To serialize allocation and submit_bio, we introduced mutex around them. As a result, preallocation must be completely disabled to avoid a deadlock. Since current relocation process relies on preallocation to move file data extents, it must be handled in another way. In ZONED mode, we just truncate the inode to the size that we wanted to pre-allocate. Then, we flush dirty pages on the file before finishing relocation process. run_delalloc_zoned() will handle all the allocation and submit IOs to the underlying layers. Signed-off-by: Naohiro Aota <naohiro.aota@xxxxxxx> --- fs/btrfs/relocation.c | 35 +++++++++++++++++++++++++++++++++-- 1 file changed, 33 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 4ba1ab9cc76d..5bd1f2e61062 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2600,6 +2600,32 @@ static noinline_for_stack int prealloc_file_extent_cluster( if (ret) return ret; + /* + * In ZONED mode, we cannot preallocate the file region. Instead, we + * dirty and fiemap_write the region. + */ + + if (btrfs_fs_incompat(inode->root->fs_info, ZONED)) { + struct btrfs_root *root = inode->root; + struct btrfs_trans_handle *trans; + + end = cluster->end - offset + 1; + trans = btrfs_start_transaction(root, 1); + if (IS_ERR(trans)) + return PTR_ERR(trans); + + inode->vfs_inode.i_ctime = current_time(&inode->vfs_inode); + i_size_write(&inode->vfs_inode, end); + ret = btrfs_update_inode(trans, root, &inode->vfs_inode); + if (ret) { + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + return ret; + } + + return btrfs_end_transaction(trans); + } + inode_lock(&inode->vfs_inode); for (nr = 0; nr < cluster->nr; nr++) { start = cluster->boundary[nr] - offset; @@ -2796,6 +2822,8 @@ static int relocate_file_extent_cluster(struct inode *inode, } } WARN_ON(nr != cluster->nr); + if (btrfs_fs_incompat(fs_info, ZONED) && !ret) + ret = btrfs_wait_ordered_range(inode, 0, (u64)-1); out: kfree(ra); return ret; @@ -3431,8 +3459,12 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, struct btrfs_path *path; struct btrfs_inode_item *item; struct extent_buffer *leaf; + u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC; int ret; + if (btrfs_fs_incompat(trans->fs_info, ZONED)) + flags &= ~BTRFS_INODE_PREALLOC; + path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -3447,8 +3479,7 @@ static int __insert_orphan_inode(struct btrfs_trans_handle *trans, btrfs_set_inode_generation(leaf, item, 1); btrfs_set_inode_size(leaf, item, 0); btrfs_set_inode_mode(leaf, item, S_IFREG | 0600); - btrfs_set_inode_flags(leaf, item, BTRFS_INODE_NOCOMPRESS | - BTRFS_INODE_PREALLOC); + btrfs_set_inode_flags(leaf, item, flags); btrfs_mark_buffer_dirty(leaf); out: btrfs_free_path(path); -- 2.27.0