From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 85373424EC; Mon, 4 Sep 2023 08:59:29 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 76C0C402AE; Mon, 4 Sep 2023 08:59:27 +0200 (CEST) Received: from EUR05-DB8-obe.outbound.protection.outlook.com (mail-db8eur05on2069.outbound.protection.outlook.com [40.107.20.69]) by mails.dpdk.org (Postfix) with ESMTP id B2F51402A9 for ; Mon, 4 Sep 2023 08:59:25 +0200 (CEST) ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=EY7BRBFPg4HDVGrGZK9aQnUPBQ9RgXvP4hYolasaR/SZ5gIfOFkX2bxr+yme1X+jIQkWLvV8qqvPGoGXWNYFcaVfWCVcWubsfMF5wNgB4xT6P9NG/WZP88QRj0Y54bbvmrpKJuveu3j6DFejCZUv7unsas24U5E7ZPNip7h2LEo3KWt+ip6iHGt24Z35OXakerWUlvLIcRVoVP6JQcHm5tS9RL/RAGcFcQJ+ih1Cll4c/6bFD5N6qQsJ/r1Uk0gqOdDZ+3b2AktDR19zOkXlERLGmN2kb1KFt6+diO9VUldKkUH3SOKXYSaqnNr/VWvI6mj9JHUNa3gu95ZL+79X8w== 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-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=FYVlqsitPbWtDyOv4lBTrWECT/PSx+ezcZQ+Lgvcvbk=; b=AGLNHrR7rTbBnzQWdWuMHk1G7+VT7jgHEsuIuuayRidlZW/f9x8Hlb6sMRKSFn5wcOSRFeipw5z44xH5LldjGdPnxfU42GjZE25JdE36zbAMD604ESScUVKYai9TRBVH6qs7BZtvLjy1njcbZZ3BqyMltRYpJjMLycRCpn9bmEuFE/4n948rr/+Nwp8IijYHiJTj6UhFb1sbIZQ2KyH9iT0IhtleCZ0iKQPNMtNmF56svo3oOfIPPHCEaEizo1r58mVG3+ht/LK85MVrArgviopYn4g/+W7nFNUS1RC1IX2dnHROXRlbiAWZE9uQpdcWwXTeFEwRc3jUZ19gnh2YOQ== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=arm.com; dmarc=pass action=none header.from=arm.com; dkim=pass header.d=arm.com; arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=armh.onmicrosoft.com; s=selector2-armh-onmicrosoft-com; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=FYVlqsitPbWtDyOv4lBTrWECT/PSx+ezcZQ+Lgvcvbk=; b=w5ePHChammNwf4LIhC3dcE2xwppIuH3bjEbM9olFuJul0p4EGVw4S3H31f/iC1GLrcxXkviIod3nRyriMz4A6vqIhyH6KHZfsrp2Ka1gq8WHNNKfiVhtxb+RLQY5gWmymnZ0vG2XVqVOw6WtaSr3HhZexrjb6OKs6DXR1BzEfIg= Received: from AS8PR08MB7718.eurprd08.prod.outlook.com (2603:10a6:20b:50a::22) by AS8PR08MB8064.eurprd08.prod.outlook.com (2603:10a6:20b:54d::8) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.6745.32; Mon, 4 Sep 2023 06:59:22 +0000 Received: from AS8PR08MB7718.eurprd08.prod.outlook.com ([fe80::5530:2382:34ac:cb8e]) by AS8PR08MB7718.eurprd08.prod.outlook.com ([fe80::5530:2382:34ac:cb8e%4]) with mapi id 15.20.6745.030; Mon, 4 Sep 2023 06:59:22 +0000 From: Feifei Wang To: Konstantin Ananyev , Konstantin Ananyev CC: "dev@dpdk.org" , nd , Honnappa Nagarahalli , Ruifeng Wang , Yuying Zhang , Beilei Xing , nd , nd , nd Subject: RE: [PATCH v11 2/4] net/i40e: implement mbufs recycle mode Thread-Topic: [PATCH v11 2/4] net/i40e: implement mbufs recycle mode Thread-Index: AQHZ1Mog0nujzlh9U0CHKeg6D9zv8K/48qdwgAvD0gCAARCtoIAATscAgAQvdqA= Date: Mon, 4 Sep 2023 06:59:22 +0000 Message-ID: References: <20220420081650.2043183-1-feifei.wang2@arm.com> <20230822072710.1945027-1-feifei.wang2@arm.com> <20230822072710.1945027-3-feifei.wang2@arm.com> <6e3a2b3f24e046358646fa26e19122d0@huawei.com> In-Reply-To: <6e3a2b3f24e046358646fa26e19122d0@huawei.com> Accept-Language: zh-CN, en-US Content-Language: zh-CN X-MS-Has-Attach: X-MS-TNEF-Correlator: x-ts-tracking-id: 7B5E0FD58B27C64C80AF85EC4C4530E9.0 x-checkrecipientchecked: true authentication-results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=arm.com; x-ms-publictraffictype: