From mboxrd@z Thu Jan 1 00:00:00 1970
Return-Path: <dev-bounces@dpdk.org>
Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124])
by inbox.dpdk.org (Postfix) with ESMTP id 0A76FA0A0F;
Wed, 30 Jun 2021 13:05:06 +0200 (CEST)
Received: from [217.70.189.124] (localhost [127.0.0.1])
by mails.dpdk.org (Postfix) with ESMTP id 8AA4440141;
Wed, 30 Jun 2021 13:05:05 +0200 (CEST)
Received: from mga14.intel.com (mga14.intel.com [192.55.52.115])
by mails.dpdk.org (Postfix) with ESMTP id 710FA40040
for <dev@dpdk.org>; Wed, 30 Jun 2021 13:05:03 +0200 (CEST)
X-IronPort-AV: E=McAfee;i="6200,9189,10030"; a="208149467"
X-IronPort-AV: E=Sophos;i="5.83,311,1616482800"; d="scan'208";a="208149467"
Received: from fmsmga005.fm.intel.com ([10.253.24.32])
by fmsmga103.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384;
30 Jun 2021 04:05:02 -0700
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.83,311,1616482800"; d="scan'208";a="644044924"
Received: from orsmsx602.amr.corp.intel.com ([10.22.229.15])
by fmsmga005.fm.intel.com with ESMTP; 30 Jun 2021 04:05:02 -0700
Received: from orsmsx611.amr.corp.intel.com (10.22.229.24) by
ORSMSX602.amr.corp.intel.com (10.22.229.15) with Microsoft SMTP Server
(version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id
15.1.2242.4; Wed, 30 Jun 2021 04:05:01 -0700
Received: from ORSEDG602.ED.cps.intel.com (10.7.248.7) by
orsmsx611.amr.corp.intel.com (10.22.229.24) with Microsoft SMTP Server
(version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2242.4
via Frontend Transport; Wed, 30 Jun 2021 04:05:01 -0700
Received: from NAM10-MW2-obe.outbound.protection.outlook.com (104.47.55.100)
by edgegateway.intel.com (134.134.137.103) with Microsoft SMTP Server
(version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id
15.1.2242.4; Wed, 30 Jun 2021 04:04:59 -0700
ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none;
b=bQkmVLNE9OAVaT/jyZhBJSMyDeRhRJWsREtSNRGxyTeFkc9p9iXlKGa6NBVGee0fYCe/U9tWOcMJvbTB2ixo+OIcZWsvndDAvnIoF9rdOJw1as5HUs+CVGXOFWQXijS+qN0KN8GyFQElClre1PSrMjCRJNC430GxDwOuFqVhuhlMtDYli9SZPgM2dbqbkji7a2+VFFxEMz1Fe22xLce5BAeU98xBiy78bMKg3UlNJXE46ckNTVhr8aJKkSj9i9Jpav0dCgGPYXaxGcCNuzd5RLBymGmzCKy9h4rdgEefWXbcZY/A+OD9kZehZ2qgxb1I17WDKhQ5jBsE4vnMPlgAsg==
ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com;
s=arcselector9901;
h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck;
bh=kn84wyi7NYUg6LQ7i3SZS4FzEWMmrG6IAIz189LXRro=;
b=BjEvFJVrZW8xMf3+pwBM80eVHpxJ84BtmWZ6KqJU0FHfvuTX+pifYN+j9v3KpAFc4tV8OdBwJu7eK0OpenkXg6wS2cyFx26BMHfvXuwl4Kk5HfOVXlenE+D+8QASCUZPb6XHGboK6mrAycM6+phdOurNLwZVblL2IwrFJqR7XfxrgDsAmgUDvYnOFFdDcUzpRfD2BwUyuSMEuvkCa7n8UhCJpasZnI8PaIXyVZdvHqBUaK+bTdT6DQbeaE0JRt+bd/53/uNDj11lw9eKOxiqtoPT2M+rgtx/V4K6LHr2byeoDsMn1en+oEN3ftqO0VRN0C2JRtW5Mj7YGlliqJbeXA==
ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass
smtp.mailfrom=intel.com; dmarc=pass action=none header.from=intel.com;
dkim=pass header.d=intel.com; arc=none
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=intel.onmicrosoft.com;
s=selector2-intel-onmicrosoft-com;
h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck;
bh=kn84wyi7NYUg6LQ7i3SZS4FzEWMmrG6IAIz189LXRro=;
b=QHCuZbysVlad+If7xmcWMq26XyAtm5yLyGOM5ta1OY5LM6Nxdd7mPjyzagbmxEdQSiFlICB9mj8//gZUQuknL7wfaAIYO3IFLWAl8FUjviymXlWrWEZgHt0RKj9QDJqI1doVczLEKhT90uzhQE/1JEkx5X4V0kVU3sf4j9W7070=
Received: from DM6PR11MB4491.namprd11.prod.outlook.com (2603:10b6:5:204::19)
by DM5PR11MB2044.namprd11.prod.outlook.com (2603:10b6:3:10::23) with
Microsoft SMTP Server (version=TLS1_2,
cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.4287.22; Wed, 30 Jun
2021 11:04:57 +0000
Received: from DM6PR11MB4491.namprd11.prod.outlook.com
([fe80::7dc4:66b0:f76b:6d48]) by DM6PR11MB4491.namprd11.prod.outlook.com
([fe80::7dc4:66b0:f76b:6d48%7]) with mapi id 15.20.4264.026; Wed, 30 Jun 2021
11:04:57 +0000
From: "Ananyev, Konstantin" <konstantin.ananyev@intel.com>
To: "Burakov, Anatoly" <anatoly.burakov@intel.com>, "dev@dpdk.org"
<dev@dpdk.org>, "Hunt, David" <david.hunt@intel.com>
CC: "Loftus, Ciara" <ciara.loftus@intel.com>
Thread-Topic: [PATCH v5 5/7] power: support callbacks for multiple Rx queues
