Merge tag 'ext4_for_linus-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "Ext4 bug fixes and cleanups, plus some additional kunit tests"

* tag 'ext4_for_linus-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (23 commits)
  ext4: initialize sbi->s_freeclusters_counter and sbi->s_dirtyclusters_counter before use in kunit test
  ext4: hold group lock in ext4 kunit test
  ext4: alloc test super block from sget
  ext4: kunit: use dynamic inode allocation
  ext4: enable meta_bg only when new desc blocks are needed
  ext4: remove unused parameter biop in ext4_issue_discard()
  ext4: remove SLAB_MEM_SPREAD flag usage
  ext4: verify s_clusters_per_group even without bigalloc
  ext4: fix corruption during on-line resize
  ext4: don't report EOPNOTSUPP errors from discard
  ext4: drop duplicate ea_inode handling in ext4_xattr_block_set()
  ext4: fold quota accounting into ext4_xattr_inode_lookup_create()
  ext4: correct best extent lstart adjustment logic
  ext4: forbid commit inconsistent quota data when errors=remount-ro
  ext4: add a hint for block bitmap corrupt state in mb_groups
  ext4: fix the comment of ext4_map_blocks()/ext4_ext_map_blocks()
  ext4: improve error msg for ext4_mb_seq_groups_show
  ext4: remove unused buddy_loaded in ext4_mb_seq_groups_show
  ext4: Add unit test for ext4_mb_mark_diskspace_used
  ext4: Add unit test for mb_free_blocks
  ...

fs/ext4/extents.c

@@ -4111,10 +4111,10 @@ static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode,
  *
  * Need to be called with
  * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block
- * (ie, create is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
+ * (ie, flags is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem)
  *
  * return > 0, number of blocks already mapped/allocated
- *          if create == 0 and these are pre-allocated blocks
+ *          if flags doesn't contain EXT4_GET_BLOCKS_CREATE and these are pre-allocated blocks
  *          	buffer head is unmapped
  *          otherwise blocks are mapped
  *
@@ -4218,7 +4218,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 
 	/*
 	 * requested block isn't allocated yet;
-	 * we couldn't try to create block if create flag is zero
+	 * we couldn't try to create block if flags doesn't contain EXT4_GET_BLOCKS_CREATE
 	 */
 	if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
 		ext4_lblk_t len;

fs/ext4/inode.c

@@ -465,9 +465,10 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
  * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping
  * based files
  *
- * On success, it returns the number of blocks being mapped or allocated.  if
- * create==0 and the blocks are pre-allocated and unwritten, the resulting @map
- * is marked as unwritten. If the create == 1, it will mark @map as mapped.
+ * On success, it returns the number of blocks being mapped or allocated.
+ * If flags doesn't contain EXT4_GET_BLOCKS_CREATE the blocks are
+ * pre-allocated and unwritten, the resulting @map is marked as unwritten.
+ * If the flags contain EXT4_GET_BLOCKS_CREATE, it will mark @map as mapped.
  *
  * It returns 0 if plain look up failed (blocks have not been allocated), in
  * that case, @map is returned as unmapped but we still do fill map->m_len to
@@ -589,8 +590,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
 	 * Returns if the blocks have already allocated
 	 *
 	 * Note that if blocks have been preallocated
-	 * ext4_ext_get_block() returns the create = 0
-	 * with buffer head unmapped.
+	 * ext4_ext_map_blocks() returns with buffer head unmapped
 	 */
 	if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED)
 		/*

fs/ext4/mballoc.c

@@ -3015,8 +3015,8 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 {
 	struct super_block *sb = pde_data(file_inode(seq->file));
 	ext4_group_t group = (ext4_group_t) ((unsigned long) v);
-	int i;
-	int err, buddy_loaded = 0;
+	int i, err;
+	char nbuf[16];
 	struct ext4_buddy e4b;
 	struct ext4_group_info *grinfo;
 	unsigned char blocksize_bits = min_t(unsigned char,
@@ -3043,23 +3043,26 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
 	if (unlikely(EXT4_MB_GRP_NEED_INIT(grinfo))) {
 		err = ext4_mb_load_buddy(sb, group, &e4b);
 		if (err) {
-			seq_printf(seq, "#%-5u: I/O error\n", group);
+			seq_printf(seq, "#%-5u: %s\n", group, ext4_decode_error(NULL, err, nbuf));
 			return 0;
 		}
-		buddy_loaded = 1;
+		ext4_mb_unload_buddy(&e4b);
 	}
 
