linux-kernel - [PATCH 2/2] io_uring/io-wq: limit io poller cpuset to ambient one

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20240910143320.123234-3-felix.moessbauer@siemens.com>
Date: Tue, 10 Sep 2024 16:33:20 +0200
From: Felix Moessbauer <felix.moessbauer@...mens.com>
To: axboe@...nel.dk
Cc: asml.silence@...il.com,
	linux-kernel@...r.kernel.org,
	io-uring@...r.kernel.org,
	cgroups@...r.kernel.org,
	dqminh@...udflare.com,
	longman@...hat.com,
	adriaan.schmidt@...mens.com,
	florian.bezdeka@...mens.com,
	Felix Moessbauer <felix.moessbauer@...mens.com>
Subject: [PATCH 2/2] io_uring/io-wq: limit io poller cpuset to ambient one

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@...mens.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