Email x-ms-traffictypediagnostic: AS8PR08MB7718:EE_|AS8PR08MB8064:EE_ x-ms-office365-filtering-correlation-id: 293f80e0-37f0-4c12-d227-08dbad1477eb nodisclaimer: true x-ms-exchange-senderadcheck: 1 x-ms-exchange-antispam-relay: 0 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:AS8PR08MB7718.eurprd08.prod.outlook.com; PTR:; CAT:NONE; SFS:(13230031)(39860400002)(376002)(136003)(366004)(396003)(346002)(1800799009)(451199024)(186009)(8676002)(8936002)(5660300002)(316002)(66946007)(66446008)(66476007)(64756008)(54906003)(110136005)(2906002)(30864003)(66556008)(76116006)(4326008)(52536014)(41300700001)(53546011)(6506007)(7696005)(26005)(9686003)(55016003)(38070700005)(38100700002)(122000001)(71200400001)(478600001)(83380400001)(33656002)(86362001)(448954002)(579004); DIR:OUT; SFP:1101; x-ms-exchange-antispam-messagedata-chunkcount: 1 x-ms-exchange-antispam-messagedata-0: =?us-ascii?Q?qXFXtizDkzaeQSqfMVwr0zJmpLhqUW98vd0jYa62dCygRsK60sBzPWL5koG+?= =?us-ascii?Q?OMXiuyDqC2SnE0oIVhzbu+6FpOuMdeAi+zZJvrPEvKjWe6247ev6ZdrCkl9d?= =?us-ascii?Q?+yNWnhkW7aCScwIBnkGoLPeLY5ZH+4poEtdktAVZ95124UDzbVyYbl1sjPMj?= =?us-ascii?Q?A5WPMEcxclVkO5hbk/tQ6QBwYWf8wKbKwGwNdRb6oGqmk0jJ1LOMdva+B0+d?= =?us-ascii?Q?F15FH/pj3LbLVJ88kxGr5ZOzG6YuA57gwnkKQytSB9ulbzIyDDHF64t13F3z?= =?us-ascii?Q?53CkDTHhbAP0v4b6Ex9CwvzUQdbclYMoD4ZX3rysvX7Txjt2BMype15bPPyV?= =?us-ascii?Q?Z8CIN35OCB1y/ufRQQeKZdnPPFcaM3NSzh5kgLOz/suLRq51TFxkh/b7uFNO?= =?us-ascii?Q?GqDXcGdqJITnRkB/+3GjMEGk9uzJBY9PHv9IM6j/FqP2K6mpGtOkqsgq+mZS?= =?us-ascii?Q?jeMEB1WTmxlf690CocL2TeKBfxHMTqk4AzqiTGVMHCpP2MSWzlZK4hkqoIQG?= =?us-ascii?Q?29FW2S0qLPIK8wJfXrSRM4+QLivvhj5VNAneEpS7QrpWuXVd0lM72dnwlJ63?= =?us-ascii?Q?QpsbtrBHKEoKpVAdQs2AizRXmT4ImdD3Bei0aphtNv4l1WomIfVk6tRoRkke?= =?us-ascii?Q?TPAzOqguQjGToKysD0Fv/EJbmnT9ZmjP2Hg3iG2w2I2z4GtsGG1ktGMvGSxg?= =?us-ascii?Q?rRpmQT10M5Ef0k52VlZe0wUaXkFo+4L/cUZOTokNcrtPm0fFqDLa5nSHbEm4?= =?us-ascii?Q?ZVutePP5ZCSDpyr9iZ7WbsCm2kOlciG46QhLZ9t//SaWfai3qX8KPFf0oZXY?= =?us-ascii?Q?FzFQor5NvWgj/eE4BLXAsKH2KF/gWihaKn+hOIw/4IVXEse40977mTZ/TsOr?= =?us-ascii?Q?q2qt9OwzPbAyindojIDNgwG74VARL4mhMzg+lqOgQb65c9VSciHrHcZdUcrR?= =?us-ascii?Q?3WBRqud4gzsn45d+kmOqnlHwDrXkwXG1EWK5pfDO4UndLstFKaMvlKs8u+1M?= =?us-ascii?Q?E5mZLiERDuFkOf4P47W3Pb1OyQr8SsFEVUKwRm19CivYM2kG9Gzyj9T4YY2w?= =?us-ascii?Q?LGioSOfgXkA5DCI79VYY1r6aH9z4gmHmtbSJUafOIqLTowPthGGGclYVCM4a?= =?us-ascii?Q?UwLdqSKFUbvT7fTvqOZJR74+xhlEvukGjU4GgcsI9ybtl2oWomeKcbJaJMyl?= =?us-ascii?Q?DKziID4hsARvwQLOJ9EttRXvL6fcca2V89FKsw9QhadBjs9p2DpSWoNEvYrS?= =?us-ascii?Q?Pm90KjvbsIN+IOOD7Xfaav6giNn/fqbLGF2zSccxjTZe7NfgQRtvPCmRBnBS?= =?us-ascii?Q?T71FjEwc64CFccx4ahRUxohx6ElP9m551dAt+XBDp8eDb20B1XNfm40tCZWU?= =?us-ascii?Q?Hkoo10O2rNE3q7N3zcRpse4Jpeb37LMf+PQRW6IS6rcyuV1ucZn3OkTggU+L?= =?us-ascii?Q?jLRNb+uAEGItO1WbJGB388LFRKnnSCHhB892YlcmTnlyOkyxUy3TbtjJ3cQb?= =?us-ascii?Q?FwlA9X0sY2DMzsr5Q4z7sODp5r++ywG4oHa1HwKwyzjkQFqi5DbidU8AKl6T?= =?us-ascii?Q?UbvuX8wLn6sA5tOPji54Dp8fr7yun0g/TwUZbvOI?= Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-OriginatorOrg: arm.