Thread-Index: AQHXbP5Dd91lY61/Z0CNJj1Qy++4O6ssW/Zw
Date: Wed, 30 Jun 2021 11:04:57 +0000
Message-ID: <DM6PR11MB4491E4F148267B17FDE2F3BC9A019@DM6PR11MB4491.namprd11.prod.outlook.com>
References: <cover.1624895595.git.anatoly.burakov@intel.com>
<cover.1624981669.git.anatoly.burakov@intel.com>
<8f5d030a77aa2f0e95e9680cb911b4e8db30c879.1624981670.git.anatoly.burakov@intel.com>
In-Reply-To: <8f5d030a77aa2f0e95e9680cb911b4e8db30c879.1624981670.git.anatoly.burakov@intel.com>
Accept-Language: en-GB, en-US
Content-Language: en-US
X-MS-Has-Attach:
X-MS-TNEF-Correlator:
dlp-product: dlpe-windows
dlp-reaction: no-action
dlp-version: 11.5.1.3
authentication-results: intel.com; dkim=none (message not signed)
header.d=none;intel.com; dmarc=none action=none header.from=intel.com;
x-originating-ip: [109.255.184.192]
x-ms-publictraffictype: Email
x-ms-office365-filtering-correlation-id: 3d4d67b0-3f8d-4ad1-49cd-08d93bb6e5af
x-ms-traffictypediagnostic: DM5PR11MB2044:
x-ld-processed: 46c98d88-e344-4ed4-8496-4ed7712e255d,ExtAddr
x-ms-exchange-transport-forked: True
x-microsoft-antispam-prvs: <DM5PR11MB2044F0FB87912788C4D92D609A019@DM5PR11MB2044.namprd11.prod.outlook.com>
x-ms-oob-tlc-oobclassifiers: OLM:10000;
x-ms-exchange-senderadcheck: 1
x-microsoft-antispam: BCL:0;
x-microsoft-antispam-message-info: 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
x-forefront-antispam-report: CIP:255.255.255.255; CTRY:; LANG:en; SCL:1; SRV:;
IPV:NLI; SFV:NSPM; H:DM6PR11MB4491.namprd11.prod.outlook.com; PTR:; CAT:NONE;
SFS:(39860400002)(366004)(376002)(136003)(396003)(346002)(52536014)(8676002)(7696005)(83380400001)(26005)(5660300002)(55236004)(38100700002)(66476007)(66556008)(86362001)(8936002)(66446008)(64756008)(71200400001)(6506007)(186003)(122000001)(316002)(76116006)(66946007)(478600001)(110136005)(30864003)(4326008)(107886003)(6636002)(33656002)(2906002)(55016002)(9686003)(559001)(579004);
DIR:OUT; SFP:1102;
x-ms-exchange-antispam-messagedata-chunkcount: 1
x-ms-exchange-antispam-messagedata-0: =?us-ascii?Q?BK2xC9tagP/E6GgB2UhIlNooQyRvotbJcFjTXs8JPiKA7Qnfl5UPsw+C/vD2?=
=?us-ascii?Q?Muy+Mp32Llp9C8dNhMkAoCL41Xs994/VUL8u6jzw/1gDoRuyzyDs2KZ6FTp7?=
=?us-ascii?Q?H80y5/2T/GHocN3o3O7YZFtOuiaE7xt0Hc18hNDWdci67UJWM/hH5Tb4HT2y?=
=?us-ascii?Q?vS8asX61kNVsUTLwrDLerF4OpIdZrUVy3+uFE2T5WqyHOm/xKEykgnyCpnBn?=
=?us-ascii?Q?sXP3JvGbWe7UrNt4E11Gls4vh31QsxHfHGE1IGh634m2LaQY7Qx/sr+brqn+?=
=?us-ascii?Q?+cbncfbVJtjWgRlpebBTWX4DOEZIgBYH/s64yYFwEyIse9JAaEAxhm9KKpXt?=
=?us-ascii?Q?txzNNIN4gjwkC3ubuGXw638F8hqRAGmyfV+erL0Mw6a4aU0LkdAQj5mbkPDx?=
=?us-ascii?Q?Mmm8Zpdz1Jo0jAIzwzZRSFp9ct98BQKXRhlzsMQ1V2pdpXtcWl4qo9Ljk2Tx?=
=?us-ascii?Q?8N3KdP9298937DZYt3d8I63afXLbUBxs5+5yN70OIaCHm0gU/dpceBykGEyb?=
=?us-ascii?Q?X1IiXVWM3JWZ4iZx3i2wlVRrbwtUXcEuJ7DK1/DxJDF++ZCn6voam9a7DQm7?=
=?us-ascii?Q?AngxXrvFGrURag+mYwJa/78Orvpg0Wm9d5643Amnbsf9E2qe+ij6JMDKCWKB?=
=?us-ascii?Q?1sa9II0zJioX4hHw6oZ89NjQ2VOH96hcDcWE3kSGWibiSKzqw73nVYBMnxlw?=
=?us-ascii?Q?ojHGVHwJ3uCiLLlNCt4NuEAaPoPO7vPPfazyeKk7cbxLr7FQToPM3BnAkRaX?=
=?us-ascii?Q?t6FuOQAfhZmfHtD74Oe6gyvx8mSStsYydCbCVM9UNJumEQlra5eANX8DtvKx?=
=?us-ascii?Q?SqgA4mpYuorLwFHc/KRm/ibligYdXGV9a94YnWINy2L2r7+0TSnBqNBEyM2E?=
=?us-ascii?Q?uSKf5+rbNAAR+xD0wttFesFyAXwt8a0USul9kFr7mXGrKuYymAK1dfj5uACg?=
=?us-ascii?Q?GU6OCoRZ03KDt7c6EysW2HGoHAE0EDgeQizzrgUDE+zUMkUnaqesVNhq+sMn?=
=?us-ascii?Q?CcfFLHl49yEKFMPFMPmF4JiRDkJ2SACzYH2RD2Css5eCL/PVEqj2+VSMZidL?=
=?us-ascii?Q?v/TpMQ0aACAteGWl8JZsz99lryLY8VXDMvOelIII4ARcGUJh2B9TL7fSX5jC?=
=?us-ascii?Q?wPKFYbs1JPoCszGfqv7GUygXFBCRK0NF299WgPmX832puiaW5FTuz+5gILSt?=
=?us-ascii?Q?oFDQoY3EA/yjh/O3M9acXG4VXGLYnG10dOkEPQ5K9okxV22W8zLgHhvNq0uE?=
=?us-ascii?Q?ohxNLL6NgPlTJBzSU8/yO6TJbhCUqA6wLPQGq/7wJISaEsKYd3KmXNeEumEz?=
=?us-ascii?Q?MTWfOegBr2jT45lwZBGVJfjq?=
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-AuthSource: DM6PR11MB4491.namprd11.prod.outlook.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 3d4d67b0-3f8d-4ad1-49cd-08d93bb6e5af
X-MS-Exchange-CrossTenant-originalarrivaltime: 30 Jun 2021 11:04:57.2103 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 46c98d88-e344-4ed4-8496-4ed7712e255d
