VFS: Change vfs_mkdir() to return the dentry.

vfs_mkdir() does not guarantee to leave the child dentry hashed or make
it positive on success, and in many such cases the filesystem had to use
a different dentry which it can now return.

This patch changes vfs_mkdir() to return the dentry provided by the
filesystems which is hashed and positive when provided.  This reduces
the number of cases where the resulting dentry is not positive to a
handful which don't deserve extra efforts.

The only callers of vfs_mkdir() which are interested in the resulting
inode are in-kernel filesystem clients: cachefiles, nfsd, smb/server.
The only filesystems that don't reliably provide the inode are:
- kernfs, tracefs which these clients are unlikely to be interested in
- cifs in some configurations would need to do a lookup to find the
  created inode, but doesn't.  cifs cannot be exported via NFS, is
  unlikely to be used by cachefiles, and smb/server only has a soft
  requirement for the inode, so this is unlikely to be a problem in
  practice.
- hostfs, nfs, cifs may need to do a lookup (rarely for NFS) and it is
  possible for a race to make that lookup fail.  Actual failure
  is unlikely and providing callers handle negative dentries graceful
  they will fail-safe.

So this patch removes the lookup code in nfsd and smb/server and adjusts
them to fail safe if a negative dentry is provided:
- cache-files already fails safe by restarting the task from the
  top - it still does with this change, though it no longer calls
  cachefiles_put_directory() as that will crash if the dentry is
  negative.
- nfsd reports "Server-fault" which it what it used to do if the lookup
  failed. This will never happen on any file-systems that it can actually
  export, so this is of no consequence.  I removed the fh_update()
  call as that is not needed and out-of-place.  A subsequent
  nfsd_create_setattr() call will call fh_update() when needed.
- smb/server only wants the inode to call ksmbd_smb_inherit_owner()
  which updates ->i_uid (without calling notify_change() or similar)
  which can be safely skipping on cifs (I hope).

If a different dentry is returned, the first one is put.  If necessary
the fact that it is new can be determined by comparing pointers.  A new
dentry will certainly have a new pointer (as the old is put after the
new is obtained).
Similarly if an error is returned (via ERR_PTR()) the original dentry is
put.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: NeilBrown <neilb@suse.de>
Link: https://lore.kernel.org/r/20250227013949.536172-7-neilb@suse.de
Signed-off-by: Christian Brauner <brauner@kernel.org>

drivers/base/devtmpfs.c

@@ -160,18 +160,17 @@ static int dev_mkdir(const char *name, umode_t mode)
 {
 	struct dentry *dentry;
 	struct path path;
-	int err;
 
 	dentry = kern_path_create(AT_FDCWD, name, &path, LOOKUP_DIRECTORY);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	err = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode);
-	if (!err)
+	dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode);
+	if (!IS_ERR(dentry))
 		/* mark as kernel-created inode */
 		d_inode(dentry)->i_private = &thread;
 	done_path_create(&path, dentry);
-	return err;
+	return PTR_ERR_OR_ZERO(dentry);
 }
 
 static int create_path(const char *nodepath)

fs/cachefiles/namei.c

@@ -128,18 +128,19 @@ retry:
 		ret = security_path_mkdir(&path, subdir, 0700);
 		if (ret < 0)
 			goto mkdir_error;
-		ret = cachefiles_inject_write_error();
-		if (ret == 0)
-			ret = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700);
-		if (ret < 0) {
+		subdir = ERR_PTR(cachefiles_inject_write_error());
+		if (!IS_ERR(subdir))
+			subdir = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), subdir, 0700);
+		ret = PTR_ERR(subdir);
+		if (IS_ERR(subdir)) {
 			trace_cachefiles_vfs_error(NULL, d_inode(dir), ret,
 						   cachefiles_trace_mkdir_error);
 			goto mkdir_error;
 		}
 		trace_cachefiles_mkdir(dir, subdir);
 
-		if (unlikely(d_unhashed(subdir))) {
-			cachefiles_put_directory(subdir);
+		if (unlikely(d_unhashed(subdir) || d_is_negative(subdir))) {
+			dput(subdir);
 			goto retry;
 		}
 		ASSERT(d_backing_inode(subdir));
@@ -195,7 +196,8 @@ mark_error:
 
 mkdir_error:
 	inode_unlock(d_inode(dir));
-	dput(subdir);
+	if (!IS_ERR(subdir))
+		dput(subdir);
 	pr_err("mkdir %s failed with error %d\n", dirname, ret);
 	return ERR_PTR(ret);
 

