linux-kernel - Re: [PATCH v2] sched/psi: Fix avgs_work re-arm in psi_avgs

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: <f7e4fe56-73b3-88e6-d6a6-6adab34f12db@bytedance.com>
Date:   Sat, 15 Oct 2022 17:43:12 +0800
From:   Chengming Zhou <zhouchengming@...edance.com>
To:     peterz@...radead.org, Suren Baghdasaryan <surenb@...gle.com>,
        Johannes Weiner <hannes@...xchg.org>
Cc:     quic_pkondeti@...cinc.com, quic_charante@...cinc.com,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2] sched/psi: Fix avgs_work re-arm in psi_avgs_work()

On 2022/10/15 00:41, Suren Baghdasaryan wrote:
> On Fri, Oct 14, 2022 at 7:18 AM Johannes Weiner <hannes@...xchg.org> wrote:
>>
>> On Fri, Oct 14, 2022 at 07:05:51PM +0800, Chengming Zhou wrote:
>>> Pavan reported a problem that PSI avgs_work idle shutoff is not
>>> working at all. Because PSI_NONIDLE condition would be observed in
>>> psi_avgs_work()->collect_percpu_times()->get_recent_times() even if
>>> only the kworker running avgs_work on the CPU.
>>>
>>> Although commit 1b69ac6b40eb ("psi: fix aggregation idle shut-off")
>>> avoided the ping-pong wake problem when the worker sleep, psi_avgs_work()
>>> still will always re-arm the avgs_work, so shutoff is not working.
>>>
>>> This patch changes to use PSI_STATE_RESCHEDULE to flag whether to
>>> re-arm avgs_work in get_recent_times(). For the current CPU, we re-arm
>>> avgs_work only when (NR_RUNNING > 1 || NR_IOWAIT > 0 || NR_MEMSTALL > 0),
>>> for other CPUs we can just check PSI_NONIDLE delta. The new flag
>>> is only used in psi_avgs_work(), so we check in get_recent_times()
>>> that current_work() is avgs_work.
>>>
>>> One potential problem is that the brief period of non-idle time
>>> incurred between the aggregation run and the kworker's dequeue will
>>> be stranded in the per-cpu buckets until avgs_work run next time.
>>> The buckets can hold 4s worth of time, and future activity will wake
>>> the avgs_work with a 2s delay, giving us 2s worth of data we can leave
>>> behind when shut off the avgs_work. If the kworker run other works after
>>> avgs_work shut off and doesn't have any scheduler activities for 2s,
>>> this maybe a problem.
>>>
>>> Reported-by: Pavan Kondeti <quic_pkondeti@...cinc.com>
>>> Signed-off-by: Chengming Zhou <zhouchengming@...edance.com>
>>
>> Acked-by: Johannes Weiner <hannes@...xchg.org>
> 
> Please make sure to test the final version. With that done,
> 
> Acked-by: Suren Baghdasaryan <surenb@...gle.com>

Thanks! Yes, I did test with this version on VM yesterday, so add:

Tested-by: Chengming Zhou <zhouchengming@...edance.com>