X-MS-Exchange-CrossTenant-mailboxtype: HOSTED
X-MS-Exchange-CrossTenant-userprincipalname: LaOFvfQi3Qfi7uQBdwp3/B9e2yzXBcuqxWCXJIpBUrBxjQR7soYtFC2xdIsfMBZN72VyEp8Qz9XUOZOfKf2DAmptQusPBpVLo254jlxvl9g=
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM5PR11MB2044
X-OriginatorOrg: intel.com
Subject: Re: [dpdk-dev] [PATCH v5 5/7] power: support callbacks for multiple
Rx queues
X-BeenThere: dev@dpdk.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: DPDK patches and discussions <dev.dpdk.org>
List-Unsubscribe: <https://mails.dpdk.org/options/dev>,
<mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://mails.dpdk.org/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <https://mails.dpdk.org/listinfo/dev>,
<mailto:dev-request@dpdk.org?subject=subscribe>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>
=20
> Currently, there is a hard limitation on the PMD power management
> support that only allows it to support a single queue per lcore. This is
> not ideal as most DPDK use cases will poll multiple queues per core.
>=20
> The PMD power management mechanism relies on ethdev Rx callbacks, so it
> is very difficult to implement such support because callbacks are
> effectively stateless and have no visibility into what the other ethdev
> devices are doing. This places limitations on what we can do within the
> framework of Rx callbacks, but the basics of this implementation are as
> follows:
>=20
> - Replace per-queue structures with per-lcore ones, so that any device
> polled from the same lcore can share data
> - Any queue that is going to be polled from a specific lcore has to be
> added to the list of queues to poll, so that the callback is aware of
> other queues being polled by the same lcore
> - Both the empty poll counter and the actual power saving mechanism is
> shared between all queues polled on a particular lcore, and is only
> activated when all queues in the list were polled and were determined
> to have no traffic.
> - The limitation on UMWAIT-based polling is not removed because UMWAIT
> is incapable of monitoring more than one address.
>=20
> Also, while we're at it, update and improve the docs.
>=20
> Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
> ---
>=20
> Notes:
> v5:
> - Remove the "power save queue" API and replace it with mechanism sug=
gested by
> Konstantin
>=20
> v3:
> - Move the list of supported NICs to NIC feature table
>=20
> v2:
> - Use a TAILQ for queues instead of a static array
> - Address feedback from Konstantin
> - Add additional checks for stopped queues
>=20
> doc/guides/nics/features.rst | 10 +
> doc/guides/prog_guide/power_man.rst | 65 ++--
> doc/guides/rel_notes/release_21_08.rst | 3 +
> lib/power/rte_power_pmd_mgmt.c | 431 ++++++++++++++++++-------
> 4 files changed, 373 insertions(+), 136 deletions(-)
>=20
> diff --git a/doc/guides/nics/features.rst b/doc/guides/nics/features.rst
> index 403c2b03a3..a96e12d155 100644
> --- a/doc/guides/nics/features.rst
> +++ b/doc/guides/nics/features.rst
> @@ -912,6 +912,16 @@ Supports to get Rx/Tx packet burst mode information.
> * **[implements] eth_dev_ops**: ``rx_burst_mode_get``, ``tx_burst_mode_g=
et``.
> * **[related] API**: ``rte_eth_rx_burst_mode_get()``, ``rte_eth_tx_burst=
_mode_get()``.
>=20
> +.. _nic_features_get_monitor_addr:
> +
> +PMD power management using monitor addresses
> +--------------------------------------------
> +
> +Supports getting a monitoring condition to use together with Ethernet PM=
D power
> +management (see :doc:`../prog_guide/power_man` for more details).
> +
> +* **[implements] eth_dev_ops**: ``get_monitor_addr``
> +
> .. _nic_features_other:
>=20
> Other dev ops not represented by a Feature
> diff --git a/doc/guides/prog_guide/power_man.rst b/doc/guides/prog_guide/=
power_man.rst
> index c70ae128ac..ec04a72108 100644
> --- a/doc/guides/prog_guide/power_man.rst
> +++ b/doc/guides/prog_guide/power_man.rst
> @@ -198,34 +198,41 @@ Ethernet PMD Power Management API
> Abstract
> ~~~~~~~~
>=20
> -Existing power management mechanisms require developers
> -to change application design or change code to make use of it.
