Re: [PATCH v4 7/9] sched/fair: allow changing cgroup of new forked task

[Chengming Zhou]

On 2022/8/8 20:57, Chengming Zhou wrote:
> commit 7dc603c9028e ("sched/fair: Fix PELT integrity for new tasks")
> introduce a TASK_NEW state and an unnessary limitation that would fail
> when changing cgroup of new forked task.
> 
> Because at that time, we can't handle task_change_group_fair() for new
> forked fair task which hasn't been woken up by wake_up_new_task(),
> which will cause detach on an unattached task sched_avg problem.
> 
> This patch delete this unnessary limitation by adding check before do
> detach or attach in task_change_group_fair().
> 
> So cpu_cgrp_subsys.can_attach() has nothing to do for fair tasks,
> only define it in #ifdef CONFIG_RT_GROUP_SCHED.
> 
> Signed-off-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
> ---
>  include/linux/sched.h |  5 ++---
>  kernel/sched/core.c   | 30 +++++++-----------------------
>  kernel/sched/fair.c   |  7 +++++++
>  3 files changed, 16 insertions(+), 26 deletions(-)
> 
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 88b8817b827d..b504e55bbf7a 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -95,10 +95,9 @@ struct task_group;
>  #define TASK_WAKEKILL			0x0100
>  #define TASK_WAKING			0x0200
>  #define TASK_NOLOAD			0x0400
> -#define TASK_NEW			0x0800
>  /* RT specific auxilliary flag to mark RT lock waiters */
> -#define TASK_RTLOCK_WAIT		0x1000
> -#define TASK_STATE_MAX			0x2000
> +#define TASK_RTLOCK_WAIT		0x0800
> +#define TASK_STATE_MAX			0x1000
>  
>  /* Convenience macros for the sake of set_current_state: */
>  #define TASK_KILLABLE			(TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index e74e79f783af..d5faa1700bd7 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -4500,11 +4500,11 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
>  {
>  	__sched_fork(clone_flags, p);
>  	/*
> -	 * We mark the process as NEW here. This guarantees that
> +	 * We mark the process as running here. This guarantees that
>  	 * nobody will actually run it, and a signal or other external
>  	 * event cannot wake it up and insert it on the runqueue either.
>  	 */
> -	p->__state = TASK_NEW;
> +	p->__state = TASK_RUNNING;
>  
>  	/*
>  	 * Make sure we do not leak PI boosting priority to the child.
> @@ -4622,7 +4622,6 @@ void wake_up_new_task(struct task_struct *p)
>  	struct rq *rq;
>  
>  	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
> -	WRITE_ONCE(p->__state, TASK_RUNNING);
>  #ifdef CONFIG_SMP
>  	/*
>  	 * Fork balancing, do it here and not earlier because:
> @@ -10238,36 +10237,19 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
>  	sched_unregister_group(tg);
>  }
>  
> +#ifdef CONFIG_RT_GROUP_SCHED
>  static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
>  {
>  	struct task_struct *task;
>  	struct cgroup_subsys_state *css;
> -	int ret = 0;
>  
>  	cgroup_taskset_for_each(task, css, tset) {
> -#ifdef CONFIG_RT_GROUP_SCHED
>  		if (!sched_rt_can_attach(css_tg(css), task))
>  			return -EINVAL;
> -#endif
> -		/*
> -		 * Serialize against wake_up_new_task() such that if it's
> -		 * running, we're sure to observe its full state.
> -		 */
> -		raw_spin_lock_irq(&task->pi_lock);
> -		/*
> -		 * Avoid calling sched_move_task() before wake_up_new_task()
> -		 * has happened. This would lead to problems with PELT, due to
> -		 * move wanting to detach+attach while we're not attached yet.
> -		 */
> -		if (READ_ONCE(task->__state) == TASK_NEW)
> -			ret = -EINVAL;
> -		raw_spin_unlock_irq(&task->pi_lock);
> -
> -		if (ret)
> -			break;
>  	}
> -	return ret;
> +	return 0;
>  }
> +#endif
>  
>  static void cpu_cgroup_attach(struct cgroup_taskset *tset)
>  {
> @@ -11103,7 +11085,9 @@ struct cgroup_subsys cpu_cgrp_subsys = {
>  	.css_released	= cpu_cgroup_css_released,
>  	.css_free	= cpu_cgroup_css_free,
>  	.css_extra_stat_show = cpu_extra_stat_show,
> +#ifdef CONFIG_RT_GROUP_SCHED
>  	.can_attach	= cpu_cgroup_can_attach,
> +#endif
>  	.attach		= cpu_cgroup_attach,
>  	.legacy_cftypes	= cpu_legacy_files,
>  	.dfl_cftypes	= cpu_files,
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 4bc76d95a99d..90aba33a3780 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -11669,6 +11669,13 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
>  #ifdef CONFIG_FAIR_GROUP_SCHED
>  static void task_change_group_fair(struct task_struct *p)
>  {
> +	/*
> +	 * We couldn't detach or attach a forked task which
> +	 * hasn't been woken up by wake_up_new_task().
> +	 */
> +	if (!p->on_rq && !se->sum_exec_runtime)

should be: if (!p->on_rq && !p->se.sum_exec_runtime)
sorry for my carelessness...


> +		return;
> +
>  	detach_task_cfs_rq(p);
>  
>  #ifdef CONFIG_SMP