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()
  ...

Author: torvalds

arch/powerpc/platforms/cell/spufs/inode.c

@@ -267,22 +267,11 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags,
 
 static int spufs_context_open(const struct path *path)
 {
-	int ret;
-	struct file *filp;
-
-	ret = get_unused_fd_flags(0);
-	if (ret < 0)
-		return ret;
-
-	filp = dentry_open(path, O_RDONLY, current_cred());
-	if (IS_ERR(filp)) {
-		put_unused_fd(ret);
-		return PTR_ERR(filp);
-	}
-
-	filp->f_op = &spufs_context_fops;
-	fd_install(ret, filp);
-	return ret;
+	FD_PREPARE(fdf, 0, dentry_open(path, O_RDONLY, current_cred()));
+	if (fdf.err)
+		return fdf.err;
+	fd_prepare_file(fdf)->f_op = &spufs_context_fops;
+	return fd_publish(fdf);
 }
 
 static struct spu_context *
@@ -508,26 +497,15 @@ static const struct file_operations spufs_gang_fops = {
 
 static int spufs_gang_open(const struct path *path)
 {
-	int ret;
-	struct file *filp;
-
-	ret = get_unused_fd_flags(0);
-	if (ret < 0)
-		return ret;
-
 	/*
 	 * get references for dget and mntget, will be released
 	 * in error path of *_open().
 	 */
-	filp = dentry_open(path, O_RDONLY, current_cred());
-	if (IS_ERR(filp)) {
-		put_unused_fd(ret);
-		return PTR_ERR(filp);
-	}
-
-	filp->f_op = &spufs_gang_fops;
-	fd_install(ret, filp);
-	return ret;
+	FD_PREPARE(fdf, 0, dentry_open(path, O_RDONLY, current_cred()));
+	if (fdf.err)
+		return fdf.err;
+	fd_prepare_file(fdf)->f_op = &spufs_gang_fops;
+	return fd_publish(fdf);
 }
 
 static int spufs_create_gang(struct inode *inode,

arch/powerpc/platforms/pseries/papr-hvpipe.c

@@ -479,10 +479,7 @@ static const struct file_operations papr_hvpipe_handle_ops = {
 
 static int papr_hvpipe_dev_create_handle(u32 srcID)
 {
-	struct hvpipe_source_info *src_info;
-	struct file *file;
-	long err;
-	int fd;
+	struct hvpipe_source_info *src_info __free(kfree) = NULL;
 
 	spin_lock(&hvpipe_src_list_lock);
 	/*
@@ -506,20 +503,13 @@ static int papr_hvpipe_dev_create_handle(u32 srcID)
 	src_info->tsk = current;
 	init_waitqueue_head(&src_info->recv_wqh);
 
-	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		err = fd;
-		goto free_buf;
-	}
-
-	file = anon_inode_getfile("[papr-hvpipe]",
-			&papr_hvpipe_handle_ops, (void *)src_info,
-			O_RDWR);
-	if (IS_ERR(file)) {
-		err = PTR_ERR(file);
-		goto free_fd;
-	}
+	FD_PREPARE(fdf, O_RDONLY | O_CLOEXEC,
+		   anon_inode_getfile("[papr-hvpipe]", &papr_hvpipe_handle_ops,
+				      (void *)src_info, O_RDWR));
+	if (fdf.err)
+		return fdf.err;
 
+	retain_and_null_ptr(src_info);
 	spin_lock(&hvpipe_src_list_lock);
 	/*
 	 * If two processes are executing ioctl() for the same
@@ -528,22 +518,11 @@ static int papr_hvpipe_dev_create_handle(u32 srcID)
 	 */
 	if (hvpipe_find_source(srcID)) {
 		spin_unlock(&hvpipe_src_list_lock);
-		err = -EALREADY;
-		goto free_file;
+		return -EALREADY;
 	}
 	list_add(&src_info->list, &hvpipe_src_list);
 	spin_unlock(&hvpipe_src_list_lock);
-
-	fd_install(fd, file);
-	return fd;
-
-free_file:
-	fput(file);
-free_fd:
-	put_unused_fd(fd);
-free_buf:
-	kfree(src_info);
-	return err;
+	return fd_publish(fdf);
 }
 
