io_uring: ensure io_queue_deferred() is out-of-line

This is not the hot path, it's a slow path. Yet the locking for it is
in the hot path, and __cold does not prevent it from being inlined.

Move the locking to the function itself, and mark it noinline as well
to avoid it polluting the icache of the hot path.

Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -550,8 +550,9 @@ void io_req_queue_iowq(struct io_kiocb *req)
 	io_req_task_work_add(req);
 }
 
-static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
+static __cold noinline void io_queue_deferred(struct io_ring_ctx *ctx)
 {
+	spin_lock(&ctx->completion_lock);
 	while (!list_empty(&ctx->defer_list)) {
 		struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
 						struct io_defer_entry, list);
@@ -562,6 +563,7 @@ static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
 		io_req_task_queue(de->req);
 		kfree(de);
 	}
+	spin_unlock(&ctx->completion_lock);
 }
 
 void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
@@ -570,11 +572,8 @@ void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
 		io_poll_wq_wake(ctx);
 	if (ctx->off_timeout_used)
 		io_flush_timeouts(ctx);
-	if (ctx->drain_active) {
-		spin_lock(&ctx->completion_lock);
+	if (ctx->drain_active)
 		io_queue_deferred(ctx);
-		spin_unlock(&ctx->completion_lock);
-	}
 	if (ctx->has_evfd)
 		io_eventfd_flush_signal(ctx);
 }