btrfs: extended inode refs

This patch adds basic support for extended inode refs. This includes support
for link and unlink of the refs, which basically gets us support for rename
as well.

Inode creation does not need changing - extended refs are only added after
the ref array is full.

Signed-off-by: Mark Fasheh <mfasheh@suse.de>

1 files changed, 274 insertions, 11 deletions

diff --git a/fs/btrfs/inode-item.c b/fs/btrfs/inode-item.c
index a13cf1a96c73..48b8fda93132 100644
--- a/fs/btrfs/inode-item.c
+++ b/fs/btrfs/inode-item.c
@@ -18,6 +18,7 @@
 
 #include "ctree.h"
 #include "disk-io.h"
+#include "hash.h"
 #include "transaction.h"
 #include "print-tree.h"
 
@@ -50,18 +51,57 @@ static int find_name_in_backref(struct btrfs_path *path, const char *name,
 	return 0;
 }
 
-struct btrfs_inode_ref *
+int btrfs_find_name_in_ext_backref(struct btrfs_path *path, u64 ref_objectid,
+				   const char *name, int name_len,
+				   struct btrfs_inode_extref **extref_ret)
+{
+	struct extent_buffer *leaf;
+	struct btrfs_inode_extref *extref;
+	unsigned long ptr;
+	unsigned long name_ptr;
+	u32 item_size;
+	u32 cur_offset = 0;
+	int ref_name_len;
+
+	leaf = path->nodes[0];
+	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+
+	/*
+	 * Search all extended backrefs in this item. We're only
+	 * looking through any collisions so most of the time this is
+	 * just going to compare against one buffer. If all is well,
+	 * we'll return success and the inode ref object.
+	 */
+	while (cur_offset < item_size) {
+		extref = (struct btrfs_inode_extref *) (ptr + cur_offset);
+		name_ptr = (unsigned long)(&extref->name);
+		ref_name_len = btrfs_inode_extref_name_len(leaf, extref);
+
+		if (ref_name_len == name_len &&
+		    btrfs_inode_extref_parent(leaf, extref) == ref_objectid &&
+		    (memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0)) {
+			if (extref_ret)
+				*extref_ret = extref;
+			return 1;
+		}
+
+		cur_offset += ref_name_len + sizeof(*extref);
+	}
+	return 0;
+}
+
+static struct btrfs_inode_ref *
 btrfs_lookup_inode_ref(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root,
-			struct btrfs_path *path,
-			const char *name, int name_len,
-			u64 inode_objectid, u64 ref_objectid, int mod)
+		       struct btrfs_root *root,
+		       struct btrfs_path *path,
+		       const char *name, int name_len,
+		       u64 inode_objectid, u64 ref_objectid, int ins_len,
+		       int cow)
 {
+	int ret;
 	struct btrfs_key key;
 	struct btrfs_inode_ref *ref;
-	int ins_len = mod < 0 ? -1 : 0;
-	int cow = mod != 0;
-	int ret;
 
 	key.objectid = inode_objectid;
 	key.type = BTRFS_INODE_REF_KEY;
@@ -77,13 +117,150 @@ btrfs_lookup_inode_ref(struct btrfs_trans_handle *trans,
 	return ref;
 }
 
