Merge tag 'for-6.8-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "A few regular fixes and one fix for space reservation regression since
  6.7 that users have been reporting:

   - fix over-reservation of metadata chunks due to not keeping proper
     balance between global block reserve and delayed refs reserve; in
     practice this leaves behind empty metadata block groups, the
     workaround is to reclaim them by using the '-musage=1' balance
     filter

   - other space reservation fixes:
      - do not delete unused block group if it may be used soon
      - do not reserve space for checksums for NOCOW files

   - fix extent map assertion failure when writing out free space inode

   - reject encoded write if inode has nodatasum flag set

   - fix chunk map leak when loading block group zone info"

* tag 'for-6.8-rc4-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: don't refill whole delayed refs block reserve when starting transaction
  btrfs: zoned: fix chunk map leak when loading block group zone info
  btrfs: reject encoded write if inode has nodatasum flag set
  btrfs: don't reserve space for checksums when writing to nocow files
  btrfs: add new unused block groups to the list of unused block groups
  btrfs: do not delete unused block group if it may be used soon
  btrfs: add and use helper to check if block group is used
  btrfs: don't drop extent_map for free space inode on write error

fs/btrfs/block-group.c

@@ -1455,6 +1455,7 @@ static bool clean_pinned_extents(struct btrfs_trans_handle *trans,
  */
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 {
+	LIST_HEAD(retry_list);
 	struct btrfs_block_group *block_group;
 	struct btrfs_space_info *space_info;
 	struct btrfs_trans_handle *trans;
@@ -1476,6 +1477,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 
 	spin_lock(&fs_info->unused_bgs_lock);
 	while (!list_empty(&fs_info->unused_bgs)) {
+		u64 used;
 		int trimming;
 
 		block_group = list_first_entry(&fs_info->unused_bgs,
@@ -1511,9 +1513,9 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			goto next;
 		}
 
+		spin_lock(&space_info->lock);
 		spin_lock(&block_group->lock);
-		if (block_group->reserved || block_group->pinned ||
-		    block_group->used || block_group->ro ||
+		if (btrfs_is_block_group_used(block_group) || block_group->ro ||
 		    list_is_singular(&block_group->list)) {
 			/*
 			 * We want to bail if we made new allocations or have
@@ -1523,10 +1525,49 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			 */
 			trace_btrfs_skip_unused_block_group(block_group);
 			spin_unlock(&block_group->lock);
+			spin_unlock(&space_info->lock);
 			up_write(&space_info->groups_sem);
 			goto next;
 		}
+
+		/*
+		 * The block group may be unused but there may be space reserved
+		 * accounting with the existence of that block group, that is,
+		 * space_info->bytes_may_use was incremented by a task but no
+		 * space was yet allocated from the block group by the task.
+		 * That space may or may not be allocated, as we are generally
+		 * pessimistic about space reservation for metadata as well as
+		 * for data when using compression (as we reserve space based on
+		 * the worst case, when data can't be compressed, and before
+		 * actually attempting compression, before starting writeback).
+		 *
+		 * So check if the total space of the space_info minus the size
+		 * of this block group is less than the used space of the
+		 * space_info - if that's the case, then it means we have tasks
+		 * that might be relying on the block group in order to allocate
+		 * extents, and add back the block group to the unused list when
+		 * we finish, so that we retry later in case no tasks ended up
+		 * needing to allocate extents from the block group.
+		 */
+		used = btrfs_space_info_used(space_info, true);
+		if (space_info->total_bytes - block_group->length < used) {
+			/*
+			 * Add a reference for the list, compensate for the ref
+			 * drop under the "next" label for the
+			 * fs_info->unused_bgs list.
+			 */
+			btrfs_get_block_group(block_group);
+			list_add_tail(&block_group->bg_list, &retry_list);
+
+			trace_btrfs_skip_unused_block_group(block_group);
+			spin_unlock(&block_group->lock);
+			spin_unlock(&space_info->lock);
+			up_write(&space_info->groups_sem);
+			goto next;
+		}
+
 		spin_unlock(&block_group->lock);
+		spin_unlock(&space_info->lock);
 
