Merge tag 'vfs-6.19-rc1.directory.locking' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull directory locking updates from Christian Brauner:
 "This contains the work to add centralized APIs for directory locking
  operations.

  This series is part of a larger effort to change directory operation
  locking to allow multiple concurrent operations in a directory. The
  ultimate goal is to lock the target dentry(s) rather than the whole
  parent directory.

  To help with changing the locking protocol, this series centralizes
  locking and lookup in new helper functions. The helpers establish a
  pattern where it is the dentry that is being locked and unlocked
  (currently the lock is held on dentry->d_parent->d_inode, but that can
  change in the future).

  This also changes vfs_mkdir() to unlock the parent on failure, as well
  as dput()ing the dentry. This allows end_creating() to only require
  the target dentry (which may be IS_ERR() after vfs_mkdir()), not the
  parent"

* tag 'vfs-6.19-rc1.directory.locking' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
  nfsd: fix end_creating() conversion
  VFS: introduce end_creating_keep()
  VFS: change vfs_mkdir() to unlock on failure.
  ecryptfs: use new start_creating/start_removing APIs
  Add start_renaming_two_dentries()
  VFS/ovl/smb: introduce start_renaming_dentry()
  VFS/nfsd/ovl: introduce start_renaming() and end_renaming()
  VFS: add start_creating_killable() and start_removing_killable()
  VFS: introduce start_removing_dentry()
  smb/server: use end_removing_noperm for for target of smb2_create_link()
  VFS: introduce start_creating_noperm() and start_removing_noperm()
  VFS/nfsd/cachefiles/ovl: introduce start_removing() and end_removing()
  VFS/nfsd/cachefiles/ovl: add start_creating() and end_creating()
  VFS: tidy up do_unlinkat()
  VFS: introduce start_dirop() and end_dirop()
  debugfs: rename end_creating() to debugfs_end_creating()

1 files changed, 639 insertions, 108 deletions

diff --git a/fs/namei.c b/fs/namei.c
index 13041756d941..bf0f66f0e9b9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2835,6 +2835,62 @@ static int filename_parentat(int dfd, struct filename *name,
 	return __filename_parentat(dfd, name, flags, parent, last, type, NULL);
 }
 
+/**
+ * start_dirop - begin a create or remove dirop, performing locking and lookup
+ * @parent:       the dentry of the parent in which the operation will occur
+ * @name:         a qstr holding the name within that parent
+ * @lookup_flags: intent and other lookup flags.
+ *
+ * The lookup is performed and necessary locks are taken so that, on success,
+ * the returned dentry can be operated on safely.
+ * The qstr must already have the hash value calculated.
+ *
+ * Returns: a locked dentry, or an error.
+ *
+ */
+static struct dentry *__start_dirop(struct dentry *parent, struct qstr *name,
+				    unsigned int lookup_flags,
+				    unsigned int state)
+{
+	struct dentry *dentry;
+	struct inode *dir = d_inode(parent);
+
+	if (state == TASK_KILLABLE) {
+		int ret = down_write_killable_nested(&dir->i_rwsem,
+						     I_MUTEX_PARENT);
+		if (ret)
+			return ERR_PTR(ret);
+	} else {
+		inode_lock_nested(dir, I_MUTEX_PARENT);
+	}
+	dentry = lookup_one_qstr_excl(name, parent, lookup_flags);
+	if (IS_ERR(dentry))
+		inode_unlock(dir);
+	return dentry;
+}
+
+struct dentry *start_dirop(struct dentry *parent, struct qstr *name,
+			   unsigned int lookup_flags)
+{
+	return __start_dirop(parent, name, lookup_flags, TASK_NORMAL);
+}
+
+/**
+ * end_dirop - signal completion of a dirop
+ * @de: the dentry which was returned by start_dirop or similar.
+ *
+ * If the de is an error, nothing happens. Otherwise any lock taken to
+ * protect the dentry is dropped and the dentry itself is release (dput()).
+ */
+void end_dirop(struct dentry *de)
+{
+	if (!IS_ERR(de)) {
+		inode_unlock(de->d_parent->d_inode);
+		dput(de);
+	}
+}
+EXPORT_SYMBOL(end_dirop);
+
 /* does lookup, returns the object with parent locked */
 static struct dentry *__start_removing_path(int dfd, struct filename *name,
 					   struct path *path)
@@ -2851,10 +2907,9 @@ static struct dentry *__start_removing_path(int dfd, struct filename *name,
 		return ERR_PTR(-EINVAL);
 	/* don't fail immediately if it's r/o, at least try to report other errors */
 	error = mnt_want_write(parent_path.mnt);
-	inode_lock_nested(parent_path.dentry->d_inode, I_MUTEX_PARENT);
-	d = lookup_one_qstr_excl(&last, parent_path.dentry, 0);
+	d = start_dirop(parent_path.dentry, &last, 0);
 	if (IS_ERR(d))
-		goto unlock;
+		goto drop;
 	if (error)
 		goto fail;
 	path->dentry = no_free_ptr(parent_path.dentry);
@@ -2862,10 +2917,9 @@ static struct dentry *__start_removing_path(int dfd, struct filename *name,
 	return d;
 
