linux-kernel - [PATCH v3 1/1] io_uring/sqpoll: inherit cpumask of creating process

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-Id: <20240907100204.28609-1-felix.moessbauer@siemens.com>
Date: Sat,  7 Sep 2024 12:02:04 +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,
	stable@...r.kernel.org,
	Felix Moessbauer <felix.moessbauer@...mens.com>
Subject: [PATCH v3 1/1] io_uring/sqpoll: inherit cpumask of creating process

The submit queue polling threads are userland threads that just never
exit to the userland. In case the creating task is part of a cgroup
with the cpuset controller enabled, the poller should also stay within
that cpuset. This also holds, as the poller belongs to the same cgroup
as the task that started it.

With the current implementation, a process can "break out" of the
defined cpuset by creating sq pollers consuming CPU time on other CPUs,
which is especially problematic for realtime applications.

Part of this problem was fixed in a5fc1441 by dropping the
PF_NO_SETAFFINITY flag, but this only becomes effective after the first
modification of the cpuset (i.e. the pollers cpuset is correct after the
first update of the enclosing cgroups cpuset).

By inheriting the cpuset of the creating tasks, we ensure that the
poller is created with a cpumask that is a subset of the cgroups mask.
Inheriting the creators cpumask is reasonable, as other userland tasks
also inherit the mask.

Fixes: 37d1e2e3642e ("io_uring: move SQPOLL thread io-wq forked worker")
Cc: stable@...r.kernel.org # 6.1+
Signed-off-by: Felix Moessbauer <felix.moessbauer@...mens.com>
---
Changes since v2:

- in v2 I accidentally sent the backport of this patch for v6.1. Will
  resend that once this one is accepted. Anyways, now we know that this
  also works on a v6.1 kernel.

Changes since v1:

- do not set poller thread cpuset in non-pinning case, as the default is already
  correct (the mask is inherited from the parent).
- Remove incorrect term "kernel thread" from the commit message

I tested this without pinning, explicit pinning of the parent task and
non-all cgroup cpusets (and all combinations).

Best regards,
Felix Moessbauer
Siemens AG

 io_uring/sqpoll.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 3b50dc9586d1..713be7c29388 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -289,7 +289,6 @@ static int io_sq_thread(void *data)
 	if (sqd->sq_cpu != -1) {
 		set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu));
 	} else {
-		set_cpus_allowed_ptr(current, cpu_online_mask);
 		sqd->sq_cpu = raw_smp_processor_id();
 	}

-- 
2.39.2