 		/* We don't want to force the issue, only flip if it's ok. */
 		ret = inc_block_group_ro(block_group, 0);
@@ -1650,12 +1691,16 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		btrfs_put_block_group(block_group);
 		spin_lock(&fs_info->unused_bgs_lock);
 	}
+	list_splice_tail(&retry_list, &fs_info->unused_bgs);
 	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 	return;
 
 flip_async:
 	btrfs_end_transaction(trans);
+	spin_lock(&fs_info->unused_bgs_lock);
+	list_splice_tail(&retry_list, &fs_info->unused_bgs);
+	spin_unlock(&fs_info->unused_bgs_lock);
 	mutex_unlock(&fs_info->reclaim_bgs_lock);
 	btrfs_put_block_group(block_group);
 	btrfs_discard_punt_unused_bgs_list(fs_info);
@@ -2684,6 +2729,37 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 		btrfs_dec_delayed_refs_rsv_bg_inserts(fs_info);
 		list_del_init(&block_group->bg_list);
 		clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags);
+
+		/*
+		 * If the block group is still unused, add it to the list of
+		 * unused block groups. The block group may have been created in
+		 * order to satisfy a space reservation, in which case the
+		 * extent allocation only happens later. But often we don't
+		 * actually need to allocate space that we previously reserved,
+		 * so the block group may become unused for a long time. For
+		 * example for metadata we generally reserve space for a worst
+		 * possible scenario, but then don't end up allocating all that
+		 * space or none at all (due to no need to COW, extent buffers
+		 * were already COWed in the current transaction and still
+		 * unwritten, tree heights lower than the maximum possible
+		 * height, etc). For data we generally reserve the axact amount
+		 * of space we are going to allocate later, the exception is
+		 * when using compression, as we must reserve space based on the
+		 * uncompressed data size, because the compression is only done
+		 * when writeback triggered and we don't know how much space we
+		 * are actually going to need, so we reserve the uncompressed
+		 * size because the data may be uncompressible in the worst case.
+		 */
+		if (ret == 0) {
+			bool used;
+
+			spin_lock(&block_group->lock);
+			used = btrfs_is_block_group_used(block_group);
+			spin_unlock(&block_group->lock);
+
+			if (!used)
+				btrfs_mark_bg_unused(block_group);
+		}
 	}
 	btrfs_trans_release_chunk_metadata(trans);
 }

fs/btrfs/block-group.h

@@ -257,6 +257,13 @@ static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group)
 	return (block_group->start + block_group->length);
 }
 
+static inline bool btrfs_is_block_group_used(const struct btrfs_block_group *bg)
+{
+	lockdep_assert_held(&bg->lock);
+
+	return (bg->used > 0 || bg->reserved > 0 || bg->pinned > 0);
+}
+
 static inline bool btrfs_is_block_group_data_only(
 					struct btrfs_block_group *block_group)
 {

fs/btrfs/delalloc-space.c

@@ -245,7 +245,6 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
 	u64 reserve_size = 0;
 	u64 qgroup_rsv_size = 0;
-	u64 csum_leaves;
 	unsigned outstanding_extents;
 
 	lockdep_assert_held(&inode->lock);
@@ -260,10 +259,12 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 						outstanding_extents);
 		reserve_size += btrfs_calc_metadata_size(fs_info, 1);
 	}
-	csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
-						 inode->csum_bytes);
-	reserve_size += btrfs_calc_insert_metadata_size(fs_info,
-							csum_leaves);
+	if (!(inode->flags & BTRFS_INODE_NODATASUM)) {
+		u64 csum_leaves;
+
+		csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes);
+		reserve_size += btrfs_calc_insert_metadata_size(fs_info, csum_leaves);
+	}
 	/*
 	 * For qgroup rsv, the calculation is very simple:
 	 * account one nodesize for each outstanding extent
@@ -278,14 +279,20 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	spin_unlock(&block_rsv->lock);
 }
 
-static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
+static void calc_inode_reservations(struct btrfs_inode *inode,
 				    u64 num_bytes, u64 disk_num_bytes,
 				    u64 *meta_reserve, u64 *qgroup_reserve)
 {
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 nr_extents = count_max_extents(fs_info, num_bytes);
-	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
+	u64 csum_leaves;
 	u64 inode_update = btrfs_calc_metadata_size(fs_info, 1);
 
+	if (inode->flags & BTRFS_INODE_NODATASUM)
+		csum_leaves = 0;
+	else
+		csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, disk_num_bytes);
+
 	*meta_reserve = btrfs_calc_insert_metadata_size(fs_info,
 						nr_extents + csum_leaves);
 
@@ -337,7 +344,7 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	 * everything out and try again, which is bad.  This way we just
 	 * over-reserve slightly, and clean up the mess when we are done.
 	 */
-	calc_inode_reservations(fs_info, num_bytes, disk_num_bytes,
+	calc_inode_reservations(inode, num_bytes, disk_num_bytes,
 				&meta_reserve, &qgroup_reserve);
 	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true,
 						 noflush);
@@ -359,7 +366,8 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes,
 	nr_extents = count_max_extents(fs_info, num_bytes);
 	spin_lock(&inode->lock);
 	btrfs_mod_outstanding_extents(inode, nr_extents);
-	inode->csum_bytes += disk_num_bytes;
+	if (!(inode->flags & BTRFS_INODE_NODATASUM))
+		inode->csum_bytes += disk_num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
 
