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

Pull fd prepare updates from Christian Brauner:
 "This adds the FD_ADD() and FD_PREPARE() primitive. They simplify the
  common pattern of get_unused_fd_flags() + create file + fd_install()
  that is used extensively throughout the kernel and currently requires
  cumbersome cleanup paths.

  FD_ADD() - For simple cases where a file is installed immediately:

      fd = FD_ADD(O_CLOEXEC, vfio_device_open_file(device));
      if (fd < 0)
          vfio_device_put_registration(device);
      return fd;

  FD_PREPARE() - For cases requiring access to the fd or file, or
  additional work before publishing:

      FD_PREPARE(fdf, O_CLOEXEC, sync_file->file);
      if (fdf.err) {
          fput(sync_file->file);
          return fdf.err;
      }

      data.fence = fd_prepare_fd(fdf);
      if (copy_to_user((void __user *)arg, &data, sizeof(data)))
          return -EFAULT;

      return fd_publish(fdf);

  The primitives are centered around struct fd_prepare. FD_PREPARE()
  encapsulates all allocation and cleanup logic and must be followed by
  a call to fd_publish() which associates the fd with the file and
  installs it into the caller's fdtable. If fd_publish() isn't called,
  both are deallocated automatically. FD_ADD() is a shorthand that does
  fd_publish() immediately and never exposes the struct to the caller.

  I've implemented this in a way that it's compatible with the cleanup
  infrastructure while also being usable separately. IOW, it's centered
  around struct fd_prepare which is aliased to class_fd_prepare_t and so
  we can make use of all the basica guard infrastructure"

* tag 'vfs-6.19-rc1.fd_prepare.fs' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (42 commits)
  io_uring: convert io_create_mock_file() to FD_PREPARE()
  file: convert replace_fd() to FD_PREPARE()
  vfio: convert vfio_group_ioctl_get_device_fd() to FD_ADD()
  tty: convert ptm_open_peer() to FD_ADD()
  ntsync: convert ntsync_obj_get_fd() to FD_PREPARE()
  media: convert media_request_alloc() to FD_PREPARE()
  hv: convert mshv_ioctl_create_partition() to FD_ADD()
  gpio: convert linehandle_create() to FD_PREPARE()
  pseries: port papr_rtas_setup_file_interface() to FD_ADD()
  pseries: convert papr_platform_dump_create_handle() to FD_ADD()
  spufs: convert spufs_gang_open() to FD_PREPARE()
  papr-hvpipe: convert papr_hvpipe_dev_create_handle() to FD_PREPARE()
  spufs: convert spufs_context_open() to FD_PREPARE()
  net/socket: convert __sys_accept4_file() to FD_ADD()
  net/socket: convert sock_map_fd() to FD_ADD()
  net/kcm: convert kcm_ioctl() to FD_PREPARE()
  net/handshake: convert handshake_nl_accept_doit() to FD_PREPARE()
  secretmem: convert memfd_secret() to FD_ADD()
  memfd: convert memfd_create() to FD_ADD()
  bpf: convert bpf_token_create() to FD_PREPARE()
  ...

1 files changed, 13 insertions, 34 deletions

diff --git a/fs/nsfs.c b/fs/nsfs.c
index a80f8d2a4122..bf27d5da91f1 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -110,7 +110,6 @@ int ns_get_path(struct path *path, struct task_struct *task,
 int open_namespace(struct ns_common *ns)
 {
 	struct path path __free(path_put) = {};
-	struct file *f;
 	int err;
 
 	/* call first to consume reference */
@@ -118,16 +117,7 @@ int open_namespace(struct ns_common *ns)
 	if (err < 0)
 		return err;
 
-	CLASS(get_unused_fd, fd)(O_CLOEXEC);
-	if (fd < 0)
-		return fd;
-
-	f = dentry_open(&path, O_RDONLY, current_cred());
-	if (IS_ERR(f))
-		return PTR_ERR(f);
-
-	fd_install(fd, f);
-	return take_fd(fd);
+	return FD_ADD(O_CLOEXEC, dentry_open(&path, O_RDONLY, current_cred()));
 }
 
 int open_related_ns(struct ns_common *ns,
@@ -313,7 +303,6 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl,
 		struct mnt_ns_info kinfo = {};
 		struct mnt_ns_info __user *uinfo = (struct mnt_ns_info __user *)arg;
 		struct path path __free(path_put) = {};
-		struct file *f __free(fput) = NULL;
 		size_t usize = _IOC_SIZE(ioctl);
 
 		if (ns->ns_type != CLONE_NEWNS)
@@ -332,28 +321,18 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl,
 		if (ret)
 			return ret;
 
-		CLASS(get_unused_fd, fd)(O_CLOEXEC);
-		if (fd < 0)
-			return fd;
-
-		f = dentry_open(&path, O_RDONLY, current_cred());
-		if (IS_ERR(f))
-			return PTR_ERR(f);
-
-		if (uinfo) {
-			/*
-			 * If @uinfo is passed return all information about the
-			 * mount namespace as well.
-			 */
-			ret = copy_ns_info_to_user(to_mnt_ns(ns), uinfo, usize, &kinfo);
-			if (ret)
-				return ret;
-		}
-
-		/* Transfer reference of @f to caller's fdtable. */
-		fd_install(fd, no_free_ptr(f));
-		/* File descriptor is live so hand it off to the caller. */
-		return take_fd(fd);
+		FD_PREPARE(fdf, O_CLOEXEC, dentry_open(&path, O_RDONLY, current_cred()));
+		if (fdf.err)
+			return fdf.err;
+		/*
+		 * If @uinfo is passed return all information about the
+		 * mount namespace as well.
+		 */
+		ret = copy_ns_info_to_user(to_mnt_ns(ns), uinfo, usize, &kinfo);
+		if (ret)
+			return ret;
+		ret = fd_publish(fdf);
+		break;
 	}
 	default:
 		ret = -ENOTTY;