KAMEZAWA Hiroyuki wrote:
> On Fri, 28 Mar 2008 13:53:16 +0530
> Balbir Singh <balbir@linux.vnet.ibm.com> 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.
>>
> Hmm, I like this approach. 
> 

Thanks,

> -a bit off topic-
> BTW, could you move mem_cgroup_from_task() to include/linux/memcontrol.h ?
> 

Yes, that can be done

> Then, I'll add an interface like
> mem_cgroup_charge_xxx(struct page *page, struct mem_cgroup *mem, gfp_mask mask)
> 
> This can be called in following way:
> mem_cgroup_charge_xxx(page, mem_cgroup_from_task(current), GFP_XXX);
> and I don't have to access mm_struct's member in this case.
> 

OK. Will do. Can that wait until Andrew picks up these patches. Then I'll put
that as an add-on?

Thanks for the review

-- 
	Warm Regards,
	Balbir Singh
	Linux Technology Center
	IBM, ISTL