@@ -393,7 +401,8 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 	spin_lock(&inode->lock);
-	inode->csum_bytes -= num_bytes;
+	if (!(inode->flags & BTRFS_INODE_NODATASUM))
+		inode->csum_bytes -= num_bytes;
 	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
 	spin_unlock(&inode->lock);
 

fs/btrfs/inode.c

@@ -3184,8 +3184,23 @@ int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
 			unwritten_start += logical_len;
 		clear_extent_uptodate(io_tree, unwritten_start, end, NULL);
 
-		/* Drop extent maps for the part of the extent we didn't write. */
-		btrfs_drop_extent_map_range(inode, unwritten_start, end, false);
+		/*
+		 * Drop extent maps for the part of the extent we didn't write.
+		 *
+		 * We have an exception here for the free_space_inode, this is
+		 * because when we do btrfs_get_extent() on the free space inode
+		 * we will search the commit root.  If this is a new block group
+		 * we won't find anything, and we will trip over the assert in
+		 * writepage where we do ASSERT(em->block_start !=
+		 * EXTENT_MAP_HOLE).
+		 *
+		 * Theoretically we could also skip this for any NOCOW extent as
+		 * we don't mess with the extent map tree in the NOCOW case, but
+		 * for now simply skip this if we are the free space inode.
+		 */
+		if (!btrfs_is_free_space_inode(inode))
+			btrfs_drop_extent_map_range(inode, unwritten_start,
+						    end, false);
 
 		/*
 		 * If the ordered extent had an IOERR or something else went
@@ -10273,6 +10288,13 @@ ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
 	if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE)
 		return -EINVAL;
 
+	/*
+	 * Compressed extents should always have checksums, so error out if we
+	 * have a NOCOW file or inode was created while mounted with NODATASUM.
+	 */
+	if (inode->flags & BTRFS_INODE_NODATASUM)
+		return -EINVAL;
+
 	orig_count = iov_iter_count(from);
 
 	/* The extent size must be sane. */

fs/btrfs/transaction.c

@@ -564,56 +564,22 @@ static int btrfs_reserve_trans_metadata(struct btrfs_fs_info *fs_info,
 					u64 num_bytes,
 					u64 *delayed_refs_bytes)
 {
-	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
 	struct btrfs_space_info *si = fs_info->trans_block_rsv.space_info;
-	u64 extra_delayed_refs_bytes = 0;
-	u64 bytes;
+	u64 bytes = num_bytes + *delayed_refs_bytes;
 	int ret;
 
-	/*
-	 * If there's a gap between the size of the delayed refs reserve and
-	 * its reserved space, than some tasks have added delayed refs or bumped
-	 * its size otherwise (due to block group creation or removal, or block
-	 * group item update). Also try to allocate that gap in order to prevent
-	 * using (and possibly abusing) the global reserve when committing the
-	 * transaction.
-	 */
-	if (flush == BTRFS_RESERVE_FLUSH_ALL &&
-	    !btrfs_block_rsv_full(delayed_refs_rsv)) {
-		spin_lock(&delayed_refs_rsv->lock);
-		if (delayed_refs_rsv->size > delayed_refs_rsv->reserved)
-			extra_delayed_refs_bytes = delayed_refs_rsv->size -
-				delayed_refs_rsv->reserved;
-		spin_unlock(&delayed_refs_rsv->lock);
-	}
-
-	bytes = num_bytes + *delayed_refs_bytes + extra_delayed_refs_bytes;
-
 	/*
 	 * We want to reserve all the bytes we may need all at once, so we only
 	 * do 1 enospc flushing cycle per transaction start.
 	 */
 	ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
-	if (ret == 0) {
-		if (extra_delayed_refs_bytes > 0)
-			btrfs_migrate_to_delayed_refs_rsv(fs_info,
-							  extra_delayed_refs_bytes);
-		return 0;
-	}
-
-	if (extra_delayed_refs_bytes > 0) {
-		bytes -= extra_delayed_refs_bytes;
-		ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);
-		if (ret == 0)
-			return 0;
-	}
 
 	/*
 	 * If we are an emergency flush, which can steal from the global block
 	 * reserve, then attempt to not reserve space for the delayed refs, as
 	 * we will consume space for them from the global block reserve.
 	 */
-	if (flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) {
+	if (ret && flush == BTRFS_RESERVE_FLUSH_ALL_STEAL) {
 		bytes -= *delayed_refs_bytes;
 		*delayed_refs_bytes = 0;
 		ret = btrfs_reserve_metadata_bytes(fs_info, si, bytes, flush);

fs/btrfs/zoned.c

@@ -1670,6 +1670,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
 	}
 	bitmap_free(active);
 	kfree(zone_info);
+	btrfs_free_chunk_map(map);
 
 	return ret;
 }