Re: [PATCH v4 2/8] socket: initial cgroup code.

[Kirill A. Shutemov]

On Mon, Oct 03, 2011 at 02:18:37PM +0400, Glauber Costa wrote:
> We aim to control the amount of kernel memory pinned at any
> time by tcp sockets. To lay the foundations for this work,
> this patch adds a pointer to the kmem_cgroup to the socket
> structure.
> 
> Signed-off-by: Glauber Costa <glommer@xxxxxxxxxxxxx>
> CC: David S. Miller <davem@xxxxxxxxxxxxx>
> CC: Hiroyouki Kamezawa <kamezawa.hiroyu@xxxxxxxxxxxxxx>
> CC: Eric W. Biederman <ebiederm@xxxxxxxxxxxx>
> ---
>  include/linux/memcontrol.h |   15 +++++++++++++++
>  include/net/sock.h         |    2 ++
>  mm/memcontrol.c            |   33 +++++++++++++++++++++++++++++++++
>  net/core/sock.c            |    3 +++
>  4 files changed, 53 insertions(+), 0 deletions(-)
> 
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 3b535db..2cb9226 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -395,5 +395,20 @@ mem_cgroup_print_bad_page(struct page *page)
>  }
>  #endif
>  
> +#ifdef CONFIG_INET
> +struct sock;
> +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> +void sock_update_memcg(struct sock *sk);
> +void sock_release_memcg(struct sock *sk);
> +
> +#else
> +static inline void sock_update_memcg(struct sock *sk)
> +{
> +}
> +static inline void sock_release_memcg(struct sock *sk)
> +{
> +}
> +#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
> +#endif /* CONFIG_INET */
>  #endif /* _LINUX_MEMCONTROL_H */
>  
> diff --git a/include/net/sock.h b/include/net/sock.h
> index 8e4062f..afe1467 100644
> --- a/include/net/sock.h
> +++ b/include/net/sock.h
> @@ -228,6 +228,7 @@ struct sock_common {
>    *	@sk_security: used by security modules
>    *	@sk_mark: generic packet mark
>    *	@sk_classid: this socket's cgroup classid
> +  *	@sk_cgrp: this socket's kernel memory (kmem) cgroup
>    *	@sk_write_pending: a write to stream socket waits to start
>    *	@sk_state_change: callback to indicate change in the state of the sock
>    *	@sk_data_ready: callback to indicate there is data to be processed
> @@ -339,6 +340,7 @@ struct sock {
>  #endif
>  	__u32			sk_mark;
>  	u32			sk_classid;
> +	struct mem_cgroup	*sk_cgrp;
>  	void			(*sk_state_change)(struct sock *sk);
>  	void			(*sk_data_ready)(struct sock *sk, int bytes);
>  	void			(*sk_write_space)(struct sock *sk);
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 8aaf4ce..08a520e 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -339,6 +339,39 @@ struct mem_cgroup {
>  	spinlock_t pcp_counter_lock;
>  };
>  
> +/* Writing them here to avoid exposing memcg's inner layout */
> +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> +#ifdef CONFIG_INET
> +#include <net/sock.h>
> +
> +void sock_update_memcg(struct sock *sk)
> +{
> +	/* right now a socket spends its whole life in the same cgroup */
> +	BUG_ON(sk->sk_cgrp);

Do we really want to panic in this case?

What about WARN() + return?

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

> +
> +	rcu_read_lock();
> +	sk->sk_cgrp = mem_cgroup_from_task(current);
> +
> +	/*
> +	 * We don't need to protect against anything task-related, because
> +	 * we are basically stuck with the sock pointer that won't change,
> +	 * even if the task that originated the socket changes cgroups.
> +	 *
> +	 * What we do have to guarantee, is that the chain leading us to
> +	 * the top level won't change under our noses. Incrementing the
> +	 * reference count via cgroup_exclude_rmdir guarantees that.
> +	 */
> +	cgroup_exclude_rmdir(mem_cgroup_css(sk->sk_cgrp));
> +	rcu_read_unlock();
> +}

-- 
 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/