On 03/28/2008 09:23 AM, Balbir Singh wrote:
> This patch removes the mem_cgroup member from mm_struct and instead adds
> an owner. This approach was suggested by Paul Menage. The advantage of
> this approach is that, once the mm->owner is known, using the subsystem
> id, the cgroup can be determined. It also allows several control groups
> that are virtually grouped by mm_struct, to exist independent of the memory
> controller i.e., without adding mem_cgroup's for each controller,
> to mm_struct.
> 
> The code initially assigns mm->owner to the task and then after the
> thread group leader is identified. The mm->owner is changed to the thread
> group leader of the task later at the end of copy_process.
> 
> A new config option CONFIG_MM_OWNER is added and the memory resource
> controller now depends on this config option.
> 
> NOTE: This patch was developed on top of 2.6.25-rc5-mm1 and is applied on top
> of the memory-controller-move-to-own-slab patch (which is already present
> in the Andrew's patchset).
> 
> These patches have been tested on a powerpc 64 bit box and on x86_64 box with
> several microbenchmarks and some simple memory controller testing.
> 
> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
> ---
> 
>  include/linux/memcontrol.h |   14 ++++++++-
>  include/linux/mm_types.h   |    6 ++--
>  include/linux/sched.h      |   19 ++++++++++++
>  init/Kconfig               |   13 ++++++++
>  kernel/exit.c              |   66 +++++++++++++++++++++++++++++++++++++++++++++
>  kernel/fork.c              |   26 +++++++++++++++++
>  mm/memcontrol.c            |   19 +++++++-----
>  7 files changed, 151 insertions(+), 12 deletions(-)
> 
> diff -puN include/linux/mm_types.h~memory-controller-add-mm-owner include/linux/mm_types.h
> --- linux-2.6.25-rc5/include/linux/mm_types.h~memory-controller-add-mm-owner	2008-03-28 09:30:47.000000000 +0530
> +++ linux-2.6.25-rc5-balbir/include/linux/mm_types.h	2008-03-28 12:26:59.000000000 +0530
> @@ -227,8 +227,10 @@ struct mm_struct {
>  	/* aio bits */
>  	rwlock_t		ioctx_list_lock;
>  	struct kioctx		*ioctx_list;
> -#ifdef CONFIG_CGROUP_MEM_RES_CTLR
> -	struct mem_cgroup *mem_cgroup;
> +#ifdef CONFIG_MM_OWNER
> +	spinlock_t owner_lock;
> +	struct task_struct *owner;	/* The thread group leader that */

Doesn't make sense to switch them (spinlock is unsigned int on x86, what's 
sizeof between and after?)?