(sb) || sb_rdonly(sb))
 		ext4_stop_mmpd(sbi);
 
+	/*
+	 * Handle aborting the filesystem as the last thing during remount to
+	 * avoid obsure errors during remount when some option changes fail to
+	 * apply due to shutdown filesystem.
+	 */
+	if (test_opt2(sb, ABORT))
+		ext4_abort(sb, ESHUTDOWN, "Abort forced by user");
+
 	return 0;
 
 restore_opts:

fs/jbd2/commit.c

@@ -662,10 +662,6 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		JBUFFER_TRACE(jh, "ph3: write metadata");
 		escape = jbd2_journal_write_metadata_buffer(commit_transaction,
 						jh, &wbuf[bufs], blocknr);
-		if (escape < 0) {
-			jbd2_journal_abort(journal, escape);
-			continue;
-		}
 		jbd2_file_log_bh(&io_bufs, wbuf[bufs]);
 
 		/* Record the new block's tag in the current descriptor

fs/jbd2/journal.c

@@ -318,7 +318,6 @@ static inline void jbd2_data_do_escape(char *data)
  *
  *
  * Return value:
- *  <0: Error
  *  =0: Finished OK without escape
  *  =1: Finished OK with escape
  */
@@ -386,12 +385,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 			goto escape_done;
 
 		spin_unlock(&jh_in->b_state_lock);
-		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
+		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS | __GFP_NOFAIL);
-		if (!tmp) {
-			brelse(new_bh);
-			free_buffer_head(new_bh);
-			return -ENOMEM;
-		}
 		spin_lock(&jh_in->b_state_lock);
 		if (jh_in->b_frozen_data) {
 			jbd2_free(tmp, bh_in->b_size);
@@ -1518,9 +1512,10 @@ static int journal_load_superblock(journal_t *journal)
  * destroy journal_t structures, and to initialise and read existing
  * journal blocks from disk.  */
 
-/* First: create and setup a journal_t object in memory.  We initialise
+/* The journal_init_common() function creates and fills a journal_t object
- * very few fields yet: that has to wait until we have created the
+ * in memory. It calls journal_load_superblock() to load the on-disk journal
- * journal structures from from scratch, or loaded them from disk. */
+ * superblock and initialize the journal_t object.
+ */
 
 static journal_t *journal_init_common(struct block_device *bdev,
 			struct block_device *fs_dev,

fs/jbd2/recovery.c

@@ -485,6 +485,104 @@ static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
 		return tag->t_checksum == cpu_to_be16(csum32);
 }
 