 /*

arch/powerpc/platforms/pseries/papr-platform-dump.c

@@ -303,8 +303,6 @@ static long papr_platform_dump_create_handle(u64 dump_tag)
 {
 	struct ibm_platform_dump_params *params;
 	u64 param_dump_tag;
-	struct file *file;
-	long err;
 	int fd;
 
 	/*
@@ -334,34 +332,22 @@ static long papr_platform_dump_create_handle(u64 dump_tag)
 	params->dump_tag_lo = (u32)(dump_tag & 0x00000000ffffffffULL);
 	params->status = RTAS_IBM_PLATFORM_DUMP_START;
 
-	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
+	fd = FD_ADD(O_RDONLY | O_CLOEXEC,
+		    anon_inode_getfile_fmode("[papr-platform-dump]",
+					     &papr_platform_dump_handle_ops,
+					     (void *)params, O_RDONLY,
+					     FMODE_LSEEK | FMODE_PREAD));
 	if (fd < 0) {
-		err = fd;
-		goto free_area;
-	}
-
-	file = anon_inode_getfile_fmode("[papr-platform-dump]",
-				&papr_platform_dump_handle_ops,
-				(void *)params, O_RDONLY,
-				FMODE_LSEEK | FMODE_PREAD);
-	if (IS_ERR(file)) {
-		err = PTR_ERR(file);
-		goto put_fd;
+		rtas_work_area_free(params->work_area);
+		kfree(params);
+		return fd;
 	}
 
-	fd_install(fd, file);
-
 	list_add(&params->list, &platform_dump_list);
 
 	pr_info("%s (%d) initiated platform dump for dump tag %llu\n",
 		current->comm, current->pid, dump_tag);
 	return fd;
-put_fd:
-	put_unused_fd(fd);
-free_area:
-	rtas_work_area_free(params->work_area);
-	kfree(params);
-	return err;
 }
 
 /*

arch/powerpc/platforms/pseries/papr-rtas-common.c

@@ -205,35 +205,18 @@ long papr_rtas_setup_file_interface(struct papr_rtas_sequence *seq,
 				char *name)
 {
 	const struct papr_rtas_blob *blob;
-	struct file *file;
-	long ret;
 	int fd;
 
 	blob = papr_rtas_retrieve(seq);
 	if (IS_ERR(blob))
 		return PTR_ERR(blob);
 
-	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		ret = fd;
-		goto free_blob;
-	}
-
-	file = anon_inode_getfile_fmode(name, fops, (void *)blob,
-			O_RDONLY, FMODE_LSEEK | FMODE_PREAD);
-	if (IS_ERR(file)) {
-		ret = PTR_ERR(file);
-		goto put_fd;
-	}
-
-	fd_install(fd, file);
+	fd = FD_ADD(O_RDONLY | O_CLOEXEC,
+		   anon_inode_getfile_fmode(name, fops, (void *)blob, O_RDONLY,
+					    FMODE_LSEEK | FMODE_PREAD));
+	if (fd < 0)
+		papr_rtas_blob_free(blob);
 	return fd;
-
-put_fd:
-	put_unused_fd(fd);
-free_blob:
-	papr_rtas_blob_free(blob);
-	return ret;
 }
 
 /*

drivers/dma-buf/dma-buf.c

@@ -768,18 +768,10 @@ EXPORT_SYMBOL_NS_GPL(dma_buf_export, "DMA_BUF");
  */
 int dma_buf_fd(struct dma_buf *dmabuf, int flags)
 {
-	int fd;
-
 	if (!dmabuf || !dmabuf->file)
 		return -EINVAL;
 
-	fd = get_unused_fd_flags(flags);
-	if (fd < 0)
-		return fd;
-
-	fd_install(fd, dmabuf->file);
-
-	return fd;
+	return FD_ADD(flags, dmabuf->file);
 }
 EXPORT_SYMBOL_NS_GPL(dma_buf_fd, "DMA_BUF");
 

drivers/gpio/gpiolib-cdev.c

@@ -298,12 +298,13 @@ static const struct file_operations linehandle_fileops = {
 #endif
 };
 
