Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Roman Gushchin <guro@fb.com>
To:     Shakeel Butt <shakeelb@google.com>
CC:     Roman Gushchin <guroan@gmail.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Linux MM <linux-mm@kvack.org>,
        LKML <linux-kernel@vger.kernel.org>,
        Kernel Team <Kernel-team@fb.com>,
        "Johannes Weiner" <hannes@cmpxchg.org>,
        Michal Hocko <mhocko@kernel.org>,
        Rik van Riel <riel@surriel.com>,
        "david@fromorbit.com" <david@fromorbit.com>,
        "Christoph Lameter" <cl@linux.com>,
        Pekka Enberg <penberg@kernel.org>,
        Vladimir Davydov <vdavydov.dev@gmail.com>,
        Cgroups <cgroups@vger.kernel.org>
Subject: Re: [PATCH 4/5] mm: rework non-root kmem_cache lifecycle management
Thread-Topic: [PATCH 4/5] mm: rework non-root kmem_cache lifecycle management
Thread-Index: AQHU9WhFLwAo90XwHUSqs2s91sh5hqZBAzaA//+a0QCAAIqtAP//ntuAgAEtKQCAAEV2gA==
Date:   Thu, 18 Apr 2019 18:14:05 +0000
Message-ID: <20190418181400.GC11008@tower.DHCP.thefacebook.com>
References: <20190417215434.25897-1-guro@fb.com>
 <20190417215434.25897-5-guro@fb.com>
 <CALvZod5K8SM2EQFH1WM9bbwWBtyXWb_PvzJGvF5dg1Z=bdR7zg@mail.gmail.com>
 <20190418003850.GA13977@tower.DHCP.thefacebook.com>
 <CALvZod6UiTeN40RgpE-4zE5zagSifqh3o_AXaw8o-ubVUWf=4w@mail.gmail.com>
 <20190418030729.GA5038@castle>
 <CALvZod4K9HymKkG9hGoU-sFxZogqP+wrBRD9AighvfUzDGoTFQ@mail.gmail.com>
In-Reply-To: <CALvZod4K9HymKkG9hGoU-sFxZogqP+wrBRD9AighvfUzDGoTFQ@mail.gmail.com>
Accept-Language: en-US
Content-Language: en-US
x-ms-exchange-messagesentrepresentingtype: 1
x-originating-ip: [2620:10d:c090:200::3:497d]
x-ms-publictraffictype: Email
x-ms-office365-filtering-correlation-id: e76cc721-e0ea-475f-3e04-08d6c429a481
x-microsoft-antispam: BCL:0;PCL:0;RULEID:(2390118)(7020095)(4652040)(8989299)(5600141)(711020)(4605104)(4534185)(4627221)(201703031133081)(201702281549075)(8990200)(2017052603328)(7193020);SRVR:BYAPR15MB3159;
x-ms-traffictypediagnostic: BYAPR15MB3159:
x-ms-exchange-purlcount: 1
x-microsoft-antispam-prvs: <BYAPR15MB3159E47BBD504E25027D428FBE260@BYAPR15MB3159.namprd15.prod.outlook.com>
x-forefront-prvs: 0011612A55
x-forefront-antispam-report: SFV:NSPM;SFS:(10019020)(366004)(396003)(39860400002)(376002)(136003)(346002)(199004)(189003)(55674003)(54094003)(316002)(446003)(256004)(76176011)(54906003)(81156014)(8676002)(81166006)(5660300002)(33656002)(14454004)(476003)(52116002)(6486002)(7416002)(2906002)(99286004)(6916009)(6436002)(93886005)(229853002)(7736002)(6246003)(4326008)(9686003)(8936002)(68736007)(6512007)(6306002)(6116002)(305945005)(966005)(71200400001)(97736004)(102836004)(6506007)(11346002)(53546011)(386003)(53936002)(25786009)(486006)(186003)(71190400001)(1076003)(14444005)(86362001)(478600001)(46003);DIR:OUT;SFP:1102;SCL:1;SRVR:BYAPR15MB3159;H:BYAPR15MB2631.namprd15.prod.outlook.com;FPR:;SPF:None;LANG:en;PTR:InfoNoRecords;A:1;MX:1;
received-spf: None (protection.outlook.com: fb.com does not designate
 permitted sender hosts)
x-ms-exchange-senderadcheck: 1
x-microsoft-antispam-message-info: MVTaA9rUXVRnPBjqqSxyxYBms6dEtKa6CgbAXJoSppfsMUnB8tYDDFbcOYWCpF4qoz7iaZ6uJxNmWuid8nO/WxBf7Wyhys9f1q09X52Q3siUdJZzjC8mqdJp9wmqm0rGfpWnmNy5NbmzshGDu82ktZjBdpa9iA6wUCPq4ylGnIivRPrKRbCABjuHoKhUgBg0Nn1bzxpjBjLkapIH60kCGA5eE+v/pHl74ZBO294zlv9EBo5PXXCDshZn0ze4UIV1chv5e3P1CoQfQLp1nln1Nq51BQCn0VcFPOF8rJV+JFbEL+Kszv8HPT8q++P6gyScC2YMaobzmY9ed8TJdWb6bEG3vsqzsB0/0XNKhJyvwxZYiKbqJ6xZJSyfet8Dyx8a0ZnjxSVoJzQ63DgIl0s54ubknsEhHVnKEEFcXDzC1jE=
Content-Type: text/plain; charset="us-ascii"
Content-ID: <ADD4024971601F44BCA664623F115C4F@namprd15.prod.outlook.com>
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: e76cc721-e0ea-475f-3e04-08d6c429a481
X-MS-Exchange-CrossTenant-originalarrivaltime: 18 Apr 2019 18:14:05.4652
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 8ae927fe-1255-47a7-a2af-5f3a069daaa2
X-MS-Exchange-CrossTenant-mailboxtype: HOSTED
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BYAPR15MB3159
X-OriginatorOrg: fb.com
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:,, definitions=2019-04-18_09:,,
 signatures=0
X-Proofpoint-Spam-Reason: safe
X-FB-Internal: Safe
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Thu, Apr 18, 2019 at 07:05:24AM -0700, Shakeel Butt wrote:
> On Wed, Apr 17, 2019 at 8:07 PM Roman Gushchin <guro@fb.com> wrote:
> >
> > On Wed, Apr 17, 2019 at 06:55:12PM -0700, Shakeel Butt wrote:
> > > On Wed, Apr 17, 2019 at 5:39 PM Roman Gushchin <guro@fb.com> wrote:
> > > >
> > > > On Wed, Apr 17, 2019 at 04:41:01PM -0700, Shakeel Butt wrote:
> > > > > On Wed, Apr 17, 2019 at 2:55 PM Roman Gushchin <guroan@gmail.com>=
 wrote:
> > > > > >
> > > > > > This commit makes several important changes in the lifecycle
> > > > > > of a non-root kmem_cache, which also affect the lifecycle
> > > > > > of a memory cgroup.
