linux-kernel - Re: [BUG] Bw accounting warning on fair-servers' parameters change

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

Message-ID: <aHpf4LfMtB2V9uNb@jlelli-thinkpadt14gen4.remote.csb>
Date: Fri, 18 Jul 2025 16:53:20 +0200
From: Juri Lelli <juri.lelli@...hat.com>
To: Yuri Andriaccio <yurand2000@...il.com>
Cc: Ingo Molnar <mingo@...hat.com>, Peter Zijlstra <peterz@...radead.org>,
	Vincent Guittot <vincent.guittot@...aro.org>,
	Dietmar Eggemann <dietmar.eggemann@....com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Ben Segall <bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>,
	Valentin Schneider <vschneid@...hat.com>,
	linux-kernel@...r.kernel.org,
	Luca Abeni <luca.abeni@...tannapisa.it>,
	Yuri Andriaccio <yuri.andriaccio@...tannapisa.it>
Subject: Re: [BUG] Bw accounting warning on fair-servers' parameters change

On 18/07/25 16:22, Juri Lelli wrote:
> Hi,
> 
> Thanks for reporting.
> 
> On 18/07/25 13:38, Yuri Andriaccio wrote:
> > Hi,
> > 
> > I've been lately working on fair-servers and dl_servers for some patches and
> > I've come across a bandwidth accounting warning on the latest tip/master (as of
> > 2025-07-18, git sha ed0272f0675f). The warning is triggered by simply starting
> > the machine, mounting debugfs and then just zeroing any fair-server's runtime.
> > 
> > 
> > The warning:
> > 
> > WARNING: kernel/sched/deadline.c:266 at dl_rq_change_utilization+0x208/0x230
> > static inline void __sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq) {
> >     ...
> > 	WARN_ON_ONCE(dl_rq->running_bw > dl_rq->this_bw);
> > }
> > 
> > Steps to reproduce:
> > 
> > mount -t debugfs none /sys/kernel/debug
> > echo 0 > /sys/kernel/debug/sched/fair_server/cpu0/runtime
> > 
> > 
> > It does not happen at every machine boot, but happens on most. Could it possibly
> > be related to some of the deadline timers?
> 
> I took a quick first look and currently suspect cccb45d7c4295
> ("sched/deadline: Less agressive dl_server handling") could be playing a
> role in this as it delays actual server stop.
> 
> Could you please try to repro after having reverted such commit?

After that (w/o the revert), could you please try to see if the
following helps?

---
 kernel/sched/debug.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 3f06ab84d53f0..02e16b70a7901 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -376,10 +376,8 @@ static ssize_t sched_fair_server_write(struct file *filp, const char __user *ubu
 			return  -EINVAL;
 		}
 
-		if (rq->cfs.h_nr_queued) {
-			update_rq_clock(rq);
-			dl_server_stop(&rq->fair_server);
-		}
+		update_rq_clock(rq);
+		dl_server_stop(&rq->fair_server);
 
 		retval = dl_server_apply_params(&rq->fair_server, runtime, period, 0);
 		if (retval)