+static __always_inline int jbd2_do_replay(journal_t *journal,
+					  struct recovery_info *info,
+					  struct buffer_head *bh,
+					  unsigned long *next_log_block,
+					  unsigned int next_commit_ID)
+{
+	char *tagp;
+	int flags;
+	int ret = 0;
+	int tag_bytes = journal_tag_bytes(journal);
+	int descr_csum_size = 0;
+	unsigned long io_block;
+	journal_block_tag_t tag;
+	struct buffer_head *obh;
+	struct buffer_head *nbh;
+
+	if (jbd2_journal_has_csum_v2or3(journal))
+		descr_csum_size = sizeof(struct jbd2_journal_block_tail);
+
+	tagp = &bh->b_data[sizeof(journal_header_t)];
+	while (tagp - bh->b_data + tag_bytes <=
+	       journal->j_blocksize - descr_csum_size) {
+		int err;
+
+		memcpy(&tag, tagp, sizeof(tag));
+		flags = be16_to_cpu(tag.t_flags);
+
+		io_block = (*next_log_block)++;
+		wrap(journal, *next_log_block);
+		err = jread(&obh, journal, io_block);
+		if (err) {
+			/* Recover what we can, but report failure at the end. */
+			ret = err;
+			pr_err("JBD2: IO error %d recovering block %lu in log\n",
+			      err, io_block);
+		} else {
+			unsigned long long blocknr;
+
+			J_ASSERT(obh != NULL);
+			blocknr = read_tag_block(journal, &tag);
+
+			/* If the block has been revoked, then we're all done here. */
+			if (jbd2_journal_test_revoke(journal, blocknr,
+						     next_commit_ID)) {
+				brelse(obh);
+				++info->nr_revoke_hits;
+				goto skip_write;
+			}
+
+			/* Look for block corruption */
+			if (!jbd2_block_tag_csum_verify(journal, &tag,
+					(journal_block_tag3_t *)tagp,
+					obh->b_data, next_commit_ID)) {
+				brelse(obh);
+				ret = -EFSBADCRC;
+				pr_err("JBD2: Invalid checksum recovering data block %llu in journal block %lu\n",
+				      blocknr, io_block);
+				goto skip_write;
+			}
+
+			/* Find a buffer for the new data being restored */
+			nbh = __getblk(journal->j_fs_dev, blocknr,
+				       journal->j_blocksize);
+			if (nbh == NULL) {
+				pr_err("JBD2: Out of memory during recovery.\n");
+				brelse(obh);
+				return -ENOMEM;
+			}
+
+			lock_buffer(nbh);
+			memcpy(nbh->b_data, obh->b_data, journal->j_blocksize);
+			if (flags & JBD2_FLAG_ESCAPE) {
+				*((__be32 *)nbh->b_data) =
+				cpu_to_be32(JBD2_MAGIC_NUMBER);
+			}
+
+			BUFFER_TRACE(nbh, "marking dirty");
+			set_buffer_uptodate(nbh);
+			mark_buffer_dirty(nbh);
+			BUFFER_TRACE(nbh, "marking uptodate");
+			++info->nr_replays;
+			unlock_buffer(nbh);
+			brelse(obh);
+			brelse(nbh);
+		}
+
+skip_write:
+		tagp += tag_bytes;
+		if (!(flags & JBD2_FLAG_SAME_UUID))
+			tagp += 16;
+
+		if (flags & JBD2_FLAG_LAST_TAG)
+			break;
+	}
+
+	return ret;
+}
+
 static int do_one_pass(journal_t *journal,
 			struct recovery_info *info, enum passtype pass)
 {
@@ -493,13 +591,10 @@ static int do_one_pass(journal_t *journal,
 	int			err, success = 0;
 	journal_superblock_t *	sb;
 	journal_header_t *	tmp;
-	struct buffer_head *	bh;
+	struct buffer_head	*bh = NULL;
 	unsigned int		sequence;
 	int			blocktype;
-	int			tag_bytes = journal_tag_bytes(journal);
 	__u32			crc32_sum = ~0; /* Transactional Checksums */
-	int			descr_csum_size = 0;
-	int			block_error = 0;
 	bool			need_check_commit_time = false;
 	__u64			last_trans_commit_time = 0, commit_time;
 
@@ -528,12 +623,6 @@ static int do_one_pass(journal_t *journal,
 	 */
 
 	while (1) {
-		int			flags;
-		char *			tagp;
-		journal_block_tag_t	tag;
-		struct buffer_head *	obh;
-		struct buffer_head *	nbh;
-
 		cond_resched();
 
 		/* If we already know where to stop the log traversal,
@@ -552,6 +641,8 @@ static int do_one_pass(journal_t *journal,
 		 * record. */
 
 		jbd2_debug(3, "JBD2: checking block %ld\n", next_log_block);
+		brelse(bh);
+		bh = NULL;
 		err = jread(&bh, journal, next_log_block);
 		if (err)
 			goto failed;
@@ -567,20 +658,16 @@ static int do_one_pass(journal_t *journal,
 
 		tmp = (journal_header_t *)bh->b_data;
 
-		if (tmp->h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER)) {
+		if (tmp->h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER))
-			brelse(bh);
 			break;
-		}
 
 		blocktype = be32_to_cpu(tmp->h_blocktype);
 		sequence = be32_to_cpu(tmp->h_sequence);
 		jbd2_debug(3, "Found magic %d, sequence %d\n",
 			  blocktype, sequence);
 
-		if (sequence != next_commit_ID) {
+		if (sequence != next_commit_ID)
-			brelse(bh);
 			break;
-		}
 
 		/* OK, we have a valid descriptor block which matches
 		 * all of the sequence number checks.  What are we going
@@ -589,11 +676,7 @@ static int do_one_pass(journal_t *journal,
 		switch(blocktype) {
 		case JBD2_DESCRIPTOR_BLOCK:
 			/* Verify checksum first */
-			if (jbd2_journal_has_csum_v2or3(journal))
+			if (!jbd2_descriptor_block_csum_verify(journal,
-				descr_csum_size =
-					sizeof(struct jbd2_journal_block_tail);
-			if (descr_csum_size > 0 &&
-			    !jbd2_descriptor_block_csum_verify(journal,
 							       bh->b_data)) {
 				/*
 				 * PASS_SCAN can see stale blocks due to lazy
@@ -603,7 +686,6 @@ static int do_one_pass(journal_t *journal,
 					pr_err("JBD2: Invalid checksum recovering block %lu in log\n",
 					       next_log_block);
 					err = -EFSBADCRC;
-					brelse(bh);
 					goto failed;
 				}
 				need_check_commit_time = true;
@@ -619,125 +701,39 @@ static int do_one_pass(journal_t *journal,
 			if (pass != PASS_REPLAY) {
 				if (pass == PASS_SCAN &&
 				    jbd2_has_feature_checksum(journal) &&
-				    !need_check_commit_time &&
 				    !info->end_transaction) {
 					if (calc_chksums(journal, bh,
 							&next_log_block,
-							&crc32_sum)) {
+							&crc32_sum))
-						put_bh(bh);
 						break;
-					}
-					put_bh(bh);
 					continue;
 				}
 				next_log_block += count_tags(journal, bh);
 				wrap(journal, next_log_block);
-				put_bh(bh);
 				continue;
 			}
 
-			/* A descriptor block: we can now write all of
+			/*
-			 * the data blocks.  Yay, useful work is finally
+			 * A descriptor block: we can now write all of the
-			 * getting done here! */
+			 * data blocks. Yay, useful work is finally getting
-
+			 * done here!
-			tagp = &bh->b_data[sizeof(journal_header_t)];
+			 */
-			while ((tagp - bh->b_data + tag_bytes)
+			err = jbd2_do_replay(journal, info, bh, &next_log_block,
-			       <= journal->j_blocksize - descr_csum_size) {
+					     next_commit_ID);
-				unsigned long io_block;
+			if (err) {
-
+				if (err == -ENOMEM)
-				memcpy(&tag, tagp, sizeof(tag));
+					goto failed;
-				flags = be16_to_cpu(tag.t_flags);
+				success = err;
-
-				io_block = next_log_block++;
-				wrap(journal, next_log_block);
-				err = jread(&obh, journal, io_block);
-				if (err) {
-					/* Recover what we can, but
-					 * report failure at the end. */
-					success = err;
-					printk(KERN_ERR
-						"JBD2: IO error %d recovering "
-						"block %lu in log\n",
-						err, io_block);
-				} else {
-					unsigned long long blocknr;
-
-					J_ASSERT(obh != NULL);
-					blocknr = read_tag_block(journal,
-								 &tag);
-
-					/* If the block has been
-					 * revoked, then we're all done
-					 * here. */
-					if (jbd2_journal_test_revoke
-					    (journal, blocknr,
-					     next_commit_ID)) {
-						brelse(obh);
-						++info->nr_revoke_hits;
-						goto skip_write;
-					}
-
-					/* Look for block corruption */
-					if (!jbd2_block_tag_csum_verify(
-			journal, &tag, (journal_block_tag3_t *)tagp,
-			obh->b_data, be32_to_cpu(tmp->h_sequence))) {
-						brelse(obh);
-						success = -EFSBADCRC;
-						printk(KERN_ERR "JBD2: Invalid "
-						       "checksum recovering "
-						       "data block %llu in "
-						       "journal block %lu\n",
-						       blocknr, io_block);
-						block_error = 1;
-						goto skip_write;
-					}
-
-					/* Find a buffer for the new
-					 * data being restored */
-					nbh = __getblk(journal->j_fs_dev,
-							blocknr,
-							journal->j_blocksize);
-					if (nbh == NULL) {
-						printk(KERN_ERR
-						       "JBD2: Out of memory "
-						       "during recovery.\n");
-						err = -ENOMEM;
-						brelse(bh);
-						brelse(obh);
-						goto failed;
-					}
-
-					lock_buffer(nbh);
-					memcpy(nbh->b_data, obh->b_data,
-							journal->j_blocksize);
-					if (flags & JBD2_FLAG_ESCAPE) {
-						*((__be32 *)nbh->b_data) =
-						cpu_to_be32(JBD2_MAGIC_NUMBER);
-					}
-
-					BUFFER_TRACE(nbh, "marking dirty");
-					set_buffer_uptodate(nbh);
-					mark_buffer_dirty(nbh);
-					BUFFER_TRACE(nbh, "marking uptodate");
-					++info->nr_replays;
-					unlock_buffer(nbh);
-					brelse(obh);
-					brelse(nbh);
-				}
-
-			skip_write:
-				tagp += tag_bytes;
-				if (!(flags & JBD2_FLAG_SAME_UUID))
-					tagp += 16;
-
-				if (flags & JBD2_FLAG_LAST_TAG)
-					break;
 			}
 
