Linux kernel -stable discussions
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@kernel.dk>
To: stable@vger.kernel.org
Subject: [PATCH 6.18.y 8/8] io_uring/io-wq: apply the current cpuset to new workers
Date: Sat, 21 Nov 2026 21:31:37 +0000	[thread overview]
Message-ID: <20261121213137.1789687-9-axboe@kernel.dk> (raw)
In-Reply-To: <20261121213137.1789687-1-axboe@kernel.dk>

From: Mikhail Malyshev <mike.malyshev@gmail.com>

Commit 0659e44ce739ecd856164c75a5325b7959a2921d upstream.

Since commit 84eacf177faa ("io_uring/io-wq: inherit cpuset of cgroup in
io worker"), io_wq_create() copies the cpuset of the creating task into
wq->cpu_mask, and io_init_new_worker() gives each new worker that copy.
A cpuset change, or a move of the task to another cgroup, updates the
workers that exist but not the copy, so workers started later run on
the CPUs the cgroup had when the io-wq was created, which may since
have been given to other tasks. Workers come and go for the life of the
io-wq, and a worker that cpuset moved is also retired at its next idle
timeout and replaced on the old CPUs.

Keep wq->cpu_mask for the affinity of the io-wq itself, all CPUs or the
mask set with IORING_REGISTER_IOWQ_AFF, and intersect it with the cpuset
of the worker when the worker starts, falling back to the cpuset if the
two do not intersect, as __set_cpus_allowed_ptr() does. Use the same
mask in the idle exit test, and go back to all CPUs when the registered
affinity is removed.

Fixes: 84eacf177faa ("io_uring/io-wq: inherit cpuset of cgroup in io worker")
Cc: stable@vger.kernel.org
Signed-off-by: Mikhail Malyshev <mike.malyshev@gmail.com>
Link: https://patch.msgid.link/20261111162705.1150983-1-mike.malyshev@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io-wq.c | 44 +++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 39 insertions(+), 5 deletions(-)

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index fd53297af26e..0d74e365d54a 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -731,6 +731,34 @@ static bool io_worker_retire(struct io_wq_acct *acct, struct io_worker *worker)
 	return false;
 }
 
+/*
+ * The CPUs a worker of @wq runs on: those of the io-wq affinity that the
+ * worker's cpuset allows, or the cpuset if they have none in common, as the
+ * scheduler does with a task's requested affinity when its cpuset changes.
+ * Read the cpuset each time: it can change while the io-wq exists.
+ */
+static void io_wq_worker_cpus(struct io_wq *wq, struct task_struct *tsk,
+			      struct cpumask *cpus)
+{
+	cpuset_cpus_allowed(tsk, cpus);
+	if (cpumask_intersects(cpus, wq->cpu_mask))
+		cpumask_and(cpus, cpus, wq->cpu_mask);
+}
+
+/* Is the current worker on a CPU that a new worker would not get? */
+static bool io_wq_worker_off_cpus(struct io_wq *wq)
+{
+	cpumask_var_t cpus;
+	bool off;
+
+	if (!alloc_cpumask_var(&cpus, GFP_KERNEL))
+		return false;
+	io_wq_worker_cpus(wq, current, cpus);
+	off = !cpumask_test_cpu(raw_smp_processor_id(), cpus);
+	free_cpumask_var(cpus);
+	return off;
+}
+
 static int io_wq_worker(void *data)
 {
 	struct io_worker *worker = data;
@@ -809,8 +837,7 @@ static int io_wq_worker(void *data)
 		}
 		if (!ret) {
 			last_timeout = true;
-			exit_mask = !cpumask_test_cpu(raw_smp_processor_id(),
-							wq->cpu_mask);
+			exit_mask = io_wq_worker_off_cpus(wq);
 		}
 	}
 
@@ -860,9 +887,16 @@ void io_wq_worker_sleeping(struct task_struct *tsk)
 static void io_init_new_worker(struct io_wq *wq, struct io_wq_acct *acct, struct io_worker *worker,
 			       struct task_struct *tsk)
 {
+	cpumask_var_t cpus;
+
 	tsk->worker_private = worker;
 	worker->task = tsk;
-	set_cpus_allowed_ptr(tsk, wq->cpu_mask);
+	/* Without a mask, the worker keeps its creator's CPUs. */
+	if (alloc_cpumask_var(&cpus, GFP_KERNEL)) {
+		io_wq_worker_cpus(wq, tsk, cpus);
+		set_cpus_allowed_ptr(tsk, cpus);
+		free_cpumask_var(cpus);
+	}
 
 	raw_spin_lock(&acct->workers_lock);
 	hlist_nulls_add_head_rcu(&worker->nulls_node, &acct->free_list);
@@ -1361,7 +1395,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 
 	if (!alloc_cpumask_var(&wq->cpu_mask, GFP_KERNEL))
 		goto err;
-	cpuset_cpus_allowed(data->task, wq->cpu_mask);
+	cpumask_copy(wq->cpu_mask, cpu_possible_mask);
 	wq->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
 	wq->acct[IO_WQ_ACCT_UNBOUND].max_workers =
 				task_rlimit(current, RLIMIT_NPROC);
@@ -1545,7 +1579,7 @@ int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask)
 		else
 			ret = -EINVAL;
 	} else {
-		cpumask_copy(tctx->io_wq->cpu_mask, allowed_mask);
+		cpumask_copy(tctx->io_wq->cpu_mask, cpu_possible_mask);
 	}
 	rcu_read_unlock();
 
-- 
2.55.0


      parent reply	other threads:[~2026-11-21 21:31 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-21 21:31 [PATCH 6.18.y 0/8] io_uring fixes for 6.18-stable Jens Axboe
2026-11-21 21:31 ` [PATCH 6.18.y 1/8] io_uring/napi: don't end the single NAPI busy poll early on need_resched() Jens Axboe
2026-11-21 21:31 ` [PATCH 6.18.y 2/8] io_uring: fail soft links on negative IOU_COMPLETE results Jens Axboe
2026-11-21 21:31 ` [PATCH 6.18.y 3/8] io_uring/futex: fail soft links when cancelling a wait Jens Axboe
2026-11-21 21:31 ` [PATCH 6.18.y 4/8] io_uring/rw: fail soft links on IOPOLL short or error IO Jens Axboe
2026-11-21 21:31 ` [PATCH 6.18.y 5/8] io_uring/timeout: don't rearm a multishot timeout on cancel Jens Axboe
2026-11-21 21:31 ` [PATCH 6.18.y 6/8] io_uring/rsrc: keep the old file when a file update fails Jens Axboe
2026-11-21 21:31 ` [PATCH 6.18.y 7/8] io_uring/kbuf: initialize arg->out_len from arg->max_len in io_buffers_select() Jens Axboe
2026-11-21 21:31 ` Jens Axboe [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20261121213137.1789687-9-axboe@kernel.dk \
    --to=axboe@kernel.dk \
    --cc=stable@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox