Received-SPF: pass (google.com: domain of linux-kernel+bounces-187716-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Date: Thu, 23 May 2024 08:30:40 -0700
From: Roman Gushchin <roman.gushchin@linux.dev>
To: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Yosry Ahmed <yosryahmed@google.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Michal Hocko <mhocko@kernel.org>,
	Muchun Song <muchun.song@linux.dev>, ying.huang@intel.com,
	feng.tang@intel.com, fengwei.yin@intel.com, oliver.sang@intel.com,
	kernel-team@meta.com, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH] memcg: rearrage fields of mem_cgroup_per_node
Message-ID: <Zk9hIBJr35_wSTMq@P9FQF9L96D.corp.robot.car>
References: <20240523034824.1255719-1-shakeel.butt@linux.dev>
 <CAJD7tkaaEn+2G46taRD1V1W=okBfZtPPOFFyj5A+MVfGzqPDqw@mail.gmail.com>
 <m4ixafl5ajnr6tgkjwead3bmgglqqcpfwsgqijb6mlz2rfgjtu@yi3jwlnfpqpx>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <m4ixafl5ajnr6tgkjwead3bmgglqqcpfwsgqijb6mlz2rfgjtu@yi3jwlnfpqpx>

On Wed, May 22, 2024 at 10:34:38PM -0700, Shakeel Butt wrote:
> On Wed, May 22, 2024 at 09:35:57PM -0700, Yosry Ahmed wrote:
> > On Wed, May 22, 2024 at 8:48 PM Shakeel Butt <shakeel.butt@linux.dev> wrote:
> [...]
> > >
> > >  struct mem_cgroup_per_node {
> > > -       struct lruvec           lruvec;
> > > +       /* Keep the read-only fields at the start */
> > > +       struct mem_cgroup       *memcg;         /* Back pointer, we cannot */
> > > +                                               /* use container_of        */
> > >
> > >         struct lruvec_stats_percpu __percpu     *lruvec_stats_percpu;
> > >         struct lruvec_stats                     *lruvec_stats;
> > > -
> > > -       unsigned long           lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
> > > -
> > > -       struct mem_cgroup_reclaim_iter  iter;
> > > -
> > >         struct shrinker_info __rcu      *shrinker_info;
> > >
> > > +       /* memcg-v1 only stuff in middle */
> > > +
> > >         struct rb_node          tree_node;      /* RB tree node */
> > >         unsigned long           usage_in_excess;/* Set to the value by which */
> > >                                                 /* the soft limit is exceeded*/
> > >         bool                    on_tree;
> > > -       struct mem_cgroup       *memcg;         /* Back pointer, we cannot */
> > > -                                               /* use container_of        */
> > 
> > Do we need CACHELINE_PADDING() here (or maybe make struct lruvec
> > cache-aligned) to make sure the false cacheline sharing doesn't happen
> > again with the fields below, or is the idea that the fields that get
> > read in hot paths (memcg, lruvec_stats_percpu, lruvec_stats) are far
> > at the top, and the memcg v1 elements in the middle act as a buffer?

It's a good point. Once we will compile out the memcg v1 stuff, it might stop
working.

> > 
> > IOW, is sharing between the fields below and memcg v1 fields okay
> > because they are not read in the hot path? If yes, I believe it's
> > worth a comment. It can be easily missed if the memcg v1 soft limit is
> > removed later for example.
> > 
> 
> For 6.10, I wanted to keep the change simple and yes, the memcg v1 stuff
> as a buffer between the pointers and lruvec/lru_zone_size fields. For
> 6.11 or later kernels, I am planning to use some asserts to make sure
> these fields don't share a cacheline, so later when we remove the
> v1-only stuff, the asserts will make sure we keep the separate cacheline
> property intact.

Sounds good. Once we'll have memcg v1 stuff under a config option, we'll
put those asserts in.
Btw, I'm about (today/tomorrow) to post the memcg-v1 separation patchset,
so it won't take a long time.

Thanks!