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:   Pankaj Suryawanshi <pankaj.suryawanshi@einfochips.com>
To:     Vlastimil Babka <vbabka@suse.cz>,
        Kirill Tkhai <ktkhai@virtuozzo.com>,
        Michal Hocko <mhocko@kernel.org>,
        "aneesh.kumar@linux.ibm.com" <aneesh.kumar@linux.ibm.com>
CC:     "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "minchan@kernel.org" <minchan@kernel.org>,
        "linux-mm@kvack.org" <linux-mm@kvack.org>,
        "khandual@linux.vnet.ibm.com" <khandual@linux.vnet.ibm.com>,
        "hillf.zj@alibaba-inc.com" <hillf.zj@alibaba-inc.com>
Subject: Re: [External] Re: vmscan: Reclaim unevictable pages
Thread-Topic: [External] Re: vmscan: Reclaim unevictable pages
Thread-Index: AQHU3WaYCAMWaFadm0e/0+hd2XPYGaYRGYZ/
Date:   Mon, 18 Mar 2019 09:09:11 +0000
Message-ID: <SG2PR02MB309841EA4764E675D4649139E8470@SG2PR02MB3098.apcprd02.prod.outlook.com>
References: <SG2PR02MB3098A05E09B0D3F3CB1C3B9BE84B0@SG2PR02MB3098.apcprd02.prod.outlook.com>
 <SG2PR02MB309806967AE91179CAFEC34BE84B0@SG2PR02MB3098.apcprd02.prod.outlook.com>
 <SG2PR02MB3098B751EC6B8E32806A42FBE84B0@SG2PR02MB3098.apcprd02.prod.outlook.com>
 <20190314084120.GF7473@dhcp22.suse.cz>
 <SG2PR02MB309894F6D7DF9148846088F3E84B0@SG2PR02MB3098.apcprd02.prod.outlook.com>
 <226a92b9-94c5-b859-c54b-3aacad3089cc@virtuozzo.com>
 <SG2PR02MB3098299456FB6AE2FD822C4CE84B0@SG2PR02MB3098.apcprd02.prod.outlook.com>
 <SG2PR02MB30988333AD658F8124070ABEE84B0@SG2PR02MB3098.apcprd02.prod.outlook.com>
 <SG2PR02MB3098AB587F4BFCD6B9D042FDE8440@SG2PR02MB3098.apcprd02.prod.outlook.com>
 <SG2PR02MB3098E6F2C4BAEB56AE071EDCE8440@SG2PR02MB3098.apcprd02.prod.outlook.com>,<0b86dbca-cbc9-3b43-e3b9-8876bcc24f22@suse.cz>
In-Reply-To: <0b86dbca-cbc9-3b43-e3b9-8876bcc24f22@suse.cz>
Accept-Language: en-GB, en-US
Content-Language: en-GB
received-spf: None (protection.outlook.com: einfochips.com does not designate
 permitted sender hosts)
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 1b17ae03-8d82-41cf-3dfc-08d6ab8162cc
X-MS-Exchange-CrossTenant-originalarrivaltime: 18 Mar 2019 09:09:11.3815
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 0adb040b-ca22-4ca6-9447-ab7b049a22ff
X-MS-Exchange-CrossTenant-mailboxtype: HOSTED
X-MS-Exchange-Transport-CrossTenantHeadersStamped: SG2PR02MB3450
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org


Hello

shrink_page_list() returns , number of pages reclaimed, when pages is unevi=
ctable it returns VM_BUG_ON_PAGE(PageLRU(page) || PageUnevicatble(page),pag=
e);

We can add the unevictable pages in reclaim list in shrink_page_list(), ret=
urn total number of reclaim pages including unevictable pages, let the call=
er handle unevictable pages.

I think the problem is shrink_page_list is awkard. If page is unevictable i=
t goto activate_locked->keep_locked->keep lables, keep lable list_add the u=
nevictable pages and throw the VM_BUG instead of passing it to caller while=
 it relies on caller for non-reclaimed-non-unevictable  page's putback.
I think we can make it consistent so that shrink_page_list could return non=
-reclaimed pages via page_list and caller can handle it. As an advance, it =
could try to migrate mlocked pages without retrial.


Below is the issue of CMA_ALLOC of large size buffer : (Kernel version - 4.=
14.65 (On Android pie [ARM])).

[=A0=A0 24.718792] page dumped because: VM_BUG_ON_PAGE(PageLRU(page) || Pag=
eUnevictable(page))
[=A0=A0 24.726949] page->mem_cgroup:bd008c00
[=A0=A0 24.730693] ------------[ cut here ]------------
[=A0=A0 24.735304] kernel BUG at mm/vmscan.c:1350!
[=A0=A0 24.739478] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP ARM


Below is the patch which solved this issue :

diff --git a/mm/vmscan.c b/mm/vmscan.c
index be56e2e..12ac353 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -998,7 +998,7 @@ static unsigned long shrink_page_list(struct list_head =
*page_list,
=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 sc->nr_scanned++;
=A0
=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 if (unlikely(!page_evictable(=
page)))
-=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 goto ac=
tivate_locked;
+=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 goto cull_=
mlocked;
=A0
=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 if (!sc->may_unmap && page_ma=
pped(page))
=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 goto =
keep_locked;
@@ -1331,7 +1331,12 @@ static unsigned long shrink_page_list(struct list_he=
ad *page_list,
=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 } else
=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 list_=
add(&page->lru, &free_pages);
=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 continue;
-
+cull_mlocked:
+=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 if (PageSwapCache(page))
+=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 try_=
to_free_swap(page);
+=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 unlock_page(page);
+=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 list_add(&page->lru, &ret_pa=
ges);
+=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 continue;
=A0activate_locked:
=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 /* Not a candidate for swappi=
ng, so reclaim swap space. */
=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 if (PageSwapCache(page) && (m=
em_cgroup_swap_full(page) ||


It fixes the below issue.