 fail:
-	dput(d);
+	end_dirop(d);
 	d = ERR_PTR(error);
-unlock:
-	inode_unlock(parent_path.dentry->d_inode);
+drop:
 	if (!error)
 		mnt_drop_write(parent_path.mnt);
 	return d;
@@ -2980,7 +3034,7 @@ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt,
 }
 EXPORT_SYMBOL(vfs_path_lookup);
 
-static int lookup_noperm_common(struct qstr *qname, struct dentry *base)
+int lookup_noperm_common(struct qstr *qname, struct dentry *base)
 {
 	const char *name = qname->name;
 	u32 len = qname->len;
@@ -3251,6 +3305,234 @@ struct dentry *lookup_noperm_positive_unlocked(struct qstr *name,
 }
 EXPORT_SYMBOL(lookup_noperm_positive_unlocked);
 
+/**
+ * start_creating - prepare to create a given name with permission checking
+ * @idmap:  idmap of the mount
+ * @parent: directory in which to prepare to create the name
+ * @name:   the name to be created
+ *
+ * Locks are taken and a lookup is performed prior to creating
+ * an object in a directory.  Permission checking (MAY_EXEC) is performed
+ * against @idmap.
+ *
+ * If the name already exists, a positive dentry is returned, so
+ * behaviour is similar to O_CREAT without O_EXCL, which doesn't fail
+ * with -EEXIST.
+ *
+ * Returns: a negative or positive dentry, or an error.
+ */
+struct dentry *start_creating(struct mnt_idmap *idmap, struct dentry *parent,
+			      struct qstr *name)
+{
+	int err = lookup_one_common(idmap, name, parent);
+
+	if (err)
+		return ERR_PTR(err);
+	return start_dirop(parent, name, LOOKUP_CREATE);
+}
+EXPORT_SYMBOL(start_creating);
+
+/**
+ * start_removing - prepare to remove a given name with permission checking
+ * @idmap:  idmap of the mount
+ * @parent: directory in which to find the name
+ * @name:   the name to be removed
+ *
+ * Locks are taken and a lookup in performed prior to removing
+ * an object from a directory.  Permission checking (MAY_EXEC) is performed
+ * against @idmap.
+ *
+ * If the name doesn't exist, an error is returned.
+ *
+ * end_removing() should be called when removal is complete, or aborted.
+ *
+ * Returns: a positive dentry, or an error.
+ */
+struct dentry *start_removing(struct mnt_idmap *idmap, struct dentry *parent,
+			      struct qstr *name)
+{
+	int err = lookup_one_common(idmap, name, parent);
+
+	if (err)
+		return ERR_PTR(err);
+	return start_dirop(parent, name, 0);
+}
+EXPORT_SYMBOL(start_removing);
+
+/**
+ * start_creating_killable - prepare to create a given name with permission checking
+ * @idmap:  idmap of the mount
+ * @parent: directory in which to prepare to create the name
+ * @name:   the name to be created
+ *
+ * Locks are taken and a lookup in performed prior to creating
+ * an object in a directory.  Permission checking (MAY_EXEC) is performed
+ * against @idmap.
+ *
+ * If the name already exists, a positive dentry is returned.
+ *
+ * If a signal is received or was already pending, the function aborts
+ * with -EINTR;
+ *
+ * Returns: a negative or positive dentry, or an error.
+ */
+struct dentry *start_creating_killable(struct mnt_idmap *idmap,
+				       struct dentry *parent,
+				       struct qstr *name)
+{
+	int err = lookup_one_common(idmap, name, parent);
+
+	if (err)
+		return ERR_PTR(err);
+	return __start_dirop(parent, name, LOOKUP_CREATE, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(start_creating_killable);
+
+/**
+ * start_removing_killable - prepare to remove a given name with permission checking
+ * @idmap:  idmap of the mount
+ * @parent: directory in which to find the name
+ * @name:   the name to be removed
+ *
+ * Locks are taken and a lookup in performed prior to removing
+ * an object from a directory.  Permission checking (MAY_EXEC) is performed
+ * against @idmap.
+ *
+ * If the name doesn't exist, an error is returned.
+ *
+ * end_removing() should be called when removal is complete, or aborted.
+ *
+ * If a signal is received or was already pending, the function aborts
+ * with -EINTR;
+ *
+ * Returns: a positive dentry, or an error.
+ */
