io_uring: use private workqueue for exit work

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@vger.kernel.org
Reported-by: Rasmus Karlsson <rasmus.karlsson@pajlada.com>
Tested-by: Rasmus Karlsson <rasmus.karlsson@pajlada.com>
Tested-by: Iskren Chernev <me@iskren.info>
Link: https://github.com/axboe/liburing/issues/1113
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 8baf8afb79c2a53d00e9103cc7b61ad8a3c9fa9b..d1defb99b89ee50bb1f4beab29946d2b892832e1 100644 (file)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -147,6 +147,7 @@ static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 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;
@@ -3166,7 +3167,7 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
         * 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)
@@ -4190,6 +4191,8 @@ static int __init io_uring_init(void)
        io_buf_cachep = KMEM_CACHE(io_buffer,
                                          SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
 
+       iou_wq = alloc_workqueue("iou_exit", WQ_UNBOUND, 64);
+
 #ifdef CONFIG_SYSCTL
        register_sysctl_init("kernel", kernel_io_uring_disabled_table);
 #endif