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:   Song Liu <songliubraving@fb.com>
To:     Thomas Gleixner <tglx@linutronix.de>
CC:     Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Linux MM <linux-mm@kvack.org>,
        Kernel Team <Kernel-team@fb.com>,
        "stable@vger.kernel.org" <stable@vger.kernel.org>,
        Joerg Roedel <jroedel@suse.de>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Andy Lutomirski <luto@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>
Subject: Re: [PATCH] x86/mm/pti: in pti_clone_pgtable() don't increase addr by
 PUD_SIZE
Thread-Topic: [PATCH] x86/mm/pti: in pti_clone_pgtable() don't increase addr
 by PUD_SIZE
Thread-Index: AQHVVywgQMe0L9XqWkSJYmnWEvsfracDwFyAgABEZoA=
Date:   Tue, 20 Aug 2019 13:17:02 +0000
Message-ID: <6A23C1AE-B447-4273-A451-38D458085C02@fb.com>
References: <20190820075128.2912224-1-songliubraving@fb.com>
 <alpine.DEB.2.21.1908201106260.2223@nanos.tec.linutronix.de>
In-Reply-To: <alpine.DEB.2.21.1908201106260.2223@nanos.tec.linutronix.de>
Accept-Language: en-US
Content-Language: en-US
received-spf: None (protection.outlook.com: fb.com does not designate
 permitted sender hosts)
Content-Type: text/plain; charset="us-ascii"
Content-ID: <E6475E0209E0ED48BFFC12D99DC757C7@namprd15.prod.outlook.com>
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 72e39f53-fdd1-480c-5748-08d72570b0b5
X-MS-Exchange-CrossTenant-originalarrivaltime: 20 Aug 2019 13:17:02.5454
 (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-CrossTenant-userprincipalname: 9WUydOEVTvl5HUP3IODwv48zCpMWooZlbSFdtPRueIFiXhMkJD28FwmjsC4tPpOkGB34hY69Q4WMdFz70uXjIQ==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MWHPR15MB1757
X-OriginatorOrg: fb.com
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:,, definitions=2019-08-20_05:,,
 signatures=0
X-Proofpoint-Spam-Details: rule=fb_default_notspam policy=fb_default score=0 priorityscore=1501
 malwarescore=0 suspectscore=0 phishscore=0 bulkscore=0 spamscore=0
 clxscore=1015 lowpriorityscore=0 mlxscore=0 impostorscore=0
 mlxlogscore=900 adultscore=0 classifier=spam adjust=0 reason=mlx
 scancount=1 engine=8.0.1-1906280000 definitions=main-1908200140
X-FB-Internal: deliver
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 Aug 20, 2019, at 2:12 AM, Thomas Gleixner <tglx@linutronix.de> wrote:
>=20
> On Tue, 20 Aug 2019, Song Liu wrote:
>=20
>> pti_clone_pgtable() increases addr by PUD_SIZE for pud_none(*pud) case.
>> This is not accurate because addr may not be PUD_SIZE aligned.
>=20
> You fail to explain how this happened. The code before the 32bit support
> did always increase by PMD_SIZE. The 32bit support broke that.

Will fix.=20

>=20
>> In our x86_64 kernel, pti_clone_pgtable() fails to clone 7 PMDs because
>> of this issuse, including PMD for the irq entry table. For a memcache
>> like workload, this introduces about 4.5x more iTLB-load and about 2.5x
>> more iTLB-load-misses on a Skylake CPU.
>=20
> This information is largely irrelevant. What matters is the fact that thi=
s
> got broken and incorrectly forwards the address by PUD_SIZE which is wron=
g
> if address is not PUD_SIZE aligned.

We started looking into this because we cannot explain the regression in=20
iTLB miss rate. I guess the patch itself explains it pretty well, so the=20
original issue doesn't matter that much?

I will remove this part.=20

>=20
>> This patch fixes this issue by adding PMD_SIZE to addr for pud_none()
>> case.
>=20
>  git grep 'This patch' Documentation/process/submitting-patches.rst

Will fix.=20

>> Cc: stable@vger.kernel.org # v4.19+
>> Fixes: 16a3fe634f6a ("x86/mm/pti: Clone kernel-image on PTE level for 32=
 bit")
>> Signed-off-by: Song Liu <songliubraving@fb.com>
>> Cc: Joerg Roedel <jroedel@suse.de>
>> Cc: Thomas Gleixner <tglx@linutronix.de>
>> Cc: Dave Hansen <dave.hansen@linux.intel.com>
>> Cc: Andy Lutomirski <luto@kernel.org>
>> Cc: Peter Zijlstra <peterz@infradead.org>
>> ---
>> arch/x86/mm/pti.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>=20
>> diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
>> index b196524759ec..5a67c3015f59 100644
>> --- a/arch/x86/mm/pti.c
>> +++ b/arch/x86/mm/pti.c
>> @@ -330,7 +330,7 @@ pti_clone_pgtable(unsigned long start, unsigned long=
 end,
>>=20
>> 		pud =3D pud_offset(p4d, addr);
>> 		if (pud_none(*pud)) {
>> -			addr +=3D PUD_SIZE;
>> +			addr +=3D PMD_SIZE;
>=20
> The right fix is to skip forward to the next PUD boundary instead of doin=
g
> this in a loop with PMD_SIZE increments.

Agreed.=20

Thanks,
Song