Re: [PATCH v4 1/5] mm/memcg: Move mod_objcg_state() to memcontrol.c

[Johannes Weiner]

On Mon, Apr 19, 2021 at 12:18:29PM -0400, Waiman Long wrote:
> On 4/19/21 11:21 AM, Waiman Long wrote:
> > On 4/19/21 11:14 AM, Johannes Weiner wrote:
> > > On Sun, Apr 18, 2021 at 08:00:28PM -0400, Waiman Long wrote:
> > > > The mod_objcg_state() function is moved from mm/slab.h to
> > > > mm/memcontrol.c
> > > > so that further optimization can be done to it in later patches without
> > > > exposing unnecessary details to other mm components.
> > > > 
> > > > Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
> > > > ---
> > > >   mm/memcontrol.c | 13 +++++++++++++
> > > >   mm/slab.h       | 16 ++--------------
> > > >   2 files changed, 15 insertions(+), 14 deletions(-)
> > > > 
> > > > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> > > > index e064ac0d850a..dc9032f28f2e 100644
> > > > --- a/mm/memcontrol.c
> > > > +++ b/mm/memcontrol.c
> > > > @@ -3150,6 +3150,19 @@ void __memcg_kmem_uncharge_page(struct
> > > > page *page, int order)
> > > >       css_put(&memcg->css);
> > > >   }
> > > >   +void mod_objcg_state(struct obj_cgroup *objcg, struct
> > > > pglist_data *pgdat,
> > > > +             enum node_stat_item idx, int nr)
> > > > +{
> > > > +    struct mem_cgroup *memcg;
> > > > +    struct lruvec *lruvec = NULL;
> > > > +
> > > > +    rcu_read_lock();
> > > > +    memcg = obj_cgroup_memcg(objcg);
> > > > +    lruvec = mem_cgroup_lruvec(memcg, pgdat);
> > > > +    mod_memcg_lruvec_state(lruvec, idx, nr);
> > > > +    rcu_read_unlock();
> > > > +}
> > > It would be more naturally placed next to the others, e.g. below
> > > __mod_lruvec_kmem_state().
> > > 
> > > But no deal breaker if there isn't another revision.
> > > 
> > > Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx>
> > > 
> > Yes, there will be another revision by rebasing patch series on the
> > linux-next. I will move the function then.
> 
> OK, it turns out that mod_objcg_state() is only defined if
> CONFIG_MEMCG_KMEM. That was why I put it in the CONFIG_MEMCG_KMEM block with
> the other obj_stock functions. I think I will keep it there.

The CONFIG_MEMCG_KMEM has become sort of useless now. It used to be
configurable, but now it just means CONFIG_MEMCG && !CONFIG_SLOB. And
even that doesn't make sense because while slob doesn't support slab
object tracking, we can still do all the other stuff we do under
KMEM. I have a patch in the works to remove the symbol and ifdefs.

With that in mind, it's better to group the functions based on what
they do rather than based on CONFIG_MEMCG_KMEM. It's easier to just
remove another ifdef later than it is to reorder the functions.