btrfs: reserve correct number of items for inode creation

The various inode creation code paths do not account for the compression
property, POSIX ACLs, or the parent inode item when starting a
transaction. Fix it by refactoring all of these code paths to use a new
function, btrfs_new_inode_prepare(), which computes the correct number
of items. To do so, it needs to know whether POSIX ACLs will be created,
so move the ACL creation into that function. To reduce the number of
arguments that need to be passed around for inode creation, define
struct btrfs_new_inode_args containing all of the relevant information.

btrfs_new_inode_prepare() will also be a good place to set up the
fscrypt context and encrypted filename in the future.
Reviewed-by: Sweet Tea Dorminy <sweettea-kernel@dorminy.me>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/acl.c

@@ -55,8 +55,8 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu)
 	return acl;
 }
 
-static int __btrfs_set_acl(struct btrfs_trans_handle *trans,
-			   struct inode *inode, struct posix_acl *acl, int type)
+int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode,
+		    struct posix_acl *acl, int type)
 {
 	int ret, size = 0;
 	const char *name;
@@ -127,35 +127,3 @@ int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		inode->i_mode = old_mode;
 	return ret;
 }
-
-int btrfs_init_acl(struct btrfs_trans_handle *trans,
-		   struct inode *inode, struct inode *dir)
-{
-	struct posix_acl *default_acl, *acl;
-	int ret = 0;
-
-	/* this happens with subvols */
-	if (!dir)
-		return 0;
-
-	ret = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
-	if (ret)
-		return ret;
-
-	if (default_acl) {
-		ret = __btrfs_set_acl(trans, inode, default_acl,
-				      ACL_TYPE_DEFAULT);
-		posix_acl_release(default_acl);
-	}
-
-	if (acl) {
-		if (!ret)
-			ret = __btrfs_set_acl(trans, inode, acl,
-					      ACL_TYPE_ACCESS);
-		posix_acl_release(acl);
-	}
-
-	if (!default_acl && !acl)
-		cache_no_acl(inode);
-	return ret;
-}

fs/btrfs/ctree.h

@@ -3284,11 +3284,32 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,
 int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 			      unsigned int extra_bits,
 			      struct extent_state **cached_state);
+struct btrfs_new_inode_args {
+	/* Input */
+	struct inode *dir;
+	struct dentry *dentry;
+	struct inode *inode;
+	bool orphan;
+	bool subvol;
+
+	/*
+	 * Output from btrfs_new_inode_prepare(), input to
+	 * btrfs_create_new_inode().
+	 */
+	struct posix_acl *default_acl;
+	struct posix_acl *acl;
+};
+int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args,
+			    unsigned int *trans_num_items);
+int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
+			   struct btrfs_new_inode_args *args,
+			   u64 *index);
+void btrfs_new_inode_args_destroy(struct btrfs_new_inode_args *args);
 struct inode *btrfs_new_subvol_inode(struct user_namespace *mnt_userns,
 				     struct inode *dir);
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *parent_root,
-			     struct inode *inode);
+			     struct btrfs_new_inode_args *args);
  void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
 			       unsigned *bits);
 void btrfs_clear_delalloc_extent(struct inode *inode,
@@ -3846,15 +3867,16 @@ static inline int __btrfs_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag)
 struct posix_acl *btrfs_get_acl(struct inode *inode, int type, bool rcu);
 int btrfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode,
 		  struct posix_acl *acl, int type);
-int btrfs_init_acl(struct btrfs_trans_handle *trans,
-		   struct inode *inode, struct inode *dir);
+int __btrfs_set_acl(struct btrfs_trans_handle *trans, struct inode *inode,
+		    struct posix_acl *acl, int type);
 #else
 #define btrfs_get_acl NULL
 #define btrfs_set_acl NULL
-static inline int btrfs_init_acl(struct btrfs_trans_handle *trans,
-				 struct inode *inode, struct inode *dir)
+static inline int __btrfs_set_acl(struct btrfs_trans_handle *trans,
+				  struct inode *inode, struct posix_acl *acl,
+				  int type)
 {
-	return 0;
+	return -EOPNOTSUPP;
 }
 #endif
 