fs/ecryptfs/inode.c

@@ -511,10 +511,16 @@ static struct dentry *ecryptfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	struct inode *lower_dir;
 
 	rc = lock_parent(dentry, &lower_dentry, &lower_dir);
-	if (!rc)
-		rc = vfs_mkdir(&nop_mnt_idmap, lower_dir,
-			       lower_dentry, mode);
-	if (rc || d_really_is_negative(lower_dentry))
+	if (rc)
+		goto out;
+
+	lower_dentry = vfs_mkdir(&nop_mnt_idmap, lower_dir,
+				 lower_dentry, mode);
+	rc = PTR_ERR(lower_dentry);
+	if (IS_ERR(lower_dentry))
+		goto out;
+	rc = 0;
+	if (d_unhashed(lower_dentry))
 		goto out;
 	rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);
 	if (rc)

fs/init.c

@@ -230,9 +230,12 @@ int __init init_mkdir(const char *pathname, umode_t mode)
 		return PTR_ERR(dentry);
 	mode = mode_strip_umask(d_inode(path.dentry), mode);
 	error = security_path_mkdir(&path, dentry, mode);
-	if (!error)
-		error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode,
+	if (!error) {
+		dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode,
 				  dentry, mode);
+		if (IS_ERR(dentry))
+			error = PTR_ERR(dentry);
+	}
 	done_path_create(&path, dentry);
 	return error;
 }

fs/namei.c

@@ -4128,7 +4128,8 @@ EXPORT_SYMBOL(kern_path_create);
 
 void done_path_create(struct path *path, struct dentry *dentry)
 {
-	dput(dentry);
+	if (!IS_ERR(dentry))
+		dput(dentry);
 	inode_unlock(path->dentry->d_inode);
 	mnt_drop_write(path->mnt);
 	path_put(path);
@@ -4274,7 +4275,7 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d
 }
 
 /**
- * vfs_mkdir - create directory
+ * vfs_mkdir - create directory returning correct dentry if possible
  * @idmap:	idmap of the mount the inode was found from
  * @dir:	inode of the parent directory
  * @dentry:	dentry of the child directory
@@ -4287,9 +4288,15 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d
  * care to map the inode according to @idmap before checking permissions.
  * On non-idmapped mounts or if permission checking is to be performed on the
  * raw inode simply pass @nop_mnt_idmap.
+ *
+ * In the event that the filesystem does not use the *@dentry but leaves it
+ * negative or unhashes it and possibly splices a different one returning it,
+ * the original dentry is dput() and the alternate is returned.
+ *
+ * In case of an error the dentry is dput() and an ERR_PTR() is returned.
  */
-int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
-	      struct dentry *dentry, umode_t mode)
+struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
+			 struct dentry *dentry, umode_t mode)
 {
 	int error;
 	unsigned max_links = dir->i_sb->s_max_links;
@@ -4297,31 +4304,35 @@ int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 
 	error = may_create(idmap, dir, dentry);
 	if (error)
-		return error;
+		goto err;
 
+	error = -EPERM;
 	if (!dir->i_op->mkdir)
-		return -EPERM;
+		goto err;
 
 	mode = vfs_prepare_mode(idmap, dir, mode, S_IRWXUGO | S_ISVTX, 0);
 	error = security_inode_mkdir(dir, dentry, mode);
 	if (error)
-		return error;
+		goto err;
 
+	error = -EMLINK;
 	if (max_links && dir->i_nlink >= max_links)
-		return -EMLINK;
+		goto err;
 
 	de = dir->i_op->mkdir(idmap, dir, dentry, mode);
+	error = PTR_ERR(de);
 	if (IS_ERR(de))
-		return PTR_ERR(de);
+		goto err;
 	if (de) {
-		fsnotify_mkdir(dir, de);
-		/* Cannot return de yet */
-		dput(de);
-	} else {
-		fsnotify_mkdir(dir, dentry);
+		dput(dentry);
+		dentry = de;
 	}
+	fsnotify_mkdir(dir, dentry);
+	return dentry;
 
-	return 0;
+err:
+	dput(dentry);
+	return ERR_PTR(error);
 }
 EXPORT_SYMBOL(vfs_mkdir);
 
