Re: [rfc patch 3/6] mm: memcg-aware global reclaim

[Johannes Weiner <hannes@cmpxchg.org>]

On Fri, May 13, 2011 at 09:40:50AM +0900, KAMEZAWA Hiroyuki wrote:
> > @@ -1954,6 +1952,19 @@ restart:
> >  		goto restart;
> >  
> >  	throttle_vm_writeout(sc->gfp_mask);
> > +}
> > +
> > +static void shrink_zone(int priority, struct zone *zone,
> > +			struct scan_control *sc)
> > +{
> > +	struct mem_cgroup *root = sc->memcg;
> > +	struct mem_cgroup *mem = NULL;
> > +
> > +	do {
> > +		mem_cgroup_hierarchy_walk(root, &mem);
> > +		sc->current_memcg = mem;
> > +		do_shrink_zone(priority, zone, sc);
> 
> If I don't miss something, css_put() against mem->css will be required somewhere.

That's a bit of a hack.  mem_cgroup_hierarchy_walk() always does
css_put() on *mem before advancing to the next child.

At the last iteration, it returns mem == root.  Since the caller must
have a reference on root to begin with, it does not css_get() root.

So when mem == root, there are no outstanding references from the walk
anymore.

This only works since it always does the full hierarchy walk, so it's
going away anyway when the hierarchy walk becomes intermittent.