This is a note to let you know that I've just added the patch titled
io_uring: use private workqueue for exit work
to the 6.8-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
io_uring-use-private-workqueue-for-exit-work.patch
and it can be found in the queue-6.8 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 73eaa2b583493b680c6f426531d6736c39643bfb Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@xxxxxxxxx>
Date: Mon, 1 Apr 2024 15:16:19 -0600
Subject: io_uring: use private workqueue for exit work
From: Jens Axboe <axboe@xxxxxxxxx>
commit 73eaa2b583493b680c6f426531d6736c39643bfb upstream.
Rather than use the system unbound event workqueue, use an io_uring
specific one. This avoids dependencies with the tty, which also uses
the system_unbound_wq, and issues flushes of said workqueue from inside
its poll handling.
Cc: stable@xxxxxxxxxxxxxxx
Reported-by: Rasmus Karlsson <rasmus.karlsson@xxxxxxxxxxx>
Tested-by: Rasmus Karlsson <rasmus.karlsson@xxxxxxxxxxx>
Tested-by: Iskren Chernev <me@xxxxxxxxxxx>
Link: https://github.com/axboe/liburing/issues/1113
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
io_uring/io_uring.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -152,6 +152,7 @@ static bool io_uring_try_cancel_requests
static void io_queue_sqe(struct io_kiocb *req);
struct kmem_cache *req_cachep;
+static struct workqueue_struct *iou_wq __ro_after_init;
static int __read_mostly sysctl_io_uring_disabled;
static int __read_mostly sysctl_io_uring_group = -1;
@@ -3139,7 +3140,7 @@ static __cold void io_ring_ctx_wait_and_
* noise and overhead, there's no discernable change in runtime
* over using system_wq.
*/
- queue_work(system_unbound_wq, &ctx->exit_work);
+ queue_work(iou_wq, &ctx->exit_work);
}
static int io_uring_release(struct inode *inode, struct file *file)
@@ -4164,6 +4165,8 @@ static int __init io_uring_init(void)
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT,
NULL);
+ iou_wq = alloc_workqueue("iou_exit", WQ_UNBOUND, 64);
+
#ifdef CONFIG_SYSCTL
register_sysctl_init("kernel", kernel_io_uring_disabled_table);
#endif
Patches currently in stable-queue which might be from axboe@xxxxxxxxx are
queue-6.8/io_uring-rw-don-t-allow-multishot-reads-without-nowait-support.patch
queue-6.8/io_uring-use-private-workqueue-for-exit-work.patch
queue-6.8/io_uring-kbuf-protect-io_buffer_list-teardown-with-a-reference.patch
queue-6.8/io_uring-kbuf-hold-io_buffer_list-reference-over-mmap.patch
queue-6.8/io_uring-kbuf-get-rid-of-lower-bgid-lists.patch
queue-6.8/io_uring-kbuf-get-rid-of-bl-is_ready.patch