+	/*
+	 * We care only about free space counters in the group info and
+	 * these are safe to access even after the buddy has been unloaded
+	 */
 	memcpy(&sg, grinfo, i);
-
-	if (buddy_loaded)
-		ext4_mb_unload_buddy(&e4b);
-
 	seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg.info.bb_free,
 			sg.info.bb_fragments, sg.info.bb_first_free);
 	for (i = 0; i <= 13; i++)
 		seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ?
 				sg.info.bb_counters[i] : 0);
-	seq_puts(seq, " ]\n");
+	seq_puts(seq, " ]");
+	if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info))
+		seq_puts(seq, " Block bitmap corrupted!");
+	seq_puts(seq, "\n");
 
 	return 0;
 }
@@ -3829,8 +3832,7 @@ void ext4_mb_release(struct super_block *sb)
 }
 
 static inline int ext4_issue_discard(struct super_block *sb,
-		ext4_group_t block_group, ext4_grpblk_t cluster, int count,
-		struct bio **biop)
+		ext4_group_t block_group, ext4_grpblk_t cluster, int count)
 {
 	ext4_fsblk_t discard_block;
 
@@ -3839,13 +3841,8 @@ static inline int ext4_issue_discard(struct super_block *sb,
 	count = EXT4_C2B(EXT4_SB(sb), count);
 	trace_ext4_discard_blocks(sb,
 			(unsigned long long) discard_block, count);
-	if (biop) {
-		return __blkdev_issue_discard(sb->s_bdev,
-			(sector_t)discard_block << (sb->s_blocksize_bits - 9),
-			(sector_t)count << (sb->s_blocksize_bits - 9),
-			GFP_NOFS, biop);
-	} else
-		return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
+
+	return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
 }
 
 static void ext4_free_data_in_buddy(struct super_block *sb,
@@ -5169,10 +5166,16 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 			.fe_len = ac->ac_orig_goal_len,
 		};
 		loff_t orig_goal_end = extent_logical_end(sbi, &ex);
+		loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex);
 
-		/* we can't allocate as much as normalizer wants.
-		 * so, found space must get proper lstart
-		 * to cover original request */
+		/*
+		 * We can't allocate as much as normalizer wants, so we try
+		 * to get proper lstart to cover the original request, except
+		 * when the goal doesn't cover the original request as below:
+		 *
+		 * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048
+		 * best_ex:0/200(200) -> adjusted: 1848/2048(200)
+		 */
 		BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical);
 		BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len);
 
@@ -5184,7 +5187,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 		 * 1. Check if best ex can be kept at end of goal (before
 		 *    cr_best_avail trimmed it) and still cover original start
 		 * 2. Else, check if best ex can be kept at start of goal and
-		 *    still cover original start
+		 *    still cover original end
 		 * 3. Else, keep the best ex at start of original request.
 		 */
 		ex.fe_len = ac->ac_b_ex.fe_len;
@@ -5194,7 +5197,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 			goto adjust_bex;
 
 		ex.fe_logical = ac->ac_g_ex.fe_logical;
-		if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex))
+		if (o_ex_end <= extent_logical_end(sbi, &ex))
 			goto adjust_bex;
 
 		ex.fe_logical = ac->ac_o_ex.fe_logical;
@@ -5202,7 +5205,6 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
 		ac->ac_b_ex.fe_logical = ex.fe_logical;
 
 		BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
-		BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
 		BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end);
 	}
 
@@ -6487,8 +6489,14 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
 	} else {
 		if (test_opt(sb, DISCARD)) {
 			err = ext4_issue_discard(sb, block_group, bit,
-						 count_clusters, NULL);
-			if (err && err != -EOPNOTSUPP)
+						 count_clusters);
+			/*
+			 * Ignore EOPNOTSUPP error. This is consistent with
+			 * what happens when using journal.
+			 */
+			if (err == -EOPNOTSUPP)
+				err = 0;
+			if (err)
 				ext4_msg(sb, KERN_WARNING, "discard request in"
 					 " group:%u block:%d count:%lu failed"
 					 " with %d", block_group, bit, count,
@@ -6738,7 +6746,7 @@ __acquires(bitlock)
 	 */
 	mb_mark_used(e4b, &ex);
 	ext4_unlock_group(sb, group);
-	ret = ext4_issue_discard(sb, group, start, count, NULL);
+	ret = ext4_issue_discard(sb, group, start, count);
 	ext4_lock_group(sb, group);
 	mb_free_blocks(NULL, e4b, start, ex.fe_len);
 	return ret;