-int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
+/* Returns NULL if no extref found */
+struct btrfs_inode_extref *
+btrfs_lookup_inode_extref(struct btrfs_trans_handle *trans,
+			  struct btrfs_root *root,
+			  struct btrfs_path *path,
+			  const char *name, int name_len,
+			  u64 inode_objectid, u64 ref_objectid, int ins_len,
+			  int cow)
+{
+	int ret;
+	struct btrfs_key key;
+	struct btrfs_inode_extref *extref;
+
+	key.objectid = inode_objectid;
+	key.type = BTRFS_INODE_EXTREF_KEY;
+	key.offset = btrfs_extref_hash(ref_objectid, name, name_len);
+
+	ret = btrfs_search_slot(trans, root, &key, path, ins_len, cow);
+	if (ret < 0)
+		return ERR_PTR(ret);
+	if (ret > 0)
+		return NULL;
+	if (!btrfs_find_name_in_ext_backref(path, ref_objectid, name, name_len, &extref))
+		return NULL;
+	return extref;
+}
+
+int btrfs_get_inode_ref_index(struct btrfs_trans_handle *trans,
+			      struct btrfs_root *root,
+			      struct btrfs_path *path,
+			      const char *name, int name_len,
+			      u64 inode_objectid, u64 ref_objectid, int mod,
+			      u64 *ret_index)
+{
+	struct btrfs_inode_ref *ref;
+	struct btrfs_inode_extref *extref;
+	int ins_len = mod < 0 ? -1 : 0;
+	int cow = mod != 0;
+
+	ref = btrfs_lookup_inode_ref(trans, root, path, name, name_len,
+				     inode_objectid, ref_objectid, ins_len,
+				     cow);
+	if (IS_ERR(ref))
+		return PTR_ERR(ref);
+
+	if (ref != NULL) {
+		*ret_index = btrfs_inode_ref_index(path->nodes[0], ref);
+		return 0;
+	}
+
+	btrfs_release_path(path);
+
+	extref = btrfs_lookup_inode_extref(trans, root, path, name,
+					   name_len, inode_objectid,
+					   ref_objectid, ins_len, cow);
+	if (IS_ERR(extref))
+		return PTR_ERR(extref);
+
+	if (extref) {
+		*ret_index = btrfs_inode_extref_index(path->nodes[0], extref);
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
+int btrfs_del_inode_extref(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   const char *name, int name_len,
 			   u64 inode_objectid, u64 ref_objectid, u64 *index)
 {
 	struct btrfs_path *path;
 	struct btrfs_key key;
+	struct btrfs_inode_extref *extref;
+	struct extent_buffer *leaf;
+	int ret;
+	int del_len = name_len + sizeof(*extref);
+	unsigned long ptr;
+	unsigned long item_start;
+	u32 item_size;
+
+	key.objectid = inode_objectid;
+	btrfs_set_key_type(&key, BTRFS_INODE_EXTREF_KEY);
+	key.offset = btrfs_extref_hash(ref_objectid, name, name_len);
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	path->leave_spinning = 1;
+
+	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
+	if (ret > 0)
+		ret = -ENOENT;
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * Sanity check - did we find the right item for this name?
+	 * This should always succeed so error here will make the FS
+	 * readonly.
+	 */
+	if (!btrfs_find_name_in_ext_backref(path, ref_objectid,
+					    name, name_len, &extref)) {
+		btrfs_std_error(root->fs_info, -ENOENT);
+		ret = -EROFS;
+		goto out;
+	}
+
+	leaf = path->nodes[0];
+	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+	if (index)
+		*index = btrfs_inode_extref_index(leaf, extref);
+
+	if (del_len == item_size) {
+		/*
+		 * Common case only one ref in the item, remove the
+		 * whole item.
+		 */
+		ret = btrfs_del_item(trans, root, path);
+		goto out;
+	}
+
+	ptr = (unsigned long)extref;
+	item_start = btrfs_item_ptr_offset(leaf, path->slots[0]);
+
+	memmove_extent_buffer(leaf, ptr, ptr + del_len,
+			      item_size - (ptr + del_len - item_start));
+
+	btrfs_truncate_item(trans, root, path, item_size - del_len, 1);
+
+out:
+	btrfs_free_path(path);
+
+	return ret;
+}
+
+int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
+			struct btrfs_root *root,
+			const char *name, int name_len,
+			u64 inode_objectid, u64 ref_objectid, u64 *index)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
 	struct btrfs_inode_ref *ref;
 	struct extent_buffer *leaf;
 	unsigned long ptr;
@@ -91,6 +268,7 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
 	u32 item_size;
 	u32 sub_item_len;
 	int ret;
+	int search_ext_refs = 0;
 	int del_len = name_len + sizeof(*ref);
 