> > > > > >
> > > > > > Currently each charged slab page has a page->mem_cgroup pointer
> > > > > > to the memory cgroup and holds a reference to it.
> > > > > > Kmem_caches are held by the cgroup. On offlining empty kmem_cac=
hes
> > > > > > are freed, all other are freed on cgroup release.
> > > > >
> > > > > No, they are not freed (i.e. destroyed) on offlining, only
> > > > > deactivated. All memcg kmem_caches are freed/destroyed on memcg's
> > > > > css_free.
> > > >
> > > > You're right, my bad. I was thinking about the corresponding sysfs =
entry
> > > > when was writing it. We try to free it from the deactivation path t=
oo.
> > > >
> > > > >
> > > > > >
> > > > > > So the current scheme can be illustrated as:
> > > > > > page->mem_cgroup->kmem_cache.
> > > > > >
> > > > > > To implement the slab memory reparenting we need to invert the =
scheme
> > > > > > into: page->kmem_cache->mem_cgroup.
> > > > > >
> > > > > > Let's make every page to hold a reference to the kmem_cache (we
> > > > > > already have a stable pointer), and make kmem_caches to hold a =
single
> > > > > > reference to the memory cgroup.
> > > > >
> > > > > What about memcg_kmem_get_cache()? That function assumes that by
> > > > > taking reference on memcg, it's kmem_caches will stay. I think yo=
u
> > > > > need to get reference on the kmem_cache in memcg_kmem_get_cache()
> > > > > within the rcu lock where you get the memcg through css_tryget_on=
line.
> > > >
> > > > Yeah, a very good question.
> > > >
> > > > I believe it's safe because css_tryget_online() guarantees that
> > > > the cgroup is online and won't go offline before css_free() in
> > > > slab_post_alloc_hook(). I do initialize kmem_cache's refcount to 1
> > > > and drop it on offlining, so it protects the online kmem_cache.
> > > >
> > >
> > > Let's suppose a thread doing a remote charging calls
> > > memcg_kmem_get_cache() and gets an empty kmem_cache of the remote
> > > memcg having refcnt equal to 1. That thread got a reference on the
> > > remote memcg but no reference on the kmem_cache. Let's suppose that
> > > thread got stuck in the reclaim and scheduled away. In the meantime
> > > that remote memcg got offlined and decremented the refcnt of all of
> > > its kmem_caches. The empty kmem_cache which the thread stuck in
> > > reclaim have pointer to can get deleted and may be using an already
> > > destroyed kmem_cache after coming back from reclaim.
> > >
> > > I think the above situation is possible unless the thread gets the
> > > reference on the kmem_cache in memcg_kmem_get_cache().
> >
> > Yes, you're right and I'm writing a nonsense: css_tryget_online()
> > can't prevent the cgroup from being offlined.
> >
>=20
> The reason I knew about that race is because I tried something similar
> but for different use-case:
>=20
> https://lkml.org/lkml/2018/3/26/472
>=20
> > So, the problem with getting a reference in memcg_kmem_get_cache()
> > is that it's an atomic operation on the hot path, something I'd like
> > to avoid.
> >
> > I can make the refcounter percpu, but it'll add some complexity and siz=
e
> > to the kmem_cache object. Still an option, of course.
> >
>=20
> I kind of prefer this option.
>=20
> > I wonder if we can use rcu_read_lock() instead, and bump the refcounter
> > only if we're going into reclaim.
> >
> > What do you think?
>=20
> Should it be just reclaim or anything that can reschedule the current thr=
ead?
>=20
> I can tell how we resolve the similar issue for our
> eager-kmem_cache-deletion use-case. Our solution (hack) works only for
> CONFIG_SLAB (we only use SLAB) and non-preemptible kernel. The
> underlying motivation was to reduce the overhead of slab reaper of
> traversing thousands of empty offlined kmem caches. CONFIG_SLAB
> disables interrupts before accessing the per-cpu caches and reenables
> the interrupts if it has to fallback to the page allocation. We use
> this window to call memcg_kmem_get_cache() and only increment the
> refcnt of kmem_cache if going to the fallback. Thus no need to do
> atomic operation on the hot path.
>=20
> Anyways, I think having percpu refcounter for each memcg kmem_cache is
> not that costy for CONFIG_MEMCG_KMEM users and to me that seems like
> the most simple solution.
>=20
> Shakeel

Ok, sounds like a percpu refcounter is the best option.
I'll try this approach in v2.

Thanks!