-			brelse(bh);
 			continue;
 
 		case JBD2_COMMIT_BLOCK:
+			if (pass != PASS_SCAN) {
+				next_commit_ID++;
+				continue;
+			}
+
 			/*     How to differentiate between interrupted commit
 			 *               and journal corruption ?
 			 *
@@ -782,7 +778,6 @@ static int do_one_pass(journal_t *journal,
 					pr_err("JBD2: Invalid checksum found in transaction %u\n",
 					       next_commit_ID);
 					err = -EFSBADCRC;
-					brelse(bh);
 					goto failed;
 				}
 			ignore_crc_mismatch:
@@ -792,7 +787,6 @@ static int do_one_pass(journal_t *journal,
 				 */
 				jbd2_debug(1, "JBD2: Invalid checksum ignored in transaction %u, likely stale data\n",
 					  next_commit_ID);
-				brelse(bh);
 				goto done;
 			}
 
@@ -802,8 +796,7 @@ static int do_one_pass(journal_t *journal,
 			 * much to do other than move on to the next sequence
 			 * number.
 			 */
-			if (pass == PASS_SCAN &&
+			if (jbd2_has_feature_checksum(journal)) {
-			    jbd2_has_feature_checksum(journal)) {
 				struct commit_header *cbh =
 					(struct commit_header *)bh->b_data;
 				unsigned found_chksum =
@@ -812,7 +805,6 @@ static int do_one_pass(journal_t *journal,
 				if (info->end_transaction) {
 					journal->j_failed_commit =
 						info->end_transaction;
-					brelse(bh);
 					break;
 				}
 
@@ -828,36 +820,33 @@ static int do_one_pass(journal_t *journal,
 					goto chksum_error;
 
 				crc32_sum = ~0;
+				goto chksum_ok;
 			}
-			if (pass == PASS_SCAN &&
-			    !jbd2_commit_block_csum_verify(journal,
-							   bh->b_data)) {
-				if (jbd2_commit_block_csum_verify_partial(
-								  journal,
-								  bh->b_data)) {
-					pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n",
-						  next_commit_ID, next_log_block);
-					goto chksum_ok;
-				}
-			chksum_error:
-				if (commit_time < last_trans_commit_time)
-					goto ignore_crc_mismatch;
-				info->end_transaction = next_commit_ID;
-				info->head_block = head_block;
 