> -The PMD power management API provides a convenient alternative
> -by utilizing Ethernet PMD RX callbacks,
> -and triggering power saving whenever empty poll count reaches a certain =
number.
> -
> -Monitor
> - This power saving scheme will put the CPU into optimized power state
> - and use the ``rte_power_monitor()`` function
> - to monitor the Ethernet PMD RX descriptor address,
> - and wake the CPU up whenever there's new traffic.
> -
> -Pause
> - This power saving scheme will avoid busy polling
> - by either entering power-optimized sleep state
> - with ``rte_power_pause()`` function,
> - or, if it's not available, use ``rte_pause()``.
> -
> -Frequency scaling
> - This power saving scheme will use ``librte_power`` library
> - functionality to scale the core frequency up/down
> - depending on traffic volume.
> -
> -.. note::
> -
> - Currently, this power management API is limited to mandatory mapping
> - of 1 queue to 1 core (multiple queues are supported,
> - but they must be polled from different cores).
> +Existing power management mechanisms require developers to change applic=
ation
> +design or change code to make use of it. The PMD power management API pr=
ovides a
> +convenient alternative by utilizing Ethernet PMD RX callbacks, and trigg=
ering
> +power saving whenever empty poll count reaches a certain number.
> +
> +* Monitor
> + This power saving scheme will put the CPU into optimized power state =
and
> + monitor the Ethernet PMD RX descriptor address, waking the CPU up whe=
never
> + there's new traffic. Support for this scheme may not be available on =
all
> + platforms, and further limitations may apply (see below).
> +
> +* Pause
> + This power saving scheme will avoid busy polling by either entering
> + power-optimized sleep state with ``rte_power_pause()`` function, or, =
if it's
> + not supported by the underlying platform, use ``rte_pause()``.
> +
> +* Frequency scaling
> + This power saving scheme will use ``librte_power`` library functional=
ity to
> + scale the core frequency up/down depending on traffic volume.
> +
> +The "monitor" mode is only supported in the following configurations and=
scenarios:
> +
> +* If ``rte_cpu_get_intrinsics_support()`` function indicates that
> + ``rte_power_monitor()`` is supported by the platform, then monitoring =
will be
> + limited to a mapping of 1 core 1 queue (thus, each Rx queue will have =
to be
> + monitored from a different lcore).
> +
> +* If ``rte_cpu_get_intrinsics_support()`` function indicates that the
> + ``rte_power_monitor()`` function is not supported, then monitor mode w=
ill not
> + be supported.
> +
> +* Not all Ethernet drivers support monitoring, even if the underlying
> + platform may support the necessary CPU instructions. Please refer to
> + :doc:`../nics/overview` for more information.
> +
>=20
> API Overview for Ethernet PMD Power Management
> ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
> @@ -242,3 +249,5 @@ References
>=20
> * The :doc:`../sample_app_ug/vm_power_management`
> chapter in the :doc:`../sample_app_ug/index` section.
> +
> +* The :doc:`../nics/overview` chapter in the :doc:`../nics/index` sect=
ion
> diff --git a/doc/guides/rel_notes/release_21_08.rst b/doc/guides/rel_note=
s/release_21_08.rst
> index f015c509fc..3926d45ef8 100644
> --- a/doc/guides/rel_notes/release_21_08.rst
> +++ b/doc/guides/rel_notes/release_21_08.rst
> @@ -57,6 +57,9 @@ New Features
>=20
> * eal: added ``rte_power_monitor_multi`` to support waiting for multiple=
events.
>=20
> +* rte_power: The experimental PMD power management API now supports mana=
ging
> + multiple Ethernet Rx queues per lcore.
> +
>=20
> Removed Items
> -------------
> diff --git a/lib/power/rte_power_pmd_mgmt.c b/lib/power/rte_power_pmd_mgm=
t.c
> index 9b95cf1794..fccfd236c2 100644
> --- a/lib/power/rte_power_pmd_mgmt.c
> +++ b/lib/power/rte_power_pmd_mgmt.c
> @@ -33,18 +33,96 @@ enum pmd_mgmt_state {
> PMD_MGMT_ENABLED
> };
>=20
> -struct pmd_queue_cfg {
> +union queue {
> + uint32_t val;
> + struct {
> + uint16_t portid;
> + uint16_t qid;
> + };
> +};
> +
> +struct queue_list_entry {
> + TAILQ_ENTRY(queue_list_entry) next;
> + union queue queue;
> + uint64_t n_empty_polls;
> + const struct rte_eth_rxtx_callback *cb;