fs/btrfs/ioctl.c

@@ -544,6 +544,33 @@ int __pure btrfs_is_empty_uuid(u8 *uuid)
 	return 1;
 }
 
+/*
+ * Calculate the number of transaction items to reserve for creating a subvolume
+ * or snapshot, not including the inode, directory entries, or parent directory.
+ */
+static unsigned int create_subvol_num_items(struct btrfs_qgroup_inherit *inherit)
+{
+	/*
+	 * 1 to add root block
+	 * 1 to add root item
+	 * 1 to add root ref
+	 * 1 to add root backref
+	 * 1 to add UUID item
+	 * 1 to add qgroup info
+	 * 1 to add qgroup limit
+	 *
+	 * Ideally the last two would only be accounted if qgroups are enabled,
+	 * but that can change between now and the time we would insert them.
+	 */
+	unsigned int num_items = 7;
+
+	if (inherit) {
+		/* 2 to add qgroup relations for each inherited qgroup */
+		num_items += 2 * inherit->num_qgroups;
+	}
+	return num_items;
+}
+
 static noinline int create_subvol(struct user_namespace *mnt_userns,
 				  struct inode *dir, struct dentry *dentry,
 				  struct btrfs_qgroup_inherit *inherit)
@@ -560,7 +587,12 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 	struct btrfs_root *new_root;
 	struct btrfs_block_rsv block_rsv;
 	struct timespec64 cur_time = current_time(dir);
-	struct inode *inode;
+	struct btrfs_new_inode_args new_inode_args = {
+		.dir = dir,
+		.dentry = dentry,
+		.subvol = true,
+	};
+	unsigned int trans_num_items;
 	int ret;
 	dev_t anon_dev;
 	u64 objectid;
@@ -587,26 +619,27 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 	if (ret < 0)
 		goto out_root_item;
 
-	inode = btrfs_new_subvol_inode(mnt_userns, dir);
-	if (!inode) {
+	new_inode_args.inode = btrfs_new_subvol_inode(mnt_userns, dir);
+	if (!new_inode_args.inode) {
 		ret = -ENOMEM;
 		goto out_anon_dev;
 	}
+	ret = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items);
+	if (ret)
+		goto out_inode;
+	trans_num_items += create_subvol_num_items(inherit);
 
 	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
-	/*
-	 * The same as the snapshot creation, please see the comment
-	 * of create_snapshot().
-	 */
-	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 8, false);
+	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
+					       trans_num_items, false);
 	if (ret)
-		goto out_inode;
+		goto out_new_inode_args;
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		btrfs_subvolume_release_metadata(root, &block_rsv);
-		goto out_inode;
+		goto out_new_inode_args;
 	}
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
@@ -689,8 +722,8 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 	}
 	/* anon_dev is owned by new_root now. */
 	anon_dev = 0;
-	BTRFS_I(inode)->root = new_root;
-	/* ... and new_root is owned by inode now. */
+	BTRFS_I(new_inode_args.inode)->root = new_root;
+	/* ... and new_root is owned by new_inode_args.inode now. */
 
 	ret = btrfs_record_root_in_trans(trans, new_root);
 	if (ret) {
@@ -698,7 +731,7 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 		goto out;
 	}
 
-	ret = btrfs_create_subvol_root(trans, root, inode);
+	ret = btrfs_create_subvol_root(trans, root, &new_inode_args);
 	if (ret) {
 		/* We potentially lose an unused inode item here */
 		btrfs_abort_transaction(trans, ret);
@@ -751,11 +784,13 @@ static noinline int create_subvol(struct user_namespace *mnt_userns,
 		ret = btrfs_commit_transaction(trans);
 
 	if (!ret) {
-		d_instantiate(dentry, inode);
-		inode = NULL;
+		d_instantiate(dentry, new_inode_args.inode);
+		new_inode_args.inode = NULL;
 	}
+out_new_inode_args:
+	btrfs_new_inode_args_destroy(&new_inode_args);
 out_inode:
-	iput(inode);
+	iput(new_inode_args.inode);
 out_anon_dev:
 	if (anon_dev)
 		free_anon_bdev(anon_dev);
@@ -771,6 +806,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
 	struct inode *inode;
 	struct btrfs_pending_snapshot *pending_snapshot;
+	unsigned int trans_num_items;
 	struct btrfs_trans_handle *trans;
 	int ret;
 
@@ -808,16 +844,14 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	btrfs_init_block_rsv(&pending_snapshot->block_rsv,
 			     BTRFS_BLOCK_RSV_TEMP);
 	/*
-	 * 1 - parent dir inode
-	 * 2 - dir entries
-	 * 1 - root item
-	 * 2 - root ref/backref
-	 * 1 - root of snapshot
-	 * 1 - UUID item
+	 * 1 to add dir item
+	 * 1 to add dir index
+	 * 1 to update parent inode item
 	 */
+	trans_num_items = create_subvol_num_items(inherit) + 3;
 	ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
-					&pending_snapshot->block_rsv, 8,
-					false);
+					       &pending_snapshot->block_rsv,
+					       trans_num_items, false);
 	if (ret)
 		goto free_pending;