+DEFINE_FREE(linehandle_free, struct linehandle_state *, if (!IS_ERR_OR_NULL(_T)) linehandle_free(_T))
+
 static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 {
 	struct gpiohandle_request handlereq;
-	struct linehandle_state *lh;
-	struct file *file;
-	int fd, i, ret;
+	struct linehandle_state *lh __free(linehandle_free) = NULL;
+	int i, ret;
 	u32 lflags;
 
 	if (copy_from_user(&handlereq, ip, sizeof(handlereq)))
@@ -327,10 +328,8 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 		lh->label = kstrndup(handlereq.consumer_label,
 				     sizeof(handlereq.consumer_label) - 1,
 				     GFP_KERNEL);
-		if (!lh->label) {
-			ret = -ENOMEM;
-			goto out_free_lh;
-		}
+		if (!lh->label)
+			return -ENOMEM;
 	}
 
 	lh->num_descs = handlereq.lines;
@@ -340,20 +339,18 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 		u32 offset = handlereq.lineoffsets[i];
 		struct gpio_desc *desc = gpio_device_get_desc(gdev, offset);
 
-		if (IS_ERR(desc)) {
-			ret = PTR_ERR(desc);
-			goto out_free_lh;
-		}
+		if (IS_ERR(desc))
+			return PTR_ERR(desc);
 
 		ret = gpiod_request_user(desc, lh->label);
 		if (ret)
-			goto out_free_lh;
+			return ret;
 		lh->descs[i] = desc;
 		linehandle_flags_to_desc_flags(handlereq.flags, &desc->flags);
 
 		ret = gpiod_set_transitory(desc, false);
 		if (ret < 0)
-			goto out_free_lh;
+			return ret;
 
 		/*
 		 * Lines have to be requested explicitly for input
@@ -364,11 +361,11 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 
 			ret = gpiod_direction_output_nonotify(desc, val);
 			if (ret)
-				goto out_free_lh;
+				return ret;
 		} else if (lflags & GPIOHANDLE_REQUEST_INPUT) {
 			ret = gpiod_direction_input_nonotify(desc);
 			if (ret)
-				goto out_free_lh;
+				return ret;
 		}
 
 		gpiod_line_state_notify(desc, GPIO_V2_LINE_CHANGED_REQUESTED);
@@ -377,44 +374,23 @@ static int linehandle_create(struct gpio_device *gdev, void __user *ip)
 			offset);
 	}
 
-	fd = get_unused_fd_flags(O_RDONLY | O_CLOEXEC);
-	if (fd < 0) {
-		ret = fd;
-		goto out_free_lh;
-	}
+	FD_PREPARE(fdf, O_RDONLY | O_CLOEXEC,
+		   anon_inode_getfile("gpio-linehandle", &linehandle_fileops,
+				      lh, O_RDONLY | O_CLOEXEC));
+	if (fdf.err)
+		return fdf.err;
+	retain_and_null_ptr(lh);
 
-	file = anon_inode_getfile("gpio-linehandle",
-				  &linehandle_fileops,
-				  lh,
-				  O_RDONLY | O_CLOEXEC);
-	if (IS_ERR(file)) {
-		ret = PTR_ERR(file);
-		goto out_put_unused_fd;
-	}
-
-	handlereq.fd = fd;
-	if (copy_to_user(ip, &handlereq, sizeof(handlereq))) {
-		/*
-		 * fput() will trigger the release() callback, so do not go onto
-		 * the regular error cleanup path here.
-		 */
-		fput(file);
-		put_unused_fd(fd);
+	handlereq.fd = fd_prepare_fd(fdf);
+	if (copy_to_user(ip, &handlereq, sizeof(handlereq)))
 		return -EFAULT;
-	}
 
-	fd_install(fd, file);
+	fd_publish(fdf);
 
 	dev_dbg(&gdev->dev, "registered chardev handle for %d lines\n",
 		lh->num_descs);
 
 	return 0;
-
-out_put_unused_fd:
-	put_unused_fd(fd);
-out_free_lh:
-	linehandle_free(lh);
-	return ret;
 }
 #endif /* CONFIG_GPIO_CDEV_V1 */