1. Large size buffer allocation using cma_alloc successful with unevictable=
 pages.

cma_alloc of current kernel will fail due to unevictable page

Please let me know if anything i am missing.

Regards,
Pankaj
 =20
From: Vlastimil Babka <vbabka@suse.cz>
Sent: 18 March 2019 14:12:50
To: Pankaj Suryawanshi; Kirill Tkhai; Michal Hocko; aneesh.kumar@linux.ibm.=
com
Cc: linux-kernel@vger.kernel.org; minchan@kernel.org; linux-mm@kvack.org; k=
handual@linux.vnet.ibm.com; hillf.zj@alibaba-inc.com
Subject: Re: [External] Re: vmscan: Reclaim unevictable pages
=A0=20

On 3/15/19 11:11 AM, Pankaj Suryawanshi wrote:
>=20
> [ cc Aneesh kumar, Anshuman, Hillf, Vlastimil]

Can you send a proper patch with changelog explaining the change? I
don't know the context of this thread.

> From: Pankaj Suryawanshi
> Sent: 15 March 2019 11:35:05
> To: Kirill Tkhai; Michal Hocko
> Cc: linux-kernel@vger.kernel.org; minchan@kernel.org; linux-mm@kvack.org
> Subject: Re: Re: [External] Re: vmscan: Reclaim unevictable pages
>=20
>=20
>=20
> [ cc linux-mm ]
>=20
>=20
> From: Pankaj Suryawanshi
> Sent: 14 March 2019 19:14:40
> To: Kirill Tkhai; Michal Hocko
> Cc: linux-kernel@vger.kernel.org; minchan@kernel.org
> Subject: Re: Re: [External] Re: vmscan: Reclaim unevictable pages
>=20
>=20
>=20
> Hello ,
>=20
> Please ignore the curly braces, they are just for debugging.
>=20
> Below is the updated patch.
>=20
>=20
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index be56e2e..12ac353 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -998,7 +998,7 @@ static unsigned long shrink_page_list(struct list_hea=
d *page_list,
>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 sc->nr_scanned++;
>=20
>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 if (unlikely(!page_evicta=
ble(page)))
> -=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 goto =
activate_locked;
> +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 goto cul=
l_mlocked;
>=20
>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 if (!sc->may_unmap && pag=
e_mapped(page))
>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 g=
oto keep_locked;
> @@ -1331,7 +1331,12 @@ static unsigned long shrink_page_list(struct list_=
head *page_list,
>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 } else
>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 l=
ist_add(&page->lru, &free_pages);
>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 continue;
> -
> +cull_mlocked:
> +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 if (PageSwapCache(page))
> +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 tr=
y_to_free_swap(page);
> +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 unlock_page(page);
> +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 list_add(&page->lru, &ret_=
pages);
> +=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 continue;
>=A0 activate_locked:
>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 /* Not a candidate for sw=
apping, so reclaim swap space. */
>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 if (PageSwapCache(page) &=
& (mem_cgroup_swap_full(page) ||
>=20
>=20
>=20
> Regards,
> Pankaj
>=20
>=20
> From: Kirill Tkhai <ktkhai@virtuozzo.com>
> Sent: 14 March 2019 14:55:34
> To: Pankaj Suryawanshi; Michal Hocko
> Cc: linux-kernel@vger.kernel.org; minchan@kernel.org
> Subject: Re: Re: [External] Re: vmscan: Reclaim unevictable pages
>=20
>=20
> On 14.03.2019 11:52, Pankaj Suryawanshi wrote:
>>
>> I am using kernel version 4.14.65 (on Android pie [ARM]).
>>
>> No additional patches applied on top of vanilla.(Core MM).
>>
>> If=A0 I change in the vmscan.c as below patch, it will work.
>=20
> Sorry, but 4.14.65 does not have braces around trylock_page(),
> like in your patch below.
>=20
> See=A0=A0=A0=A0  https://git.kernel.org/pub/scm/linux/kernel/git/stable/l=
inux.git/tree/mm/vmscan.c?h=3Dv4.14.65
>=20
> [...]
>=20
>>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>>> index be56e2e..2e51edc 100644
>>> --- a/mm/vmscan.c
>>> +++ b/mm/vmscan.c
>>> @@ -990,15 +990,17 @@ static unsigned long shrink_page_list(struct list=
_head *page_list,
>>>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 page =3D lru_to_page=
(page_list);
>>>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 list_del(&page->lru)=
;
>>>
>>>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 if (!trylock_page(page)=
) {
>>>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=
=A0 goto keep;
>>>=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0=A0 }
>=20
> *************************************************************************=
***************************************************************************=
********* eInfochips Business Disclaimer: This e-mail message and all attac=
hments transmitted with it are intended  solely for the use of the addresse=
e and may contain legally privileged and confidential information. If the r=
eader of this message is not the intended recipient, or an employee or agen=
t responsible for delivering this message to the intended recipient, you  a=
re hereby notified that any dissemination, distribution, copying, or other =
use of this message or its attachments is strictly prohibited. If you have =
received this message in error, please notify the sender immediately by rep=
lying to this message and please  delete it from your computer. Any views e=
xpressed in this message are those of the individual sender unless otherwis=
e stated. Company has taken enough precautions to prevent the spread of vir=
uses. However the company accepts no liability for any damage caused  by an=
y virus transmitted by this email. ****************************************=
***************************************************************************=
******************************************
>=20

    =