-				if (!jbd2_has_feature_async_commit(journal)) {
+			if (jbd2_commit_block_csum_verify(journal, bh->b_data))
-					journal->j_failed_commit =
+				goto chksum_ok;
-						next_commit_ID;
+
-					brelse(bh);
+			if (jbd2_commit_block_csum_verify_partial(journal,
-					break;
+								  bh->b_data)) {
-				}
+				pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n",
+					  next_commit_ID, next_log_block);
+				goto chksum_ok;
 			}
-			if (pass == PASS_SCAN) {
+
-			chksum_ok:
+chksum_error:
-				last_trans_commit_time = commit_time;
+			if (commit_time < last_trans_commit_time)
-				head_block = next_log_block;
+				goto ignore_crc_mismatch;
+			info->end_transaction = next_commit_ID;
+			info->head_block = head_block;
+
+			if (!jbd2_has_feature_async_commit(journal)) {
+				journal->j_failed_commit = next_commit_ID;
+				break;
 			}
-			brelse(bh);
+
+chksum_ok:
+			last_trans_commit_time = commit_time;
+			head_block = next_log_block;
 			next_commit_ID++;
 			continue;
 
@@ -876,14 +865,11 @@ static int do_one_pass(journal_t *journal,
 
 			/* If we aren't in the REVOKE pass, then we can
 			 * just skip over this block. */
-			if (pass != PASS_REVOKE) {
+			if (pass != PASS_REVOKE)
-				brelse(bh);
 				continue;
-			}
 
 			err = scan_revoke_records(journal, bh,
 						  next_commit_ID, info);
-			brelse(bh);
 			if (err)
 				goto failed;
 			continue;
@@ -891,12 +877,12 @@ static int do_one_pass(journal_t *journal,
 		default:
 			jbd2_debug(3, "Unrecognised magic %d, end of scan.\n",
 				  blocktype);
-			brelse(bh);
 			goto done;
 		}
 	}
 
  done:
+	brelse(bh);
 	/*
 	 * We broke out of the log scan loop: either we came to the
 	 * known end of the log or we found an unexpected block in the
@@ -927,11 +913,10 @@ static int do_one_pass(journal_t *journal,
 			success = err;
 	}
 
-	if (block_error && success == 0)
-		success = -EIO;
 	return success;
 
  failed:
+	brelse(bh);
 	return err;
 }
 

include/linux/jbd2.h

@@ -1796,22 +1796,21 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal)
 static inline u32 jbd2_chksum(journal_t *journal, u32 crc,
 			      const void *address, unsigned int length)
 {
-	struct {
+	DEFINE_RAW_FLEX(struct shash_desc, desc, __ctx,
-		struct shash_desc shash;
+		DIV_ROUND_UP(JBD_MAX_CHECKSUM_SIZE,
-		char ctx[JBD_MAX_CHECKSUM_SIZE];
+			     sizeof(*((struct shash_desc *)0)->__ctx)));
-	} desc;
 	int err;
 
 	BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) >
 		JBD_MAX_CHECKSUM_SIZE);
 
-	desc.shash.tfm = journal->j_chksum_driver;
+	desc->tfm = journal->j_chksum_driver;
-	*(u32 *)desc.ctx = crc;
+	*(u32 *)desc->__ctx = crc;
 
-	err = crypto_shash_update(&desc.shash, address, length);
+	err = crypto_shash_update(desc, address, length);
 	BUG_ON(err);
 
-	return *(u32 *)desc.ctx;
+	return *(u32 *)desc->__ctx;
 }
 
 /* Return most recent uncommitted transaction */

mm/truncate.c

@@ -796,6 +796,21 @@ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to)
 	 */
 	if (folio_mkclean(folio))
 		folio_mark_dirty(folio);
+
+	/*
+	 * The post-eof range of the folio must be zeroed before it is exposed
+	 * to the file. Writeback normally does this, but since i_size has been
+	 * increased we handle it here.
+	 */
+	if (folio_test_dirty(folio)) {
+		unsigned int offset, end;
+
+		offset = from - folio_pos(folio);
+		end = min_t(unsigned int, to - folio_pos(folio),
+			    folio_size(folio));
+		folio_zero_segment(folio, offset, end);
+	}
+
 	folio_unlock(folio);
 	folio_put(folio);
 }