Re: [RFC PATCH v2 12/17] sched: A quick and dirty cgroup tagging interface

From: Phil Auld
Date: Thu Apr 25 2019 - 10:27:01 EST


On Tue, Apr 23, 2019 at 04:18:17PM +0000 Vineeth Remanan Pillai wrote:
> From: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
>
> Marks all tasks in a cgroup as matching for core-scheduling.
>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
> ---
> 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
>

Since CPU0 never goes through the cpu add code it will never get initialized if
it's the only cpu and then enabling core scheduling and adding a task crashes.

Since there is no point in using core sched in this case maybe just disallow it
with something the below?


Cheers,
Phil

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e8e5f26db052..b312ea1e28a4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7541,6 +7541,9 @@ static int cpu_core_tag_write_u64(struct cgroup_subsys_state *css, struct cftype
if (val > 1)
return -ERANGE;

+ if (num_online_cpus() <= 1)
+ return -EINVAL;
+
if (tg->tagged == !!val)
return 0;




--