> +};
> +
> +struct pmd_core_cfg {
> + TAILQ_HEAD(queue_list_head, queue_list_entry) head;
> + /**< List of queues associated with this lcore */
> + size_t n_queues;
> + /**< How many queues are in the list? */
> volatile enum pmd_mgmt_state pwr_mgmt_state;
> /**< State of power management for this queue */
> enum rte_power_pmd_mgmt_type cb_mode;
> /**< Callback mode for this queue */
> - const struct rte_eth_rxtx_callback *cur_cb;
> - /**< Callback instance */
> - uint64_t empty_poll_stats;
> - /**< Number of empty polls */
> + uint64_t n_queues_ready_to_sleep;
> + /**< Number of queues ready to enter power optimized state */
> } __rte_cache_aligned;
> +static struct pmd_core_cfg lcore_cfgs[RTE_MAX_LCORE];
>=20
> -static struct pmd_queue_cfg port_cfg[RTE_MAX_ETHPORTS][RTE_MAX_QUEUES_PE=
R_PORT];
> +static inline bool
> +queue_equal(const union queue *l, const union queue *r)
> +{
> + return l->val =3D=3D r->val;
> +}
> +
> +static inline void
> +queue_copy(union queue *dst, const union queue *src)
> +{
> + dst->val =3D src->val;
> +}
> +
> +static struct queue_list_entry *
> +queue_list_find(const struct pmd_core_cfg *cfg, const union queue *q)
> +{
> + struct queue_list_entry *cur;
> +
> + TAILQ_FOREACH(cur, &cfg->head, next) {
> + if (queue_equal(&cur->queue, q))
> + return cur;
> + }
> + return NULL;
> +}
> +
> +static int
> +queue_list_add(struct pmd_core_cfg *cfg, const union queue *q)
> +{
> + struct queue_list_entry *qle;
> +
> + /* is it already in the list? */
> + if (queue_list_find(cfg, q) !=3D NULL)
> + return -EEXIST;
> +
> + qle =3D malloc(sizeof(*qle));
> + if (qle =3D=3D NULL)
> + return -ENOMEM;
> + memset(qle, 0, sizeof(*qle));
> +
> + queue_copy(&qle->queue, q);
> + TAILQ_INSERT_TAIL(&cfg->head, qle, next);
> + cfg->n_queues++;
> + qle->n_empty_polls =3D 0;
> +
> + return 0;
> +}
> +
> +static struct queue_list_entry *
> +queue_list_take(struct pmd_core_cfg *cfg, const union queue *q)
> +{
> + struct queue_list_entry *found;
> +
> + found =3D queue_list_find(cfg, q);
> + if (found =3D=3D NULL)
> + return NULL;
> +
> + TAILQ_REMOVE(&cfg->head, found, next);
> + cfg->n_queues--;
> +
> + /* freeing is responsibility of the caller */
> + return found;
> +}
>=20
> static void
> calc_tsc(void)
> @@ -74,21 +152,56 @@ calc_tsc(void)
> }
> }
>=20
> +static inline void
> +queue_reset(struct pmd_core_cfg *cfg, struct queue_list_entry *qcfg)
> +{
> + /* reset empty poll counter for this queue */
> + qcfg->n_empty_polls =3D 0;
> + /* reset the sleep counter too */
> + cfg->n_queues_ready_to_sleep =3D 0;
> +}
> +
> +static inline bool
> +queue_can_sleep(struct pmd_core_cfg *cfg, struct queue_list_entry *qcfg)
> +{
> + /* this function is called - that means we have an empty poll */
> + qcfg->n_empty_polls++;
> +
> + /* if we haven't reached threshold for empty polls, we can't sleep */
> + if (qcfg->n_empty_polls <=3D EMPTYPOLL_MAX)
> + return false;
> +
> + /* we're ready to sleep */
> + cfg->n_queues_ready_to_sleep++;
> +
> + return true;
> +}
> +
> +static inline bool
> +lcore_can_sleep(struct pmd_core_cfg *cfg)
> +{
> + /* are all queues ready to sleep? */
> + if (cfg->n_queues_ready_to_sleep !=3D cfg->n_queues)
> + return false;
> +
> + /* we've reached an iteration where we can sleep, reset sleep counter *=
/
> + cfg->n_queues_ready_to_sleep =3D 0;
> +
> + return true;
> +}
As I can see it a slightly modified one from what was discussed.
I understand that it seems simpler, but I think there are some problems wit=
h it:
- each queue can be counted more than once at lcore_cfg->n_queues_ready_to_=
sleep
- queues n_empty_polls are not reset after sleep().
To illustrate the problem, let say we have 2 queues, and at some moment we =
have:
q0.n_empty_polls =3D=3D EMPTYPOLL_MAX + 1
q1.n_empty_polls =3D=3D EMPTYPOLL_MAX + 1
cfg->n_queues_ready_to_sleep =3D=3D 2
So lcore_can_sleep() returns 'true' and sets:
cfg->n_queues_ready_to_sleep =3D=3D 0
Now, after sleep():
q0.n_empty_polls =3D=3D EMPTYPOLL_MAX + 1
q1.n_empty_polls =3D=3D EMPTYPOLL_MAX + 1
So after:
queue_can_sleep(q0);
queue_can_sleep(q1);
will have:
cfg->n_queues_ready_to_sleep =3D=3D 2=20
again, and we'll go to another sleep after just one rx_burst() attempt for =
each queue.