+struct dentry *start_removing_killable(struct mnt_idmap *idmap,
+				       struct dentry *parent,
+				       struct qstr *name)
+{
+	int err = lookup_one_common(idmap, name, parent);
+
+	if (err)
+		return ERR_PTR(err);
+	return __start_dirop(parent, name, 0, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(start_removing_killable);
+
+/**
+ * start_creating_noperm - prepare to create a given name without permission checking
+ * @parent: directory in which to prepare to create the name
+ * @name:   the name to be created
+ *
+ * Locks are taken and a lookup in performed prior to creating
+ * an object in a directory.
+ *
+ * If the name already exists, a positive dentry is returned.
+ *
+ * Returns: a negative or positive dentry, or an error.
+ */
+struct dentry *start_creating_noperm(struct dentry *parent,
+				     struct qstr *name)
+{
+	int err = lookup_noperm_common(name, parent);
+
+	if (err)
+		return ERR_PTR(err);
+	return start_dirop(parent, name, LOOKUP_CREATE);
+}
+EXPORT_SYMBOL(start_creating_noperm);
+
+/**
+ * start_removing_noperm - prepare to remove a given name without permission checking
+ * @parent: directory in which to find the name
+ * @name:   the name to be removed
+ *
+ * Locks are taken and a lookup in performed prior to removing
+ * an object from a directory.
+ *
+ * If the name doesn't exist, an error is returned.
+ *
+ * end_removing() should be called when removal is complete, or aborted.
+ *
+ * Returns: a positive dentry, or an error.
+ */
+struct dentry *start_removing_noperm(struct dentry *parent,
+				     struct qstr *name)
+{
+	int err = lookup_noperm_common(name, parent);
+
+	if (err)
+		return ERR_PTR(err);
+	return start_dirop(parent, name, 0);
+}
+EXPORT_SYMBOL(start_removing_noperm);
+
+/**
+ * start_creating_dentry - prepare to create a given dentry
+ * @parent: directory from which dentry should be removed
+ * @child:  the dentry to be removed
+ *
+ * A lock is taken to protect the dentry again other dirops and
+ * the validity of the dentry is checked: correct parent and still hashed.
+ *
+ * If the dentry is valid and negative a reference is taken and
+ * returned.  If not an error is returned.
+ *
+ * end_creating() should be called when creation is complete, or aborted.
+ *
+ * Returns: the valid dentry, or an error.
+ */
+struct dentry *start_creating_dentry(struct dentry *parent,
+				     struct dentry *child)
+{
+	inode_lock_nested(parent->d_inode, I_MUTEX_PARENT);
+	if (unlikely(IS_DEADDIR(parent->d_inode) ||
+		     child->d_parent != parent ||
+		     d_unhashed(child))) {
+		inode_unlock(parent->d_inode);
+		return ERR_PTR(-EINVAL);
+	}
+	if (d_is_positive(child)) {
+		inode_unlock(parent->d_inode);
+		return ERR_PTR(-EEXIST);
+	}
+	return dget(child);
+}
+EXPORT_SYMBOL(start_creating_dentry);
+
+/**
+ * start_removing_dentry - prepare to remove a given dentry
+ * @parent: directory from which dentry should be removed
+ * @child:  the dentry to be removed
+ *
+ * A lock is taken to protect the dentry again other dirops and
+ * the validity of the dentry is checked: correct parent and still hashed.
+ *
+ * If the dentry is valid and positive, a reference is taken and
+ * returned.  If not an error is returned.
+ *
+ * end_removing() should be called when removal is complete, or aborted.
+ *
+ * Returns: the valid dentry, or an error.
+ */
+struct dentry *start_removing_dentry(struct dentry *parent,
+				     struct dentry *child)
+{
+	inode_lock_nested(parent->d_inode, I_MUTEX_PARENT);
+	if (unlikely(IS_DEADDIR(parent->d_inode) ||
+		     child->d_parent != parent ||
+		     d_unhashed(child))) {
+		inode_unlock(parent->d_inode);
+		return ERR_PTR(-EINVAL);
+	}
+	if (d_is_negative(child)) {
+		inode_unlock(parent->d_inode);
+		return ERR_PTR(-ENOENT);
+	}
+	return dget(child);
+}
+EXPORT_SYMBOL(start_removing_dentry);
+
 #ifdef CONFIG_UNIX98_PTYS
 int path_pts(struct path *path)
 {
@@ -3489,6 +3771,290 @@ void unlock_rename(struct dentry *p1, struct dentry *p2)
 EXPORT_SYMBOL(unlock_rename);
 
