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 2C171A054A for ; Wed, 15 Jun 2022 09:08:12 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 105E54280E; Wed, 15 Jun 2022 09:08:12 +0200 (CEST) Received: from mga04.intel.com (mga04.intel.com [192.55.52.120]) by mails.dpdk.org (Postfix) with ESMTP id 2520340220; Wed, 15 Jun 2022 09:08:06 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1655276887; x=1686812887; h=from:to:cc:subject:date:message-id:references: in-reply-to:content-transfer-encoding:mime-version; bh=sDhZ+Qrg9FZk7pzC6RnSVwHY7+s9bzf2e/Tz4vc+hEE=; b=Nivp+9GEmfnYYTTMFDwgznZuY7jNrK43MUGQTn3UMC6n/2ExkIJJq01C ZfoVnIegnpWA1o42jYAqstNodb4vAPeUyvomBtTZl8not/YvUnXR8xf8P PpMZzRG41Kebm2vmwbseJnqFGAVPFzKX1GDtjbRtfB49PDuW5hHOckOjd /2akZ45O8DeC6+aFFw7OY5TnKdMspgMyGctDdKuFXTbiClselXvV4a1Sl BsakmCEIKrwKJ/oEXA5IykrzVazyuiZCkijITMTZ5ysbq7+m0u6Fa2EW7 hzvMLgSqfphHSl6vSZujBzVVJ+6QWFz98suHx6v/gqmGlQxlNJJ9ssybZ Q==; X-IronPort-AV: E=McAfee;i="6400,9594,10378"; a="277654162" X-IronPort-AV: E=Sophos;i="5.91,300,1647327600"; d="scan'208";a="277654162" Received: from orsmga005.jf.intel.com ([10.7.209.41]) by fmsmga104.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 15 Jun 2022 00:08:04 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.91,300,1647327600"; d="scan'208";a="762331824" Received: from orsmsx606.amr.corp.intel.com ([10.22.229.19]) by orsmga005.jf.intel.com with ESMTP; 15 Jun 2022 00:08:04 -0700 Received: from orsmsx608.amr.corp.intel.com (10.22.229.21) by ORSMSX606.amr.corp.intel.com (10.22.229.19) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.27; Wed, 15 Jun 2022 00:08:03 -0700 Received: from ORSEDG601.ED.cps.intel.com (10.7.248.6) by orsmsx608.amr.corp.intel.com (10.22.229.21) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2308.27 via Frontend Transport; Wed, 15 Jun 2022 00:08:03 -0700 Received: from NAM10-BN7-obe.outbound.protection.outlook.com (104.47.70.103) by edgegateway.intel.com (134.134.137.102) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.1.2308.27; Wed, 15 Jun 2022 00:08:01 -0700 ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=aiP5uTnFTt5FBt3d5wTghXzYLaR0J096IiPytxZKM0FFW2A5D9+vcntV7KDf4XUzAu1qia/r5Rf1aod0elQL0j8ZWfdn0GC9g96XTWU//pEIjC/ej25yspbVL5OpgjbgD+uQNg9WrBkmQ/A0DwzQHl85HG25QUMSi5ZIEOrxPiJ+z6BNNqoiBfJjNYOqL7HLu3ytq1Dt48C1yq6qaF2RuiLIdxrBDeOTAknln0k6uOshNM/+u+i3FYbSAX26tNazn4vsyi8ULUvKCW7JvechETqBMOYwU+LMD8voIR3+gLjavqWXgfMMLWAfm9zF95SbGXvmE5yCRadE9D39ZE7xZg== 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=Ie5kYA/J2v2bqtg+3G+oVL65CEUzPAWCMsBQaJc0+Ks=; b=GTBwo8h4Nnt4j5oxOhtLWB8yXrqtlA+T+nY36TaeAofYMQqYAFRxlxta9cAIO4O1Y9oRBmlILmbdszlGgIQ6eZRobTiGk/2oWxaPanLLx99FtUWWPVA2VQSjAamlwvns9nFwT3wc3IWRxsR9LwpSgdqewunfcci2coz8eolRaVRwIgpAXUdWhr5QtjgaqL2C4vVw+EDhY6UjEG0v1bcivahnEL2ogXUqe8aHmkm1EqbD+toIJZGZ/iY5tawYZIhdv5ZI2wmR97NIjMPVC2dQgS209k/00+ehhR9NDwRZwubiDAVux6z+lJHSy4RN7FxMUx3mSk4gyKiGIhTt5BoGzA== 