1 files changed, 93 insertions, 13 deletions

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 19b7db8b2117..232d5da7b7be 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -97,6 +97,7 @@ struct tree_block {
 		struct rb_node rb_node;
 		u64 bytenr;
 	}; /* Use rb_simple_node for search/insert */
+	u64 owner;
 	struct btrfs_key key;
 	unsigned int level:8;
 	unsigned int key_ready:1;
@@ -668,9 +669,7 @@ static void __del_reloc_root(struct btrfs_root *root)
 			RB_CLEAR_NODE(&node->rb_node);
 		}
 		spin_unlock(&rc->reloc_root_tree.lock);
-		if (!node)
-			return;
-		BUG_ON((struct btrfs_root *)node->data != root);
+		ASSERT(!node || (struct btrfs_root *)node->data == root);
 	}
 
 	/*
@@ -2393,8 +2392,8 @@ static int get_tree_block_key(struct btrfs_fs_info *fs_info,
 {
 	struct extent_buffer *eb;
 
-	eb = read_tree_block(fs_info, block->bytenr, 0, block->key.offset,
-			     block->level, NULL);
+	eb = read_tree_block(fs_info, block->bytenr, block->owner,
+			     block->key.offset, block->level, NULL);
 	if (IS_ERR(eb)) {
 		return PTR_ERR(eb);
 	} else if (!extent_buffer_uptodate(eb)) {
@@ -2493,7 +2492,8 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 	/* Kick in readahead for tree blocks with missing keys */
 	rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) {
 		if (!block->key_ready)
-			btrfs_readahead_tree_block(fs_info, block->bytenr, 0, 0,
+			btrfs_readahead_tree_block(fs_info, block->bytenr,
+						   block->owner, 0,
 						   block->level);
 	}
 
@@ -2553,6 +2553,31 @@ static noinline_for_stack int prealloc_file_extent_cluster(
 	if (ret)
 		return ret;
 
+	/*
+	 * On a zoned filesystem, we cannot preallocate the file region.
+	 * Instead, we dirty and fiemap_write the region.
+	 */
+	if (btrfs_is_zoned(inode->root->fs_info)) {
+		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);
+		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;
@@ -2615,7 +2640,7 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
 /*
  * Allow error injection to test balance cancellation
  */
-int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info)
+noinline int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info)
 {
 	return atomic_read(&fs_info->balance_cancel_req) ||
 		fatal_signal_pending(current);
@@ -2679,6 +2704,15 @@ static int relocate_file_extent_cluster(struct inode *inode,
 				goto out;
 			}
 		}
+		ret = set_page_extent_mapped(page);
+		if (ret < 0) {
+			btrfs_delalloc_release_metadata(BTRFS_I(inode),
+							PAGE_SIZE, true);
+			btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+			unlock_page(page);
+			put_page(page);
+			goto out;
+		}
 
 		if (PageReadahead(page)) {
 			page_cache_async_readahead(inode->i_mapping,
@@ -2706,8 +2740,6 @@ static int relocate_file_extent_cluster(struct inode *inode,
 
 		lock_extent(&BTRFS_I(inode)->io_tree, page_start, page_end);
 
-		set_page_extent_mapped(page);
-
 		if (nr < cluster->nr &&
 		    page_start + offset == cluster->boundary[nr]) {
 			set_extent_bits(&BTRFS_I(inode)->io_tree,
@@ -2749,6 +2781,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
 		}
 	}
 	WARN_ON(nr != cluster->nr);
+	if (btrfs_is_zoned(fs_info) && !ret)
+		ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
 out:
 	kfree(ra);
 	return ret;
@@ -2801,21 +2835,58 @@ static int add_tree_block(struct reloc_control *rc,
 	u32 item_size;
 	int level = -1;
 	u64 generation;
+	u64 owner = 0;
 
 	eb =  path->nodes[0];
 	item_size = btrfs_item_size_nr(eb, path->slots[0]);
 
