Re: [PATCH next-20130703] net: sock: Add ifdef CONFIG_MEMCG_KMEM for mem_cgroup_sockets_{init,destroy}
From: Sedat Dilek
Date: Wed Jul 03 2013 - 12:42:49 EST
On Wed, Jul 3, 2013 at 6:34 PM, Michal Hocko <mhocko@xxxxxxx> wrote:
>
On Wed 03-07-13 18:11:28, Sedat Dilek wrote:
>
> On Wed, Jul 3, 2013 at 5:59 PM, Michal Hocko <mhocko@xxxxxxx> wrote:
>
> > On Wed 03-07-13 17:53:21, Sedat Dilek wrote:
>
> >> On Wed, Jul 3, 2013 at 5:20 PM, Michal Hocko <mhocko@xxxxxxx> wrote:
>
> >> > On Wed 03-07-13 20:51:00, Li Zefan wrote:
>
> >> > [...]
>
> >> >> [PATCH] memcg: fix build error if CONFIG_MEMCG_KMEM=n
>
> >> >>
>
> >> >> Fix this build error:
>
> >> >>
>
> >> >> mm/built-in.o: In function `mem_cgroup_css_free':
>
> >> >> memcontrol.c:(.text+0x5caa6): undefined reference to
>
> >> >> 'mem_cgroup_sockets_destroy'
>
> >> >>
>
> >> >> Reported-by: Fengguang Wu <fengguang.wu@xxxxxxxxx>
>
> >> >> Reported-by: Stephen Rothwell <sfr@xxxxxxxxxxxxxxxx>
>
> >> >> Signed-off-by: Li Zefan <lizefan@xxxxxxxxxx>
>
> >> >
>
> >> > I am seeing the same thing I just didn't get to reporting it.
>
> >> > The other approach is not bad as well but I find this tiny better
>
> >> > because mem_cgroup_css_free should care only about a single cleanup
>
> >> > function for whole kmem. If that one needs to do tcp kmem specific
>
> >> > cleanup then it should be done inside kmem_cgroup_css_offline.
>
> >> >
>
> >>
>
> >> As said in my other mail, for me this makes sense as it is a followup.
>
> >>
>
> >> But, still I don't know why sock.c has is own mem_cgroup_sockets_{init,destroy}.
>
> >
>
> > That is the only definition AFAICS (except for !CONFIG_NET where it
>
> > expands to NOOP). Please note that memcg_init_kmem is a common kmem
>
> > initializator and it needs to be prepared for !CONFIG_NET.
>
> >
>
> > The same applies to _destroy.
>
> > Makes more sense now?
>
> >
>
>
>
> So, that stuff comes originally from the net-tree.
>
>
No, it all came from tcp kmem accounting. It is a memcg thingy and I
>
guess it was placed into sock.c because it depends on some static
>
symbols there (e.g. proto_list_mutex).
>
memcg thingies should belong to mm-tree :-).
>
> I understand the !CONFIG_NET case, but lack the understanding why
>
> memcontrol.c needs _destroy.
>
>
Because it is memcg specific and it has to be called when a group is
>
destroyed.
>
I looked again into my local GIT tree where I applied Li Zefan's patch.
memcg_destroy_kmem() makes sense with existing memcg_init_kmem().
I have now a better picture, but it's balck/white not coloured :-).
Thanks for your patience and explanations.
- Sedat -
>
> Can you explain that (sorry /me is no mm-geek)?
>
>
>
> - Sedat -
>
>
>
> [1] http://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git/tree/net/core/sock.c?id=next-20130703#n147
>
> [2] http://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git/tree/include/net/sock.h?id=next-20130703#n73
>
>
>
> > [...]
>
> > --
>
> > Michal Hocko
>
> > SUSE Labs
>
>
--
>
Michal Hocko
>
SUSE Labs
--
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/