fs/ext4/resize.c

@@ -1602,7 +1602,8 @@ static int ext4_flex_group_add(struct super_block *sb,
 		int gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
 		int gdb_num_end = ((group + flex_gd->count - 1) /
 				   EXT4_DESC_PER_BLOCK(sb));
-		int meta_bg = ext4_has_feature_meta_bg(sb);
+		int meta_bg = ext4_has_feature_meta_bg(sb) &&
+			      gdb_num >= le32_to_cpu(es->s_first_meta_bg);
 		sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr -
 					 ext4_group_first_block_no(sb, 0);
 
@@ -2084,7 +2085,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
 		}
 	}
 
-	if ((!resize_inode && !meta_bg) || n_blocks_count == o_blocks_count) {
+	if ((!resize_inode && !meta_bg && n_desc_blocks > o_desc_blocks) || n_blocks_count == o_blocks_count) {
 		err = ext4_convert_meta_bg(sb, resize_inode);
 		if (err)
 			goto out;

fs/ext4/super.c

@@ -4421,22 +4421,6 @@ static int ext4_handle_clustersize(struct super_block *sb)
 		}
 		sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
 			le32_to_cpu(es->s_log_block_size);
-		sbi->s_clusters_per_group =
-			le32_to_cpu(es->s_clusters_per_group);
-		if (sbi->s_clusters_per_group > sb->s_blocksize * 8) {
-			ext4_msg(sb, KERN_ERR,
-				 "#clusters per group too big: %lu",
-				 sbi->s_clusters_per_group);
-			return -EINVAL;
-		}
-		if (sbi->s_blocks_per_group !=
-		    (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) {
-			ext4_msg(sb, KERN_ERR, "blocks per group (%lu) and "
-				 "clusters per group (%lu) inconsistent",
-				 sbi->s_blocks_per_group,
-				 sbi->s_clusters_per_group);
-			return -EINVAL;
-		}
 	} else {
 		if (clustersize != sb->s_blocksize) {
 			ext4_msg(sb, KERN_ERR,
@@ -4450,9 +4434,21 @@ static int ext4_handle_clustersize(struct super_block *sb)
 				 sbi->s_blocks_per_group);
 			return -EINVAL;
 		}
-		sbi->s_clusters_per_group = sbi->s_blocks_per_group;
 		sbi->s_cluster_bits = 0;
 	}
+	sbi->s_clusters_per_group = le32_to_cpu(es->s_clusters_per_group);
+	if (sbi->s_clusters_per_group > sb->s_blocksize * 8) {
+		ext4_msg(sb, KERN_ERR, "#clusters per group too big: %lu",
+			 sbi->s_clusters_per_group);
+		return -EINVAL;
+	}
+	if (sbi->s_blocks_per_group !=
+	    (sbi->s_clusters_per_group * (clustersize / sb->s_blocksize))) {
+		ext4_msg(sb, KERN_ERR,
+			 "blocks per group (%lu) and clusters per group (%lu) inconsistent",
+			 sbi->s_blocks_per_group, sbi->s_clusters_per_group);
+		return -EINVAL;
+	}
 	sbi->s_cluster_ratio = clustersize / sb->s_blocksize;
 
 	/* Do we have standard group size of clustersize * 8 blocks ? */
@@ -6864,6 +6860,10 @@ static int ext4_write_dquot(struct dquot *dquot)
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 	ret = dquot_commit(dquot);
+	if (ret < 0)
+		ext4_error_err(dquot->dq_sb, -ret,
+			       "Failed to commit dquot type %d",
+			       dquot->dq_id.type);
 	err = ext4_journal_stop(handle);
 	if (!ret)
 		ret = err;
@@ -6880,6 +6880,10 @@ static int ext4_acquire_dquot(struct dquot *dquot)
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 	ret = dquot_acquire(dquot);
+	if (ret < 0)
+		ext4_error_err(dquot->dq_sb, -ret,
+			      "Failed to acquire dquot type %d",
+			      dquot->dq_id.type);
 	err = ext4_journal_stop(handle);
 	if (!ret)
 		ret = err;
@@ -6899,6 +6903,10 @@ static int ext4_release_dquot(struct dquot *dquot)
 		return PTR_ERR(handle);
 	}
 	ret = dquot_release(dquot);
+	if (ret < 0)
+		ext4_error_err(dquot->dq_sb, -ret,
+			       "Failed to release dquot type %d",
+			       dquot->dq_id.type);
 	err = ext4_journal_stop(handle);
 	if (!ret)
 		ret = err;