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-AuthSource: AS8PR08MB7718.eurprd08.prod.outlook.com X-MS-Exchange-CrossTenant-Network-Message-Id: 293f80e0-37f0-4c12-d227-08dbad1477eb X-MS-Exchange-CrossTenant-originalarrivaltime: 04 Sep 2023 06:59:22.5481 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: f34e5979-57d9-4aaa-ad4d-b122a662184d X-MS-Exchange-CrossTenant-mailboxtype: HOSTED X-MS-Exchange-CrossTenant-userprincipalname: ITb1rxAPjS6odJBua9BiHV2tc/KYIaIGkybT15GYx2Ildae/tz5d8nQ71X7amQRdetefs3+QBe/OM7K4u3WXNg== X-MS-Exchange-Transport-CrossTenantHeadersStamped: AS8PR08MB8064 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org > -----Original Message----- > From: Konstantin Ananyev > Sent: Friday, September 1, 2023 10:23 PM > To: Feifei Wang ; Konstantin Ananyev > > Cc: dev@dpdk.org; nd ; Honnappa Nagarahalli > ; Ruifeng Wang > ; Yuying Zhang ; Beilei > Xing ; nd ; nd > Subject: RE: [PATCH v11 2/4] net/i40e: implement mbufs recycle mode >=20 >=20 >=20 > > > > > > > > > > Define specific function implementation for i40e driver. > > > > > Currently, mbufs recycle mode can support 128bit vector path and > > > > > avx2 > > > path. > > > > > And can be enabled both in fast free and no fast free mode. > > > > > > > > > > Suggested-by: Honnappa Nagarahalli > > > > > > > > > > Signed-off-by: Feifei Wang > > > > > Reviewed-by: Ruifeng Wang > > > > > Reviewed-by: Honnappa Nagarahalli > > > > > > --- > > > > > drivers/net/i40e/i40e_ethdev.c | 1 + > > > > > drivers/net/i40e/i40e_ethdev.h | 2 + > > > > > .../net/i40e/i40e_recycle_mbufs_vec_common.c | 147 > > > > > ++++++++++++++++++ > > > > > drivers/net/i40e/i40e_rxtx.c | 32 ++++ > > > > > drivers/net/i40e/i40e_rxtx.h | 4 + > > > > > drivers/net/i40e/meson.build | 1 + > > > > > 6 files changed, 187 insertions(+) create mode 100644 > > > > > drivers/net/i40e/i40e_recycle_mbufs_vec_common.c > > > > > > > > > > diff --git a/drivers/net/i40e/i40e_ethdev.c > > > > > b/drivers/net/i40e/i40e_ethdev.c index 8271bbb394..50ba9aac94 > > > > > 100644 > > > > > --- a/drivers/net/i40e/i40e_ethdev.c > > > > > +++ b/drivers/net/i40e/i40e_ethdev.c > > > > > @@ -496,6 +496,7 @@ static const struct eth_dev_ops > > > > > i40e_eth_dev_ops > > > =3D { > > > > > .flow_ops_get =3D i40e_dev_flow_ops_get, > > > > > .rxq_info_get =3D i40e_rxq_info_get, > > > > > .txq_info_get =3D i40e_txq_info_get, > > > > > + .recycle_rxq_info_get =3D i40e_recycle_rxq_info_get, > > > > > .rx_burst_mode_get =3D i40e_rx_burst_mode_get, > > > > > .tx_burst_mode_get =3D i40e_tx_burst_mode_get, > > > > > .timesync_enable =3D i40e_timesync_enable, > > > > > diff --git a/drivers/net/i40e/i40e_ethdev.h > > > > > b/drivers/net/i40e/i40e_ethdev.h index 6f65d5e0ac..af758798e1 > > > > > 100644 > > > > > --- a/drivers/net/i40e/i40e_ethdev.h > > > > > +++ b/drivers/net/i40e/i40e_ethdev.h > > > > > @@ -1355,6 +1355,8 @@ void i40e_rxq_info_get(struct rte_eth_dev > > > > > *dev, uint16_t queue_id, > > > > > struct rte_eth_rxq_info *qinfo); void > > > > > i40e_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id, > > > > > struct rte_eth_txq_info *qinfo); > > > > > +void i40e_recycle_rxq_info_get(struct rte_eth_dev *dev, > > > > > +uint16_t > > > queue_id, > > > > > + struct rte_eth_recycle_rxq_info *recycle_rxq_info); > > > > > int i40e_rx_burst_mode_get(struct rte_eth_dev *dev, uint16_t > queue_id, > > > > > struct rte_eth_burst_mode *mode); int > > > > > i40e_tx_burst_mode_get(struct rte_eth_dev *dev, uint16_t > > > > > queue_id, diff -- git > > > > > a/drivers/net/i40e/i40e_recycle_mbufs_vec_common.c > > > > > b/drivers/net/i40e/i40e_recycle_mbufs_vec_common.c > > > > > new file mode 100644 > > > > > index 0000000000..5663ecccde > > > > > --- /dev/null > > > > > +++ b/drivers/net/i40e/i40e_recycle_mbufs_vec_common.c > > > > > @@ -0,0 +1,147 @@ > > > > > +/* SPDX-License-Identifier: BSD-3-Clause > > > > > + * Copyright (c) 2023 Arm Limited. > > > > > + */ > > > > > + > > > > > +#include > > > > > +#include > > > > > + > > > > > +#include "base/i40e_prototype.h" > > > > > +#include "base/i40e_type.h" > > > > > +#include "i40e_ethdev.h" > > > > > +#include "i40e_rxtx.h" > > > > > + > > > > > +#pragma GCC diagnostic ignored "-Wcast-qual" > > > > > + > > > > > +void > > > > > +i40e_recycle_rx_descriptors_refill_vec(void *rx_queue, uint16_t > > > > > +nb_mbufs) { > > > > > + struct i40e_rx_queue *rxq =3D rx_queue; > > > > > + struct i40e_rx_entry *rxep; > > > > > + volatile union i40e_rx_desc *rxdp; > > > > > + uint16_t rx_id; > > > > > + uint64_t paddr; > > > > > + uint64_t dma_addr; > > > > > + uint16_t i; > > > > > + > > > > > + rxdp =3D rxq->rx_ring + rxq->rxrearm_start; > > > > > + rxep =3D &rxq->sw_ring[rxq->rxrearm_start]; > > > > > + > > > > > + for (i =3D 0; i < nb_mbufs; i++) { > > > > > + /* Initialize rxdp descs. */ > > > > > + paddr =3D (rxep[i].mbuf)->buf_iova + > > > > > RTE_PKTMBUF_HEADROOM; > > > > > + dma_addr =3D rte_cpu_to_le_64(paddr); > > > > > + /* flush desc with pa dma_addr */ > > > > > + rxdp[i].read.hdr_addr =3D 0; > > > > > + rxdp[i].read.pkt_addr =3D dma_addr; > > > > > + } > > > > > + > > > > > + /* Update the descriptor initializer index */ > > > > > + rxq->rxrearm_start +=3D nb_mbufs; > > > > > + rx_id =3D rxq->rxrearm_start - 1; > > > > > + > > > > > + if (unlikely(rxq->rxrearm_start >=3D rxq->nb_rx_desc)) { > > > > > + rxq->rxrearm_start =3D 0; > > > > > + rx_id =3D rxq->nb_rx_desc - 1; > > > > > + } > > > > > + > > > > > + rxq->rxrearm_nb -=3D nb_mbufs; > > > > > + > > > > > + rte_io_wmb(); > > > > > + /* Update the tail pointer on the NIC */ > > > > > + I40E_PCI_REG_WRITE_RELAXED(rxq->qrx_tail, rx_id); } > > > > > + > > > > > +uint16_t > > > > > +i40e_recycle_tx_mbufs_reuse_vec(void *tx_queue, > > > > > + struct rte_eth_recycle_rxq_info *recycle_rxq_info) { > > > > > + struct i40e_tx_queue *txq =3D tx_queue; > > > > > + struct i40e_tx_entry *txep; > > > > > + struct rte_mbuf **rxep; > > > > > + int i, n; > > > > > + uint16_t nb_recycle_mbufs; > > > > > + uint16_t avail =3D 0; > > > > > + uint16_t mbuf_ring_size =3D recycle_rxq_info->mbuf_ring_size; > > > > > + uint16_t mask =3D recycle_rxq_info->mbuf_ring_size - 1; > > > > > + uint16_t refill_requirement =3D recycle_rxq_info- > >refill_requirement; > > > > > + uint16_t refill_head =3D *recycle_rxq_info->refill_head; > > > > > + uint16_t receive_tail =3D *recycle_rxq_info->receive_tail; > > > > > + > > > > > + /* Get available recycling Rx buffers. */ > > > > > + avail =3D (mbuf_ring_size - (refill_head - receive_tail)) & > > > > > +mask; > > > > > + > > > > > + /* Check Tx free thresh and Rx available space. */ > > > > > + if (txq->nb_tx_free > txq->tx_free_thresh || avail <=3D txq- > >tx_rs_thresh) > > > > > + return 0; > > > > > + > > > > > + /* check DD bits on threshold descriptor */ > > > > > + if ((txq->tx_ring[txq->tx_next_dd].cmd_type_offset_bsz & > > > > > + > > > > > rte_cpu_to_le_64(I40E_TXD_QW1_DTYPE_MASK)) !