io_uring: partially uninline io_put_task()

In most cases io_put_task() is called from the submitter task and go
through a higly optimised fast path, which has to be inlined. The other
branch though is bulkier and we don't care about it as much because it
implies atomics and other heavy calls. Extract it into a helper, which
is expected not to be inlined.

[before] size ./fs/io_uring.o
   text    data     bss     dec     hex filename
  89328   13646       8  102982   19246 ./fs/io_uring.o
[after] size ./fs/io_uring.o
   text    data     bss     dec     hex filename
  89096   13646       8  102750   1915e ./fs/io_uring.o
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/dec213db0e0b8605132da81e0a0be687a4d140cb.1648209006.git.asml.silence@gmail.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -1963,19 +1963,23 @@ static bool io_cqring_overflow_flush(struct io_ring_ctx *ctx)
 	return ret;
 }
 
-/* must to be called somewhat shortly after putting a request */
-static inline void io_put_task(struct task_struct *task, int nr)
+static void __io_put_task(struct task_struct *task, int nr)
 {
 	struct io_uring_task *tctx = task->io_uring;
 
-	if (likely(task == current)) {
-		tctx->cached_refs += nr;
-	} else {
-		percpu_counter_sub(&tctx->inflight, nr);
-		if (unlikely(atomic_read(&tctx->in_idle)))
-			wake_up(&tctx->wait);
-		put_task_struct_many(task, nr);
-	}
+	percpu_counter_sub(&tctx->inflight, nr);
+	if (unlikely(atomic_read(&tctx->in_idle)))
+		wake_up(&tctx->wait);
+	put_task_struct_many(task, nr);
+}
+
+/* must to be called somewhat shortly after putting a request */
+static inline void io_put_task(struct task_struct *task, int nr)
+{
+	if (likely(task == current))
+		task->io_uring->cached_refs += nr;
+	else
+		__io_put_task(task, nr);
 }
 
 static void io_task_refs_refill(struct io_uring_task *tctx)