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 Received: from DM6PR11MB4252.namprd11.prod.outlook.com (2603:10b6:5:201::26) by BY5PR11MB4370.namprd11.prod.outlook.com (2603:10b6:a03:1c3::20) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.5332.13; Wed, 15 Jun 2022 07:07:52 +0000 Received: from DM6PR11MB4252.namprd11.prod.outlook.com ([fe80::b9d5:600c:9f13:bc96]) by DM6PR11MB4252.namprd11.prod.outlook.com ([fe80::b9d5:600c:9f13:bc96%7]) with mapi id 15.20.5332.023; Wed, 15 Jun 2022 07:07:52 +0000 From: "Xu, Rosen" To: "Huang, Wei" , "dev@dpdk.org" , "thomas@monjalon.net" , "nipun.gupta@nxp.com" , "hemant.agrawal@nxp.com" CC: "stable@dpdk.org" , "Zhang, Tianfei" , "Zhang, Qi Z" Subject: RE: [PATCH v7 2/5] raw/ifpga: add N3000 AFU driver Thread-Topic: [PATCH v7 2/5] raw/ifpga: add N3000 AFU driver Thread-Index: AQHYe9K8hiocWy1l8ESYmAOIeRhe761QEp4A Date: Wed, 15 Jun 2022 07:07:52 +0000 Message-ID: References: <1654742650-7214-1-git-send-email-wei.huang@intel.com> <1654760242-7832-1-git-send-email-wei.huang@intel.com> <1654760242-7832-3-git-send-email-wei.huang@intel.com> In-Reply-To: <1654760242-7832-3-git-send-email-wei.huang@intel.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: dlp-product: dlpe-windows dlp-version: 11.6.500.17 dlp-reaction: no-action x-titus-metadata-40: eyJDYXRlZ29yeUxhYmVscyI6IiIsIk1ldGFkYXRhIjp7Im5zIjoiaHR0cDpcL1wvd3d3LnRpdHVzLmNvbVwvbnNcL0ludGVsMyIsImlkIjoiOWZkMmUxNTMtNWZiNy00ODFlLTg5NTktODFkYzg1MWYxYjQyIiwicHJvcHMiOlt7Im4iOiJDVFBDbGFzc2lmaWNhdGlvbiIsInZhbHMiOlt7InZhbHVlIjoiQ1RQX05UIn1dfV19LCJTdWJqZWN0TGFiZWxzIjpbXSwiVE1DVmVyc2lvbiI6IjE3LjEwLjE4MDQuNDkiLCJUcnVzdGVkTGFiZWxIYXNoIjoiOGdjakQ1NlJCOUFyWVJkT2t5SENSMXZlaWVxNXBNNndWSmpKbjlwV2s4Y25KZlYrTGdNTFJYOUpYdWg3ZGNJciJ9 x-ctpclassification: CTP_NT authentication-results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=intel.com; x-ms-publictraffictype: Email x-ms-office365-filtering-correlation-id: 1c12ecf1-40c7-453c-bc8f-08da4e9dc392 x-ms-traffictypediagnostic: BY5PR11MB4370:EE_ x-microsoft-antispam-prvs: 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:DM6PR11MB4252.namprd11.prod.outlook.com; PTR:; CAT:NONE; SFS:(13230016)(366004)(5660300002)(2906002)(8936002)(82960400001)(52536014)(33656002)(122000001)(86362001)(508600001)(38100700002)(7696005)(186003)(76116006)(83380400001)(66556008)(66946007)(66446008)(66476007)(110136005)(38070700005)(53546011)(54906003)(26005)(316002)(4326008)(30864003)(8676002)(55016003)(107886003)(71200400001)(9686003)(64756008)(6506007)(579004)(559001); DIR:OUT; SFP:1102; x-ms-exchange-antispam-messagedata-chunkcount: 1 x-ms-exchange-antispam-messagedata-0: =?us-ascii?Q?JeSFKyEOwscv1lktUcZNpesHyq/Y3/WBGqXfR3iDo2K0Y3GYRyeNj90pXYWS?