Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.36 as permitted sender) client-ip=23.128.96.36;
MIME-Version: 1.0
References: <20231102032330.1036151-1-chengming.zhou@linux.dev>
 <20231102032330.1036151-8-chengming.zhou@linux.dev> <CAB=+i9RR-n4q5NU6LFqmhM8ys4kM0SPqwj0zYtr4twu=yYmPPA@mail.gmail.com>
 <af74599e-6384-4bcc-9773-d37b061eabdf@linux.dev>
In-Reply-To: <af74599e-6384-4bcc-9773-d37b061eabdf@linux.dev>
From:   Hyeonggon Yoo <42.hyeyoo@gmail.com>
Date:   Sun, 3 Dec 2023 20:19:38 +0900
Message-ID: <CAB=+i9T+aLEj6BHdXXJxqY914O1ZVCbmL8iL_5wiFB3dQN6yUg@mail.gmail.com>
Subject: Re: [PATCH v5 7/9] slub: Optimize deactivate_slab()
To:     Chengming Zhou <chengming.zhou@linux.dev>
Cc:     vbabka@suse.cz, cl@linux.com, penberg@kernel.org,
        rientjes@google.com, iamjoonsoo.kim@lge.com,
        akpm@linux-foundation.org, roman.gushchin@linux.dev,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org,
        Chengming Zhou <zhouchengming@bytedance.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Sun, Dec 3, 2023 at 7:26=E2=80=AFPM Chengming Zhou <chengming.zhou@linux=
.dev> wrote:
>
> On 2023/12/3 17:23, Hyeonggon Yoo wrote:
> > On Thu, Nov 2, 2023 at 12:25=E2=80=AFPM <chengming.zhou@linux.dev> wrot=
e:
> >>
> >> From: Chengming Zhou <zhouchengming@bytedance.com>
> >>
> >> Since the introduce of unfrozen slabs on cpu partial list, we don't
> >> need to synchronize the slab frozen state under the node list_lock.
> >>
> >> The caller of deactivate_slab() and the caller of __slab_free() won't
> >> manipulate the slab list concurrently.
> >>
> >> So we can get node list_lock in the last stage if we really need to
> >> manipulate the slab list in this path.
> >>
> >> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
> >> Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
> >> Tested-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
> >> ---
> >>  mm/slub.c | 79 ++++++++++++++++++------------------------------------=
-
> >>  1 file changed, 26 insertions(+), 53 deletions(-)
> >>
> >> diff --git a/mm/slub.c b/mm/slub.c
> >> index bcb5b2c4e213..d137468fe4b9 100644
> >> --- a/mm/slub.c
> >> +++ b/mm/slub.c
> >> @@ -2468,10 +2468,8 @@ static void init_kmem_cache_cpus(struct kmem_ca=
che *s)
> >>  static void deactivate_slab(struct kmem_cache *s, struct slab *slab,
> >>                             void *freelist)
> >>  {
> >> -       enum slab_modes { M_NONE, M_PARTIAL, M_FREE, M_FULL_NOLIST };
> >>         struct kmem_cache_node *n =3D get_node(s, slab_nid(slab));
> >>         int free_delta =3D 0;
> >> -       enum slab_modes mode =3D M_NONE;
> >>         void *nextfree, *freelist_iter, *freelist_tail;
> >>         int tail =3D DEACTIVATE_TO_HEAD;
> >>         unsigned long flags =3D 0;
> >> @@ -2509,65 +2507,40 @@ static void deactivate_slab(struct kmem_cache =
*s, struct slab *slab,
> >>         /*
> >>          * Stage two: Unfreeze the slab while splicing the per-cpu
> >>          * freelist to the head of slab's freelist.
> >> -        *
> >> -        * Ensure that the slab is unfrozen while the list presence
> >> -        * reflects the actual number of objects during unfreeze.
> >> -        *
> >> -        * We first perform cmpxchg holding lock and insert to list
> >> -        * when it succeed. If there is mismatch then the slab is not
> >> -        * unfrozen and number of objects in the slab may have changed=
.
> >> -        * Then release lock and retry cmpxchg again.
> >>          */
> >> -redo:
> >> -
> >> -       old.freelist =3D READ_ONCE(slab->freelist);
> >> -       old.counters =3D READ_ONCE(slab->counters);
> >> -       VM_BUG_ON(!old.frozen);
> >> -
> >> -       /* Determine target state of the slab */
> >> -       new.counters =3D old.counters;
> >> -       if (freelist_tail) {
> >> -               new.inuse -=3D free_delta;
> >> -               set_freepointer(s, freelist_tail, old.freelist);
> >> -               new.freelist =3D freelist;
> >> -       } else
> >> -               new.freelist =3D old.freelist;
> >> -
> >> -       new.frozen =3D 0;
> >> +       do {
> >> +               old.freelist =3D READ_ONCE(slab->freelist);
> >> +               old.counters =3D READ_ONCE(slab->counters);
> >> +               VM_BUG_ON(!old.frozen);
> >> +
> >> +               /* Determine target state of the slab */
> >> +               new.counters =3D old.counters;
> >> +               new.frozen =3D 0;
> >> +               if (freelist_tail) {
> >> +                       new.inuse -=3D free_delta;
> >> +                       set_freepointer(s, freelist_tail, old.freelist=
);
> >> +                       new.freelist =3D freelist;
> >> +               } else {
> >> +                       new.freelist =3D old.freelist;
> >> +               }
> >> +       } while (!slab_update_freelist(s, slab,
> >> +               old.freelist, old.counters,
> >> +               new.freelist, new.counters,
> >> +               "unfreezing slab"));
> >>
> >> +       /*
> >> +        * Stage three: Manipulate the slab list based on the updated =
state.
> >> +        */
> >
> > deactivate_slab() might unconsciously put empty slabs into partial list=
, like:
> >
> > deactivate_slab()                    __slab_free()
> > cmpxchg(), slab's not empty
> >                                                cmpxchg(), slab's empty
> > and unfrozen
>
> Hi,
>
> Sorry, but I don't get it here how __slab_free() can see the slab empty,
> since the slab is not empty from deactivate_slab() path, and it can't be
> used by any CPU at that time?

The scenario is CPU B previously allocated an object from slab X, but
put it into node partial list and then CPU A have taken slab X into cpu sla=
b.

While slab X is CPU A's cpu slab, when CPU B frees an object from slab X,
it puts the object into slab X's freelist using cmpxchg.

Let's say in CPU A the deactivation path performs cmpxchg and X.inuse was 1=
,
and then CPU B frees (__slab_free()) to slab X's freelist using cmpxchg,
_before_ slab X's put into partial list by CPU A.

Then CPU A thinks it's not empty so put it into partial list, but by CPU B
the slab has become empty.

Maybe I am confused, in that case please tell me I'm wrong :)

Thanks!

--
Hyeonggon