> +
> static uint16_t
> clb_umwait(uint16_t port_id, uint16_t qidx, struct rte_mbuf **pkts __rte=
_unused,
> - uint16_t nb_rx, uint16_t max_pkts __rte_unused,
> - void *addr __rte_unused)
> + uint16_t nb_rx, uint16_t max_pkts __rte_unused, void *arg)
> {
> + struct queue_list_entry *queue_conf =3D arg;
>=20
> - struct pmd_queue_cfg *q_conf;
> -
> - q_conf =3D &port_cfg[port_id][qidx];
> -
> + /* this callback can't do more than one queue, omit multiqueue logic */
> if (unlikely(nb_rx =3D=3D 0)) {
> - q_conf->empty_poll_stats++;
> - if (unlikely(q_conf->empty_poll_stats > EMPTYPOLL_MAX)) {
> + queue_conf->n_empty_polls++;
> + if (unlikely(queue_conf->n_empty_polls > EMPTYPOLL_MAX)) {
> struct rte_power_monitor_cond pmc;
> - uint16_t ret;
> + int ret;
>=20
> /* use monitoring condition to sleep */
> ret =3D rte_eth_get_monitor_addr(port_id, qidx,
> @@ -97,60 +210,77 @@ clb_umwait(uint16_t port_id, uint16_t qidx, struct r=
te_mbuf **pkts __rte_unused,
> rte_power_monitor(&pmc, UINT64_MAX);
> }
> } else
> - q_conf->empty_poll_stats =3D 0;
> + queue_conf->n_empty_polls =3D 0;
>=20
> return nb_rx;
> }
>=20
> static uint16_t
> -clb_pause(uint16_t port_id, uint16_t qidx, struct rte_mbuf **pkts __rte_=
unused,
> - uint16_t nb_rx, uint16_t max_pkts __rte_unused,
> - void *addr __rte_unused)
> +clb_pause(uint16_t port_id __rte_unused, uint16_t qidx __rte_unused,
> + struct rte_mbuf **pkts __rte_unused, uint16_t nb_rx,
> + uint16_t max_pkts __rte_unused, void *arg)
> {
> - struct pmd_queue_cfg *q_conf;
> + const unsigned int lcore =3D rte_lcore_id();
> + struct queue_list_entry *queue_conf =3D arg;
> + struct pmd_core_cfg *lcore_conf;
> + const bool empty =3D nb_rx =3D=3D 0;
>=20
> - q_conf =3D &port_cfg[port_id][qidx];
> + lcore_conf =3D &lcore_cfgs[lcore];
>=20
> - if (unlikely(nb_rx =3D=3D 0)) {
> - q_conf->empty_poll_stats++;
> - /* sleep for 1 microsecond */
> - if (unlikely(q_conf->empty_poll_stats > EMPTYPOLL_MAX)) {
> - /* use tpause if we have it */
> - if (global_data.intrinsics_support.power_pause) {
> - const uint64_t cur =3D rte_rdtsc();
> - const uint64_t wait_tsc =3D
> - cur + global_data.tsc_per_us;
> - rte_power_pause(wait_tsc);
> - } else {
> - uint64_t i;
> - for (i =3D 0; i < global_data.pause_per_us; i++)
> - rte_pause();
> - }
> + if (likely(!empty))
> + /* early exit */
> + queue_reset(lcore_conf, queue_conf);
> + else {
> + /* can this queue sleep? */
> + if (!queue_can_sleep(lcore_conf, queue_conf))
> + return nb_rx;
> +
> + /* can this lcore sleep? */
> + if (!lcore_can_sleep(lcore_conf))
> + return nb_rx;
> +
> + /* sleep for 1 microsecond, use tpause if we have it */
> + if (global_data.intrinsics_support.power_pause) {
> + const uint64_t cur =3D rte_rdtsc();
> + const uint64_t wait_tsc =3D
> + cur + global_data.tsc_per_us;
> + rte_power_pause(wait_tsc);
> + } else {
> + uint64_t i;
> + for (i =3D 0; i < global_data.pause_per_us; i++)
> + rte_pause();
> }
> - } else
> - q_conf->empty_poll_stats =3D 0;
> + }
>=20
> return nb_rx;
> }
>=20
> static uint16_t
> -clb_scale_freq(uint16_t port_id, uint16_t qidx,
> +clb_scale_freq(uint16_t port_id __rte_unused, uint16_t qidx __rte_unused=
,
> struct rte_mbuf **pkts __rte_unused, uint16_t nb_rx,
> - uint16_t max_pkts __rte_unused, void *_ __rte_unused)
> + uint16_t max_pkts __rte_unused, void *arg)
> {
> - struct pmd_queue_cfg *q_conf;
> + const unsigned int lcore =3D rte_lcore_id();
> + const bool empty =3D nb_rx =3D=3D 0;
> + struct pmd_core_cfg *lcore_conf =3D &lcore_cfgs[lcore];
> + struct queue_list_entry *queue_conf =3D arg;
>=20
> - q_conf =3D &port_cfg[port_id][qidx];
> + if (likely(!empty)) {
> + /* early exit */
> + queue_reset(lcore_conf, queue_conf);
>=20
> - if (unlikely(nb_rx =3D=3D 0)) {
> - q_conf->empty_poll_stats++;
> - if (unlikely(q_conf->empty_poll_stats > EMPTYPOLL_MAX))
> - /* scale down freq */
> - rte_power_freq_min(rte_lcore_id());
> - } else {
> - q_conf->empty_poll_stats =3D 0;
> - /* scale up freq */
> + /* scale up freq immediately */
> rte_power_freq_max(rte_lcore_id());
> + } else {
> + /* can this queue sleep? */
> + if (!queue_can_sleep(lcore_conf, queue_conf))
> + return nb_rx;
> +
> + /* can this lcore sleep? */
> + if (!lcore_can_sleep(lcore_conf))
> + return nb_rx;
> +
> + rte_power_freq_min(rte_lcore_id());
> }
>=20
> return nb_rx;
> @@ -167,11 +297,80 @@ queue_stopped(const uint16_t port_id, const uint16_=
t queue_id)
