io_uring: move ctx->flags from SQ cacheline

ctx->flags are heavily used by both, completion and submission sides, so
move it out from the ctx fields related to submissions. Instead, place
it together with ctx->refs, because it's already cacheline-aligned and
so pads lots of space, and both almost never change. Also, in most
occasions they are accessed together as refs are taken at submission
time and put back during completion.

Do same with ctx->rings, where the pointer itself is never modified
apart from ring init/free.

Note: in percpu mode, struct percpu_ref doesn't modify the struct itself
but takes indirection with ref->percpu_count_ptr.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/4c48c173e63d35591383ba2b87e8b8e8dfdbd23d.1623709150.git.asml.silence@gmail.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -341,17 +341,19 @@ struct io_submit_state {
 };
 
 struct io_ring_ctx {
+	/* const or read-mostly hot data */
 	struct {
 		struct percpu_ref	refs;
-	} ____cacheline_aligned_in_smp;
 
-	struct {
+		struct io_rings		*rings;
 		unsigned int		flags;
 		unsigned int		compat: 1;
 		unsigned int		drain_next: 1;
 		unsigned int		eventfd_async: 1;
 		unsigned int		restricted: 1;
+	} ____cacheline_aligned_in_smp;
 
+	struct {
 		/*
 		 * Ring buffer of indices into array of io_uring_sqe, which is
 		 * mmapped by the application using the IORING_OFF_SQES offset.
@@ -386,8 +388,6 @@ struct io_ring_ctx {
 	struct list_head	locked_free_list;
 	unsigned int		locked_free_nr;
 
-	struct io_rings	*rings;
-
 	const struct cred	*sq_creds;	/* cred used for __io_sq_thread() */
 	struct io_sq_data	*sq_data;	/* if using sq thread polling */