fs/ext4/xattr.c

@@ -1565,46 +1565,49 @@ ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
 /*
  * Add value of the EA in an inode.
  */
-static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode,
-					  const void *value, size_t value_len,
-					  struct inode **ret_inode)
+static struct inode *ext4_xattr_inode_lookup_create(handle_t *handle,
+		struct inode *inode, const void *value, size_t value_len)
 {
 	struct inode *ea_inode;
 	u32 hash;
 	int err;
 
+	/* Account inode & space to quota even if sharing... */
+	err = ext4_xattr_inode_alloc_quota(inode, value_len);
+	if (err)
+		return ERR_PTR(err);
+
 	hash = ext4_xattr_inode_hash(EXT4_SB(inode->i_sb), value, value_len);
 	ea_inode = ext4_xattr_inode_cache_find(inode, value, value_len, hash);
 	if (ea_inode) {
 		err = ext4_xattr_inode_inc_ref(handle, ea_inode);
-		if (err) {
-			iput(ea_inode);
-			return err;
-		}
-
-		*ret_inode = ea_inode;
-		return 0;
+		if (err)
+			goto out_err;
+		return ea_inode;
 	}
 
 	/* Create an inode for the EA value */
 	ea_inode = ext4_xattr_inode_create(handle, inode, hash);
-	if (IS_ERR(ea_inode))
-		return PTR_ERR(ea_inode);
+	if (IS_ERR(ea_inode)) {
+		ext4_xattr_inode_free_quota(inode, NULL, value_len);
+		return ea_inode;
+	}
 
 	err = ext4_xattr_inode_write(handle, ea_inode, value, value_len);
 	if (err) {
 		if (ext4_xattr_inode_dec_ref(handle, ea_inode))
 			ext4_warning_inode(ea_inode, "cleanup dec ref error %d", err);
-		iput(ea_inode);
-		return err;
+		goto out_err;
 	}
 
 	if (EA_INODE_CACHE(inode))
 		mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash,
 				      ea_inode->i_ino, true /* reusable */);
-
-	*ret_inode = ea_inode;
-	return 0;
+	return ea_inode;
+out_err:
+	iput(ea_inode);
+	ext4_xattr_inode_free_quota(inode, NULL, value_len);
+	return ERR_PTR(err);
 }
 
 /*
@@ -1712,16 +1715,11 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 	if (i->value && in_inode) {
 		WARN_ON_ONCE(!i->value_len);
 
-		ret = ext4_xattr_inode_alloc_quota(inode, i->value_len);
-		if (ret)
-			goto out;
-
-		ret = ext4_xattr_inode_lookup_create(handle, inode, i->value,
-						     i->value_len,
-						     &new_ea_inode);
-		if (ret) {
+		new_ea_inode = ext4_xattr_inode_lookup_create(handle, inode,
+					i->value, i->value_len);
+		if (IS_ERR(new_ea_inode)) {
+			ret = PTR_ERR(new_ea_inode);
 			new_ea_inode = NULL;
-			ext4_xattr_inode_free_quota(inode, NULL, i->value_len);
 			goto out;
 		}
 	}
@@ -2160,17 +2158,6 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 						      ENTRY(header(s->base)+1));
 			if (error)
 				goto getblk_failed;
-			if (ea_inode) {
-				/* Drop the extra ref on ea_inode. */
-				error = ext4_xattr_inode_dec_ref(handle,
-								 ea_inode);
-				if (error)
-					ext4_warning_inode(ea_inode,
-							   "dec ref error=%d",
-							   error);
-				iput(ea_inode);
-				ea_inode = NULL;
-			}
 
 			lock_buffer(new_bh);
 			error = ext4_journal_get_create_access(handle, sb,