> return qinfo.queue_state =3D=3D RTE_ETH_QUEUE_STATE_STOPPED;
> }
>=20
> +static int
> +cfg_queues_stopped(struct pmd_core_cfg *queue_cfg)
> +{
> + const struct queue_list_entry *entry;
> +
> + TAILQ_FOREACH(entry, &queue_cfg->head, next) {
> + const union queue *q =3D &entry->queue;
> + int ret =3D queue_stopped(q->portid, q->qid);
> + if (ret !=3D 1)
> + return ret;
> + }
> + return 1;
> +}
> +
> +static int
> +check_scale(unsigned int lcore)
> +{
> + enum power_management_env env;
> +
> + /* only PSTATE and ACPI modes are supported */
> + if (!rte_power_check_env_supported(PM_ENV_ACPI_CPUFREQ) &&
> + !rte_power_check_env_supported(PM_ENV_PSTATE_CPUFREQ)) {
> + RTE_LOG(DEBUG, POWER, "Neither ACPI nor PSTATE modes are supported\n")=
;
> + return -ENOTSUP;
> + }
> + /* ensure we could initialize the power library */
> + if (rte_power_init(lcore))
> + return -EINVAL;
> +
> + /* ensure we initialized the correct env */
> + env =3D rte_power_get_env();
> + if (env !=3D PM_ENV_ACPI_CPUFREQ && env !=3D PM_ENV_PSTATE_CPUFREQ) {
> + RTE_LOG(DEBUG, POWER, "Neither ACPI nor PSTATE modes were initialized\=
n");
> + return -ENOTSUP;
> + }
> +
> + /* we're done */
> + return 0;
> +}
> +
> +static int
> +check_monitor(struct pmd_core_cfg *cfg, const union queue *qdata)
> +{
> + struct rte_power_monitor_cond dummy;
> +
> + /* check if rte_power_monitor is supported */
> + if (!global_data.intrinsics_support.power_monitor) {
> + RTE_LOG(DEBUG, POWER, "Monitoring intrinsics are not supported\n");
> + return -ENOTSUP;
> + }
> +
> + if (cfg->n_queues > 0) {
> + RTE_LOG(DEBUG, POWER, "Monitoring multiple queues is not supported\n")=
;
> + return -ENOTSUP;
> + }
> +
> + /* check if the device supports the necessary PMD API */
> + if (rte_eth_get_monitor_addr(qdata->portid, qdata->qid,
> + &dummy) =3D=3D -ENOTSUP) {
> + RTE_LOG(DEBUG, POWER, "The device does not support rte_eth_get_monitor=
_addr\n");
> + return -ENOTSUP;
> + }
> +
> + /* we're done */
> + return 0;
> +}
> +
> int
> rte_power_ethdev_pmgmt_queue_enable(unsigned int lcore_id, uint16_t port=
_id,
> uint16_t queue_id, enum rte_power_pmd_mgmt_type mode)
> {
> - struct pmd_queue_cfg *queue_cfg;
> + const union queue qdata =3D {.portid =3D port_id, .qid =3D queue_id};
> + struct pmd_core_cfg *lcore_cfg;
> + struct queue_list_entry *queue_cfg;
> struct rte_eth_dev_info info;
> rte_rx_callback_fn clb;
> int ret;
> @@ -202,9 +401,19 @@ rte_power_ethdev_pmgmt_queue_enable(unsigned int lco=
re_id, uint16_t port_id,
> goto end;
> }
>=20
> - queue_cfg =3D &port_cfg[port_id][queue_id];
> + lcore_cfg =3D &lcore_cfgs[lcore_id];
>=20
> - if (queue_cfg->pwr_mgmt_state !=3D PMD_MGMT_DISABLED) {
> + /* check if other queues are stopped as well */
> + ret =3D cfg_queues_stopped(lcore_cfg);
> + if (ret !=3D 1) {
> + /* error means invalid queue, 0 means queue wasn't stopped */
> + ret =3D ret < 0 ? -EINVAL : -EBUSY;
> + goto end;
> + }
> +
> + /* if callback was already enabled, check current callback type */
> + if (lcore_cfg->pwr_mgmt_state !=3D PMD_MGMT_DISABLED &&
> + lcore_cfg->cb_mode !=3D mode) {
> ret =3D -EINVAL;
> goto end;
> }
> @@ -214,53 +423,20 @@ rte_power_ethdev_pmgmt_queue_enable(unsigned int lc=
ore_id, uint16_t port_id,
>=20
> switch (mode) {
> case RTE_POWER_MGMT_TYPE_MONITOR:
> - {
> - struct rte_power_monitor_cond dummy;
> -
> - /* check if rte_power_monitor is supported */
> - if (!global_data.intrinsics_support.power_monitor) {
> - RTE_LOG(DEBUG, POWER, "Monitoring intrinsics are not supported\n");
> - ret =3D -ENOTSUP;
> + /* check if we can add a new queue */
> + ret =3D check_monitor(lcore_cfg, &qdata);
> + if (ret < 0)
> goto end;
> - }
>=20
> - /* check if the device supports the necessary PMD API */
> - if (rte_eth_get_monitor_addr(port_id, queue_id,
> - &dummy) =3D=3D -ENOTSUP) {
> - RTE_LOG(DEBUG, POWER, "The device does not support rte_eth_get_monito=
r_addr\n");
> - ret =3D -ENOTSUP;
> - goto end;
> - }
> clb =3D clb_umwait;
> break;
> - }
> case RTE_POWER_MGMT_TYPE_SCALE:
> - {
> - enum power_management_env env;
> - /* only PSTATE and ACPI modes are supported */
> - if (!rte_power_check_env_supported(PM_ENV_ACPI_CPUFREQ) &&
> - !rte_power_check_env_supported(
> - PM_ENV_PSTATE_CPUFREQ)) {
> - RTE_LOG(DEBUG, POWER, "Neither ACPI nor PSTATE modes are supported\n"=
);
> - ret =3D -ENOTSUP;
> + /* check if we can add a new queue */
> + ret =3D check_scale(lcore_id);
