io_uring: separate task_work/waiting cache line

task_work's are typically queued up from IRQ/softirq potentially by a
random CPU like in case of networking. Batch ctx fields bouncing as this
into a separate cache line.

We also move ->cq_timeouts there because waiters have to read and check
it. We can also conditionally hide ->cq_timeouts in the future from the
CQ wait path as a not really useful rudiment.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/b7f3fcb5b6b9cca0238778262c1fdb7ada6286b7.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: isilence

include/linux/io_uring_types.h

@@ -270,15 +270,25 @@ struct io_ring_ctx {
 		unsigned		cached_cq_tail;
 		unsigned		cq_entries;
 		struct io_ev_fd	__rcu	*io_ev_fd;
-		struct wait_queue_head	cq_wait;
 		unsigned		cq_extra;
 	} ____cacheline_aligned_in_smp;
 
+	/*
+	 * task_work and async notification delivery cacheline. Expected to
+	 * regularly bounce b/w CPUs.
+	 */
+	struct {
+		struct llist_head	work_llist;
+		unsigned long		check_cq;
+		atomic_t		cq_wait_nr;
+		atomic_t		cq_timeouts;
+		struct wait_queue_head	cq_wait;
+	} ____cacheline_aligned_in_smp;
+
 	struct {
 		spinlock_t		completion_lock;
 
 		bool			poll_multi_queue;
-		atomic_t		cq_wait_nr;
 
 		/*
 		 * ->iopoll_list is protected by the ctx->uring_lock for
@@ -287,14 +297,11 @@ struct io_ring_ctx {
 		 * manipulate the list, hence no extra locking is needed there.
 		 */
 		struct io_wq_work_list	iopoll_list;
-
-		struct llist_head	work_llist;
 	} ____cacheline_aligned_in_smp;
 
 	/* 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;
@@ -314,8 +321,6 @@ struct io_ring_ctx {
 	struct wait_queue_head	sqo_sq_wait;
 	struct list_head	sqd_list;
 
-	unsigned long		check_cq;
-
 	unsigned int		file_alloc_start;
 	unsigned int		file_alloc_end;