diff --git a/fs/aio.c b/fs/aio.c
index 48fdeebdb544df9e008affb6814789035d4e94ce..1ccf25cef1f027a61449ed2cf12b56fb077686ea 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -527,7 +527,7 @@ static void aio_fput_routine(struct work_struct *data)
 
 		/* Complete the fput(s) */
 		if (req->ki_filp != NULL)
-			__fput(req->ki_filp);
+			fput(req->ki_filp);
 
 		/* Link the iocb into the context's free list */
 		spin_lock_irq(&ctx->ctx_lock);
@@ -560,11 +560,11 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 
 	/*
 	 * Try to optimize the aio and eventfd file* puts, by avoiding to
-	 * schedule work in case it is not __fput() time. In normal cases,
+	 * schedule work in case it is not final fput() time. In normal cases,
 	 * we would not be holding the last reference to the file*, so
 	 * this function will be executed w/out any aio kthread wakeup.
 	 */
-	if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) {
+	if (unlikely(!fput_atomic(req->ki_filp))) {
 		get_ioctx(ctx);
 		spin_lock(&fput_lock);
 		list_add(&req->ki_list, &fput_head);
diff --git a/fs/file_table.c b/fs/file_table.c
index 32d12b78bac8e2c05a80dc53386b355bdc10ef73..5c7d10ead4ad774981f294428bd1ef7fa9e4cccf 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -194,14 +194,6 @@ struct file *alloc_file(struct path *path, fmode_t mode,
 }
 EXPORT_SYMBOL(alloc_file);
 
-void fput(struct file *file)
-{
-	if (atomic_long_dec_and_test(&file->f_count))
-		__fput(file);
-}
-
-EXPORT_SYMBOL(fput);
-
 /**
  * drop_file_write_access - give up ability to write to a file
  * @file: the file to which we will stop writing
@@ -227,10 +219,9 @@ void drop_file_write_access(struct file *file)
 }
 EXPORT_SYMBOL_GPL(drop_file_write_access);
 
-/* __fput is called from task context when aio completion releases the last
- * last use of a struct file *.  Do not use otherwise.
+/* the real guts of fput() - releasing the last reference to file
  */
-void __fput(struct file *file)
+static void __fput(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct vfsmount *mnt = file->f_path.mnt;
@@ -268,6 +259,14 @@ void __fput(struct file *file)
 	mntput(mnt);
 }
 
+void fput(struct file *file)
+{
+	if (atomic_long_dec_and_test(&file->f_count))
+		__fput(file);
+}
+
+EXPORT_SYMBOL(fput);
+
 struct file *fget(unsigned int fd)
 {
 	struct file *file;
diff --git a/include/linux/file.h b/include/linux/file.h
index 5555508fd5171f6c7a546c2d7364876223e7c9cc..b1e12970f617b919ad71b48ee44deaa306b6f05b 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -11,7 +11,6 @@
 
 struct file;
 
-extern void __fput(struct file *);
 extern void fput(struct file *);
 extern void drop_file_write_access(struct file *file);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 85e823adcd4a7d82bc1a1dedf684e02cde5039ac..3d9ed8302402e38c33b041d8f5a61ffca0c884b3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -954,6 +954,7 @@ extern spinlock_t files_lock;
 #define file_list_unlock() spin_unlock(&files_lock);
 
 #define get_file(x)	atomic_long_inc(&(x)->f_count)
+#define fput_atomic(x)	atomic_long_add_unless(&(x)->f_count, -1, 1)
 #define file_count(x)	atomic_long_read(&(x)->f_count)
 
 #ifdef CONFIG_DEBUG_WRITECOUNT