The patch below does not apply to the 5.18-stable tree.
If someone wants it applied there, or to any other stable or longterm
tree, then please email the backport, including the original git commit
id to <stable@xxxxxxxxxxxxxxx>.
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
>From 4a0fef62788b69df09267c8e3f3f11d4bb9d50e7 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@xxxxxxxxx>
Date: Mon, 20 Jun 2022 15:27:35 +0100
Subject: [PATCH] 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@xxxxxxxxxxxxxxx # 5.15+
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
diff --git a/io_uring/tctx.h b/io_uring/tctx.h
index dde82ce4d8e2..dead0ed00429 100644
--- a/io_uring/tctx.h
+++ b/io_uring/tctx.h
@@ -7,22 +7,24 @@
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;
- atomic_t in_idle;
-
- spinlock_t task_lock;
- 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];
+ int cached_refs;
+ const struct io_ring_ctx *last;
+ struct io_wq *io_wq;
+ 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;
+ } ____cacheline_aligned_in_smp;
};
struct io_tctx_node {
