Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Fri, 10 May 2019 11:12:25 -0400
From:   Julien Desfossez <jdesfossez@digitalocean.com>
To:     Vineeth Remanan Pillai <vpillai@digitalocean.com>
Cc:     Nishanth Aravamudan <naravamudan@digitalocean.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Tim Chen <tim.c.chen@linux.intel.com>, mingo@kernel.org,
        tglx@linutronix.de, pjt@google.com, torvalds@linux-foundation.org,
        linux-kernel@vger.kernel.org, subhra.mazumdar@oracle.com,
        fweisbec@gmail.com, keescook@chromium.org, kerrnel@google.com,
        Phil Auld <pauld@redhat.com>, Aaron Lu <aaron.lwe@gmail.com>,
        Aubrey Li <aubrey.intel@gmail.com>,
        Valentin Schneider <valentin.schneider@arm.com>,
        Mel Gorman <mgorman@techsingularity.net>,
        Pawan Gupta <pawan.kumar.gupta@linux.intel.com>,
        Paolo Bonzini <pbonzini@redhat.com>
Subject: Re: [RFC PATCH v2 12/17] sched: A quick and dirty cgroup tagging
 interface
Message-ID: <20190510151225.GA13930@sinkpad>
References: <cover.1556025155.git.vpillai@digitalocean.com>
 <b058b74f303fe40e5822925c90a5b0161c4a0a2d.1556025155.git.vpillai@digitalocean.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <b058b74f303fe40e5822925c90a5b0161c4a0a2d.1556025155.git.vpillai@digitalocean.com>
User-Agent: Mutt/1.5.24 (2015-08-30)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 23-Apr-2019 04:18:17 PM, Vineeth Remanan Pillai wrote:
> From: Peter Zijlstra (Intel) <peterz@infradead.org>
> 
> Marks all tasks in a cgroup as matching for core-scheduling.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
>  kernel/sched/core.c  | 62 ++++++++++++++++++++++++++++++++++++++++++++
>  kernel/sched/sched.h |  4 +++
>  2 files changed, 66 insertions(+)
> 
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 5066a1493acf..e5bdc1c4d8d7 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -6658,6 +6658,15 @@ static void sched_change_group(struct task_struct *tsk, int type)
>  	tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
>  			  struct task_group, css);
>  	tg = autogroup_task_group(tsk, tg);
> +
> +#ifdef CONFIG_SCHED_CORE
> +	if ((unsigned long)tsk->sched_task_group == tsk->core_cookie)
> +		tsk->core_cookie = 0UL;
> +
> +	if (tg->tagged /* && !tsk->core_cookie ? */)
> +		tsk->core_cookie = (unsigned long)tg;
> +#endif
> +
>  	tsk->sched_task_group = tg;
>  
>  #ifdef CONFIG_FAIR_GROUP_SCHED
> @@ -7117,6 +7126,43 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
>  }
>  #endif /* CONFIG_RT_GROUP_SCHED */
>  
> +#ifdef CONFIG_SCHED_CORE
> +static u64 cpu_core_tag_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
> +{
> +	struct task_group *tg = css_tg(css);
> +
> +	return !!tg->tagged;
> +}
> +
> +static int cpu_core_tag_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, u64 val)
> +{
> +	struct task_group *tg = css_tg(css);
> +	struct css_task_iter it;
> +	struct task_struct *p;
> +
> +	if (val > 1)
> +		return -ERANGE;
> +
> +	if (tg->tagged == !!val)
> +		return 0;
> +
> +	tg->tagged = !!val;
> +
> +	if (!!val)
> +		sched_core_get();
> +
> +	css_task_iter_start(css, 0, &it);
> +	while ((p = css_task_iter_next(&it)))
> +		p->core_cookie = !!val ? (unsigned long)tg : 0UL;
> +	css_task_iter_end(&it);
> +
> +	if (!val)
> +		sched_core_put();
> +
> +	return 0;
> +}
> +#endif
> +
>  static struct cftype cpu_legacy_files[] = {
>  #ifdef CONFIG_FAIR_GROUP_SCHED
>  	{
> @@ -7152,6 +7198,14 @@ static struct cftype cpu_legacy_files[] = {
>  		.read_u64 = cpu_rt_period_read_uint,
>  		.write_u64 = cpu_rt_period_write_uint,
>  	},
> +#endif
> +#ifdef CONFIG_SCHED_CORE
> +	{
> +		.name = "tag",
> +		.flags = CFTYPE_NOT_ON_ROOT,
> +		.read_u64 = cpu_core_tag_read_u64,
> +		.write_u64 = cpu_core_tag_write_u64,
> +	},
>  #endif
>  	{ }	/* Terminate */
>  };
> @@ -7319,6 +7373,14 @@ static struct cftype cpu_files[] = {
>  		.seq_show = cpu_max_show,
>  		.write = cpu_max_write,
>  	},
> +#endif
> +#ifdef CONFIG_SCHED_CORE
> +	{
> +		.name = "tag",
> +		.flags = CFTYPE_NOT_ON_ROOT,
> +		.read_u64 = cpu_core_tag_read_u64,
> +		.write_u64 = cpu_core_tag_write_u64,
> +	},
>  #endif
>  	{ }	/* terminate */
>  };
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 42dd620797d7..16fb236eab7b 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -363,6 +363,10 @@ struct cfs_bandwidth {
>  struct task_group {
>  	struct cgroup_subsys_state css;
>  
> +#ifdef CONFIG_SCHED_CORE
> +	int			tagged;
> +#endif
> +
>  #ifdef CONFIG_FAIR_GROUP_SCHED
>  	/* schedulable entities of this group on each CPU */
>  	struct sched_entity	**se;
> -- 
> 2.17.1

Even though this may not be the definitive interface, a quick fix to
remove the tag if it was set and the cgroup is getting removed.

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 6dc072c..be981e3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7190,6 +7190,18 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
        return 0;
 }

+static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
+{
+#ifdef CONFIG_SCHED_CORE
+       struct task_group *tg = css_tg(css);
+
+       if (tg->tagged) {
+               sched_core_put();
+               tg->tagged = 0;
+       }
+#endif
+}
+
 static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
 {
        struct task_group *tg = css_tg(css);
@@ -7832,6 +7844,7 @@ static struct cftype cpu_files[] = {
 struct cgroup_subsys cpu_cgrp_subsys = {
        .css_alloc      = cpu_cgroup_css_alloc,
        .css_online     = cpu_cgroup_css_online,
+       .css_offline    = cpu_cgroup_css_offline,
        .css_released   = cpu_cgroup_css_released,
        .css_free       = cpu_cgroup_css_free,
        .css_extra_stat_show = cpu_extra_stat_show,