 /**
+ * __start_renaming - lookup and lock names for rename
+ * @rd:           rename data containing parents and flags, and
+ *                for receiving found dentries
+ * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL,
+ *                LOOKUP_NO_SYMLINKS etc).
+ * @old_last:     name of object in @rd.old_parent
+ * @new_last:     name of object in @rd.new_parent
+ *
+ * Look up two names and ensure locks are in place for
+ * rename.
+ *
+ * On success the found dentries are stored in @rd.old_dentry,
+ * @rd.new_dentry and an extra ref is taken on @rd.old_parent.
+ * These references and the lock are dropped by end_renaming().
+ *
+ * The passed in qstrs must have the hash calculated, and no permission
+ * checking is performed.
+ *
+ * Returns: zero or an error.
+ */
+static int
+__start_renaming(struct renamedata *rd, int lookup_flags,
+		 struct qstr *old_last, struct qstr *new_last)
+{
+	struct dentry *trap;
+	struct dentry *d1, *d2;
+	int target_flags = LOOKUP_RENAME_TARGET | LOOKUP_CREATE;
+	int err;
+
+	if (rd->flags & RENAME_EXCHANGE)
+		target_flags = 0;
+	if (rd->flags & RENAME_NOREPLACE)
+		target_flags |= LOOKUP_EXCL;
+
+	trap = lock_rename(rd->old_parent, rd->new_parent);
+	if (IS_ERR(trap))
+		return PTR_ERR(trap);
+
+	d1 = lookup_one_qstr_excl(old_last, rd->old_parent,
+				  lookup_flags);
+	err = PTR_ERR(d1);
+	if (IS_ERR(d1))
+		goto out_unlock;
+
+	d2 = lookup_one_qstr_excl(new_last, rd->new_parent,
+				  lookup_flags | target_flags);
+	err = PTR_ERR(d2);
+	if (IS_ERR(d2))
+		goto out_dput_d1;
+
+	if (d1 == trap) {
+		/* source is an ancestor of target */
+		err = -EINVAL;
+		goto out_dput_d2;
+	}
+
+	if (d2 == trap) {
+		/* target is an ancestor of source */
+		if (rd->flags & RENAME_EXCHANGE)
+			err = -EINVAL;
+		else
+			err = -ENOTEMPTY;
+		goto out_dput_d2;
+	}
+
+	rd->old_dentry = d1;
+	rd->new_dentry = d2;
+	dget(rd->old_parent);
+	return 0;
+
+out_dput_d2:
+	dput(d2);
+out_dput_d1:
+	dput(d1);
+out_unlock:
+	unlock_rename(rd->old_parent, rd->new_parent);
+	return err;
+}
+
+/**
+ * start_renaming - lookup and lock names for rename with permission checking
+ * @rd:           rename data containing parents and flags, and
+ *                for receiving found dentries
+ * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL,
+ *                LOOKUP_NO_SYMLINKS etc).
+ * @old_last:     name of object in @rd.old_parent
+ * @new_last:     name of object in @rd.new_parent
+ *
+ * Look up two names and ensure locks are in place for
+ * rename.
+ *
+ * On success the found dentries are stored in @rd.old_dentry,
+ * @rd.new_dentry.  Also the refcount on @rd->old_parent is increased.
+ * These references and the lock are dropped by end_renaming().
+ *
+ * The passed in qstrs need not have the hash calculated, and basic
+ * eXecute permission checking is performed against @rd.mnt_idmap.
+ *
+ * Returns: zero or an error.
+ */
+int start_renaming(struct renamedata *rd, int lookup_flags,
