Merge patch series "VFS: change kern_path_locked() and user_path_locked_at() to never return negative dentry"

NeilBrown <neilb@suse.de> says:

I found these opportunities for simplification as part of my work to
enhance filesystem directory operations to not require an exclusive
lock on the directory.
There are quite a collection of users of these interfaces incluing NFS,
smb/server, bcachefs, devtmpfs, and audit.  Hence the long Cc line.

* patches from https://lore.kernel.org/r/20250217003020.3170652-2-neilb@suse.de:
  VFS: add common error checks to lookup_one_qstr_excl()
  VFS: change kern_path_locked() and user_path_locked_at() to never return negative dentry

Link: https://lore.kernel.org/r/20250217003020.3170652-2-neilb@suse.de
Signed-off-by: Christian Brauner <brauner@kernel.org>

Author: brauner

Documentation/filesystems/porting.rst

@@ -1157,3 +1157,24 @@ in normal case it points into the pathname being looked up.
 NOTE: if you need something like full path from the root of filesystem,
 you are still on your own - this assists with simple cases, but it's not
 magic.
+
+---
+
+** recommended**
+
+kern_path_locked() and user_path_locked() no longer return a negative
+dentry so this doesn't need to be checked.  If the name cannot be found,
+ERR_PTR(-ENOENT) is returned.
+
+** recommend**
+
+lookup_one_qstr_excl() is changed to return errors in more cases, so
+these conditions don't require explicit checks:
+
+ - if LOOKUP_CREATE is NOT given, then the dentry won't be negative,
+   ERR_PTR(-ENOENT) is returned instead
+ - if LOOKUP_EXCL IS given, then the dentry won't be positive,
+   ERR_PTR(-EEXIST) is rreturned instread
+
+LOOKUP_EXCL now means "target must not exist".  It can be combined with
+LOOK_CREATE or LOOKUP_RENAME_TARGET.

drivers/base/devtmpfs.c

@@ -245,15 +245,12 @@ static int dev_rmdir(const char *name)
 	dentry = kern_path_locked(name, &parent);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
-	if (d_really_is_positive(dentry)) {
-		if (d_inode(dentry)->i_private == &thread)
-			err = vfs_rmdir(&nop_mnt_idmap, d_inode(parent.dentry),
-					dentry);
-		else
-			err = -EPERM;
-	} else {
-		err = -ENOENT;
-	}
+	if (d_inode(dentry)->i_private == &thread)
+		err = vfs_rmdir(&nop_mnt_idmap, d_inode(parent.dentry),
+				dentry);
+	else
+		err = -EPERM;
+
 	dput(dentry);
 	inode_unlock(d_inode(parent.dentry));
 	path_put(&parent);
@@ -310,39 +307,37 @@ static int handle_remove(const char *nodename, struct device *dev)
 {
 	struct path parent;
 	struct dentry *dentry;
+	struct kstat stat;
+	struct path p;
 	int deleted = 0;
 	int err;
 
 	dentry = kern_path_locked(nodename, &parent);
 	if (IS_ERR(dentry))
 		return PTR_ERR(dentry);
 
-	if (d_really_is_positive(dentry)) {
-		struct kstat stat;
-		struct path p = {.mnt = parent.mnt, .dentry = dentry};
-		err = vfs_getattr(&p, &stat, STATX_TYPE | STATX_MODE,
-				  AT_STATX_SYNC_AS_STAT);
-		if (!err && dev_mynode(dev, d_inode(dentry), &stat)) {
-			struct iattr newattrs;
-			/*
-			 * before unlinking this node, reset permissions
-			 * of possible references like hardlinks
-			 */
-			newattrs.ia_uid = GLOBAL_ROOT_UID;
-			newattrs.ia_gid = GLOBAL_ROOT_GID;
-			newattrs.ia_mode = stat.mode & ~0777;
-			newattrs.ia_valid =
-				ATTR_UID|ATTR_GID|ATTR_MODE;
-			inode_lock(d_inode(dentry));
-			notify_change(&nop_mnt_idmap, dentry, &newattrs, NULL);
-			inode_unlock(d_inode(dentry));
-			err = vfs_unlink(&nop_mnt_idmap, d_inode(parent.dentry),
-					 dentry, NULL);
-			if (!err || err == -ENOENT)
-				deleted = 1;
-		}
-	} else {
-		err = -ENOENT;
+	p.mnt = parent.mnt;
+	p.dentry = dentry;
+	err = vfs_getattr(&p, &stat, STATX_TYPE | STATX_MODE,
+			  AT_STATX_SYNC_AS_STAT);
+	if (!err && dev_mynode(dev, d_inode(dentry), &stat)) {
+		struct iattr newattrs;
+		/*
+		 * before unlinking this node, reset permissions
+		 * of possible references like hardlinks
+		 */
+		newattrs.ia_uid = GLOBAL_ROOT_UID;
+		newattrs.ia_gid = GLOBAL_ROOT_GID;
+		newattrs.ia_mode = stat.mode & ~0777;
+		newattrs.ia_valid =
+			ATTR_UID|ATTR_GID|ATTR_MODE;
+		inode_lock(d_inode(dentry));
+		notify_change(&nop_mnt_idmap, dentry, &newattrs, NULL);
+		inode_unlock(d_inode(dentry));
+		err = vfs_unlink(&nop_mnt_idmap, d_inode(parent.dentry),
+				 dentry, NULL);
+		if (!err || err == -ENOENT)
+			deleted = 1;
 	}
 	dput(dentry);
 	inode_unlock(d_inode(parent.dentry));