=3D > > > > > + > > > > > rte_cpu_to_le_64(I40E_TX_DESC_DTYPE_DESC_DONE)) > > > > > + return 0; > > > > > + > > > > > + n =3D txq->tx_rs_thresh; > > > > > + nb_recycle_mbufs =3D n; > > > > > + > > > > > + /* Mbufs recycle mode can only support no ring buffer > wrapping > > > > > around. > > > > > + * Two case for this: > > > > > + * > > > > > + * case 1: The refill head of Rx buffer ring needs to be aligne= d > with > > > > > + * mbuf ring size. In this case, the number of Tx freeing buffe= rs > > > > > + * should be equal to refill_requirement. > > > > > + * > > > > > + * case 2: The refill head of Rx ring buffer does not need to b= e > aligned > > > > > + * with mbuf ring size. In this case, the update of refill head > can not > > > > > + * exceed the Rx mbuf ring size. > > > > > + */ > > > > > + if (refill_requirement !=3D n || > > > > > + (!refill_requirement && (refill_head + n > > mbuf_ring_size))) > > > > > + return 0; > > > > > + > > > > > + /* First buffer to free from S/W ring is at index > > > > > + * tx_next_dd - (tx_rs_thresh-1). > > > > > + */ > > > > > + txep =3D &txq->sw_ring[txq->tx_next_dd - (n - 1)]; > > > > > + rxep =3D recycle_rxq_info->mbuf_ring; > > > > > + rxep +=3D refill_head; > > > > > + > > > > > + if (txq->offloads & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE) { > > > > > + /* Avoid txq contains buffers from unexpected > mempool. */ > > > > > + if (unlikely(recycle_rxq_info->mp > > > > > + !=3D txep[0].mbuf->pool)) > > > > > + return 0; > > > > > + > > > > > + /* Directly put mbufs from Tx to Rx. */ > > > > > + for (i =3D 0; i < n; i++) > > > > > + rxep[i] =3D txep[i].mbuf; > > > > > + } else { > > > > > + for (i =3D 0; i < n; i++) { > > > > > + rxep[i] =3D > rte_pktmbuf_prefree_seg(txep[i].mbuf); > > > > > + > > > > > + /* If Tx buffers are not the last reference or > from > > > > > + * unexpected mempool, previous copied > buffers are > > > > > + * considered as invalid. > > > > > + */ > > > > > + if (unlikely((rxep[i] =3D=3D NULL && > refill_requirement) || > > > > [Konstantin] > > > > Could you pls remind me why it is ok to have rxep[i]=3D=3DNULL when > > > > refill_requirement is not set? > > > > > > > > If reill_requirement is not zero, it means each tx freed buffer > > > > must be valid and can be put into Rx sw_ring. Then the refill > > > > head of Rx buffer ring can be aligned with mbuf ring size. Briefly > > > > speaking the number > > > of Tx valid freed buffer must be equal to Rx refill_requirement. For > > > example, i40e driver. > > > > > > > > If reill_requirement is zero, it means that the refill head of Rx > > > > buffer ring does not need to be aligned with mbuf ring size, thus > > > > if Tx have n valid freed buffers, we just need to put these n > > > > buffers into Rx sw- > > > ring, and not to be equal to the Rx setting rearm number. For > > > example, mlx5 driver. > > > > > > > > In conclusion, above difference is due to pmd drivers have > > > > different > > > strategies to update their Rx rearm(refill) head. > > > > For i40e driver, if rearm_head exceed 1024, it will be set as 0 > > > > due to the > > > number of each rearm is a fixed value by default. > > > > For mlx5 driver. Its rearm_head can exceed 1024, and use mask to > > > > achieve > > > real index. Thus its rearm number can be a different value. > > > > > > Ok, but if rte_pktmbuf_prefree_seg(txep[i].mbuf), it means that this > > > mbuf is not free yet and can't be reused. > > > Shouldn't we then set nb_recycle_mbufs =3D 0 in that case too? > > > Or probably would be enough to skip that mbuf? > > > Might be something like that: > > > > > > for (i =3D 0, j =3D 0; i < n; i++) { > > > > > > rxep[j] =3D rte_pktmbuf_prefree_seg(txep[i].mbuf); > > > if (rxep[j] =3D=3D NULL || recycle_rxq_info->mp !=3D rxep[j].mbuf->p= ool)) { > > > if (refill_requirement) { > > > nb_recycle_mbufs =3D 0; > > > break; > > > } > > > } else > > > j++; > > > } > > > > > > /* now j contains actual number of recycled mbufs */ > > > > > > ? > > > > > > > > > > > > + recycle_rxq_info->mp !=3D > txep[i].mbuf- > > > > > >pool)) > > > > > + nb_recycle_mbufs =3D 0; > > > > > + } > > > > > + /* If Tx buffers are not the last reference or > > > > > + * from unexpected mempool, all recycled buffers > > > > > + * are put into mempool. > > > > > + */ > > > > > + if (nb_recycle_mbufs =3D=3D 0) > > > > > + for (i =3D 0; i < n; i++) { > > > > > + if (rxep[i] !=3D NULL) > > > > > + rte_mempool_put(rxep[i]- > >pool, > > > > > rxep[i]); > > > > > + } > > > > > + } > > > > > + > > [Konstantin] After another thought, it might be easier and cleaner just= to: > > if (rxep[j] =3D=3D NULL || recycle_rxq_info->mp !=3D rxep[j].mbuf->pool= ) > > nb_recycle_mbufs =3D 0; > > > > Anyway, from my understanding - if rte_pktmbuf_prefree_seg(mbuf) > > returns NULL, then we can't recycle that mbuf. > > > > [Feifei] Agree with that 'rte_pktmbuf_prefree_seg(mbuf) returns NULL, t= hen > we can't recycle that mbuf'. > > > > Firstly, we should know for i40e driver, the number of free mbufs is f= ixed, it > must equal to 'tx_rs_thresh' > > This means if we start to free Tx mbufs, it cannot be interrupted until= the > given amount of mbufs are freed. > > In the meanwhile, doing prefree operation for a Tx mbuf can be looked > > at this mbuf is freed from this TX sw-ring if the API returns NULL. Th= is is due > to that call 'prefree_seg' function means update the mbuf refcnt. > > > > So let's come back our recycle mbuf case. > > Here we consider that the case if we have 32 mbufs need to be freed, an= d > we firstly do the pre-free. > > And then first 8 mbufs is good and return value is not none. But the 9t= h > mbuf is bad, its refcnt is more than 1. > > So we just update its refcnt and cannot put it into Rx sw-ring. For Tx = sw-ring, > this mbuf has been freed. > > Then we should continue to do pre-free operation for the next Tx mbufs > > to ensure the given amount of mbufs are freed. > > > > Do a conclusion for this, this is because if we start to do pre-free > > operation, the Tx mbuf refcnt value maybe changed, so we cannot stop o= r > break until finish all the pre-free operation. > > > > Finally, in the case that Rx refill_request is not zero, but the valid > > mbuf amount is less than this value, we must put back this Tx mbufs int= o > mempool. > > > > Above is the reason why I do not