Skip to contentSkip to conversation

6.18-stable inclusion request

PATCH Jens Axboe 2 participants 3 messages Feb 11 – Feb 12

Subsystems (2)
Stable branch io_uring
lore
Share & tools
lore

Jens Axboe

author maintainer
#0 lore raw

Hi Greg/stable,

Can you add these two patches to the 6.18-stable queue? You can also just cherry pick these in order:

38aa434ab9335ce2d178b7538cdf01d60b2014c3
91214661489467f8452d34edbf257488d85176e4

It's in the nice-to-have category just to be consistent with the older/current stable release.

Thanks!

Signature · 1 line
Jens Axboe

From efa9f164e9345e613b50c203eb763922a3d130d0 Mon Sep 17 00:00:00 2001
From: Li Chen <[email protected]>
Date: Mon, 2 Feb 2026 22:37:53 +0800
Subject: [PATCH 1/2] io_uring/io-wq: add exit-on-idle state

Commit 38aa434ab9335ce2d178b7538cdf01d60b2014c3 upstream.

io-wq uses an idle timeout to shrink the pool, but keeps the last worker around indefinitely to avoid churn.

For tasks that used io_uring for file I/O and then stop using io_uring, this can leave an iou-wrk-* thread behind even after all io_uring instances are gone. This is unnecessary overhead and also gets in the way of process checkpoint/restore.

Add an exit-on-idle state that makes all io-wq workers exit as soon as they become idle, and provide io_wq_set_exit_on_idle() to toggle it.

Signed-off-by Li Chen <[email protected]>
Signed-off-by Jens Axboe <[email protected]>
---
 io_uring/io-wq.c | 27 +++++++++++++++++++++++++--
 io_uring/io-wq.h |  1 +
 2 files changed, 26 insertions(+), 2 deletions(-)
io_uring/io-wq.c +25 -2
index 56b6a8257959..49a9c914b4e9 100644
@@ -34,6 +34,7 @@ enum {
 
 enum {
 	IO_WQ_BIT_EXIT		= 0,	/* wq exiting */
+	IO_WQ_BIT_EXIT_ON_IDLE	= 1,	/* allow all workers to exit on idle */
 };
 
 enum {

@@ -706,9 +707,13 @@ static int io_wq_worker(void *data)
 		raw_spin_lock(&acct->workers_lock);
 		/*
 		 * Last sleep timed out. Exit if we're not the last worker,
-		 * or if someone modified our affinity.
+		 * or if someone modified our affinity. If wq is marked
+		 * idle-exit, drop the worker as well. This is used to avoid
+		 * keeping io-wq workers around for tasks that no longer have
+		 * any active io_uring instances.
 		 */
-		if (last_timeout && (exit_mask || acct->nr_workers > 1)) {
+		if ((last_timeout && (exit_mask || acct->nr_workers > 1)) ||
+		    test_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state)) {
 			acct->nr_workers--;
 			raw_spin_unlock(&acct->workers_lock);
 			__set_current_state(TASK_RUNNING);

@@ -965,6 +970,24 @@ static bool io_wq_worker_wake(struct io_worker *worker, void *data)
 	return false;
 }
 
+void io_wq_set_exit_on_idle(struct io_wq *wq, bool enable)
+{
+	if (!wq->task)
+		return;
+
+	if (!enable) {
+		clear_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state);
+		return;
+	}
+
+	if (test_and_set_bit(IO_WQ_BIT_EXIT_ON_IDLE, &wq->state))
+		return;
+
+	rcu_read_lock();
+	io_wq_for_each_worker(wq, io_wq_worker_wake, NULL);
+	rcu_read_unlock();
+}
+
 static void io_run_cancel(struct io_wq_work *work, struct io_wq *wq)
 {
 	do {
io_uring/io-wq.h +1 -0
index 774abab54732..94b14742b703 100644
@@ -41,6 +41,7 @@ struct io_wq_data {
 struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data);
 void io_wq_exit_start(struct io_wq *wq);
 void io_wq_put_and_exit(struct io_wq *wq);
+void io_wq_set_exit_on_idle(struct io_wq *wq, bool enable);
 
 void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work);
 void io_wq_hash_work(struct io_wq_work *work, void *val);
Signature · 1 line
2.51.0

From 6809ad872df9f746f737ab762ee72f1d9a692c1d Mon Sep 17 00:00:00 2001
From: Li Chen <[email protected]>
Date: Mon, 2 Feb 2026 22:37:54 +0800
Subject: [PATCH 2/2] io_uring: allow io-wq workers to exit when unused

Commit 91214661489467f8452d34edbf257488d85176e4 upstream.

io_uring keeps a per-task io-wq around, even when the task no longer has any io_uring instances.

If the task previously used io_uring for file I/O, this can leave an unrelated iou-wrk-* worker thread behind after the last io_uring instance is gone.

When the last io_uring ctx is removed from the task context, mark the io-wq exit-on-idle so workers can go away. Clear the flag on subsequent io_uring usage.

Signed-off-by Li Chen <[email protected]>
Signed-off-by Jens Axboe <[email protected]>
---
 io_uring/tctx.c | 11 +++++++++++
 1 file changed, 11 insertions(+)
io_uring/tctx.c +11 -0
index 5b66755579c0..03c278aa5812 100644
@@ -122,6 +122,14 @@ int __io_uring_add_tctx_node(struct io_ring_ctx *ctx)
 				return ret;
 		}
 	}
+
+	/*
+	 * Re-activate io-wq keepalive on any new io_uring usage. The wq may have
+	 * been marked for idle-exit when the task temporarily had no active
+	 * io_uring instances.
+	 */
+	if (tctx->io_wq)
+		io_wq_set_exit_on_idle(tctx->io_wq, false);
 	if (!xa_load(&tctx->xa, (unsigned long)ctx)) {
 		node = kmalloc(sizeof(*node), GFP_KERNEL);
 		if (!node)

@@ -183,6 +191,9 @@ __cold void io_uring_del_tctx_node(unsigned long index)
 	if (tctx->last == node->ctx)
 		tctx->last = NULL;
 	kfree(node);
+
+	if (xa_empty(&tctx->xa) && tctx->io_wq)
+		io_wq_set_exit_on_idle(tctx->io_wq, true);
 }
 
 __cold void io_uring_clean_tctx(struct io_uring_task *tctx)
Signature · 1 line
2.51.0
author maintainer
#1 lore raw
Quoted 10 lines · Jens Axboe

Hi Greg/stable,

Can you add these two patches to the 6.18-stable queue? You can also just cherry pick these in order:

38aa434ab9335ce2d178b7538cdf01d60b2014c3
91214661489467f8452d34edbf257488d85176e4

It's in the nice-to-have category just to be consistent with the older/current stable release.

Oh and since 6.19 is out as well, 6.19-stable queue as well, please.

Signature · 1 line
Jens Axboe
maintainer
#2 lore raw
Quoted 6 lines · Jens Axboe
Quoted 5 lines · Jens Axboe

Hi Greg/stable,

Can you add these two patches to the 6.18-stable queue? You can also just cherry pick these in order:

Quoted 7 lines
Quoted 5 lines

38aa434ab9335ce2d178b7538cdf01d60b2014c3
91214661489467f8452d34edbf257488d85176e4

It's in the nice-to-have category just to be consistent with the older/current stable release.

Oh and since 6.19 is out as well, 6.19-stable queue as well, please.

Now done, thanks!

greg k-h