Merge tag 'pull-18-rc1-work.fd' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull file descriptor updates from Al Viro.

 - Descriptor handling cleanups

* tag 'pull-18-rc1-work.fd' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  Unify the primitives for file descriptor closing
  fs: remove fget_many and fput_many interface
  io_uring_enter(): don't leave f.flags uninitialized

4 files changed, 52 insertions, 87 deletions

diff --git a/fs/file.c b/fs/file.c
index ee9317346702..dd6692048f4f 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -630,32 +630,23 @@ EXPORT_SYMBOL(fd_install);
  * @files: file struct to retrieve file from
  * @fd: file descriptor to retrieve file for
  *
- * If this functions returns an EINVAL error pointer the fd was beyond the
- * current maximum number of file descriptors for that fdtable.
+ * Context: files_lock must be held.
  *
- * Returns: The file associated with @fd, on error returns an error pointer.
+ * Returns: The file associated with @fd (NULL if @fd is not open)
  */
 static struct file *pick_file(struct files_struct *files, unsigned fd)
 {
+	struct fdtable *fdt = files_fdtable(files);
 	struct file *file;
-	struct fdtable *fdt;
 
-	spin_lock(&files->file_lock);
-	fdt = files_fdtable(files);
-	if (fd >= fdt->max_fds) {
-		file = ERR_PTR(-EINVAL);
-		goto out_unlock;
-	}
+	if (fd >= fdt->max_fds)
+		return NULL;
+
 	file = fdt->fd[fd];
-	if (!file) {
-		file = ERR_PTR(-EBADF);
-		goto out_unlock;
+	if (file) {
+		rcu_assign_pointer(fdt->fd[fd], NULL);
+		__put_unused_fd(files, fd);
 	}
-	rcu_assign_pointer(fdt->fd[fd], NULL);
-	__put_unused_fd(files, fd);
-
-out_unlock:
-	spin_unlock(&files->file_lock);
 	return file;
 }
 
@@ -664,8 +655,10 @@ int close_fd(unsigned fd)
 	struct files_struct *files = current->files;
 	struct file *file;
 
+	spin_lock(&files->file_lock);
 	file = pick_file(files, fd);
-	if (IS_ERR(file))
+	spin_unlock(&files->file_lock);
+	if (!file)
 		return -EBADF;
 
 	return filp_close(file, files);
@@ -702,20 +695,25 @@ static inline void __range_cloexec(struct files_struct *cur_fds,
 static inline void __range_close(struct files_struct *cur_fds, unsigned int fd,
 				 unsigned int max_fd)
 {
+	unsigned n;
+
+	rcu_read_lock();
+	n = last_fd(files_fdtable(cur_fds));
+	rcu_read_unlock();
+	max_fd = min(max_fd, n);
+
 	while (fd <= max_fd) {
 		struct file *file;
 
+		spin_lock(&cur_fds->file_lock);
 		file = pick_file(cur_fds, fd++);
-		if (!IS_ERR(file)) {
+		spin_unlock(&cur_fds->file_lock);
+
+		if (file) {
 			/* found a valid file to close */
 			filp_close(file, cur_fds);
 			cond_resched();
-			continue;
 		}
-
-		/* beyond the last fd in that table */
-		if (PTR_ERR(file) == -EINVAL)
-			return;
 	}
 }
 
@@ -795,26 +793,9 @@ int __close_range(unsigned fd, unsigned max_fd, unsigned int flags)
  * See close_fd_get_file() below, this variant assumes current->files->file_lock
  * is held.
  */
-int __close_fd_get_file(unsigned int fd, struct file **res)
+struct file *__close_fd_get_file(unsigned int fd)
 {
-	struct files_struct *files = current->files;
-	struct file *file;
-	struct fdtable *fdt;
-
-	fdt = files_fdtable(files);
-	if (fd >= fdt->max_fds)
-		goto out_err;
-	file = fdt->fd[fd];
-	if (!file)
-		goto out_err;
-	rcu_assign_pointer(fdt->fd[fd], NULL);
-	__put_unused_fd(files, fd);
-	get_file(file);
-	*res = file;
-	return 0;
-out_err:
-	*res = NULL;
-	return -ENOENT;
+	return pick_file(current->files, fd);
 }
 
 /*
@@ -822,16 +803,16 @@ out_err:
  * The caller must ensure that filp_close() called on the file, and then
  * an fput().
  */
-int close_fd_get_file(unsigned int fd, struct file **res)
+struct file *close_fd_get_file(unsigned int fd)
 {
 	struct files_struct *files = current->files;
-	int ret;
+	struct file *file;
 
 	spin_lock(&files->file_lock);
-	ret = __close_fd_get_file(fd, res);
+	file = pick_file(files, fd);
 	spin_unlock(&files->file_lock);
 
-	return ret;
+	return file;
 }
 
 void do_close_on_exec(struct files_struct *files)
@@ -871,7 +852,7 @@ void do_close_on_exec(struct files_struct *files)
 }
 
 static inline struct file *__fget_files_rcu(struct files_struct *files,
-	unsigned int fd, fmode_t mask, unsigned int refs)
+	unsigned int fd, fmode_t mask)
 {
 	for (;;) {
 		struct file *file;
@@ -897,10 +878,9 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 		 * Such a race can take two forms:
 		 *
 		 *  (a) the file ref already went down to zero,
-		 *      and get_file_rcu_many() fails. Just try
-		 *      again:
+		 *      and get_file_rcu() fails. Just try again:
 		 */
-		if (unlikely(!get_file_rcu_many(file, refs)))
+		if (unlikely(!get_file_rcu(file)))
 			continue;
 