@@ -4341,8 +4352,10 @@ retry:
 	error = security_path_mkdir(&path, dentry,
 			mode_strip_umask(path.dentry->d_inode, mode));
 	if (!error) {
-		error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode,
+		dentry = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode,
 				  dentry, mode);
+		if (IS_ERR(dentry))
+			error = PTR_ERR(dentry);
 	}
 	done_path_create(&path, dentry);
 	if (retry_estale(error, lookup_flags)) {

fs/nfsd/nfs4recover.c

@@ -233,9 +233,12 @@ nfsd4_create_clid_dir(struct nfs4_client *clp)
 		 * as well be forgiving and just succeed silently.
 		 */
 		goto out_put;
-	status = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, S_IRWXU);
+	dentry = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, S_IRWXU);
+	if (IS_ERR(dentry))
+		status = PTR_ERR(dentry);
 out_put:
-	dput(dentry);
+	if (!status)
+		dput(dentry);
 out_unlock:
 	inode_unlock(d_inode(dir));
 	if (status == 0) {

fs/nfsd/vfs.c

@@ -1461,7 +1461,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	struct inode	*dirp;
 	struct iattr	*iap = attrs->na_iattr;
 	__be32		err;
-	int		host_err;
+	int		host_err = 0;
 
 	dentry = fhp->fh_dentry;
 	dirp = d_inode(dentry);
@@ -1488,25 +1488,15 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			nfsd_check_ignore_resizing(iap);
 		break;
 	case S_IFDIR:
-		host_err = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode);
-		if (!host_err && unlikely(d_unhashed(dchild))) {
-			struct dentry *d;
-			d = lookup_one_len(dchild->d_name.name,
-					   dchild->d_parent,
-					   dchild->d_name.len);
-			if (IS_ERR(d)) {
-				host_err = PTR_ERR(d);
-				break;
-			}
-			if (unlikely(d_is_negative(d))) {
-				dput(d);
-				err = nfserr_serverfault;
-				goto out;
-			}
+		dchild = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode);
+		if (IS_ERR(dchild)) {
+			host_err = PTR_ERR(dchild);
+		} else if (d_is_negative(dchild)) {
+			err = nfserr_serverfault;
+			goto out;
+		} else if (unlikely(dchild != resfhp->fh_dentry)) {
 			dput(resfhp->fh_dentry);
-			resfhp->fh_dentry = dget(d);
-			dput(dchild);
-			dchild = d;
+			resfhp->fh_dentry = dget(dchild);
 		}
 		break;
 	case S_IFCHR:
@@ -1527,7 +1517,8 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	err = nfsd_create_setattr(rqstp, fhp, resfhp, attrs);
 
 out:
-	dput(dchild);
+	if (!IS_ERR(dchild))
+		dput(dchild);
 	return err;
 
 out_nfserr:

fs/overlayfs/dir.c

@@ -138,37 +138,6 @@ kill_whiteout:
 	goto out;
 }
 
-int ovl_mkdir_real(struct ovl_fs *ofs, struct inode *dir,
-		   struct dentry **newdentry, umode_t mode)
-{
-	int err;
-	struct dentry *d, *dentry = *newdentry;
-
-	err = ovl_do_mkdir(ofs, dir, dentry, mode);
-	if (err)
-		return err;
-
-	if (likely(!d_unhashed(dentry)))
-		return 0;
-
-	/*
-	 * vfs_mkdir() may succeed and leave the dentry passed
-	 * to it unhashed and negative. If that happens, try to
-	 * lookup a new hashed and positive dentry.
-	 */
-	d = ovl_lookup_upper(ofs, dentry->d_name.name, dentry->d_parent,
-			     dentry->d_name.len);
-	if (IS_ERR(d)) {
-		pr_warn("failed lookup after mkdir (%pd2, err=%i).\n",
-			dentry, err);
-		return PTR_ERR(d);
-	}
-	dput(dentry);
-	*newdentry = d;
-
-	return 0;
-}
-
 struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir,
 			       struct dentry *newdentry, struct ovl_cattr *attr)
 {
@@ -191,7 +160,8 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir,
 
 		case S_IFDIR:
 			/* mkdir is special... */
-			err =  ovl_mkdir_real(ofs, dir, &newdentry, attr->mode);
+			newdentry =  ovl_do_mkdir(ofs, dir, newdentry, attr->mode);
+			err = PTR_ERR_OR_ZERO(newdentry);
 			break;
 
 		case S_IFCHR:
@@ -219,7 +189,8 @@ struct dentry *ovl_create_real(struct ovl_fs *ofs, struct inode *dir,
 	}
 out:
 	if (err) {
-		dput(newdentry);
+		if (!IS_ERR(newdentry))
+			dput(newdentry);
 		return ERR_PTR(err);
 	}
 	return newdentry;

fs/overlayfs/overlayfs.h

@@ -241,13 +241,14 @@ static inline int ovl_do_create(struct ovl_fs *ofs,
 	return err;
 }
 
