[PATCH v3 6/6] btrfs: pre-allocate delayed dir index for non-overwrite rename

Jeff Layton <[email protected]>
Newsgroups org.kernel.vger.linux-btrfs,org.kernel.vger.linux-kernel
Message-ID <[email protected]>
For rename() without an overwrite target, pre-allocate the delayed
dir index before any btree modifications so that ENOMEM can be returned
before the source is unlinked from the old directory.

Add a prealloc parameter to btrfs_add_link() that allows callers to
pass pre-allocated delayed dir index resources. When provided,
btrfs_add_link() takes ownership: it either passes the prealloc to
btrfs_insert_dir_item() (which commits or frees it), or frees it
on early error. All existing callers pass NULL to preserve the current
behavior.

In btrfs_rename(), when new_inode is NULL (no overwrite), call
btrfs_prealloc_delayed_dir_index() before the first btree modification
and pass the result through to btrfs_add_link(). If the prealloc fails,
-ENOMEM is returned before any btree state has changed. The local
prealloc pointer is cleared once ownership passes to btrfs_add_link(),
so the out_fail path only frees one we still own.

For overwrite rename (new_inode != NULL), the transaction still aborts
on ENOMEM since earlier unlink operations have already made irreversible
btree modifications.

Assisted-by: LLM
Signed-off-by: Jeff Layton <[email protected]>
---
 fs/btrfs/btrfs_inode.h |  4 +++-
 fs/btrfs/inode.c       | 40 ++++++++++++++++++++++++++++++++--------
 fs/btrfs/tree-log.c    |  4 ++--
 3 files changed, 37 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 1082fa92c145..d4280f152027 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -525,9 +525,11 @@ int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 		       struct btrfs_inode *dir, struct btrfs_inode *inode,
 		       const struct fscrypt_str *name);
+struct btrfs_dir_index_prealloc;
 int btrfs_add_link(struct btrfs_trans_handle *trans,
 		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
-		   const struct fscrypt_str *name, bool add_backref, u64 index);
+		   const struct fscrypt_str *name, bool add_backref, u64 index,
+		   struct btrfs_dir_index_prealloc *prealloc);
 int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry);
 int btrfs_truncate_block(struct btrfs_inode *inode, u64 offset, u64 start, u64 end);
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 5b79910d72f5..fd6d481f4d12 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6862,7 +6862,7 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
 		}
 	} else {
 		ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name,
-				     false, BTRFS_I(inode)->dir_index);
+				     false, BTRFS_I(inode)->dir_index, NULL);
 		if (ret == -ENOMEM) {
 			/*
 			 * Orphan the new inode instead of aborting. The inode
@@ -6914,7 +6914,8 @@ int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
  */
 int btrfs_add_link(struct btrfs_trans_handle *trans,
 		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
-		   const struct fscrypt_str *name, bool add_backref, u64 index)
+		   const struct fscrypt_str *name, bool add_backref, u64 index,
+		   struct btrfs_dir_index_prealloc *prealloc)
 {
 	int ret = 0;
 	struct btrfs_key key;
@@ -6940,11 +6941,13 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 	}
 
 	/* Nothing to clean up yet */
-	if (ret)
+	if (ret) {
+		btrfs_free_delayed_dir_index_prealloc(trans, prealloc);
 		return ret;
+	}
 
 	ret = btrfs_insert_dir_item(trans, name, parent_inode, &key,
-				    btrfs_inode_type(inode), index, NULL);
+				    btrfs_inode_type(inode), index, prealloc);
 	if (ret == -EEXIST || ret == -EOVERFLOW || ret == -ENOMEM)
 		goto fail_dir_item;
 	else if (unlikely(ret)) {
@@ -7098,7 +7101,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	inode_set_ctime_current(inode);
 
 	ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
-			     &fname.disk_name, true, index);
+			     &fname.disk_name, true, index, NULL);
 	if (ret)
 		goto fail;
 
@@ -8512,14 +8515,14 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	}
 
 	ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode),
-			     new_name, false, old_idx);
+			     new_name, false, old_idx, NULL);
 	if (unlikely(ret)) {
 		btrfs_abort_transaction(trans, ret);
 		goto out_fail;
 	}
 
 	ret = btrfs_add_link(trans, BTRFS_I(old_dir), BTRFS_I(new_inode),
-			     old_name, false, new_idx);
+			     old_name, false, new_idx, NULL);
 	if (unlikely(ret)) {
 		btrfs_abort_transaction(trans, ret);
 		goto out_fail;
@@ -8592,6 +8595,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	struct inode *new_inode = d_inode(new_dentry);
 	struct inode *old_inode = d_inode(old_dentry);
 	struct btrfs_rename_ctx rename_ctx;
+	struct btrfs_dir_index_prealloc *prealloc = NULL;
 	u64 index = 0;
 	int ret;
 	int ret2;
@@ -8715,6 +8719,24 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	if (ret)
 		goto out_fail;
 
+	/*
+	 * When not overwriting an existing entry, pre-allocate the delayed
+	 * dir index now so that ENOMEM is returned before any btree
+	 * modifications. For the overwrite case, too many btree changes
+	 * have already happened by the time btrfs_add_link() is called.
+	 */
+	if (!new_inode) {
+		prealloc = btrfs_prealloc_delayed_dir_index(
+				BTRFS_I(new_dir),
+				new_fname.disk_name.name,
+				new_fname.disk_name.len);
+		if (IS_ERR(prealloc)) {
+			ret = PTR_ERR(prealloc);
+			prealloc = NULL;
+			goto out_fail;
+		}
+	}
+
 	BTRFS_I(old_inode)->dir_index = 0ULL;
 	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		/* force full log commit if subvolume involved. */
@@ -8810,7 +8832,8 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 	}
 
 	ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode),
-			     &new_fname.disk_name, false, index);
+			     &new_fname.disk_name, false, index, prealloc);
+	prealloc = NULL;
 	if (unlikely(ret)) {
 		btrfs_abort_transaction(trans, ret);
 		goto out_fail;
@@ -8835,6 +8858,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
 		}
 	}
 out_fail:
+	btrfs_free_delayed_dir_index_prealloc(trans, prealloc);
 	if (logs_pinned) {
 		btrfs_end_log_trans(root);
 		btrfs_end_log_trans(dest);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 7ba7b6098aa5..a043611f82e1 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1683,7 +1683,7 @@ static noinline int add_inode_ref(struct walk_control *wc)
 			}
 
 			/* insert our name */
-			ret = btrfs_add_link(trans, dir, inode, &name, false, ref_index);
+			ret = btrfs_add_link(trans, dir, inode, &name, false, ref_index, NULL);
 			if (ret) {
 				btrfs_abort_log_replay(wc, ret,
 "failed to add link for inode %llu in dir %llu ref_index %llu name %.*s root %llu",
@@ -2031,7 +2031,7 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans,
 		return PTR_ERR(dir);
 	}
 
-	ret = btrfs_add_link(trans, dir, inode, name, true, index);
+	ret = btrfs_add_link(trans, dir, inode, name, true, index, NULL);
 
 	/* FIXME, put inode into FIXUP list */
 

-- 
2.55.0
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.