file: add fput and file_ref_put routines optimized for use when closing a fd

Vast majority of the time closing a file descriptor also operates on the
last reference, where a regular fput usage will result in 2 atomics.
This can be changed to only suffer 1.

See commentary above file_ref_put_close() for more information.

Signed-off-by: Mateusz Guzik <mjguzik@gmail.com>
Link: https://lore.kernel.org/r/20250305123644.554845-2-mjguzik@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 49 insertions, 21 deletions

diff --git a/fs/file_table.c b/fs/file_table.c
index f0291a66f9db..18debb7bd285 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -495,31 +495,37 @@ void flush_delayed_fput(void)
 }
 EXPORT_SYMBOL_GPL(flush_delayed_fput);
 
-void fput(struct file *file)
+static void __fput_deferred(struct file *file)
 {
-	if (file_ref_put(&file->f_ref)) {
-		struct task_struct *task = current;
+	struct task_struct *task = current;
+
+	if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) {
+		file_free(file);
+		return;
+	}
 
-		if (unlikely(!(file->f_mode & (FMODE_BACKING | FMODE_OPENED)))) {
-			file_free(file);
+	if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
+		init_task_work(&file->f_task_work, ____fput);
+		if (!task_work_add(task, &file->f_task_work, TWA_RESUME))
 			return;
-		}
-		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
-			init_task_work(&file->f_task_work, ____fput);
-			if (!task_work_add(task, &file->f_task_work, TWA_RESUME))
-				return;
-			/*
-			 * After this task has run exit_task_work(),
-			 * task_work_add() will fail.  Fall through to delayed
-			 * fput to avoid leaking *file.
-			 */
-		}
-
-		if (llist_add(&file->f_llist, &delayed_fput_list))
-			schedule_delayed_work(&delayed_fput_work, 1);
+		/*
+		 * After this task has run exit_task_work(),
+		 * task_work_add() will fail.  Fall through to delayed
+		 * fput to avoid leaking *file.
+		 */
 	}
+
+	if (llist_add(&file->f_llist, &delayed_fput_list))
+		schedule_delayed_work(&delayed_fput_work, 1);
 }
 
+void fput(struct file *file)
+{
+	if (unlikely(file_ref_put(&file->f_ref)))
+		__fput_deferred(file);
+}
+EXPORT_SYMBOL(fput);
+
 /*
  * synchronous analog of fput(); for kernel threads that might be needed
  * in some umount() (and thus can't use flush_delayed_fput() without
@@ -533,10 +539,32 @@ void __fput_sync(struct file *file)
 	if (file_ref_put(&file->f_ref))
 		__fput(file);
 }
-
-EXPORT_SYMBOL(fput);
 EXPORT_SYMBOL(__fput_sync);
 
+/*
+ * Equivalent to __fput_sync(), but optimized for being called with the last
+ * reference.
+ *
+ * See file_ref_put_close() for details.
+ */
+void fput_close_sync(struct file *file)
+{
+	if (likely(file_ref_put_close(&file->f_ref)))
+		__fput(file);
+}
+
+/*
+ * Equivalent to fput(), but optimized for being called with the last
+ * reference.
+ *
+ * See file_ref_put_close() for details.
+ */
+void fput_close(struct file *file)
+{
+	if (file_ref_put_close(&file->f_ref))
+		__fput_deferred(file);
+}
+
 void __init files_init(void)
 {
 	struct kmem_cache_args args = {