 	if (extent_key->type == BTRFS_METADATA_ITEM_KEY ||
 	    item_size >= sizeof(*ei) + sizeof(*bi)) {
+		unsigned long ptr = 0, end;
+
 		ei = btrfs_item_ptr(eb, path->slots[0],
 				struct btrfs_extent_item);
+		end = (unsigned long)ei + item_size;
 		if (extent_key->type == BTRFS_EXTENT_ITEM_KEY) {
 			bi = (struct btrfs_tree_block_info *)(ei + 1);
 			level = btrfs_tree_block_level(eb, bi);
+			ptr = (unsigned long)(bi + 1);
 		} else {
 			level = (int)extent_key->offset;
+			ptr = (unsigned long)(ei + 1);
 		}
 		generation = btrfs_extent_generation(eb, ei);
+
+		/*
+		 * We're reading random blocks without knowing their owner ahead
+		 * of time.  This is ok most of the time, as all reloc roots and
+		 * fs roots have the same lock type.  However normal trees do
+		 * not, and the only way to know ahead of time is to read the
+		 * inline ref offset.  We know it's an fs root if
+		 *
+		 * 1. There's more than one ref.
+		 * 2. There's a SHARED_DATA_REF_KEY set.
+		 * 3. FULL_BACKREF is set on the flags.
+		 *
+		 * Otherwise it's safe to assume that the ref offset == the
+		 * owner of this block, so we can use that when calling
+		 * read_tree_block.
+		 */
+		if (btrfs_extent_refs(eb, ei) == 1 &&
+		    !(btrfs_extent_flags(eb, ei) &
+		      BTRFS_BLOCK_FLAG_FULL_BACKREF) &&
+		    ptr < end) {
+			struct btrfs_extent_inline_ref *iref;
+			int type;
+
+			iref = (struct btrfs_extent_inline_ref *)ptr;
+			type = btrfs_get_extent_inline_ref_type(eb, iref,
+							BTRFS_REF_TYPE_BLOCK);
+			if (type == BTRFS_REF_TYPE_INVALID)
+				return -EINVAL;
+			if (type == BTRFS_TREE_BLOCK_REF_KEY)
+				owner = btrfs_extent_inline_ref_offset(eb, iref);
+		}
 	} else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) {
 		btrfs_print_v0_err(eb->fs_info);
 		btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
@@ -2837,6 +2908,7 @@ static int add_tree_block(struct reloc_control *rc,
 	block->key.offset = generation;
 	block->level = level;
 	block->key_ready = 0;
+	block->owner = owner;
 
 	rb_node = rb_simple_insert(blocks, block->bytenr, &block->rb_node);
 	if (rb_node)
@@ -2975,11 +3047,16 @@ static int delete_v1_space_cache(struct extent_buffer *leaf,
 		return 0;
 
 	for (i = 0; i < btrfs_header_nritems(leaf); i++) {
+		u8 type;
+
 		btrfs_item_key_to_cpu(leaf, &key, i);
 		if (key.type != BTRFS_EXTENT_DATA_KEY)
 			continue;
 		ei = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
-		if (btrfs_file_extent_type(leaf, ei) == BTRFS_FILE_EXTENT_REG &&
+		type = btrfs_file_extent_type(leaf, ei);
+
+		if ((type == BTRFS_FILE_EXTENT_REG ||
+		     type == BTRFS_FILE_EXTENT_PREALLOC) &&
 		    btrfs_file_extent_disk_bytenr(leaf, ei) == data_bytenr) {
 			found = true;
 			space_cache_ino = key.objectid;
@@ -3384,8 +3461,12 @@ 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_is_zoned(trans->fs_info))
+		flags &= ~BTRFS_INODE_PREALLOC;
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -3400,8 +3481,7 @@ 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);
@@ -3429,7 +3509,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
 		return ERR_CAST(trans);
 	}
 
-	err = btrfs_find_free_objectid(root, &objectid);
+	err = btrfs_get_free_objectid(root, &objectid);
 	if (err)
 		goto out;