-static inline int ovl_do_mkdir(struct ovl_fs *ofs,
-			       struct inode *dir, struct dentry *dentry,
-			       umode_t mode)
+static inline struct dentry *ovl_do_mkdir(struct ovl_fs *ofs,
+					  struct inode *dir,
+					  struct dentry *dentry,
+					  umode_t mode)
 {
-	int err = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode);
-	pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, err);
-	return err;
+	dentry = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode);
+	pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(dentry));
+	return dentry;
 }
 
 static inline int ovl_do_mknod(struct ovl_fs *ofs,
@@ -838,8 +839,6 @@ struct ovl_cattr {
 
 #define OVL_CATTR(m) (&(struct ovl_cattr) { .mode = (m) })
 
-int ovl_mkdir_real(struct ovl_fs *ofs, struct inode *dir,
-		   struct dentry **newdentry, umode_t mode);
 struct dentry *ovl_create_real(struct ovl_fs *ofs,
 			       struct inode *dir, struct dentry *newdentry,
 			       struct ovl_cattr *attr);

fs/overlayfs/super.c

@@ -327,9 +327,10 @@ retry:
 			goto retry;
 		}
 
-		err = ovl_mkdir_real(ofs, dir, &work, attr.ia_mode);
-		if (err)
-			goto out_dput;
+		work = ovl_do_mkdir(ofs, dir, work, attr.ia_mode);
+		err = PTR_ERR(work);
+		if (IS_ERR(work))
+			goto out_err;
 
 		/* Weird filesystem returning with hashed negative (kernfs)? */
 		err = -EINVAL;

fs/smb/server/vfs.c

@@ -206,8 +206,8 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode)
 {
 	struct mnt_idmap *idmap;
 	struct path path;
-	struct dentry *dentry;
-	int err;
+	struct dentry *dentry, *d;
+	int err = 0;
 
 	dentry = ksmbd_vfs_kern_path_create(work, name,
 					    LOOKUP_NO_SYMLINKS | LOOKUP_DIRECTORY,
@@ -222,27 +222,15 @@ int ksmbd_vfs_mkdir(struct ksmbd_work *work, const char *name, umode_t mode)
 
 	idmap = mnt_idmap(path.mnt);
 	mode |= S_IFDIR;
-	err = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode);
-	if (!err && d_unhashed(dentry)) {
-		struct dentry *d;
+	d = dentry;
+	dentry = vfs_mkdir(idmap, d_inode(path.dentry), dentry, mode);
+	if (IS_ERR(dentry))
+		err = PTR_ERR(dentry);
+	else if (d_is_negative(dentry))
+		err = -ENOENT;
+	if (!err && dentry != d)
+		ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), d_inode(dentry));
 
-		d = lookup_one(idmap, dentry->d_name.name, dentry->d_parent,
-			       dentry->d_name.len);
-		if (IS_ERR(d)) {
-			err = PTR_ERR(d);
-			goto out_err;
-		}
-		if (unlikely(d_is_negative(d))) {
-			dput(d);
-			err = -ENOENT;
-			goto out_err;
-		}
-
-		ksmbd_vfs_inherit_owner(work, d_inode(path.dentry), d_inode(d));
-		dput(d);
-	}
-
-out_err:
 	done_path_create(&path, dentry);
 	if (err)
 		pr_err("mkdir(%s): creation failed (err:%d)\n", name, err);

fs/xfs/scrub/orphanage.c

@@ -167,10 +167,11 @@ xrep_orphanage_create(
 	 * directory to control access to a file we put in here.
 	 */
 	if (d_really_is_negative(orphanage_dentry)) {
-		error = vfs_mkdir(&nop_mnt_idmap, root_inode, orphanage_dentry,
-				0750);
-		if (error)
-			goto out_dput_orphanage;
+		orphanage_dentry = vfs_mkdir(&nop_mnt_idmap, root_inode,
+					     orphanage_dentry, 0750);
+		error = PTR_ERR(orphanage_dentry);
+		if (IS_ERR(orphanage_dentry))
+			goto out_unlock_root;
 	}
 
 	/* Not a directory? Bail out. */

include/linux/fs.h

@@ -1981,8 +1981,8 @@ bool inode_owner_or_capable(struct mnt_idmap *idmap,
  */
 int vfs_create(struct mnt_idmap *, struct inode *,
 	       struct dentry *, umode_t, bool);
-int vfs_mkdir(struct mnt_idmap *, struct inode *,
-	      struct dentry *, umode_t);
+struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *,
+			 struct dentry *, umode_t);
 int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *,
               umode_t, dev_t);
 int vfs_symlink(struct mnt_idmap *, struct inode *,