From:   Zi Yan <ziy@nvidia.com>
To:     Huang Ying <ying.huang@intel.com>
Cc:     Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org, Yang Shi <shy828301@gmail.com>,
        Baolin Wang <baolin.wang@linux.alibaba.com>,
        Oscar Salvador <osalvador@suse.de>,
        Matthew Wilcox <willy@infradead.org>,
        Bharata B Rao <bharata@amd.com>,
        Alistair Popple <apopple@nvidia.com>,
        haoxin <xhao@linux.alibaba.com>,
        Minchan Kim <minchan@kernel.org>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Hyeonggon Yoo <42.hyeyoo@gmail.com>
Subject: Re: [PATCH -v4 8/9] migrate_pages: batch flushing TLB
Date:   Tue, 07 Feb 2023 09:52:28 -0500
Message-ID: <E6CE5A79-E1B0-4FCB-94A5-EE268C160410@nvidia.com>
In-Reply-To: <20230206063313.635011-9-ying.huang@intel.com>
References: <20230206063313.635011-1-ying.huang@intel.com>
 <20230206063313.635011-9-ying.huang@intel.com>
Content-Type: multipart/signed;
 boundary="=_MailMate_2696EDC7-7B4A-45D6-A749-E4523F28BB1D_=";
 micalg=pgp-sha512; protocol="application/pgp-signature"
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?yiyfLYYm8HxMUFI3PfZ8Do2L+PNHrj+a+ta2zPs8DQzGzY7TZSIk1o7Q4MQu?=
 =?us-ascii?Q?WyOxbupyGQE0FQBYzASTpi++LDdc9KzELAUFl+KQrILQ4vvFEFBKdiyZlDEW?=
 =?us-ascii?Q?e6JO/GiQHge7UX1OfUgFUt+axWH96W0wCon156FJJ8RFgK4Qw8U1VrAGy3rW?=
 =?us-ascii?Q?S6SeRodbEvHPPW8x4L6P+j2UDJTpDazMp2bQVs1dhs2SDjHqgEh+LqT4x1XC?=
 =?us-ascii?Q?UQrQMXYmDVhhuO1JJvMlrqvSz1kxXdP0k2VdK2sReTdwiHsW2CEcNbfr9Ygp?=
 =?us-ascii?Q?IuKYb5CZajsz8QvQI75FODoSB0DYrrOdaFP7NTgFLpm5F8tsGMa+BQFDxX1I?=
 =?us-ascii?Q?NsdAYWWeaxUk058h8VkrVNpmNpidoHJY4Q85lfAnMvoyADYqg5QgfqCWIrOW?=
 =?us-ascii?Q?fErotIFwogDRxC9LN3veFhYyDA6yWb+xZ+awBSZ4QA8AUuLdqKMRZWCHnnzs?=
 =?us-ascii?Q?sqGMm8hy3Pd8wq3bvM/st4Jpb3gtXPNWa07ogPGfDg5eihr12Ni33afBXyW8?=