fs/bcachefs/fs-ioctl.c

@@ -511,10 +511,6 @@ static long bch2_ioctl_subvolume_destroy(struct bch_fs *c, struct file *filp,
 		ret = -EXDEV;
 		goto err;
 	}
-	if (!d_is_positive(victim)) {
-		ret = -ENOENT;
-		goto err;
-	}
 	ret = __bch2_unlink(dir, victim, true);
 	if (!ret) {
 		fsnotify_rmdir(dir, victim);

fs/namei.c

@@ -1670,6 +1670,8 @@ static struct dentry *lookup_dcache(const struct qstr *name,
  * dentries - as the matter of fact, this only gets called
  * when directory is guaranteed to have no in-lookup children
  * at all.
+ * Will return -ENOENT if name isn't found and LOOKUP_CREATE wasn't passed.
+ * Will return -EEXIST if name is found and LOOKUP_EXCL was passed.
  */
 struct dentry *lookup_one_qstr_excl(const struct qstr *name,
 				    struct dentry *base,
@@ -1680,7 +1682,7 @@ struct dentry *lookup_one_qstr_excl(const struct qstr *name,
 	struct inode *dir = base->d_inode;
 
 	if (dentry)
-		return dentry;
+		goto found;
 
 	/* Don't create child dentry for a dead directory. */
 	if (unlikely(IS_DEADDIR(dir)))
@@ -1695,6 +1697,17 @@ struct dentry *lookup_one_qstr_excl(const struct qstr *name,
 		dput(dentry);
 		dentry = old;
 	}
+found:
+	if (IS_ERR(dentry))
+		return dentry;
+	if (d_is_negative(dentry) && !(flags & LOOKUP_CREATE)) {
+		dput(dentry);
+		return ERR_PTR(-ENOENT);
+	}
+	if (d_is_positive(dentry) && (flags & LOOKUP_EXCL)) {
+		dput(dentry);
+		return ERR_PTR(-EEXIST);
+	}
 	return dentry;
 }
 EXPORT_SYMBOL(lookup_one_qstr_excl);
@@ -4078,27 +4091,13 @@ static struct dentry *filename_create(int dfd, struct filename *name,
 	 * '/', and a directory wasn't requested.
 	 */
 	if (last.name[last.len] && !want_dir)
-		create_flags = 0;
+		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);
 	if (IS_ERR(dentry))
 		goto unlock;
 
-	error = -EEXIST;
-	if (d_is_positive(dentry))
-		goto fail;
-
-	/*
-	 * Special case - lookup gave negative, but... we had foo/bar/
-	 * From the vfs_mknod() POV we just have a negative dentry -
-	 * all is fine. Let's be bastards - you had / on the end, you've
-	 * been asking for (non-existent) directory. -ENOENT for you.
-	 */
-	if (unlikely(!create_flags)) {
-		error = -ENOENT;
-		goto fail;
-	}
 	if (unlikely(err2)) {
 		error = err2;
 		goto fail;
@@ -4445,10 +4444,6 @@ int do_rmdir(int dfd, struct filename *name)
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto exit3;
-	if (!dentry->d_inode) {
-		error = -ENOENT;
-		goto exit4;
-	}
 	error = security_path_rmdir(&path, dentry);
 	if (error)
 		goto exit4;
@@ -4579,7 +4574,7 @@ int do_unlinkat(int dfd, struct filename *name)
 	if (!IS_ERR(dentry)) {
 
 		/* Why not before? Because we want correct error value */
-		if (last.name[last.len] || d_is_negative(dentry))
+		if (last.name[last.len])
 			goto slashes;
 		inode = dentry->d_inode;
 		ihold(inode);
@@ -4613,9 +4608,7 @@ int do_unlinkat(int dfd, struct filename *name)
 	return error;
 
 slashes:
-	if (d_is_negative(dentry))
-		error = -ENOENT;
-	else if (d_is_dir(dentry))
+	if (d_is_dir(dentry))
 		error = -EISDIR;
 	else
 		error = -ENOTDIR;
@@ -5115,7 +5108,8 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd,
 	struct qstr old_last, new_last;
 	int old_type, new_type;
 	struct inode *delegated_inode = NULL;
-	unsigned int lookup_flags = 0, target_flags = LOOKUP_RENAME_TARGET;
+	unsigned int lookup_flags = 0, target_flags =
+		LOOKUP_RENAME_TARGET | LOOKUP_CREATE;
 	bool should_retry = false;
 	int error = -EINVAL;
 
