linux-kernel - Re: [RFC PATCH 3/7] sched/fair: Handle unthrottle path for task based throttle

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: <c4f999f1-6086-4849-92ee-23a5efa2a9d2@amd.com>
Date: Fri, 14 Mar 2025 09:36:36 +0530
From: K Prateek Nayak <kprateek.nayak@....com>
To: Aaron Lu <ziqianlu@...edance.com>, Valentin Schneider
	<vschneid@...hat.com>, Ben Segall <bsegall@...gle.com>, Peter Zijlstra
	<peterz@...radead.org>, Josh Don <joshdon@...gle.com>, Ingo Molnar
	<mingo@...hat.com>, Vincent Guittot <vincent.guittot@...aro.org>
CC: <linux-kernel@...r.kernel.org>, Juri Lelli <juri.lelli@...hat.com>,
	Dietmar Eggemann <dietmar.eggemann@....com>, Steven Rostedt
	<rostedt@...dmis.org>, Mel Gorman <mgorman@...e.de>, Chengming Zhou
	<chengming.zhou@...ux.dev>, Chuyi Zhou <zhouchuyi@...edance.com>
Subject: Re: [RFC PATCH 3/7] sched/fair: Handle unthrottle path for task based
 throttle

On 3/14/2025 9:23 AM, K Prateek Nayak wrote:

[..snip..]

>>
>> +    /* Re-enqueue the tasks that have been throttled at this level. */
>> +    list_for_each_entry_safe(p, tmp, &cfs_rq->throttled_limbo_list,
>> throttle_node) {
>> +        list_del_init(&p->throttle_node);
>> +        /*
>> +         * FIXME: p may not be allowed to run on this rq anymore
>> +         * due to affinity change while p is throttled.
>> +         */
> 
> Using dequeue_task_fair() for throttle should ensure that the core now
> sees task_on_rq_queued() which should make it go throgh a full dequeue
> cycle which will remove the task from the "throttled_limbo_list" and
> the enqueue should put it back on the correct runqueue.
> 
> Is the above comment inaccurate with your changes or did I miss
> something?

Please ignore this, I just reached Patch 5. Sorry for the noise.

> 
>> +        enqueue_task_fair(rq_of(cfs_rq), p, ENQUEUE_WAKEUP);
>> +    }
>> +
>> +    /* Add cfs_rq with load or one or more already running entities to the list */
>> +    if (!cfs_rq_is_decayed(cfs_rq))
>> +        list_add_leaf_cfs_rq(cfs_rq);
>> +
>>       return 0;
>>   }
>>

-- 
Thanks and Regards,
Prateek