= =?us-ascii?Q?CzLwY3EtzAsKGAaQQgb0hx6mtpOyA2ixAwxttHINhz2yL1h7JxbCxK3mQ5HM?= =?us-ascii?Q?LaFU6MWWGn80a+C29vxDRMP8NveQP58sRENfN1kcMC3c5KB/bw55IzT34Dja?= =?us-ascii?Q?7q0VP7J+HrcjnAM1kmIkqzAZncZy/SQmtwhcn6QkrUu00qMkUwZyul9uySfB?= =?us-ascii?Q?+yPxfJ5Q7BuD+1+d0m10LQvC7XeKD7kxUwuCFVbSdZkQ/SrTyZmV+8NyWZes?= =?us-ascii?Q?mSbaiKw9xs/Uzy5T0SCDattvxeAV+04AHuSVn7EApQopSlWM1jz/JXT+vvn6?= =?us-ascii?Q?I1NNqpf4ev37W9GD04Gd+BmDMEkBOOMMlxZz6TuVapxIp9riWHO2mBFwQsKo?= =?us-ascii?Q?XD5nDVxOLPIhuqosPScsysSEPjItligMYfwy9259fAqiaiSFLINiHl7Kl6L3?= =?us-ascii?Q?ypCCYw74K7Kkr3h73yPI6sb/uoEDJjBzJGlM7MR2g/8feTAaPUkUryL4paE5?= =?us-ascii?Q?7de2+OthyghPSd0YkuAjNcpABnNtDRgPRE0X8GMmXZJuKEg25f4Y/rCfctiO?= =?us-ascii?Q?pElOD9Q99Wso9ysETtcPLC2/bO++xoL6Ou9KDZFZQoZNF1gwtWICRPKBKR1Z?= =?us-ascii?Q?oOdSf3y082LPs9WGUyDxHbFIOpwhVHQ6M5nIN5W+fgphsZYDZ4XlbjdlGhny?= =?us-ascii?Q?ma3pGrZuxqSuzTRW0w3AVc+Ulf7Pgbfkyk4h+8SpNf08UNRPIXHn78/De67z?= =?us-ascii?Q?Q4SoVwUYl2Tu6+RdYEriB+jfTMYN41AmhOVk0DN+UwpdKrUaLcqzcmQnNbMl?= =?us-ascii?Q?K8+8V9mUkwibtobWepPJSuJfdbZ34P8kRU1T8GXFO8P75UDrPChUc8ln9BhA?= =?us-ascii?Q?0pReVUoYQnCCyDsqZvWmp4l5QHCgLpBDkW/oJg6U+SsGRbvL+u+LkyZ8VLJn?= =?us-ascii?Q?JoqDmv7R3gYe9oH7v+BlzJ2xyk3uj50QSbcUH71HD4Qp7woEt/yZEDX4F1PP?= =?us-ascii?Q?q+OrvuBpZAF+RhZIYPyz3/TOPBlXDou0NhzYW2eUNL0xvnHZEX6NRgNMfM0Q?= =?us-ascii?Q?CuvNSlfhvRKu9/JTfzXLA0yaMmeY05DaGQGYYy8/KNWlJ5wO6aH8t9f/alCx?= =?us-ascii?Q?wyW6eCZ+pBN8iRT8TYCJPJqF0L1omz0HRRkEBx6umN9SbL++z5nZKL3RcZsY?= =?us-ascii?Q?Wovwp7kvs0SBAJuKAQJ48ldemWUTW+wX3yuoGwnQs+KN9/eHhRrr2kAq/LgS?= =?us-ascii?Q?kys7iBkuqNdEQ3ryx+/xeJiwQTpDQxK77Z060LCfj7LWU2qfbLCsGbHPyIpK?= =?us-ascii?Q?uamOFFEYl2AaRyBDTTu9eSPDXiS3e7gXbqnBssAVrCJEE5NQ8DTkJD4e026l?= =?us-ascii?Q?aUQOOVKsmjDoSBANSOHSEO17/kGvIfrINbSCAidwJsvgtNg7NOcrYrpaNBT2?= =?us-ascii?Q?AwMDQ97AVNNR1BfHhWQoB0YwwFb7OnDe4/B+K9o400NuMJXKN8K9Kskn6STQ?= =?us-ascii?Q?+0Vh/rlaFGAU8SOX9JxLDXjQU+a6/lx2Fn6K+/41MM+HKSB/jrUZkPq+uEWk?= =?us-ascii?Q?68i3KsfWpI5P7aIbTeFTwEe0KOOapBsVSo60/otf6Xtxvz++/Dwipw7p6SHE?= =?us-ascii?Q?Szj7U88tj9gHbvqnsUNsr4NwAAbV/SiFKFbAGx5g429m2raEDzohrtzM7uFj?= =?us-ascii?Q?uoFgzFw0RMj7seGlhP7P1doCg0QcfukwZo2cBanVe8bCkk4NcrL0//4CRKiG?= =?us-ascii?Q?wygiFNT3dw=3D=3D?= 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: DM6PR11MB4252.namprd11.prod.outlook.com X-MS-Exchange-CrossTenant-Network-Message-Id: 1c12ecf1-40c7-453c-bc8f-08da4e9dc392 X-MS-Exchange-CrossTenant-originalarrivaltime: 15 Jun 2022 07:07:52.3727 (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: cla/CxaexlVkA6g0SuMYag+VlItAFYmj/vIRFMmDGmPICUKef6xAeM0+JaZT16UlmIKAUW/CPKDC0j8cAGjGBw== X-MS-Exchange-Transport-CrossTenantHeadersStamped: BY5PR11MB4370 X-OriginatorOrg: intel.com X-BeenThere: stable@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: patches for DPDK stable branches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: stable-bounces@dpdk.org Hi Wei, Some comments. Thanks, Rosen > -----Original Message----- > From: Huang, Wei > Sent: Thursday, June 09, 2022 15:37 > To: dev@dpdk.org; thomas@monjalon.net; nipun.gupta@nxp.com; > hemant.agrawal@nxp.com > Cc: stable@dpdk.org; Xu, Rosen ; Zhang, Tianfei > ; Zhang, Qi Z ; Huang, Wei > > Subject: [PATCH v7 2/5] raw/ifpga: add N3000 AFU driver >=20 > N3000 AFU includes NLB0 and DMA modules, NLB0 is used to test PCI bus > and DMA is used to test local memory. > This driver initialize the modules and report test result. >=20 > Signed-off-by: Wei Huang > --- > v2: move source files to ifpga and rename, refine code > --- > v3: fix Ubuntu 20.04 ARM build > --- > drivers/raw/ifpga/afu_pmd_core.h | 19 + > drivers/raw/ifpga/afu_pmd_n3000.c | 2019 > +++++++++++++++++++++++++++++++++++++ > drivers/raw/ifpga/afu_pmd_n3000.h | 339 +++++++ > drivers/raw/ifpga/meson.build | 3 +- > drivers/raw/ifpga/rte_pmd_afu.h | 97 ++ > 5 files changed, 2476 insertions(+), 1 deletion(-) > create mode 100644 drivers/raw/ifpga/afu_pmd_n3000.c > create mode 100644 drivers/raw/ifpga/afu_pmd_n3000.h > create mode 100644 drivers/raw/ifpga/rte_pmd_afu.h >=20 > diff --git a/drivers/raw/ifpga/afu_pmd_core.h > b/drivers/raw/ifpga/afu_pmd_core.h > index 4fad2c7..a938172 100644 > --- a/drivers/raw/ifpga/afu_pmd_core.h > +++ b/drivers/raw/ifpga/afu_pmd_core.h > @@ -14,6 +14,7 @@ > #include >=20 > #include > +#include > #include > #include >=20 > @@ -60,6 +61,24 @@ struct afu_rawdev { > return rawdev ? (struct afu_rawdev *)rawdev->dev_private : NULL; > } >=20 > +#define CLS_TO_SIZE(n) ((n) << 6) /* get size of n cache lines */ > +#define SIZE_TO_CLS(s) ((s) >> 6) /* convert size to number of cache l= ines > */ > +#define MHZ(f) ((f) * 1000000) > + > +#define dsm_poll_timeout(addr, val, cond, invl, timeout) \ > +({ \ > + uint64_t __wait =3D 0; \ > + uint64_t __invl =3D (invl); \ > + uint64_t __timeout =3D (timeout); \ > + for (; __wait <=3D __timeout; __wait +=3D __invl) { \ > + (val) =3D *(addr); \ > + if (cond) \ > + break; \ > + rte_delay_ms(__invl); \ > + } \ > + (cond) ? 0 : 1; \ > +}) > + > void afu_pmd_register(struct afu_rawdev_drv *driver); > void afu_pmd_unregister(struct afu_rawdev_drv *driver); >=20 > diff --git a/drivers/raw/ifpga/afu_pmd_n3000.c > b/drivers/raw/ifpga/afu_pmd_n3000.c > new file mode 100644 > index 0000000..14f7fe0 > --- /dev/null > +++ b/drivers/raw/ifpga/afu_pmd_n3000.c > @@ -0,0 +1,2019 @@ > +/* SPDX-License-Identifier: BSD-3-Clause > + * Copyright(c) 2022 Intel Corporation > + */ > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +#include "afu_pmd_core.h" > +#include "afu_pmd_n3000.h" > + > +static int