Merge tag 'for-4.16-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - when NR_CPUS is large, a SRCU structure can significantly inflate
   size of the main filesystem structure that would not be possible to
   allocate by kmalloc, so the kvalloc fallback is used

 - improved error handling

 - fix endiannes when printing some filesystem attributes via sysfs,
   this is could happen when a filesystem is moved between different
   endianity hosts

 - send fixes: the NO_HOLE mode should not send a write operation for a
   file hole

 - fix log replay for for special files followed by file hardlinks

 - fix log replay failure after unlink and link combination

 - fix max chunk size calculation for DUP allocation

* tag 'for-4.16-rc3-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  Btrfs: fix log replay failure after unlink and link combination
  Btrfs: fix log replay failure after linking special file and fsync
  Btrfs: send, fix issuing write op when processing hole in no data mode
  btrfs: use proper endianness accessors for super_copy
  btrfs: alloc_chunk: fix DUP stripe size handling
  btrfs: Handle btrfs_set_extent_delalloc failure in relocate_file_extent_cluster
  btrfs: handle failure of add_pending_csums
  btrfs: use kvzalloc to allocate btrfs_fs_info

1 files changed, 110 insertions, 4 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 4fd19b4d6675..434457794c27 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -967,7 +967,9 @@ static noinline int backref_in_log(struct btrfs_root *log,
 	ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
 
 	if (key->type == BTRFS_INODE_EXTREF_KEY) {
-		if (btrfs_find_name_in_ext_backref(path, ref_objectid,
+		if (btrfs_find_name_in_ext_backref(path->nodes[0],
+						   path->slots[0],
+						   ref_objectid,
 						   name, namelen, NULL))
 			match = 1;
 
@@ -1191,7 +1193,8 @@ static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
 	read_extent_buffer(eb, *name, (unsigned long)&extref->name,
 			   *namelen);
 
-	*index = btrfs_inode_extref_index(eb, extref);
+	if (index)
+		*index = btrfs_inode_extref_index(eb, extref);
 	if (parent_objectid)
 		*parent_objectid = btrfs_inode_extref_parent(eb, extref);
 
@@ -1212,12 +1215,102 @@ static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
 
 	read_extent_buffer(eb, *name, (unsigned long)(ref + 1), *namelen);
 
-	*index = btrfs_inode_ref_index(eb, ref);
+	if (index)
+		*index = btrfs_inode_ref_index(eb, ref);
 
 	return 0;
 }
 
 /*
+ * Take an inode reference item from the log tree and iterate all names from the
+ * inode reference item in the subvolume tree with the same key (if it exists).
+ * For any name that is not in the inode reference item from the log tree, do a
+ * proper unlink of that name (that is, remove its entry from the inode
+ * reference item and both dir index keys).
+ */
+static int unlink_old_inode_refs(struct btrfs_trans_handle *trans,
+				 struct btrfs_root *root,
+				 struct btrfs_path *path,
+				 struct btrfs_inode *inode,
+				 struct extent_buffer *log_eb,
+				 int log_slot,
+				 struct btrfs_key *key)
+{
+	int ret;
+	unsigned long ref_ptr;
+	unsigned long ref_end;
+	struct extent_buffer *eb;
+
+again:
+	btrfs_release_path(path);
+	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
+	if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
+	if (ret < 0)
+		goto out;
+
+	eb = path->nodes[0];
+	ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]);
+	ref_end = ref_ptr + btrfs_item_size_nr(eb, path->slots[0]);
+	while (ref_ptr < ref_end) {
+		char *name = NULL;
+		int namelen;
+		u64 parent_id;
+
+		if (key->type == BTRFS_INODE_EXTREF_KEY) {
+			ret = extref_get_fields(eb, ref_ptr, &namelen, &name,
+						NULL, &parent_id);
+		} else {
+			parent_id = key->offset;
+			ret = ref_get_fields(eb, ref_ptr, &namelen, &name,
+					     NULL);
+		}
+		if (ret)
+			goto out;
+
+		if (key->type == BTRFS_INODE_EXTREF_KEY)
+			ret = btrfs_find_name_in_ext_backref(log_eb, log_slot,
+							     parent_id, name,
+							     namelen, NULL);
+		else
+			ret = btrfs_find_name_in_backref(log_eb, log_slot, name,
+							 namelen, NULL);
+
+		if (!ret) {
+			struct inode *dir;
+
+			btrfs_release_path(path);
+			dir = read_one_inode(root, parent_id);
+			if (!dir) {
+				ret = -ENOENT;
+				kfree(name);
+				goto out;
+			}
+			ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
+						 inode, name, namelen);
+			kfree(name);
+			iput(dir);
+			if (ret)
+				goto out;
+			goto again;
+		}
+
+		kfree(name);
+		ref_ptr += namelen;
+		if (key->type == BTRFS_INODE_EXTREF_KEY)
+			ref_ptr += sizeof(struct btrfs_inode_extref);
+		else
+			ref_ptr += sizeof(struct btrfs_inode_ref);
+	}
+	ret = 0;
+ out:
+	btrfs_release_path(path);
+	return ret;
+}
+
+/*
  * replay one inode back reference item found in the log tree.
  * eb, slot and key refer to the buffer and key found in the log tree.
  * root is the destination we are replaying into, and path is for temp
@@ -1345,6 +1438,19 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 		}
 	}
 
+	/*
+	 * Before we overwrite the inode reference item in the subvolume tree
+	 * with the item from the log tree, we must unlink all names from the
+	 * parent directory that are in the subvolume's tree inode reference
+	 * item, otherwise we end up with an inconsistent subvolume tree where
+	 * dir index entries exist for a name but there is no inode reference
+	 * item with the same name.
+	 */
+	ret = unlink_old_inode_refs(trans, root, path, BTRFS_I(inode), eb, slot,
+				    key);
+	if (ret)
+		goto out;
+
 	/* finally write the back reference in the inode */
 	ret = overwrite_item(trans, root, path, eb, slot, key);
 out:
@@ -5853,7 +5959,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 	 * this will force the logging code to walk the dentry chain
 	 * up for the file
 	 */
-	if (S_ISREG(inode->vfs_inode.i_mode))
+	if (!S_ISDIR(inode->vfs_inode.i_mode))
 		inode->last_unlink_trans = trans->transid;
 
 	/*