+		   struct qstr *old_last, struct qstr *new_last)
+{
+	int err;
+
+	err = lookup_one_common(rd->mnt_idmap, old_last, rd->old_parent);
+	if (err)
+		return err;
+	err = lookup_one_common(rd->mnt_idmap, new_last, rd->new_parent);
+	if (err)
+		return err;
+	return __start_renaming(rd, lookup_flags, old_last, new_last);
+}
+EXPORT_SYMBOL(start_renaming);
+
+static int
+__start_renaming_dentry(struct renamedata *rd, int lookup_flags,
+			struct dentry *old_dentry, struct qstr *new_last)
+{
+	struct dentry *trap;
+	struct dentry *d2;
+	int target_flags = LOOKUP_RENAME_TARGET | LOOKUP_CREATE;
+	int err;
+
+	if (rd->flags & RENAME_EXCHANGE)
+		target_flags = 0;
+	if (rd->flags & RENAME_NOREPLACE)
+		target_flags |= LOOKUP_EXCL;
+
+	/* Already have the dentry - need to be sure to lock the correct parent */
+	trap = lock_rename_child(old_dentry, rd->new_parent);
+	if (IS_ERR(trap))
+		return PTR_ERR(trap);
+	if (d_unhashed(old_dentry) ||
+	    (rd->old_parent && rd->old_parent != old_dentry->d_parent)) {
+		/* dentry was removed, or moved and explicit parent requested */
+		err = -EINVAL;
+		goto out_unlock;
+	}
+
+	d2 = lookup_one_qstr_excl(new_last, rd->new_parent,
+				  lookup_flags | target_flags);
+	err = PTR_ERR(d2);
+	if (IS_ERR(d2))
+		goto out_unlock;
+
+	if (old_dentry == trap) {
+		/* source is an ancestor of target */
+		err = -EINVAL;
+		goto out_dput_d2;
+	}
+
+	if (d2 == trap) {
+		/* target is an ancestor of source */
+		if (rd->flags & RENAME_EXCHANGE)
+			err = -EINVAL;
+		else
+			err = -ENOTEMPTY;
+		goto out_dput_d2;
+	}
+
+	rd->old_dentry = dget(old_dentry);
+	rd->new_dentry = d2;
+	rd->old_parent = dget(old_dentry->d_parent);
+	return 0;
+
+out_dput_d2:
+	dput(d2);
+out_unlock:
+	unlock_rename(old_dentry->d_parent, rd->new_parent);
+	return err;
+}
+
+/**
+ * start_renaming_dentry - lookup and lock name for rename with permission checking
+ * @rd:           rename data containing parents and flags, and
+ *                for receiving found dentries
+ * @lookup_flags: extra flags to pass to ->lookup (e.g. LOOKUP_REVAL,
+ *                LOOKUP_NO_SYMLINKS etc).
+ * @old_dentry:   dentry of name to move
+ * @new_last:     name of target in @rd.new_parent
+ *
+ * Look up target name and ensure locks are in place for
+ * rename.
+ *
+ * On success the found dentry is stored in @rd.new_dentry and
+ * @rd.old_parent is confirmed to be the parent of @old_dentry.  If it
+ * was originally %NULL, it is set.  In either case a reference is taken
+ * so that end_renaming() can have a stable reference to unlock.
+ *
+ * References and the lock can be dropped with end_renaming()
+ *
+ * The passed in qstr need not have the hash calculated, and basic
+ * eXecute permission checking is performed against @rd.mnt_idmap.
+ *
+ * Returns: zero or an error.
+ */
+int start_renaming_dentry(struct renamedata *rd, int lookup_flags,
+			  struct dentry *old_dentry, struct qstr *new_last)