> + if (ret < 0)
> goto end;
> - }
> - /* ensure we could initialize the power library */
> - if (rte_power_init(lcore_id)) {
> - ret =3D -EINVAL;
> - goto end;
> - }
> - /* ensure we initialized the correct env */
> - env =3D rte_power_get_env();
> - if (env !=3D PM_ENV_ACPI_CPUFREQ &&
> - env !=3D PM_ENV_PSTATE_CPUFREQ) {
> - RTE_LOG(DEBUG, POWER, "Neither ACPI nor PSTATE modes were initialized=
\n");
> - ret =3D -ENOTSUP;
> - goto end;
> - }
> clb =3D clb_scale_freq;
> break;
> - }
> case RTE_POWER_MGMT_TYPE_PAUSE:
> /* figure out various time-to-tsc conversions */
> if (global_data.tsc_per_us =3D=3D 0)
> @@ -273,13 +449,23 @@ rte_power_ethdev_pmgmt_queue_enable(unsigned int lc=
ore_id, uint16_t port_id,
> ret =3D -EINVAL;
> goto end;
> }
> + /* add this queue to the list */
> + ret =3D queue_list_add(lcore_cfg, &qdata);
> + if (ret < 0) {
> + RTE_LOG(DEBUG, POWER, "Failed to add queue to list: %s\n",
> + strerror(-ret));
> + goto end;
> + }
> + /* new queue is always added last */
> + queue_cfg =3D TAILQ_LAST(&lcore_cfgs->head, queue_list_head);
>=20
> /* initialize data before enabling the callback */
> - queue_cfg->empty_poll_stats =3D 0;
> - queue_cfg->cb_mode =3D mode;
> - queue_cfg->pwr_mgmt_state =3D PMD_MGMT_ENABLED;
> - queue_cfg->cur_cb =3D rte_eth_add_rx_callback(port_id, queue_id,
> - clb, NULL);
> + if (lcore_cfg->n_queues =3D=3D 1) {
> + lcore_cfg->cb_mode =3D mode;
> + lcore_cfg->pwr_mgmt_state =3D PMD_MGMT_ENABLED;
> + }
> + queue_cfg->cb =3D rte_eth_add_rx_callback(port_id, queue_id,
> + clb, queue_cfg);
>=20
> ret =3D 0;
> end:
> @@ -290,7 +476,9 @@ int
> rte_power_ethdev_pmgmt_queue_disable(unsigned int lcore_id,
> uint16_t port_id, uint16_t queue_id)
> {
> - struct pmd_queue_cfg *queue_cfg;
> + const union queue qdata =3D {.portid =3D port_id, .qid =3D queue_id};
> + struct pmd_core_cfg *lcore_cfg;
> + struct queue_list_entry *queue_cfg;
> int ret;
>=20
> RTE_ETH_VALID_PORTID_OR_ERR_RET(port_id, -EINVAL);
> @@ -306,24 +494,40 @@ rte_power_ethdev_pmgmt_queue_disable(unsigned int l=
core_id,
> }
>=20
> /* no need to check queue id as wrong queue id would not be enabled */
> - queue_cfg =3D &port_cfg[port_id][queue_id];
> + lcore_cfg =3D &lcore_cfgs[lcore_id];
>=20
> - if (queue_cfg->pwr_mgmt_state !=3D PMD_MGMT_ENABLED)
> + /* check if other queues are stopped as well */
> + ret =3D cfg_queues_stopped(lcore_cfg);
> + if (ret !=3D 1) {
> + /* error means invalid queue, 0 means queue wasn't stopped */
> + return ret < 0 ? -EINVAL : -EBUSY;
> + }
> +
> + if (lcore_cfg->pwr_mgmt_state !=3D PMD_MGMT_ENABLED)
> return -EINVAL;
>=20
> - /* stop any callbacks from progressing */
> - queue_cfg->pwr_mgmt_state =3D PMD_MGMT_DISABLED;
> + /*
> + * There is no good/easy way to do this without race conditions, so we
> + * are just going to throw our hands in the air and hope that the user
> + * has read the documentation and has ensured that ports are stopped at
> + * the time we enter the API functions.
> + */
> + queue_cfg =3D queue_list_take(lcore_cfg, &qdata);
> + if (queue_cfg =3D=3D NULL)
> + return -ENOENT;
>=20
> - switch (queue_cfg->cb_mode) {
> + /* if we've removed all queues from the lists, set state to disabled */
> + if (lcore_cfg->n_queues =3D=3D 0)
> + lcore_cfg->pwr_mgmt_state =3D PMD_MGMT_DISABLED;
> +
> + switch (lcore_cfg->cb_mode) {
> case RTE_POWER_MGMT_TYPE_MONITOR: /* fall-through */
> case RTE_POWER_MGMT_TYPE_PAUSE:
> - rte_eth_remove_rx_callback(port_id, queue_id,
> - queue_cfg->cur_cb);
> + rte_eth_remove_rx_callback(port_id, queue_id, queue_cfg->cb);
> break;
> case RTE_POWER_MGMT_TYPE_SCALE:
> rte_power_freq_max(lcore_id);
> - rte_eth_remove_rx_callback(port_id, queue_id,
> - queue_cfg->cur_cb);
> + rte_eth_remove_rx_callback(port_id, queue_id, queue_cfg->cb);
> rte_power_exit(lcore_id);
> break;
> }
> @@ -332,7 +536,18 @@ rte_power_ethdev_pmgmt_queue_disable(unsigned int lc=
ore_id,
> * ports before calling any of these API's, so we can assume that the
> * callbacks can be freed. we're intentionally casting away const-ness.
> */
> - rte_free((void *)queue_cfg->cur_cb);
> + rte_free((void *)queue_cfg->cb);
> + free(queue_cfg);
>=20
> return 0;
> }
> +
> +RTE_INIT(rte_power_ethdev_pmgmt_init) {
> + size_t i;
> +
> + /* initialize all tailqs */
> + for (i =3D 0; i < RTE_DIM(lcore_cfgs); i++) {
> + struct pmd_core_cfg *cfg =3D &lcore_cfgs[i];
> + TAILQ_INIT(&cfg->head);
> + }
> +}
> --
> 2.25.1