nlb_afu_config(struct afu_rawdev *dev) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + struct rte_pmd_afu_nlb_cfg *cfg =3D NULL; > + struct nlb_csr_cfg v; > + > + if (!dev) > + return -EINVAL; > + > + if (!dev->priv) > + return -ENOENT; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + cfg =3D &priv->nlb_cfg; > + > + v.csr =3D 0; > + > + if (cfg->cont) > + v.cont =3D 1; > + > + if (cfg->cache_policy =3D=3D NLB_WRPUSH_I) > + v.wrpush_i =3D 1; > + else > + v.wrthru_en =3D cfg->cache_policy; > + > + if (cfg->cache_hint =3D=3D NLB_RDLINE_MIXED) > + v.rdsel =3D 3; > + else > + v.rdsel =3D cfg->cache_hint; > + > + v.mode =3D cfg->mode; > + v.chsel =3D cfg->read_vc; > + v.wr_chsel =3D cfg->write_vc; > + v.wrfence_chsel =3D cfg->wrfence_vc; > + v.wrthru_en =3D cfg->cache_policy; > + v.multicl_len =3D cfg->multi_cl - 1; > + > + IFPGA_RAWDEV_PMD_DEBUG("cfg: 0x%08x", v.csr); > + rte_write32(v.csr, priv->nlb_ctx.addr + CSR_CFG); > + > + return 0; > +} > + > +static void nlb_afu_report(struct afu_rawdev *dev, uint32_t cl) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + struct rte_pmd_afu_nlb_cfg *cfg =3D NULL; > + struct nlb_dsm_status *stat =3D NULL; > + uint64_t ticks =3D 0; > + double num, rd_bw, wr_bw; > + > + if (!dev || !dev->priv) > + return; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + > + cfg =3D &priv->nlb_cfg; > + stat =3D priv->nlb_ctx.status_ptr; > + > + if (cfg->cont) > + ticks =3D stat->num_clocks - stat->start_overhead; > + else > + ticks =3D stat->num_clocks - > + (stat->start_overhead + stat->end_overhead); > + > + if (cfg->freq_mhz =3D=3D 0) > + cfg->freq_mhz =3D 200; > + > + num =3D (double)stat->num_reads; > + rd_bw =3D (num * CLS_TO_SIZE(1) * MHZ(cfg->freq_mhz)) / ticks; > + num =3D (double)stat->num_writes; > + wr_bw =3D (num * CLS_TO_SIZE(1) * MHZ(cfg->freq_mhz)) / ticks; > + > + printf("Cachelines Read_Count Write_Count Clocks@%uMHz " > + "Rd_Bandwidth Wr_Bandwidth\n", cfg->freq_mhz); > + printf("%10u %10u %11u %12"PRIu64" %7.3f GB/s %7.3f GB/s\n", > + cl, stat->num_reads, stat->num_writes, ticks, > + rd_bw / 1e9, wr_bw / 1e9); > +} > + > +static int nlb_afu_test(struct afu_rawdev *dev) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + struct nlb_afu_ctx *ctx =3D NULL; > + struct rte_pmd_afu_nlb_cfg *cfg =3D NULL; > + struct nlb_csr_ctl ctl; > + uint32_t *ptr =3D NULL; > + uint32_t i, j, cl, val =3D 0; > + uint64_t sval =3D 0; > + int ret =3D 0; > + > + if (!dev) > + return -EINVAL; > + > + if (!dev->priv) > + return -ENOENT; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + ctx =3D &priv->nlb_ctx; > + cfg =3D &priv->nlb_cfg; > + > + /* initialize registers */ > + IFPGA_RAWDEV_PMD_DEBUG("dsm_addr: 0x%"PRIx64, ctx- > >dsm_iova); > + rte_write64(ctx->dsm_iova, ctx->addr + CSR_AFU_DSM_BASEL); > + > + ctl.csr =3D 0; > + rte_write32(ctl.csr, ctx->addr + CSR_CTL); > + ctl.reset =3D 1; > + rte_write32(ctl.csr, ctx->addr + CSR_CTL); > + > + IFPGA_RAWDEV_PMD_DEBUG("src_addr: 0x%"PRIx64, ctx- > >src_iova); > + rte_write64(SIZE_TO_CLS(ctx->src_iova), ctx->addr + > CSR_SRC_ADDR); > + IFPGA_RAWDEV_PMD_DEBUG("dst_addr: 0x%"PRIx64, ctx- > >dest_iova); > + rte_write64(SIZE_TO_CLS(ctx->dest_iova), ctx->addr + > CSR_DST_ADDR); > + > + ret =3D nlb_afu_config(dev); > + if (ret) > + return ret; > + > + /* initialize src data */ > + ptr =3D (uint32_t *)ctx->src_ptr; > + j =3D CLS_TO_SIZE(cfg->end) >> 2; > + for (i =3D 0; i < j; i++) > + *ptr++ =3D i; > + > + /* start test */ > + for (cl =3D cfg->begin; cl <=3D cfg->end; cl +=3D cfg->multi_cl) { > + memset(ctx->dest_ptr, 0, CLS_TO_SIZE(cl)); > + memset(ctx->dsm_ptr, 0, DSM_SIZE); > + > + ctl.csr =3D 0; > + rte_write32(ctl.csr, ctx->addr + CSR_CTL); > + ctl.reset =3D 1; > + rte_write32(ctl.csr, ctx->addr + CSR_CTL); > + > + rte_write32(cl, ctx->addr + CSR_NUM_LINES); > + > + rte_delay_us(10); > + > + ctl.start =3D 1; > + rte_write32(ctl.csr, ctx->addr + CSR_CTL); > + > + if (cfg->cont) { > + rte_delay_ms(cfg->timeout * 1000); > + ctl.force_completion =3D 1; > + rte_write32(ctl.csr, ctx->addr + CSR_CTL); > + ret =3D dsm_poll_timeout(&ctx->status_ptr- > >test_complete, > + val, (val & 0x1) =3D=3D 1, DSM_POLL_INTERVAL, > + DSM_TIMEOUT); > + if (ret) { > + printf("DSM poll timeout\n"); > + goto end; > + } > + } else { > + ret =3D dsm_poll_timeout(&ctx->status_ptr- > >test_complete, > + val, (val & 0x1) =3D=3D 1, DSM_POLL_INTERVAL, > + DSM_TIMEOUT); > + if (ret) { > + printf("DSM poll timeout\n"); > + goto end; > + } > + ctl.force_completion =3D 1; > + rte_write32(ctl.csr, ctx->addr + CSR_CTL); > + } > + > + nlb_afu_report(dev, cl); > + > + i =3D 0; > + while (i++ < 100) { > + sval =3D rte_read64(ctx->addr + CSR_STATUS1); > + if (sval =3D=3D 0) > + break; > + rte_delay_us(1000); > + } > + > + ptr =3D (uint32_t *)ctx->dest_ptr; > + j =3D CLS_TO_SIZE(cl) >> 2; > + for (i =3D 0; i < j; i++) { > + if (*ptr++ !=3D i) { > + IFPGA_RAWDEV_PMD_ERR("Data mismatch > @ %u", i); > + break; > + } > + } > + } > + > +end: > + return ret; > +} > + > +static void dma_afu_buf_free(struct dma_afu_ctx *ctx) > +{ > + int i =3D 0; > + > + if (!ctx) > + return; > + > + for (i =3D 0; i < NUM_DMA_BUF; i++) { > + rte_free(ctx->dma_buf[i]); > + ctx->dma_buf[i] =3D NULL; > + } > + > + rte_free(ctx->data_buf); > + ctx->data_buf =3D NULL; > + > + rte_free(ctx->ref_buf); > + ctx->ref_buf =3D NULL; > +} > + > +static int dma_afu_buf_alloc(struct dma_afu_ctx *ctx, > + struct rte_pmd_afu_dma_cfg *cfg) > +{ > + size_t page_sz =3D sysconf(_SC_PAGE_SIZE); > + int i, ret =3D 0; > + > + if (!ctx || !cfg) > + return -EINVAL; > + > + for (i =3D 0; i < NUM_DMA_BUF; i++) { > + ctx->dma_buf[i] =3D (uint64_t *)rte_zmalloc(NULL, cfg->size, > + TEST_MEM_ALIGN); > + if (!ctx->dma_buf[i]) { > + ret =3D -ENOMEM; > + goto free_dma_buf; > + } > + ctx->dma_iova[i] =3D rte_malloc_virt2iova(ctx->dma_buf[i]); > + if (ctx->dma_iova[i] =3D=3D RTE_BAD_IOVA) { > + ret =3D -ENOMEM; > + goto free_dma_buf; > + } > + } > + > + ctx->data_buf =3D rte_malloc(NULL, cfg->length, page_sz); > + if (!ctx->data_buf) { > + ret =3D -ENOMEM; > + goto free_dma_buf; > + } > + > + ctx->ref_buf =3D rte_malloc(NULL, cfg->length, page_sz); > + if (!ctx->ref_buf) { > + ret =3D -ENOMEM; > + goto free_data_buf; > + } > + > + return 0; > + > +free_data_buf: > + rte_free(ctx->data_buf); > + ctx->data_buf =3D NULL; > +free_dma_buf: > + for (i =3D 0; i < NUM_DMA_BUF; i++) { > + rte_free(ctx->dma_buf[i]); > + ctx->dma_buf[i] =3D NULL; > + } > + return ret; > +} > + > +static void dma_afu_buf_init(struct dma_afu_ctx *ctx, size_t size) > +{ > + int *ptr =3D NULL; > + size_t i =3D 0; > + size_t dword_size =3D 0; > + > + if (!ctx || !size) > + return; > + > + ptr =3D (int *)ctx->ref_buf; > + > + if (ctx->pattern) { > + memset(ptr, ctx->pattern, size); > + } else { > + srand(99); > + dword_size =3D size >> 2; > + for (i =3D 0; i < dword_size; i++) > + *ptr++ =3D rand(); > + } > + rte_memcpy(ctx->data_buf, ctx->ref_buf, size); > +} > + > +static int dma_afu_buf_verify(struct dma_afu_ctx *ctx, size_t size) > +{ > + uint8_t *src =3D NULL; > + uint8_t *dst =3D NULL; > + size_t i =3D 0; > + int n =3D 0; > + > + if (!ctx || !size) > + return -EINVAL; > + > + src =3D (uint8_t *)ctx->ref_buf; > + dst =3D (uint8_t *)ctx->data_buf; > + > + if (memcmp(src, dst, size)) { > + printf("Transfer is corrupted\n"); > + if (ctx->verbose) { > + for (i =3D 0; i < size; i++) { > + if (*src !=3D *dst) { > + if (++n >=3D ERR_CHECK_LIMIT) > + break; > + printf("Mismatch at 0x%zx, " > + "Expected %02x > Actual %02x\n", > + i, *src, *dst); > + } > + src++; > + dst++; > + } > + if (n < ERR_CHECK_LIMIT) { > + printf("Found %d error bytes\n", n); > + } else { > + printf("......\n"); > + printf("Found more than %d error bytes\n", > n); > + } > + } > + return -1; > + } > + > + printf("Transfer is verified\n"); > + return 0; > +} > + > +static void blk_write64(uint64_t *dev_addr, uint64_t *host_addr, uint64_= t > bytes) > +{ > + uint64_t qwords =3D bytes / sizeof(uint64_t); > + > + if (!IS_ALIGNED_QWORD((uint64_t)dev_addr) || > + !IS_ALIGNED_QWORD((uint64_t)bytes)) > + return; > + > + for (; qwords > 0; qwords--, host_addr++, dev_addr++) > + rte_write64(*host_addr, dev_addr); > +} > + > +static void blk_read64(uint64_t *dev_addr, uint64_t *host_addr, uint64_t > bytes) > +{ > + uint64_t qwords =3D bytes / sizeof(uint64_t); > + > + if (!IS_ALIGNED_QWORD((uint64_t)dev_addr) || > + !IS_ALIGNED_QWORD((uint64_t)bytes)) > + return; > + > + for (; qwords > 0; qwords--, host_addr++, dev_addr++) > + *host_addr =3D rte_read64(dev_addr); > +} > + > +static void switch_ase_page(struct dma_afu_ctx *ctx, uint64_t addr) > +{ > + uint64_t requested_page =3D addr & ~DMA_ASE_WINDOW_MASK; > + > + if (!ctx) > + return; > + > + if (requested_page !