+{
+	int err;
+
+	err = lookup_one_common(rd->mnt_idmap, new_last, rd->new_parent);
+	if (err)
+		return err;
+	return __start_renaming_dentry(rd, lookup_flags, old_dentry, new_last);
+}
+EXPORT_SYMBOL(start_renaming_dentry);
+
+/**
+ * start_renaming_two_dentries - Lock to dentries in given parents for rename
+ * @rd:           rename data containing parent
+ * @old_dentry:   dentry of name to move
+ * @new_dentry:   dentry to move to
+ *
+ * Ensure locks are in place for rename and check parentage is still correct.
+ *
+ * On success the two dentries are stored in @rd.old_dentry and
+ * @rd.new_dentry and @rd.old_parent and @rd.new_parent are confirmed to
+ * be the parents of the dentries.
+ *
+ * References and the lock can be dropped with end_renaming()
+ *
+ * Returns: zero or an error.
+ */
+int
+start_renaming_two_dentries(struct renamedata *rd,
+			    struct dentry *old_dentry, struct dentry *new_dentry)
+{
+	struct dentry *trap;
+	int err;
+
+	/* Already have the dentry - need to be sure to lock the correct parent */
+	trap = lock_rename_child(old_dentry, rd->new_parent);
+	if (IS_ERR(trap))
+		return PTR_ERR(trap);
+	err = -EINVAL;
+	if (d_unhashed(old_dentry) ||
+	    (rd->old_parent && rd->old_parent != old_dentry->d_parent))
+		/* old_dentry was removed, or moved and explicit parent requested */
+		goto out_unlock;
+	if (d_unhashed(new_dentry) ||
+	    rd->new_parent != new_dentry->d_parent)
+		/* new_dentry was removed or moved */
+		goto out_unlock;
+
+	if (old_dentry == trap)
+		/* source is an ancestor of target */
+		goto out_unlock;
+
+	if (new_dentry == trap) {
+		/* target is an ancestor of source */
+		if (rd->flags & RENAME_EXCHANGE)
+			err = -EINVAL;
+		else
+			err = -ENOTEMPTY;
+		goto out_unlock;
+	}
+
+	err = -EEXIST;
+	if (d_is_positive(new_dentry) && (rd->flags & RENAME_NOREPLACE))
+		goto out_unlock;
+
+	rd->old_dentry = dget(old_dentry);
+	rd->new_dentry = dget(new_dentry);
+	rd->old_parent = dget(old_dentry->d_parent);
+	return 0;
+
+out_unlock:
+	unlock_rename(old_dentry->d_parent, rd->new_parent);
+	return err;
+}
+EXPORT_SYMBOL(start_renaming_two_dentries);
+
+void end_renaming(struct renamedata *rd)
+{
+	unlock_rename(rd->old_parent, rd->new_parent);
+	dput(rd->old_dentry);
+	dput(rd->new_dentry);
+	dput(rd->old_parent);
+}
+EXPORT_SYMBOL(end_renaming);
+
+/**
  * vfs_prepare_mode - prepare the mode to be used for a new inode
  * @idmap:	idmap of the mount the inode was found from
  * @dir:	parent directory of the new inode
@@ -4310,21 +4876,18 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 	 */
 	if (last.name[last.len] && !want_dir)
 		create_flags &= ~LOOKUP_CREATE;
-	inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT);
-	dentry = lookup_one_qstr_excl(&last, path->dentry,
-				      reval_flag | create_flags);
+	dentry = start_dirop(path->dentry, &last, reval_flag | create_flags);
 	if (IS_ERR(dentry))
-		goto unlock;
+		goto out_drop_write;
 
