vfs: make vfs_mknod break delegations on parent directory

In order to add directory delegation support, we need to break
delegations on the parent whenever there is going to be a change in the
directory.

Add a new delegated_inode pointer to vfs_mknod() and have the
appropriate callers wait when there is an outstanding delegation. All
other callers just set the pointer to NULL.

Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: NeilBrown <neil@brown.name>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20251111-dir-deleg-ro-v6-11-52f3feebb2f2@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>

drivers/base/devtmpfs.c

@@ -231,7 +231,7 @@ static int handle_create(const char *nodename, umode_t mode, kuid_t uid,
 		return PTR_ERR(dentry);
 
 	err = vfs_mknod(&nop_mnt_idmap, d_inode(path.dentry), dentry, mode,
-			dev->devt);
+			dev->devt, NULL);
 	if (!err) {
 		struct iattr newattrs;
 

fs/ecryptfs/inode.c

@@ -564,7 +564,7 @@ ecryptfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	rc = lock_parent(dentry, &lower_dentry, &lower_dir);
 	if (!rc)
 		rc = vfs_mknod(&nop_mnt_idmap, lower_dir,
-			       lower_dentry, mode, dev);
+			       lower_dentry, mode, dev, NULL);
 	if (rc || d_really_is_negative(lower_dentry))
 		goto out;
 	rc = ecryptfs_interpose(lower_dentry, dentry, dir->i_sb);

fs/init.c

@@ -157,7 +157,7 @@ int __init init_mknod(const char *filename, umode_t mode, unsigned int dev)
 	error = security_path_mknod(&path, dentry, mode, dev);
 	if (!error)
 		error = vfs_mknod(mnt_idmap(path.mnt), path.dentry->d_inode,
-				  dentry, mode, new_decode_dev(dev));
+				  dentry, mode, new_decode_dev(dev), NULL);
 	end_creating_path(&path, dentry);
 	return error;
 }

fs/namei.c

@@ -4295,13 +4295,15 @@ inline struct dentry *start_creating_user_path(
 }
 EXPORT_SYMBOL(start_creating_user_path);
 
+
 /**
  * vfs_mknod - create device node or file
- * @idmap:	idmap of the mount the inode was found from
+ * @idmap:		idmap of the mount the inode was found from
- * @dir:	inode of the parent directory
+ * @dir:		inode of the parent directory
- * @dentry:	dentry of the child device node
+ * @dentry:		dentry of the child device node
- * @mode:	mode of the child device node
+ * @mode:		mode of the child device node
- * @dev:	device number of device to create
+ * @dev:		device number of device to create
+ * @delegated_inode:	returns parent inode, if the inode is delegated.
  *
  * Create a device node or file.
  *
@@ -4312,7 +4314,8 @@ EXPORT_SYMBOL(start_creating_user_path);
  * raw inode simply pass @nop_mnt_idmap.
  */
 int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
-	      struct dentry *dentry, umode_t mode, dev_t dev)
+	      struct dentry *dentry, umode_t mode, dev_t dev,
+	      struct delegated_inode *delegated_inode)
 {
 	bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV;
 	int error = may_create(idmap, dir, dentry);
@@ -4336,6 +4339,10 @@ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	if (error)
 		return error;
 
+	error = try_break_deleg(dir, delegated_inode);
+	if (error)
+		return error;
+
 	error = dir->i_op->mknod(idmap, dir, dentry, mode, dev);
 	if (!error)
 		fsnotify_create(dir, dentry);
@@ -4393,11 +4400,11 @@ static int do_mknodat(int dfd, struct filename *name, umode_t mode,
 			break;
 		case S_IFCHR: case S_IFBLK:
 			error = vfs_mknod(idmap, path.dentry->d_inode,
-					  dentry, mode, new_decode_dev(dev));
+					  dentry, mode, new_decode_dev(dev), &di);
 			break;
 		case S_IFIFO: case S_IFSOCK:
 			error = vfs_mknod(idmap, path.dentry->d_inode,
-					  dentry, mode, 0);
+					  dentry, mode, 0, &di);
 			break;
 	}
 out2:

fs/nfsd/vfs.c

@@ -1573,7 +1573,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	case S_IFIFO:
 	case S_IFSOCK:
 		host_err = vfs_mknod(&nop_mnt_idmap, dirp, dchild,
-				     iap->ia_mode, rdev);
+				     iap->ia_mode, rdev, NULL);
 		break;
 	default:
 		printk(KERN_WARNING "nfsd: bad file type %o in nfsd_create\n",

fs/overlayfs/overlayfs.h

@@ -257,7 +257,7 @@ static inline int ovl_do_mknod(struct ovl_fs *ofs,
 			       struct inode *dir, struct dentry *dentry,
 			       umode_t mode, dev_t dev)
 {
-	int err = vfs_mknod(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, dev);
+	int err = vfs_mknod(ovl_upper_mnt_idmap(ofs), dir, dentry, mode, dev, NULL);
 
 	pr_debug("mknod(%pd2, 0%o, 0%o) = %i\n", dentry, mode, dev, err);
 	return err;

include/linux/fs.h

@@ -2116,7 +2116,7 @@ int vfs_create(struct mnt_idmap *, struct dentry *, umode_t,
 struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *,
 			 struct dentry *, umode_t, struct delegated_inode *);
 int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *,
-              umode_t, dev_t);
+	      umode_t, dev_t, struct delegated_inode *);
 int vfs_symlink(struct mnt_idmap *, struct inode *,
 		struct dentry *, const char *);
 int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *,
@@ -2152,7 +2152,7 @@ static inline int vfs_whiteout(struct mnt_idmap *idmap,
 			       struct inode *dir, struct dentry *dentry)
 {
 	return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE,
-			 WHITEOUT_DEV);
+			 WHITEOUT_DEV, NULL);
 }
 
 struct file *kernel_tmpfile_open(struct mnt_idmap *idmap,

net/unix/af_unix.c

@@ -1399,7 +1399,7 @@ static int unix_bind_bsd(struct sock *sk, struct sockaddr_un *sunaddr,
 	idmap = mnt_idmap(parent.mnt);
 	err = security_path_mknod(&parent, dentry, mode, 0);
 	if (!err)
-		err = vfs_mknod(idmap, d_inode(parent.dentry), dentry, mode, 0);
+		err = vfs_mknod(idmap, d_inode(parent.dentry), dentry, mode, 0, NULL);
 	if (err)
 		goto out_path;
 	err = mutex_lock_interruptible(&u->bindlock);