io_uring: optimize io_uring_task layout

task_work bits of io_uring_task are split into two cache lines causing
extra cache bouncing, place them into a separate cache line. Also move
the most used submission path fields closer together, so there are hot.

Cc: stable@vger.kernel.org # 5.15+
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/tctx.h

@@ -8,21 +8,23 @@
 struct io_uring_task {
 	/* submission side */
 	int				cached_refs;
-	struct xarray		xa;
-	struct wait_queue_head	wait;
 	const struct io_ring_ctx 	*last;
 	struct io_wq			*io_wq;
-	struct percpu_counter	inflight;
-	atomic_t		inflight_tracked;
+	struct file			*registered_rings[IO_RINGFD_REG_MAX];
+
+	struct xarray			xa;
+	struct wait_queue_head		wait;
 	atomic_t			in_idle;
+	atomic_t			inflight_tracked;
+	struct percpu_counter		inflight;
 
+	struct { /* task_work */
 		spinlock_t		task_lock;
+		bool			task_running;
 		struct io_wq_work_list	task_list;
 		struct io_wq_work_list	prio_task_list;
 		struct callback_head	task_work;
-	bool			task_running;
-
-	struct file		*registered_rings[IO_RINGFD_REG_MAX];
+	} ____cacheline_aligned_in_smp;
 };
 
 struct io_tctx_node {