io_uring: better caching for ctx timeout fields

Following timeout fields access patterns, move all of them into a
separate cache line inside ctx, so they don't intervene with normal
completion caching, especially since timeout removals and completion
are separated and the later is done via tw.

It also sheds some bytes from io_ring_ctx, 1216B -> 1152B
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/4b163793072840de53b3cb66e0c2995e7226ff78.1655310733.git.asml.silence@gmail.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring_types.h

@@ -181,8 +181,6 @@ struct io_ring_ctx {
 		struct xarray		io_bl_xa;
 		struct list_head	io_buffers_cache;
 
-		struct list_head	timeout_list;
-		struct list_head	ltimeout_list;
 		struct list_head	cq_overflow_list;
 		struct list_head	apoll_cache;
 		struct xarray		personalities;
@@ -215,15 +213,11 @@ struct io_ring_ctx {
 		struct io_ev_fd	__rcu	*io_ev_fd;
 		struct wait_queue_head	cq_wait;
 		unsigned		cq_extra;
-		atomic_t		cq_timeouts;
-		unsigned		cq_last_tm_flush;
 	} ____cacheline_aligned_in_smp;
 
 	struct {
 		spinlock_t		completion_lock;
 
-		spinlock_t		timeout_lock;
-
 		/*
 		 * ->iopoll_list is protected by the ctx->uring_lock for
 		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
@@ -255,6 +249,15 @@ struct io_ring_ctx {
 		struct list_head	io_buffers_pages;
 	};
 
+	/* timeouts */
+	struct {
+		spinlock_t		timeout_lock;
+		atomic_t		cq_timeouts;
+		struct list_head	timeout_list;
+		struct list_head	ltimeout_list;
+		unsigned		cq_last_tm_flush;
+	} ____cacheline_aligned_in_smp;
+
 	/* Keep this last, we don't need it for the fast path */
 	struct {
 		#if defined(CONFIG_UNIX)