 =?us-ascii?Q?nf/bki1HwnC4GRzT6O18pPRZB4VJw9baCv1XW8Y5mLR9Rv12nfdAZWgVMZvR?=
 =?us-ascii?Q?cKJuMiymIXNC01UQfXDNrPUFsC96HHI4CaApDVE3ZJaMUg1wtm4uqLLxlJoE?=
 =?us-ascii?Q?LCP/2AFs+DKqpdQtcHtRdDOrWP7JZp125bzV65Zcz7FnS9IcWDyxsRBenzH3?=
 =?us-ascii?Q?y/9xQ7GKMZyD8hoph2MzEu3DwBxkMYcwspPW9Ldy9cOsi64Tx/5wjQnMST01?=
 =?us-ascii?Q?G5Wt9lKUOePCb+m7orOYwygzzw0NvmbVrOUdN9niQAB8atuH0cnxn/U2CFAh?=
 =?us-ascii?Q?5BEVGZsbomVl3p3FPvMC1iEOg6KiGcPjaMCrxyBdCuOrCFGDwyzw6EZyH05S?=
 =?us-ascii?Q?Keo5fQhven6wRjf8iBrUQC6FPWE2Uinz+GLw7ksQJo7xOprTzgsCoySBXpSJ?=
 =?us-ascii?Q?ZedOq03Ul44AHTWqD+2Vwc4CnBJNuAk00gO1o6iYbUUy7zzhsi+HAvC4z8vY?=
 =?us-ascii?Q?4a5PhjFV7iTNSSLJ98/YhXKw56EuxhuHIOdnG9AQFazAOT04peMbvZ3ABsDo?=
 =?us-ascii?Q?ovITgYtS8r0up/NBuHtm5HwHtsTe4FMHXV69xzpGm2ZuwOgWmP72HdaWOMwj?=
 =?us-ascii?Q?pW8axCdhWbrfhzaNfam6noM+cjmammYvCU8S0Srh/6WRe3WQKntIh5c1kpbV?=
 =?us-ascii?Q?lXWRInvSGy1cvMiROVHlJKgxAFI56xejDrzfY28NigvsN/epJRWVoJk1/D95?=
 =?us-ascii?Q?fxuMl2TcIOgj+L8JFQ3nwOidSfS+88HineV0G3fs4nL8lcXcdHvsrr4LySxQ?=
 =?us-ascii?Q?bPdUP0kYapmgRZi4YJcbCo6QQoJ9qvMNfhXlHGpY8WufgscqqQSON69OFrvg?=
 =?us-ascii?Q?5rNcPQpZyNf+jHO41a6V4bGx4NuBZNG9Y+873DGihnXCYtwaB2v2NmbuhBpF?=
 =?us-ascii?Q?JMg6E0Id1Z0+mp7r8gnEq88UMe7LNrRBAsAdJCJWM1gKI4GJpfAEsqDEn981?=
 =?us-ascii?Q?HE4ZRXCAo3j2fhd4cfIS0WrwCNxq2BLTyPcQaJeKlPbxe6WDjbLIyQstwM2O?=
 =?us-ascii?Q?BNobx37++8xJkbjumWXiKYUNs63rYCNQf+GPPC3p?=
X-OriginatorOrg: Nvidia.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 6128455e-725b-41d8-b510-08db091af08a
X-MS-Exchange-CrossTenant-AuthSource: DS7PR12MB5744.namprd12.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 07 Feb 2023 14:52:31.3883
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: 8TM2O0pd7e8ss2MO1At/XkSwFUhK+Nd5IgQHEzIybPFSVEZC/Yv7plU4FTZGhPyF
X-MS-Exchange-Transport-CrossTenantHeadersStamped: CY8PR12MB7193
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