directly jump out of the loop if some = mbuf > return value is NULL. >=20 > Yep, I already realized that it is a bit more complicated and we need to > continue with prefree() for all packets even when we get NULL in the midd= le. > Anyway the code has to be changed, right? >=20 Sorry, I think for the code, it is unnecessary to be changed. For no fast free path, currently: 1. We check whether each mbuf is Ok and call pre_free function ---------------------------------------------------------------------------= --------------------------------------------------------- 2.1 For the mbuf return value is not NULL, it is put into Rx sw-ring. 2.2 For the mbuf return value is zero and refill-request, it will also firs= tly put into Rx sw-ring, and we set nb_recycle =3D 0 ---------------------------------------------------------------------------= --------------------------------------------------------- 3.1 We check nb_recycle, if it is not 0, we will continue to rearm Rx descs= and update its index by call descs_refill function. =20 3.2 if nb_recycle is 0, we will put valid recycle mbufs back into mempool a= s general path. This is necessary, because we need to ensure the freed Tx number is fixed.(Some buffers return is null can be = seen as freed, others need to be put into mempool) Or maybe I ignore something? > > > > > > > + /* Update counters for Tx. */ > > > > > + txq->nb_tx_free =3D (uint16_t)(txq->nb_tx_free + txq- > >tx_rs_thresh); > > > > > + txq->tx_next_dd =3D (uint16_t)(txq->tx_next_dd + txq- > >tx_rs_thresh); > > > > > + if (txq->tx_next_dd >=3D txq->nb_tx_desc) > > > > > + txq->tx_next_dd =3D (uint16_t)(txq->tx_rs_thresh - 1); > > > > > + > > > > > + return nb_recycle_mbufs; > > > > > +} > > > > > diff --git a/drivers/net/i40e/i40e_rxtx.c > > > > > b/drivers/net/i40e/i40e_rxtx.c index b4f65b58fa..a9c9eb331c > > > > > 100644 > > > > > --- a/drivers/net/i40e/i40e_rxtx.c > > > > > +++ b/drivers/net/i40e/i40e_rxtx.c > > > > > @@ -3199,6 +3199,30 @@ i40e_txq_info_get(struct rte_eth_dev > > > > > *dev, uint16_t queue_id, > > > > > qinfo->conf.offloads =3D txq->offloads; } > > > > > > > > > > +void > > > > > +i40e_recycle_rxq_info_get(struct rte_eth_dev *dev, uint16_t > queue_id, > > > > > + struct rte_eth_recycle_rxq_info *recycle_rxq_info) { > > > > > + struct i40e_rx_queue *rxq; > > > > > + struct i40e_adapter *ad =3D > > > > > + I40E_DEV_PRIVATE_TO_ADAPTER(dev->data- > >dev_private); > > > > > + > > > > > + rxq =3D dev->data->rx_queues[queue_id]; > > > > > + > > > > > + recycle_rxq_info->mbuf_ring =3D (void *)rxq->sw_ring; > > > > > + recycle_rxq_info->mp =3D rxq->mp; > > > > > + recycle_rxq_info->mbuf_ring_size =3D rxq->nb_rx_desc; > > > > > + recycle_rxq_info->receive_tail =3D &rxq->rx_tail; > > > > > + > > > > > + if (ad->rx_vec_allowed) { > > > > > + recycle_rxq_info->refill_requirement =3D > > > > > RTE_I40E_RXQ_REARM_THRESH; > > > > > + recycle_rxq_info->refill_head =3D &rxq->rxrearm_start; > > > > > + } else { > > > > > + recycle_rxq_info->refill_requirement =3D rxq- > >rx_free_thresh; > > > > > + recycle_rxq_info->refill_head =3D &rxq->rx_free_trigger; > > > > > + } > > > > > +} > > > > > + > > > > > #ifdef RTE_ARCH_X86 > > > > > static inline bool > > > > > get_avx_supported(bool request_avx512) @@ -3293,6 +3317,8 @@ > > > > > i40e_set_rx_function(struct rte_eth_dev *dev) > > > > > dev->rx_pkt_burst =3D ad->rx_use_avx2 ? > > > > > i40e_recv_scattered_pkts_vec_avx2 : > > > > > i40e_recv_scattered_pkts_vec; > > > > > + dev->recycle_rx_descriptors_refill =3D > > > > > + > i40e_recycle_rx_descriptors_refill_vec; > > > > > } > > > > > } else { > > > > > if (ad->rx_use_avx512) { > > > > > @@ -3311,9 +3337,12 @@ i40e_set_rx_function(struct rte_eth_dev > *dev) > > > > > dev->rx_pkt_burst =3D ad->rx_use_avx2 ? > > > > > i40e_recv_pkts_vec_avx2 : > > > > > i40e_recv_pkts_vec; > > > > > + dev->recycle_rx_descriptors_refill =3D > > > > > + > i40e_recycle_rx_descriptors_refill_vec; > > > > > } > > > > > } > > > > > #else /* RTE_ARCH_X86 */ > > > > > + dev->recycle_rx_descriptors_refill =3D > > > > > +i40e_recycle_rx_descriptors_refill_vec; > > > > > if (dev->data->scattered_rx) { > > > > > PMD_INIT_LOG(DEBUG, > > > > > "Using Vector Scattered Rx (port %d).", @@ > > > > > -3481,15 +3510,18 @@ i40e_set_tx_function(struct rte_eth_dev *dev= ) > > > > > dev->tx_pkt_burst =3D ad->tx_use_avx2 ? > > > > > i40e_xmit_pkts_vec_avx2 : > > > > > i40e_xmit_pkts_vec; > > > > > + dev->recycle_tx_mbufs_reuse =3D > > > > > i40e_recycle_tx_mbufs_reuse_vec; > > > > > } > > > > > #else /* RTE_ARCH_X86 */ > > > > > PMD_INIT_LOG(DEBUG, "Using Vector Tx (port %d).", > > > > > dev->data->port_id); > > > > > dev->tx_pkt_burst =3D i40e_xmit_pkts_vec; > > > > > + dev->recycle_tx_mbufs_reuse =3D > > > > > i40e_recycle_tx_mbufs_reuse_vec; #endif /* RTE_ARCH_X86 */ > > > > > } else { > > > > > PMD_INIT_LOG(DEBUG, "Simple tx finally be used."); > > > > > dev->tx_pkt_burst =3D i40e_xmit_pkts_simple; > > > > > + dev->recycle_tx_mbufs_reuse =3D > > > > > i40e_recycle_tx_mbufs_reuse_vec; > > > > > } > > > > > dev->tx_pkt_prepare =3D i40e_simple_prep_pkts; > > > > > } else { > > > > > diff --git a/drivers/net/i40e/i40e_rxtx.h > > > > > b/drivers/net/i40e/i40e_rxtx.h index a8686224e5..b191f23e1f > > > > > 100644 > > > > > --- a/drivers/net/i40e/i40e_rxtx.h > > > > > +++ b/drivers/net/i40e/i40e_rxtx.h > > > > > @@ -236,6 +236,10 @@ uint32_t i40e_dev_rx_queue_count(void > > > > > *rx_queue); int i40e_dev_rx_descriptor_status(void *rx_queue, > > > > > uint16_t offset); int i40e_dev_tx_descriptor_status(void > > > > > *tx_queue, uint16_t offset); > > > > > > > > > > +uint16_t i40e_recycle_tx_mbufs_reuse_vec(void *tx_queue, > > > > > + struct rte_eth_recycle_rxq_info *recycle_rxq_info); > void > > > > > +i40e_recycle_rx_descriptors_refill_vec(void *rx_queue, uint16_t > > > > > +nb_mbufs); > > > > > + > > > > > uint16_t i40e_recv_pkts_vec(void *rx_queue, struct rte_mbuf > **rx_pkts, > > > > > uint16_t nb_pkts); > > > > > uint16_t i40e_recv_scattered_pkts_vec(void *rx_queue, diff > > > > > --git a/drivers/net/i40e/meson.build > > > > > b/drivers/net/i40e/meson.build index > > > > > 8e53b87a65..3b1a233c84 100644 > > > > > --- a/drivers/net/i40e/meson.build > > > > > +++ b/drivers/net/i40e/meson.build > > > > > @@ -34,6 +34,7 @@ sources =3D files( > > > > > 'i40e_tm.c', > > > > > 'i40e_hash.c', > > > > > 'i40e_vf_representor.c', > > > > > + 'i40e_recycle_mbufs_vec_common.c', > > > > > 'rte_pmd_i40e.c', > > > > > ) > > > > > > > > > > -- > > > > > 2.25.1