Merge tag 'for-5.18-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "A few more code and warning fixes.

  There's one feature ioctl removal patch slated for 5.18 that did not
  make it to the main pull request. It's just a one-liner and the ioctl
  has a v2 that's in use for a long time, no point to postpone it to
  5.19.

  Late update:

   - remove balance v1 ioctl, superseded by v2 in 2012

  Fixes:

   - add back cgroup attribution for compressed writes

   - add super block write start/end annotations to asynchronous balance

   - fix root reference count on an error handling path

   - in zoned mode, activate zone at the chunk allocation time to avoid
     ENOSPC due to timing issues

   - fix delayed allocation accounting for direct IO

  Warning fixes:

   - simplify assertion condition in zoned check

   - remove an unused variable"

* tag 'for-5.18-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: fix btrfs_submit_compressed_write cgroup attribution
  btrfs: fix root ref counts in error handling in btrfs_get_root_ref
  btrfs: zoned: activate block group only for extent allocation
  btrfs: return allocated block group from do_chunk_alloc()
  btrfs: mark resumed async balance as writing
  btrfs: remove support of balance v1 ioctl
  btrfs: release correct delalloc amount in direct IO write path
  btrfs: remove unused variable in btrfs_{start,write}_dirty_block_groups()
  btrfs: zoned: remove redundant condition in btrfs_run_delalloc_range

Author: torvalds

fs/btrfs/block-group.c

@@ -2503,12 +2503,6 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran
 		return ERR_PTR(ret);
 	}
 
-	/*
-	 * New block group is likely to be used soon. Try to activate it now.
-	 * Failure is OK for now.
-	 */
-	btrfs_zone_activate(cache);
-
 	ret = exclude_super_stripes(cache);
 	if (ret) {
 		/* We may have excluded something, so call this just in case */
@@ -2946,7 +2940,6 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans)
 	struct btrfs_path *path = NULL;
 	LIST_HEAD(dirty);
 	struct list_head *io = &cur_trans->io_bgs;
-	int num_started = 0;
 	int loops = 0;
 
 	spin_lock(&cur_trans->dirty_bgs_lock);
@@ -3012,7 +3005,6 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans)
 			cache->io_ctl.inode = NULL;
 			ret = btrfs_write_out_cache(trans, cache, path);
 			if (ret == 0 && cache->io_ctl.inode) {
-				num_started++;
 				should_put = 0;
 
 				/*
@@ -3113,7 +3105,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
 	int should_put;
 	struct btrfs_path *path;
 	struct list_head *io = &cur_trans->io_bgs;
-	int num_started = 0;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -3171,7 +3162,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
 			cache->io_ctl.inode = NULL;
 			ret = btrfs_write_out_cache(trans, cache, path);
 			if (ret == 0 && cache->io_ctl.inode) {
-				num_started++;
 				should_put = 0;
 				list_add_tail(&cache->io_list, io);
 			} else {
@@ -3455,7 +3445,7 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type)
 	return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
 }
 
-static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags)
+static struct btrfs_block_group *do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags)
 {
 	struct btrfs_block_group *bg;
 	int ret;
@@ -3542,7 +3532,11 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags)
 out:
 	btrfs_trans_release_chunk_metadata(trans);
 
-	return ret;
+	if (ret)
+		return ERR_PTR(ret);
+
+	btrfs_get_block_group(bg);
+	return bg;
 }
 
 /*
@@ -3657,10 +3651,17 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_space_info *space_info;
+	struct btrfs_block_group *ret_bg;
 	bool wait_for_alloc = false;
 	bool should_alloc = false;
+	bool from_extent_allocation = false;
 	int ret = 0;
 
+	if (force == CHUNK_ALLOC_FORCE_FOR_EXTENT) {
+		from_extent_allocation = true;
+		force = CHUNK_ALLOC_FORCE;
+	}
+
 	/* Don't re-enter if we're already allocating a chunk */
 	if (trans->allocating_chunk)
 		return -ENOSPC;
@@ -3750,9 +3751,22 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 			force_metadata_allocation(fs_info);
 	}
 
-	ret = do_chunk_alloc(trans, flags);
+	ret_bg = do_chunk_alloc(trans, flags);
 	trans->allocating_chunk = false;
 
+	if (IS_ERR(ret_bg)) {
+		ret = PTR_ERR(ret_bg);
+	} else if (from_extent_allocation) {
+		/*
+		 * New block group is likely to be used soon. Try to activate
+		 * it now. Failure is OK for now.
+		 */
+		btrfs_zone_activate(ret_bg);
+	}
+
+	if (!ret)
+		btrfs_put_block_group(ret_bg);
+
 	spin_lock(&space_info->lock);
 	if (ret < 0) {
 		if (ret == -ENOSPC)

fs/btrfs/block-group.h

@@ -35,11 +35,15 @@ enum btrfs_discard_state {
  * the FS with empty chunks
  *
  * CHUNK_ALLOC_FORCE means it must try to allocate one
+ *
+ * CHUNK_ALLOC_FORCE_FOR_EXTENT like CHUNK_ALLOC_FORCE but called from
+ * find_free_extent() that also activaes the zone
  */
 enum btrfs_chunk_alloc_enum {
 	CHUNK_ALLOC_NO_FORCE,
 	CHUNK_ALLOC_LIMITED,
 	CHUNK_ALLOC_FORCE,
+	CHUNK_ALLOC_FORCE_FOR_EXTENT,
 };
 
 struct btrfs_caching_control {

fs/btrfs/compression.c

@@ -537,6 +537,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	cb->orig_bio = NULL;
 	cb->nr_pages = nr_pages;
 
