Merge tag 'for-5.18-rc5-tag' of git://git.kernel.org/pub/scm/linux/ke…

…rnel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "Regression fixes in zone activation:

   - move a loop invariant out of the loop to avoid checking space
     status

   - properly handle unlimited activation

  Other fixes:

   - for subpage, force the free space v2 mount to avoid a warning and
     make it easy to switch a filesystem on different page size systems

   - export sysfs status of exclusive operation 'balance paused', so the
     user space tools can recognize it and allow adding a device with
     paused balance

   - fix assertion failure when logging directory key range item"

* tag 'for-5.18-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: sysfs: export the balance paused state of exclusive operation
  btrfs: fix assertion failure when logging directory key range item
  btrfs: zoned: activate block group properly on unlimited active zone device
  btrfs: zoned: move non-changing condition check out of the loop
  btrfs: force v2 space cache usage for subpage mount

fs/btrfs/disk-io.c

@@ -3658,6 +3658,17 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	if (sectorsize < PAGE_SIZE) {
 		struct btrfs_subpage_info *subpage_info;
 
+		/*
+		 * V1 space cache has some hardcoded PAGE_SIZE usage, and is
+		 * going to be deprecated.
+		 *
+		 * Force to use v2 cache for subpage case.
+		 */
+		btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE);
+		btrfs_set_and_info(fs_info, FREE_SPACE_TREE,
+			"forcing free space tree for sector size %u with page size %lu",
+			sectorsize, PAGE_SIZE);
+
 		btrfs_warn(fs_info,
 		"read-write for sector size %u with page size %lu is experimental",
 			   sectorsize, PAGE_SIZE);

fs/btrfs/sysfs.c

@@ -922,6 +922,9 @@ static ssize_t btrfs_exclusive_operation_show(struct kobject *kobj,
 		case BTRFS_EXCLOP_BALANCE:
 			str = "balance\n";
 			break;
+		case BTRFS_EXCLOP_BALANCE_PAUSED:
+			str = "balance paused\n";
+			break;
 		case BTRFS_EXCLOP_DEV_ADD:
 			str = "device add\n";
 			break;

fs/btrfs/tree-log.c

@@ -3721,11 +3721,29 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans,
 	key.offset = first_offset;
 	key.type = BTRFS_DIR_LOG_INDEX_KEY;
 	ret = btrfs_insert_empty_item(trans, log, path, &key, sizeof(*item));
-	if (ret)
+	/*
+	 * -EEXIST is fine and can happen sporadically when we are logging a
+	 * directory and have concurrent insertions in the subvolume's tree for
+	 * items from other inodes and that result in pushing off some dir items
+	 * from one leaf to another in order to accommodate for the new items.
+	 * This results in logging the same dir index range key.
+	 */
+	if (ret && ret != -EEXIST)
 		return ret;
 
 	item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 			      struct btrfs_dir_log_item);
+	if (ret == -EEXIST) {
+		const u64 curr_end = btrfs_dir_log_end(path->nodes[0], item);
+
+		/*
+		 * btrfs_del_dir_entries_in_log() might have been called during
+		 * an unlink between the initial insertion of this key and the
+		 * current update, or we might be logging a single entry deletion
+		 * during a rename, so set the new last_offset to the max value.
+		 */
+		last_offset = max(last_offset, curr_end);
+	}
 	btrfs_set_dir_log_end(path->nodes[0], item, last_offset);
 	btrfs_mark_buffer_dirty(path->nodes[0]);
 	btrfs_release_path(path);
@@ -3849,13 +3867,6 @@ static int process_dir_items_leaf(struct btrfs_trans_handle *trans,
 				ret = insert_dir_log_key(trans, log, dst_path,
 						 ino, *last_old_dentry_offset + 1,
 						 key.offset - 1);
-				/*
-				 * -EEXIST should never happen because when we
-				 * log a directory in full mode (LOG_INODE_ALL)
-				 * we drop all BTRFS_DIR_LOG_INDEX_KEY keys from
-				 * the log tree.
-				 */
-				ASSERT(ret != -EEXIST);
 				if (ret < 0)
 					return ret;
 			}
@@ -7031,12 +7042,12 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
 		/*
 		 * Other concurrent task might be logging the old directory,
 		 * as it can be triggered when logging other inode that had or
-		 * still has a dentry in the old directory. So take the old
-		 * directory's log_mutex to prevent getting an -EEXIST when
-		 * logging a key to record the deletion, or having that other
-		 * task logging the old directory get an -EEXIST if it attempts
-		 * to log the same key after we just did it. In both cases that
-		 * would result in falling back to a transaction commit.
+		 * still has a dentry in the old directory. We lock the old
+		 * directory's log_mutex to ensure the deletion of the old
+		 * name is persisted, because during directory logging we
+		 * delete all BTRFS_DIR_LOG_INDEX_KEY keys and the deletion of
+		 * the old name's dir index item is in the delayed items, so
+		 * it could be missed by an in progress directory logging.
 		 */
 		mutex_lock(&old_dir->log_mutex);
 		ret = del_logged_dentry(trans, log, path, btrfs_ino(old_dir),

fs/btrfs/zoned.c

@@ -1835,42 +1835,36 @@ bool btrfs_zone_activate(struct btrfs_block_group *block_group)
 		goto out_unlock;
 	}
 
+	/* No space left */
+	if (block_group->alloc_offset == block_group->zone_capacity) {
+		ret = false;
+		goto out_unlock;
+	}
+
 	for (i = 0; i < map->num_stripes; i++) {
 		device = map->stripes[i].dev;
 		physical = map->stripes[i].physical;
 
 		if (device->zone_info->max_active_zones == 0)
 			continue;
 
-		/* No space left */
-		if (block_group->alloc_offset == block_group->zone_capacity) {
-			ret = false;
-			goto out_unlock;
-		}
-
 		if (!btrfs_dev_set_active_zone(device, physical)) {
 			/* Cannot activate the zone */
 			ret = false;
 			goto out_unlock;
 		}
-
-		/* Successfully activated all the zones */
-		if (i == map->num_stripes - 1)
-			block_group->zone_is_active = 1;
-
-
 	}
+
+	/* Successfully activated all the zones */
+	block_group->zone_is_active = 1;
 	spin_unlock(&block_group->lock);
 
-	if (block_group->zone_is_active) {
-		/* For the active block group list */
-		btrfs_get_block_group(block_group);
+	/* For the active block group list */
+	btrfs_get_block_group(block_group);
 
-		spin_lock(&fs_info->zone_active_bgs_lock);
-		list_add_tail(&block_group->active_bg_list,
-			      &fs_info->zone_active_bgs);
-		spin_unlock(&fs_info->zone_active_bgs_lock);
-	}
+	spin_lock(&fs_info->zone_active_bgs_lock);
+	list_add_tail(&block_group->active_bg_list, &fs_info->zone_active_bgs);
+	spin_unlock(&fs_info->zone_active_bgs_lock);
 
 	return true;