 	key.objectid = inode_objectid;
@@ -106,12 +284,14 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret > 0) {
 		ret = -ENOENT;
+		search_ext_refs = 1;
 		goto out;
 	} else if (ret < 0) {
 		goto out;
 	}
 	if (!find_name_in_backref(path, name, name_len, &ref)) {
 		ret = -ENOENT;
+		search_ext_refs = 1;
 		goto out;
 	}
 	leaf = path->nodes[0];
@@ -129,8 +309,78 @@ int btrfs_del_inode_ref(struct btrfs_trans_handle *trans,
 	item_start = btrfs_item_ptr_offset(leaf, path->slots[0]);
 	memmove_extent_buffer(leaf, ptr, ptr + sub_item_len,
 			      item_size - (ptr + sub_item_len - item_start));
-	btrfs_truncate_item(trans, root, path,
-				  item_size - sub_item_len, 1);
+	btrfs_truncate_item(trans, root, path, item_size - sub_item_len, 1);
+out:
+	btrfs_free_path(path);
+
+	if (search_ext_refs) {
+		/*
+		 * No refs were found, or we could not find the
+		 * name in our ref array. Find and remove the extended
+		 * inode ref then.
+		 */
+		return btrfs_del_inode_extref(trans, root, name, name_len,
+					      inode_objectid, ref_objectid, index);
+	}
+
+	return ret;
+}
+
+/*
+ * btrfs_insert_inode_extref() - Inserts an extended inode ref into a tree.
+ *
+ * The caller must have checked against BTRFS_LINK_MAX already.
+ */
+static int btrfs_insert_inode_extref(struct btrfs_trans_handle *trans,
+				     struct btrfs_root *root,
+				     const char *name, int name_len,
+				     u64 inode_objectid, u64 ref_objectid, u64 index)
+{
+	struct btrfs_inode_extref *extref;
+	int ret;
+	int ins_len = name_len + sizeof(*extref);
+	unsigned long ptr;
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct extent_buffer *leaf;
+	struct btrfs_item *item;
+
+	key.objectid = inode_objectid;
+	key.type = BTRFS_INODE_EXTREF_KEY;
+	key.offset = btrfs_extref_hash(ref_objectid, name, name_len);
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	path->leave_spinning = 1;
+	ret = btrfs_insert_empty_item(trans, root, path, &key,
+				      ins_len);
+	if (ret == -EEXIST) {
+		if (btrfs_find_name_in_ext_backref(path, ref_objectid,
+						   name, name_len, NULL))
+			goto out;
+
+		btrfs_extend_item(trans, root, path, ins_len);
+		ret = 0;
+	}
+	if (ret < 0)
+		goto out;
+
+	leaf = path->nodes[0];
+	item = btrfs_item_nr(leaf, path->slots[0]);
+	ptr = (unsigned long)btrfs_item_ptr(leaf, path->slots[0], char);
+	ptr += btrfs_item_size(leaf, item) - ins_len;
+	extref = (struct btrfs_inode_extref *)ptr;
+
+	btrfs_set_inode_extref_name_len(path->nodes[0], extref, name_len);
+	btrfs_set_inode_extref_index(path->nodes[0], extref, index);
+	btrfs_set_inode_extref_parent(path->nodes[0], extref, ref_objectid);
+
+	ptr = (unsigned long)&extref->name;
+	write_extent_buffer(path->nodes[0], name, ptr, name_len);
+	btrfs_mark_buffer_dirty(path->nodes[0]);
+
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -191,6 +441,19 @@ int btrfs_insert_inode_ref(struct btrfs_trans_handle *trans,
 
 out:
 	btrfs_free_path(path);
+
+	if (ret == -EMLINK) {
+		struct btrfs_super_block *disk_super = root->fs_info->super_copy;
+		/* We ran out of space in the ref array. Need to
+		 * add an extended ref. */
+		if (btrfs_super_incompat_flags(disk_super)
+		    & BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
+			ret = btrfs_insert_inode_extref(trans, root, name,
+							name_len,
+							inode_objectid,
+							ref_objectid, index);
+	}
+
 	return ret;
 }