Re: [PATCH 04/10] cgroups: New cancel_attach_task subsystem callback

[Kirill A. Shutemov]

On Mon, Oct 03, 2011 at 09:07:06PM +0200, Frederic Weisbecker wrote:
> To cancel a process attachment on a subsystem, we only call the
> cancel_attach() callback once on the leader but we have no
> way to cancel the attachment individually for each member of
> the process group.
> 
> This is going to be needed for the max number of tasks susbystem
> that is coming.
> 
> To prepare for this integration, call a new cancel_attach_task()
> callback on each task of the group until we reach the member that
> failed to attach.
> 
> Signed-off-by: Frederic Weisbecker <fweisbec@xxxxxxxxx>
> Acked-by: Paul Menage <paul@xxxxxxxxxxxxxx>

Acked-by: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>

> Cc: Li Zefan <lizf@xxxxxxxxxxxxxx>
> Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
> Cc: Aditya Kali <adityakali@xxxxxxxxxx>
> Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
> Cc: Kay Sievers <kay.sievers@xxxxxxxx>
> Cc: Tim Hockin <thockin@xxxxxxxxxx>
> Cc: Tejun Heo <tj@xxxxxxxxxx>
> Cc: Kirill A. Shutemov <kirill@xxxxxxxxxxxxx>
> Cc: Containers <containers@xxxxxxxxxxxxxxxxxxxxxxxxxx>
> ---
>  Documentation/cgroups/cgroups.txt |    7 +++++++
>  include/linux/cgroup.h            |    2 ++
>  kernel/cgroup.c                   |   24 ++++++++++++++++++++----
>  3 files changed, 29 insertions(+), 4 deletions(-)
> 
> diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
> index 0621e93..3bc1dc9 100644
> --- a/Documentation/cgroups/cgroups.txt
> +++ b/Documentation/cgroups/cgroups.txt
> @@ -623,6 +623,13 @@ function, so that the subsystem can implement a rollback. If not, not necessary.
>  This will be called only about subsystems whose can_attach() operation have
>  succeeded.
>  
> +void cancel_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
> +(cgroup_mutex held by caller)
> +
> +As cancel_attach, but for operations that must be cancelled once per
> +task that wanted to be attached. This typically revert the effect of
> +can_attach_task().
> +
>  void pre_attach(struct cgroup *cgrp);
>  (cgroup_mutex held by caller)
>  
> diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
> index ed34eb8..b62cf5e 100644
> --- a/include/linux/cgroup.h
> +++ b/include/linux/cgroup.h
> @@ -472,6 +472,8 @@ struct cgroup_subsys {
>  			       struct task_struct *tsk);
>  	void (*cancel_attach)(struct cgroup_subsys *ss, struct cgroup *cgrp,
>  			      struct task_struct *tsk);
> +	void (*cancel_attach_task)(struct cgroup *cgrp,
> +				   struct task_struct *tsk);
>  	void (*pre_attach)(struct cgroup *cgrp);
>  	void (*attach_task)(struct cgroup *cgrp, struct cgroup *old_cgrp,
>  			    struct task_struct *tsk);
> diff --git a/kernel/cgroup.c b/kernel/cgroup.c
> index fafebdb..709baef 100644
> --- a/kernel/cgroup.c
> +++ b/kernel/cgroup.c
> @@ -1883,6 +1883,9 @@ out:
>  				 * remaining subsystems.
>  				 */
>  				break;
> +
> +			if (ss->cancel_attach_task)
> +				ss->cancel_attach_task(cgrp, tsk);
>  			if (ss->cancel_attach)
>  				ss->cancel_attach(ss, cgrp, tsk);
>  		}
> @@ -1992,7 +1995,7 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
>  {
>  	int retval, i, group_size;
>  	struct cgroup_subsys *ss, *failed_ss = NULL;
> -	bool cancel_failed_ss = false;
> +	struct task_struct *failed_task = NULL;
>  	/* guaranteed to be initialized later, but the compiler needs this */
>  	struct cgroup *oldcgrp = NULL;
>  	struct css_set *oldcg;
> @@ -2081,7 +2084,7 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
>  							     oldcgrp, tsk);
>  				if (retval) {
>  					failed_ss = ss;
> -					cancel_failed_ss = true;
> +					failed_task = tsk;
>  					goto out_cancel_attach;
>  				}
>  			}
> @@ -2146,8 +2149,11 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader)
>  				if (ss->attach_task)
>  					ss->attach_task(cgrp, oldcgrp, tsk);
>  			}
> +		} else if (retval == -ESRCH) {
> +			if (ss->cancel_attach_task)
> +				ss->cancel_attach_task(cgrp, tsk);
>  		} else {
> -			BUG_ON(retval != -ESRCH);
> +			BUG_ON(1);
>  		}
>  	}
>  	/* nothing is sensitive to fork() after this point. */
> @@ -2179,8 +2185,18 @@ out_cancel_attach:
>  	/* same deal as in cgroup_attach_task */
>  	if (retval) {
>  		for_each_subsys(root, ss) {
> +			if (ss->cancel_attach_task && (ss != failed_ss ||
> +						       failed_task)) {
> +				for (i = 0; i < group_size; i++) {
> +					tsk = flex_array_get_ptr(group, i);
> +					if (tsk == failed_task)
> +						break;
> +					ss->cancel_attach_task(cgrp, tsk);
> +				}
> +			}
> +
>  			if (ss == failed_ss) {
> -				if (cancel_failed_ss && ss->cancel_attach)
> +				if (failed_task && ss->cancel_attach)
>  					ss->cancel_attach(ss, cgrp, leader);
>  				break;
>  			}
> -- 
> 1.7.5.4
> 

-- 
 Kirill A. Shutemov
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/