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()
  ...

Author: torvalds

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(len, GFP_KERNEL);
+	new_fn = kzalloc(struct_size(new_fn, name, ent_name->len + 1),
+			 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 @@ static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode,
 	/* 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 @@ static int ext4_alloc_file_blocks(struct file *file, ext4_lblk_t offset,
 			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 @@ static int __es_insert_extent(struct inode *inode, struct extent_status *newes,
  */
 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",
-		 lblk, len, pblk, status, flags, inode->i_ino);
+	es_debug("add [%u/%u) %llu %x %d to extent status tree of inode %lu\n",
+		 lblk, len, pblk, status, delalloc_reserve_used, inode->i_ino);
 
 	if (!len)
 		return;
@@ -945,7 +945,7 @@ void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
 	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 &&
-	    (!is_ineligible ||
-	     (is_ineligible && tid_gt(tid, sbi->s_fc_ineligible_tid))))
+	if (has_transaction && (!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 ext4_handle_inode_extension(inode, pos, size, size);
+		return 0;
+	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_simulate_fail_bh(sb, bh, EXT4_SIM_IBITMAP_EIO);
+	ext4_read_bh(bh, REQ_META | REQ_PRIO,
+		     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 - "