+	if (blkcg_css)
+		kthread_associate_blkcg(blkcg_css);
+
 	while (cur_disk_bytenr < disk_start + compressed_len) {
 		u64 offset = cur_disk_bytenr - disk_start;
 		unsigned int index = offset >> PAGE_SHIFT;
@@ -555,6 +558,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 				bio = NULL;
 				goto finish_cb;
 			}
+			if (blkcg_css)
+				bio->bi_opf |= REQ_CGROUP_PUNT;
 		}
 		/*
 		 * We should never reach next_stripe_start start as we will
@@ -612,6 +617,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start,
 	return 0;
 
 finish_cb:
+	if (blkcg_css)
+		kthread_associate_blkcg(NULL);
+
 	if (bio) {
 		bio->bi_status = ret;
 		bio_endio(bio);

fs/btrfs/disk-io.c

@@ -1850,9 +1850,10 @@ static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
 
 	ret = btrfs_insert_fs_root(fs_info, root);
 	if (ret) {
-		btrfs_put_root(root);
-		if (ret == -EEXIST)
+		if (ret == -EEXIST) {
+			btrfs_put_root(root);
 			goto again;
+		}
 		goto fail;
 	}
 	return root;

fs/btrfs/extent-tree.c

@@ -4082,7 +4082,7 @@ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info,
 			}
 
 			ret = btrfs_chunk_alloc(trans, ffe_ctl->flags,
-						CHUNK_ALLOC_FORCE);
+						CHUNK_ALLOC_FORCE_FOR_EXTENT);
 
 			/* Do not bail out on ENOSPC since we can do more. */
 			if (ret == -ENOSPC)

fs/btrfs/inode.c

@@ -2016,8 +2016,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page
 		 * to use run_delalloc_nocow() here, like for  regular
 		 * preallocated inodes.
 		 */
-		ASSERT(!zoned ||
-		       (zoned && btrfs_is_data_reloc_root(inode->root)));
+		ASSERT(!zoned || btrfs_is_data_reloc_root(inode->root));
 		ret = run_delalloc_nocow(inode, locked_page, start, end,
 					 page_started, nr_written);
 	} else if (!inode_can_compress(inode) ||
@@ -7444,6 +7443,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	u64 block_start, orig_start, orig_block_len, ram_bytes;
 	bool can_nocow = false;
 	bool space_reserved = false;
+	u64 prev_len;
 	int ret = 0;
 
 	/*
@@ -7471,6 +7471,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 			can_nocow = true;
 	}
 
+	prev_len = len;
 	if (can_nocow) {
 		struct extent_map *em2;
 
@@ -7500,8 +7501,6 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 			goto out;
 		}
 	} else {
-		const u64 prev_len = len;
-
 		/* Our caller expects us to free the input extent map. */
 		free_extent_map(em);
 		*map = NULL;
@@ -7532,7 +7531,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 	 * We have created our ordered extent, so we can now release our reservation
 	 * for an outstanding extent.
 	 */
-	btrfs_delalloc_release_extents(BTRFS_I(inode), len);
+	btrfs_delalloc_release_extents(BTRFS_I(inode), prev_len);
 
 	/*
 	 * Need to update the i_size under the extent lock so buffered

fs/btrfs/ioctl.c

@@ -5456,8 +5456,6 @@ long btrfs_ioctl(struct file *file, unsigned int
 		return btrfs_ioctl_fs_info(fs_info, argp);
 	case BTRFS_IOC_DEV_INFO:
 		return btrfs_ioctl_dev_info(fs_info, argp);
-	case BTRFS_IOC_BALANCE:
-		return btrfs_ioctl_balance(file, NULL);
 	case BTRFS_IOC_TREE_SEARCH:
 		return btrfs_ioctl_tree_search(inode, argp);
 	case BTRFS_IOC_TREE_SEARCH_V2:

fs/btrfs/volumes.c

@@ -4430,10 +4430,12 @@ static int balance_kthread(void *data)
 	struct btrfs_fs_info *fs_info = data;
 	int ret = 0;
 
+	sb_start_write(fs_info->sb);
 	mutex_lock(&fs_info->balance_mutex);
 	if (fs_info->balance_ctl)
 		ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL);
 	mutex_unlock(&fs_info->balance_mutex);
+	sb_end_write(fs_info->sb);
 
 	return ret;
 }