@@ -5128,6 +5122,8 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd,
 
 	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,
@@ -5169,23 +5165,12 @@ int do_renameat2(int olddfd, struct filename *from, int newdfd,
 	error = PTR_ERR(old_dentry);
 	if (IS_ERR(old_dentry))
 		goto exit3;
-	/* source must exist */
-	error = -ENOENT;
-	if (d_is_negative(old_dentry))
-		goto exit4;
 	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;
-	error = -EEXIST;
-	if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry))
-		goto exit5;
 	if (flags & RENAME_EXCHANGE) {
-		error = -ENOENT;
-		if (d_is_negative(new_dentry))
-			goto exit5;
-
 		if (!d_is_dir(new_dentry)) {
 			error = -ENOTDIR;
 			if (new_last.name[new_last.len])

fs/nfs/dir.c

@@ -1532,7 +1532,8 @@ static int nfs_is_exclusive_create(struct inode *dir, unsigned int flags)
 {
 	if (NFS_PROTO(dir)->version == 2)
 		return 0;
-	return flags & LOOKUP_EXCL;
+	return (flags & (LOOKUP_CREATE | LOOKUP_EXCL)) ==
+		(LOOKUP_CREATE | LOOKUP_EXCL);
 }
 
 /*

fs/smb/server/vfs.c

@@ -113,11 +113,6 @@ static int ksmbd_vfs_path_lookup_locked(struct ksmbd_share_config *share_conf,
 	if (IS_ERR(d))
 		goto err_out;
 
-	if (d_is_negative(d)) {
-		dput(d);
-		goto err_out;
-	}
-
 	path->dentry = d;
 	path->mnt = mntget(parent_path->mnt);
 
@@ -693,6 +688,7 @@ int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path,
 	struct ksmbd_file *parent_fp;
 	int new_type;
 	int err, lookup_flags = LOOKUP_NO_SYMLINKS;
+	int target_lookup_flags = LOOKUP_RENAME_TARGET;
 
 	if (ksmbd_override_fsids(work))
 		return -ENOMEM;
@@ -703,6 +699,14 @@ int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path,
 		goto revert_fsids;
 	}
 
+	/*
+	 * explicitly handle file overwrite case, for compatibility with
+	 * filesystems that may not support rename flags (e.g: fuse)
+	 */
+	if (flags & RENAME_NOREPLACE)
+		target_lookup_flags |= LOOKUP_EXCL;
+	flags &= ~(RENAME_NOREPLACE);
+
 retry:
 	err = vfs_path_parent_lookup(to, lookup_flags | LOOKUP_BENEATH,
 				     &new_path, &new_last, &new_type,
@@ -743,7 +747,7 @@ int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path,
 	}
 
 	new_dentry = lookup_one_qstr_excl(&new_last, new_path.dentry,
-					  lookup_flags | LOOKUP_RENAME_TARGET);
+					  lookup_flags | target_lookup_flags);
 	if (IS_ERR(new_dentry)) {
 		err = PTR_ERR(new_dentry);
 		goto out3;
@@ -754,16 +758,6 @@ int ksmbd_vfs_rename(struct ksmbd_work *work, const struct path *old_path,
 		goto out4;
 	}
 
-	/*
-	 * explicitly handle file overwrite case, for compatibility with
-	 * filesystems that may not support rename flags (e.g: fuse)
-	 */
-	if ((flags & RENAME_NOREPLACE) && d_is_positive(new_dentry)) {
-		err = -EEXIST;
-		goto out4;
-	}
-	flags &= ~(RENAME_NOREPLACE);
-
 	if (old_child == trap) {
 		err = -EINVAL;
 		goto out4;

kernel/audit_watch.c

@@ -350,11 +350,10 @@ static int audit_get_nd(struct audit_watch *watch, struct path *parent)
 	struct dentry *d = kern_path_locked(watch->path, parent);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
-	if (d_is_positive(d)) {
-		/* update watch filter fields */
-		watch->dev = d->d_sb->s_dev;
-		watch->ino = d_backing_inode(d)->i_ino;
-	}
+	/* update watch filter fields */
+	watch->dev = d->d_sb->s_dev;
+	watch->ino = d_backing_inode(d)->i_ino;
+
 	inode_unlock(d_backing_inode(parent->dentry));
 	dput(d);
 	return 0;
@@ -419,10 +418,11 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 	/* caller expects mutex locked */
 	mutex_lock(&audit_filter_mutex);
 
-	if (ret) {
+	if (ret && ret != -ENOENT) {
 		audit_put_watch(watch);
 		return ret;
 	}
+	ret = 0;
 
 	/* either find an old parent or attach a new one */
 	parent = audit_find_parent(d_backing_inode(parent_path.dentry));