 		/*
@@ -909,11 +889,11 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 		 *       pointer having changed, because it always goes
 		 *       hand-in-hand with 'fdt'.
 		 *
-		 * If so, we need to put our refs and try again.
+		 * If so, we need to put our ref and try again.
 		 */
 		if (unlikely(rcu_dereference_raw(files->fdt) != fdt) ||
 		    unlikely(rcu_dereference_raw(*fdentry) != file)) {
-			fput_many(file, refs);
+			fput(file);
 			continue;
 		}
 
@@ -926,37 +906,31 @@ static inline struct file *__fget_files_rcu(struct files_struct *files,
 }
 
 static struct file *__fget_files(struct files_struct *files, unsigned int fd,
-				 fmode_t mask, unsigned int refs)
+				 fmode_t mask)
 {
 	struct file *file;
 
 	rcu_read_lock();
-	file = __fget_files_rcu(files, fd, mask, refs);
+	file = __fget_files_rcu(files, fd, mask);
 	rcu_read_unlock();
 
 	return file;
 }
 
-static inline struct file *__fget(unsigned int fd, fmode_t mask,
-				  unsigned int refs)
-{
-	return __fget_files(current->files, fd, mask, refs);
-}
-
-struct file *fget_many(unsigned int fd, unsigned int refs)
+static inline struct file *__fget(unsigned int fd, fmode_t mask)
 {
-	return __fget(fd, FMODE_PATH, refs);
+	return __fget_files(current->files, fd, mask);
 }
 
 struct file *fget(unsigned int fd)
 {
-	return __fget(fd, FMODE_PATH, 1);
+	return __fget(fd, FMODE_PATH);
 }
 EXPORT_SYMBOL(fget);
 
 struct file *fget_raw(unsigned int fd)
 {
-	return __fget(fd, 0, 1);
+	return __fget(fd, 0);
 }
 EXPORT_SYMBOL(fget_raw);
 
@@ -966,7 +940,7 @@ struct file *fget_task(struct task_struct *task, unsigned int fd)
 
 	task_lock(task);
 	if (task->files)
-		file = __fget_files(task->files, fd, 0, 1);
+		file = __fget_files(task->files, fd, 0);
 	task_unlock(task);
 
 	return file;
@@ -1035,7 +1009,7 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask)
 			return 0;
 		return (unsigned long)file;
 	} else {
-		file = __fget(fd, mask, 1);
+		file = __fget(fd, mask);
 		if (!file)
 			return 0;
 		return FDPUT_FPUT | (unsigned long)file;
diff --git a/fs/file_table.c b/fs/file_table.c
index ada8fe814db9..5424e3a8df5f 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -368,9 +368,9 @@ EXPORT_SYMBOL_GPL(flush_delayed_fput);
 
 static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
 
-void fput_many(struct file *file, unsigned int refs)
+void fput(struct file *file)
 {
-	if (atomic_long_sub_and_test(refs, &file->f_count)) {
+	if (atomic_long_dec_and_test(&file->f_count)) {
 		struct task_struct *task = current;
 
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
@@ -389,11 +389,6 @@ void fput_many(struct file *file, unsigned int refs)
 	}
 }
 
-void fput(struct file *file)
-{
-	fput_many(file, 1);
-}
-
 /*
  * synchronous analog of fput(); for kernel threads that might be needed
  * in some umount() (and thus can't use flush_delayed_fput() without
diff --git a/fs/internal.h b/fs/internal.h
index 9a6c233ee7f1..ad77723779f9 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -125,7 +125,7 @@ extern struct file *do_file_open_root(const struct path *,
 		const char *, const struct open_flags *);
 extern struct open_how build_open_how(int flags, umode_t mode);
 extern int build_open_flags(const struct open_how *how, struct open_flags *op);
-extern int __close_fd_get_file(unsigned int fd, struct file **res);
+extern struct file *__close_fd_get_file(unsigned int fd);
 
 long do_sys_ftruncate(unsigned int fd, loff_t length, int small);
 int chmod_common(const struct path *path, umode_t mode);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2a9b9a24fc22..86f9df56526b 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -6039,13 +6039,10 @@ static int io_close(struct io_kiocb *req, unsigned int issue_flags)
 		return -EAGAIN;
 	}
 
-	ret = __close_fd_get_file(close->fd, &file);
+	file = __close_fd_get_file(close->fd);
 	spin_unlock(&files->file_lock);
-	if (ret < 0) {
-		if (ret == -ENOENT)
-			ret = -EBADF;
+	if (!file)
 		goto err;
-	}
 
 	/* No ->flush() or already async, safely close from here */
 	ret = filp_close(file, current->files);
@@ -12053,14 +12050,14 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			return -EINVAL;
 		fd = array_index_nospec(fd, IO_RINGFD_REG_MAX);
 		f.file = tctx->registered_rings[fd];
-		if (unlikely(!f.file))
-			return -EBADF;
+		f.flags = 0;
 	} else {
 		f = fdget(fd);
-		if (unlikely(!f.file))
-			return -EBADF;
 	}
 
+	if (unlikely(!f.file))
+		return -EBADF;
+
 	ret = -EOPNOTSUPP;
 	if (unlikely(f.file->f_op != &io_uring_fops))
 		goto out_fput;
@@ -12158,8 +12155,7 @@ iopoll_locked:
 out:
 	percpu_ref_put(&ctx->refs);
 out_fput:
-	if (!(flags & IORING_ENTER_REGISTERED_RING))
-		fdput(f);
+	fdput(f);
 	return ret;
 }