 	if (unlikely(error))
 		goto fail;
 
 	return dentry;
 fail:
-	dput(dentry);
+	end_dirop(dentry);
 	dentry = ERR_PTR(error);
-unlock:
-	inode_unlock(path->dentry->d_inode);
+out_drop_write:
 	if (!error)
 		mnt_drop_write(path->mnt);
 out:
@@ -4343,11 +4906,20 @@ struct dentry *start_creating_path(int dfd, const char *pathname,
 }
 EXPORT_SYMBOL(start_creating_path);
 
+/**
+ * end_creating_path - finish a code section started by start_creating_path()
+ * @path: the path instantiated by start_creating_path()
+ * @dentry: the dentry returned by start_creating_path()
+ *
+ * end_creating_path() will unlock and locks taken by start_creating_path()
+ * and drop an references that were taken.  It should only be called
+ * if start_creating_path() returned a non-error.
+ * If vfs_mkdir() was called and it returned an error, that error *should*
+ * be passed to end_creating_path() together with the path.
+ */
 void end_creating_path(const struct path *path, struct dentry *dentry)
 {
-	if (!IS_ERR(dentry))
-		dput(dentry);
-	inode_unlock(path->dentry->d_inode);
+	end_creating(dentry);
 	mnt_drop_write(path->mnt);
 	path_put(path);
 }
@@ -4567,7 +5139,7 @@ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	return dentry;
 
 err:
-	dput(dentry);
+	end_creating(dentry);
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL(vfs_mkdir);
@@ -4709,8 +5281,7 @@ retry:
 	if (error)
 		goto exit2;
 
-	inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
-	dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags);
+	dentry = start_dirop(path.dentry, &last, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto exit3;
@@ -4720,9 +5291,8 @@ retry:
 	error = vfs_rmdir(mnt_idmap(path.mnt), path.dentry->d_inode,
 			  dentry, &delegated_inode);
 exit4:
-	dput(dentry);
+	end_dirop(dentry);
 exit3:
-	inode_unlock(path.dentry->d_inode);
 	mnt_drop_write(path.mnt);
 exit2:
 	path_put(&path);
@@ -4831,67 +5401,62 @@ int do_unlinkat(int dfd, struct filename *name)
 	struct path path;
 	struct qstr last;
 	int type;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	struct delegated_inode delegated_inode = { };
 	unsigned int lookup_flags = 0;
 retry:
 	error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
 	if (error)
-		goto exit1;
+		goto exit_putname;
 
 	error = -EISDIR;
 	if (type != LAST_NORM)
-		goto exit2;
+		goto exit_path_put;
 
 	error = mnt_want_write(path.mnt);
 	if (error)
-		goto exit2;
+		goto exit_path_put;
 retry_deleg:
-	inode_lock_nested(path.dentry->d_inode, I_MUTEX_PARENT);
-	dentry = lookup_one_qstr_excl(&last, path.dentry, lookup_flags);
+	dentry = start_dirop(path.dentry, &last, lookup_flags);
 	error = PTR_ERR(dentry);
-	if (!IS_ERR(dentry)) {
+	if (IS_ERR(dentry))
+		goto exit_drop_write;
 
-		/* Why not before? Because we want correct error value */
-		if (last.name[last.len])
-			goto slashes;
-		inode = dentry->d_inode;
-		ihold(inode);
-		error = security_path_unlink(&path, dentry);
-		if (error)
-			goto exit3;
-		error = vfs_unlink(mnt_idmap(path.mnt), path.dentry->d_inode,
-				   dentry, &delegated_inode);
-exit3:
-		dput(dentry);
+	/* Why not before? Because we want correct error value */
+	if (unlikely(last.name[last.len])) {
+		if (d_is_dir(dentry))
+			error = -EISDIR;
+		else
+			error = -ENOTDIR;
+		end_dirop(dentry);
+		goto exit_drop_write;
 	}
-	inode_unlock(path.dentry->d_inode);
-	if (inode)
-		iput(inode);	/* truncate the inode here */
-	inode = NULL;
+	inode = dentry->d_inode;
+	ihold(inode);
+	error = security_path_unlink(&path, dentry);
+	if (error)
+		goto exit_end_dirop;
+	error = vfs_unlink(mnt_idmap(path.mnt), path.dentry->d_inode,
+			   dentry, &delegated_inode);
+exit_end_dirop:
+	end_dirop(dentry);
+	iput(inode);	/* truncate the inode here */
 	if (is_delegated(&delegated_inode)) {
 		error = break_deleg_wait(&delegated_inode);
 		if (!error)
 			goto retry_deleg;
 	}
+exit_drop_write:
 	mnt_drop_write(path.mnt);
-exit2:
+exit_path_put:
 	path_put(&path);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
-		inode = NULL;
 		goto retry;
 	}
-exit1:
+exit_putname:
 	putname(name);
 	return error;
-
-slashes:
-	if (d_is_dir(dentry))
-		error = -EISDIR;
-	else
-		error = -ENOTDIR;
-	goto exit3;
 }
 
 SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag)
@@ -5404,14 +5969,11 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd,
 		 struct filename *to, unsigned int flags)
 {
 	struct renamedata rd;
-	struct dentry *old_dentry, *new_dentry;
-	struct dentry *trap;
 	struct path old_path, new_path;
 	struct qstr old_last, new_last;
 	int old_type, new_type;
 	struct delegated_inode delegated_inode = { };
-	unsigned int lookup_flags = 0, target_flags =
-		LOOKUP_RENAME_TARGET | LOOKUP_CREATE;
+	unsigned int lookup_flags = 0;
 	bool should_retry = false;
 	int error = -EINVAL;
 
@@ -5422,11 +5984,6 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd,
 	    (flags & RENAME_EXCHANGE))
 		goto put_names;
 
-	if (flags & RENAME_EXCHANGE)
-		target_flags = 0;
-	if (flags & RENAME_NOREPLACE)
-		target_flags |= LOOKUP_EXCL;
-
 retry:
 	error = filename_parentat(olddfd, from, lookup_flags, &old_path,
 				  &old_last, &old_type);
@@ -5456,66 +6013,40 @@ retry:
 		goto exit2;
 
 retry_deleg:
-	trap = lock_rename(new_path.dentry, old_path.dentry);
-	if (IS_ERR(trap)) {
-		error = PTR_ERR(trap);
+	rd.old_parent	   = old_path.dentry;
+	rd.mnt_idmap	   = mnt_idmap(old_path.mnt);
+	rd.new_parent	   = new_path.dentry;
+	rd.delegated_inode = &delegated_inode;
+	rd.flags	   = flags;
+
+	error = __start_renaming(&rd, lookup_flags, &old_last, &new_last);
+	if (error)
 		goto exit_lock_rename;
-	}
 
-	old_dentry = lookup_one_qstr_excl(&old_last, old_path.dentry,
-					  lookup_flags);
-	error = PTR_ERR(old_dentry);
-	if (IS_ERR(old_dentry))
-		goto exit3;
-	new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry,
-					  lookup_flags | target_flags);
-	error = PTR_ERR(new_dentry);
-	if (IS_ERR(new_dentry))
-		goto exit4;
 	if (flags & RENAME_EXCHANGE) {
-		if (!d_is_dir(new_dentry)) {
+		if (!d_is_dir(rd.new_dentry)) {
 			error = -ENOTDIR;
 			if (new_last.name[new_last.len])
-				goto exit5;
+				goto exit_unlock;
 		}
 	}
 	/* unless the source is a directory trailing slashes give -ENOTDIR */
-	if (!d_is_dir(old_dentry)) {
+	if (!d_is_dir(rd.old_dentry)) {
 		error = -ENOTDIR;
 		if (old_last.name[old_last.len])
-			goto exit5;
+			goto exit_unlock;
 		if (!(flags & RENAME_EXCHANGE) && new_last.name[new_last.len])
-			goto exit5;
+			goto exit_unlock;
 	}
-	/* source should not be ancestor of target */
-	error = -EINVAL;
-	if (old_dentry == trap)
-		goto exit5;
-	/* target should not be an ancestor of source */
-	if (!(flags & RENAME_EXCHANGE))
-		error = -ENOTEMPTY;
-	if (new_dentry == trap)
-		goto exit5;
 
-	error = security_path_rename(&old_path, old_dentry,
-				     &new_path, new_dentry, flags);
+	error = security_path_rename(&old_path, rd.old_dentry,
+				     &new_path, rd.new_dentry, flags);
 	if (error)
-		goto exit5;
+		goto exit_unlock;
 
-	rd.old_parent	   = old_path.dentry;
-	rd.old_dentry	   = old_dentry;
-	rd.mnt_idmap	   = mnt_idmap(old_path.mnt);
-	rd.new_parent	   = new_path.dentry;
-	rd.new_dentry	   = new_dentry;
-	rd.delegated_inode = &delegated_inode;
-	rd.flags	   = flags;
 	error = vfs_rename(&rd);
-exit5:
-	dput(new_dentry);
-exit4:
-	dput(old_dentry);
-exit3:
-	unlock_rename(new_path.dentry, old_path.dentry);
+exit_unlock:
+	end_renaming(&rd);
 exit_lock_rename:
 	if (is_delegated(&delegated_inode)) {
 		error = break_deleg_wait(&delegated_inode);