The io work queue polling threads are userland threads that just never
exit to the userland. By that, they are also assigned to a cgroup (the
group of the creating task).

When creating a new io poller, this poller should inherit the cpu limits
of the cgroup, as it belongs to the cgroup of the creating task.

Fixes: da64d6db3bd3 ("io_uring: One wqe per wq")
Signed-off-by: Felix Moessbauer <felix.moessbauer@siemens.com>
---
 io_uring/io-wq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index c7055a8895d7..a38f36b68060 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -1168,7 +1168,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 
 	if (!alloc_cpumask_var(&wq->cpu_mask, GFP_KERNEL))
 		goto err;
-	cpumask_copy(wq->cpu_mask, cpu_possible_mask);
+	cpuset_cpus_allowed(data->task, wq->cpu_mask);
 	wq->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
 	wq->acct[IO_WQ_ACCT_UNBOUND].max_workers =
 				task_rlimit(current, RLIMIT_NPROC);
-- 
2.39.2

On 9/10/24 8:33 AM, Felix Moessbauer wrote:
> The io work queue polling threads are userland threads that just never
> exit to the userland. By that, they are also assigned to a cgroup (the
> group of the creating task).
> 
> When creating a new io poller, this poller should inherit the cpu limits
> of the cgroup, as it belongs to the cgroup of the creating task.

Same comment on polling threads and the use of ambient.

-- 
Jens Axboe