--=_MailMate_2696EDC7-7B4A-45D6-A749-E4523F28BB1D_=
Content-Type: text/plain
Content-Transfer-Encoding: quoted-printable

On 6 Feb 2023, at 1:33, Huang Ying wrote:

> The TLB flushing will cost quite some CPU cycles during the folio
> migration in some situations.  For example, when migrate a folio of a
> process with multiple active threads that run on multiple CPUs.  After
> batching the _unmap and _move in migrate_pages(), the TLB flushing can
> be batched easily with the existing TLB flush batching mechanism.
> This patch implements that.
>
> We use the following test case to test the patch.
>
> On a 2-socket Intel server,
>
> - Run pmbench memory accessing benchmark
>
> - Run `migratepages` to migrate pages of pmbench between node 0 and
>   node 1 back and forth.
>
> With the patch, the TLB flushing IPI reduces 99.1% during the test and
> the number of pages migrated successfully per second increases 291.7%.
>
> NOTE: TLB flushing is batched only for normal folios, not for THP
> folios.  Because the overhead of TLB flushing for THP folios is much
> lower than that for normal folios (about 1/512 on x86 platform).
>
> Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
> Cc: Zi Yan <ziy@nvidia.com>
> Cc: Yang Shi <shy828301@gmail.com>
> Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
> Cc: Oscar Salvador <osalvador@suse.de>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Bharata B Rao <bharata@amd.com>
> Cc: Alistair Popple <apopple@nvidia.com>
> Cc: haoxin <xhao@linux.alibaba.com>
> Cc: Minchan Kim <minchan@kernel.org>
> Cc: Mike Kravetz <mike.kravetz@oracle.com>
> Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
> ---
>  mm/migrate.c |  4 +++-
>  mm/rmap.c    | 20 +++++++++++++++++---
>  2 files changed, 20 insertions(+), 4 deletions(-)
>
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 9378fa2ad4a5..ca6e2ff02a09 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -1230,7 +1230,7 @@ static int migrate_folio_unmap(new_page_t get_new=
_page, free_page_t put_new_page
>  		/* Establish migration ptes */
>  		VM_BUG_ON_FOLIO(folio_test_anon(src) &&
>  			       !folio_test_ksm(src) && !anon_vma, src);
> -		try_to_migrate(src, 0);
> +		try_to_migrate(src, TTU_BATCH_FLUSH);
>  		page_was_mapped =3D 1;
>  	}
>
> @@ -1781,6 +1781,8 @@ static int migrate_pages_batch(struct list_head *=
from, new_page_t get_new_page,
>  	stats->nr_thp_failed +=3D thp_retry;
>  	stats->nr_failed_pages +=3D nr_retry_pages;
>  move:

Maybe a comment:
/* Flush TLBs for all the unmapped pages */

> +	try_to_unmap_flush();
> +
>  	retry =3D 1;
>  	for (pass =3D 0;
>  	     pass < NR_MAX_MIGRATE_PAGES_RETRY && (retry || large_retry);
> diff --git a/mm/rmap.c b/mm/rmap.c
> index b616870a09be..2e125f3e462e 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -1976,7 +1976,21 @@ static bool try_to_migrate_one(struct folio *fol=
io, struct vm_area_struct *vma,
>  		} else {
>  			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
>  			/* Nuke the page table entry. */
> -			pteval =3D ptep_clear_flush(vma, address, pvmw.pte);
> +			if (should_defer_flush(mm, flags)) {
> +				/*
> +				 * We clear the PTE but do not flush so potentially
> +				 * a remote CPU could still be writing to the folio.
> +				 * If the entry was previously clean then the
> +				 * architecture must guarantee that a clear->dirty
> +				 * transition on a cached TLB entry is written through
> +				 * and traps if the PTE is unmapped.
> +				 */
> +				pteval =3D ptep_get_and_clear(mm, address, pvmw.pte);
> +
> +				set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
> +			} else {
> +				pteval =3D ptep_clear_flush(vma, address, pvmw.pte);
> +			}
>  		}
>
>  		/* Set the dirty flag on the folio now the pte is gone. */
> @@ -2148,10 +2162,10 @@ void try_to_migrate(struct folio *folio, enum t=
tu_flags flags)
>
>  	/*
>  	 * Migration always ignores mlock and only supports TTU_RMAP_LOCKED a=
nd
> -	 * TTU_SPLIT_HUGE_PMD and TTU_SYNC flags.
> +	 * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags.
>  	 */
>  	if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD |
> -					TTU_SYNC)))
> +					TTU_SYNC | TTU_BATCH_FLUSH)))
>  		return;
>
>  	if (folio_is_zone_device(folio) &&
> -- =

> 2.35.1

Everything else looks good to me. Reviewed-by: Zi Yan <ziy@nvidia.com>

--
Best Regards,
Yan, Zi

--=_MailMate_2696EDC7-7B4A-45D6-A749-E4523F28BB1D_=
Content-Description: OpenPGP digital signature
Content-Disposition: attachment; filename=signature.asc
Content-Type: application/pgp-signature; name=signature.asc

-----BEGIN PGP SIGNATURE-----
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=cRX8
-----END PGP SIGNATURE-----

--=_MailMate_2696EDC7-7B4A-45D6-A749-E4523F28BB1D_=--