linux-kernel - Re: [PATCH v10 2/5] sched: CGroup tagging interface for core scheduling

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]

Date:   Fri, 5 Feb 2021 12:41:58 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     "Joel Fernandes (Google)" <joel@...lfernandes.org>
Cc:     Nishanth Aravamudan <naravamudan@...italocean.com>,
        Julien Desfossez <jdesfossez@...italocean.com>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Vineeth Pillai <viremana@...ux.microsoft.com>,
        Aaron Lu <aaron.lwe@...il.com>,
        Aubrey Li <aubrey.intel@...il.com>, tglx@...utronix.de,
        linux-kernel@...r.kernel.org, mingo@...nel.org,
        torvalds@...ux-foundation.org, fweisbec@...il.com,
        keescook@...omium.org, kerrnel@...gle.com,
        Phil Auld <pauld@...hat.com>,
        Valentin Schneider <valentin.schneider@....com>,
        Mel Gorman <mgorman@...hsingularity.net>,
        Pawan Gupta <pawan.kumar.gupta@...ux.intel.com>,
        Paolo Bonzini <pbonzini@...hat.com>, vineeth@...byteword.org,
        Chen Yu <yu.c.chen@...el.com>,
        Christian Brauner <christian.brauner@...ntu.com>,
        Agata Gruza <agata.gruza@...el.com>,
        Antonio Gomez Iglesias <antonio.gomez.iglesias@...el.com>,
        graf@...zon.com, konrad.wilk@...cle.com, dfaggioli@...e.com,
        pjt@...gle.com, rostedt@...dmis.org, derkling@...gle.com,
        benbjiang@...cent.com,
        Alexandre Chartre <alexandre.chartre@...cle.com>,
        James.Bottomley@...senpartnership.com, OWeisse@...ch.edu,
        Dhaval Giani <dhaval.giani@...cle.com>,
        Junaid Shahid <junaids@...gle.com>, jsbarnes@...gle.com,
        chris.hyser@...cle.com, Ben Segall <bsegall@...gle.com>,
        Josh Don <joshdon@...gle.com>, Hao Luo <haoluo@...gle.com>,
        Tom Lendacky <thomas.lendacky@....com>
Subject: Re: [PATCH v10 2/5] sched: CGroup tagging interface for core
 scheduling

On Fri, Jan 22, 2021 at 08:17:01PM -0500, Joel Fernandes (Google) wrote:
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -736,6 +736,7 @@ void __put_task_struct(struct task_struct *tsk)
>  	exit_creds(tsk);
>  	delayacct_tsk_free(tsk);
>  	put_signal_struct(tsk->signal);
> +	sched_tsk_free(tsk);
>  
>  	if (!profile_handoff_task(tsk))
>  		free_task(tsk);

> +struct sched_core_task_cookie {
> +	refcount_t refcnt;
> +	struct work_struct work; /* to free in WQ context. */;
> +};

> +static void sched_core_put_cookie_work(struct work_struct *ws);
> +
> +/* Caller has to call sched_core_get() if non-zero value is returned. */
> +static unsigned long sched_core_alloc_task_cookie(void)
> +{
> +	struct sched_core_task_cookie *ck =
> +		kmalloc(sizeof(struct sched_core_task_cookie), GFP_KERNEL);
> +
> +	if (!ck)
> +		return 0;
> +	refcount_set(&ck->refcnt, 1);
> +	INIT_WORK(&ck->work, sched_core_put_cookie_work);
> +
> +	return (unsigned long)ck;
> +}

> +static void sched_core_put_task_cookie(unsigned long cookie)
> +{
> +	struct sched_core_task_cookie *ptr =
> +		(struct sched_core_task_cookie *)cookie;
> +
> +	if (refcount_dec_and_test(&ptr->refcnt))
> +		kfree(ptr);
> +}

> +static void sched_core_put_cookie_work(struct work_struct *ws)
> +{
> +	struct sched_core_task_cookie *ck =
> +		container_of(ws, struct sched_core_task_cookie, work);
> +
> +	sched_core_put_task_cookie((unsigned long)ck);
> +	sched_core_put();
> +}

> +void sched_tsk_free(struct task_struct *tsk)
> +{
> +	struct sched_core_task_cookie *ck;
> +
> +	sched_core_put_cookie((struct sched_core_cookie *)tsk->core_cookie);
> +
> +	if (!tsk->core_task_cookie)
> +		return;
> +
> +	ck = (struct sched_core_task_cookie *)tsk->core_task_cookie;
> +	queue_work(system_wq, &ck->work);
> +}

*groan*.. so the purpose of that work is to be able to disable
core-scheduling after the last such task dies.

Maybe add sched_core_put_async() instead?