linux-kernel - [RFC PATCH v1 1/1] wq: Avoid using isolated cpus' timers on unbounded queue_delayed

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: <20240124082938.2527697-2-leobras@redhat.com>
Date: Wed, 24 Jan 2024 05:29:37 -0300
From: Leonardo Bras <leobras@...hat.com>
To: Tejun Heo <tj@...nel.org>,
	Lai Jiangshan <jiangshanlai@...il.com>,
	Marcelo Tosatti <mtosatti@...hat.com>
Cc: Leonardo Bras <leobras@...hat.com>,
	linux-kernel@...r.kernel.org
Subject: [RFC PATCH v1 1/1] wq: Avoid using isolated cpus' timers on unbounded queue_delayed_work

When __queue_delayed_work() is called with WORK_CPU_UNBOUND, it means any
cpu is able to run the work, as well as any cpu timer is able to be used.

This is not good if a system does use CPU isolation, because it can take
away some valuable cpu time to:
1 - deal with the timer interrupt,
2 - schedule-out the desired task,
3 - queue work on a random workqueue, and
4 - schedule the desired task back to the cpu.

So to fix this, during __queue_delayed_work(), if both:
- Work is not cpu-bounded,
- CPU isolation is in place,
then pick a random non-isolated cpu to use both the timer and the
system per-cpu workqueue.

Signed-off-by: Leonardo Bras <leobras@...hat.com>
---
 kernel/workqueue.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 76e60faed8923..0c50f41d9f95e 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1954,6 +1954,14 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq,
 		return;
 	}
 
+	/*
+	 * If the work is cpu-unbound, and cpu isolation is in place, only
+	 * schedule use timers from housekeeping cpus. In favor of avoiding
+	 * cacheline bouncing, run the WQ in the same cpu as the timer.
+	 */
+	if (cpu == WORK_CPU_UNBOUND && housekeeping_enabled(HK_TYPE_TIMER))
+		cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
+
 	dwork->wq = wq;
 	dwork->cpu = cpu;
 	timer->expires = jiffies + delay;
-- 
2.43.0