=3D ctx->cur_ase_page) { > + rte_write64(requested_page, ctx->ase_ctrl_addr); > + ctx->cur_ase_page =3D requested_page; > + } > +} > + > +static int ase_write_unaligned(struct dma_afu_ctx *ctx, uint64_t dev_add= r, > + uint64_t host_addr, uint32_t count) > +{ > + uint64_t dev_aligned_addr =3D 0; > + uint64_t shift =3D 0; > + uint64_t val =3D 0; > + uintptr_t addr =3D (uintptr_t)host_addr; /* transfer to pointer size *= / > + > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" --> 0x%"PRIx64" > (0x%x)", host_addr, > + dev_addr, count); > + > + if (!ctx || (count >=3D QWORD_BYTES)) > + return -EINVAL; > + > + if (!count) > + return 0; > + > + switch_ase_page(ctx, dev_addr); > + > + shift =3D dev_addr % QWORD_BYTES; > + dev_aligned_addr =3D (dev_addr - shift) & DMA_ASE_WINDOW_MASK; > + val =3D rte_read64(ctx->ase_data_addr + dev_aligned_addr); > + rte_memcpy(((char *)(&val)) + shift, (void *)addr, count); > + > + /* write back to device */ > + rte_write64(val, ctx->ase_data_addr + dev_aligned_addr); > + > + return 0; > +} > + > +static int ase_write(struct dma_afu_ctx *ctx, uint64_t *dst_ptr, > + uint64_t *src_ptr, uint64_t *count) > +{ > + uint64_t src =3D *src_ptr; > + uint64_t dst =3D *dst_ptr; > + uint64_t align_bytes =3D *count; > + uint64_t offset =3D 0; > + uint64_t left_in_page =3D DMA_ASE_WINDOW; > + uint64_t size_to_copy =3D 0; > + > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" --> 0x%"PRIx64" > (0x%"PRIx64")", src, dst, > + align_bytes); > + > + if (!ctx || !IS_ALIGNED_DWORD(dst)) > + return -EINVAL; > + > + if (align_bytes < DWORD_BYTES) > + return 0; > + > + if (!IS_ALIGNED_QWORD(dst)) { > + /* Write out a single DWORD to get QWORD aligned */ > + switch_ase_page(ctx, dst); > + offset =3D dst & DMA_ASE_WINDOW_MASK; > + > + rte_write32(*(uint32_t *)(uintptr_t)src, > + ctx->ase_data_addr + offset); > + src +=3D DWORD_BYTES; > + dst +=3D DWORD_BYTES; > + align_bytes -=3D DWORD_BYTES; > + } > + > + if (!align_bytes) > + return 0; > + > + /* Write out blocks of 64-bit values */ > + while (align_bytes >=3D QWORD_BYTES) { > + left_in_page -=3D dst & DMA_ASE_WINDOW_MASK; > + size_to_copy =3D > + MIN(left_in_page, (align_bytes & ~(QWORD_BYTES - > 1))); > + if (size_to_copy < QWORD_BYTES) > + break; > + switch_ase_page(ctx, dst); > + offset =3D dst & DMA_ASE_WINDOW_MASK; > + blk_write64((uint64_t *)(ctx->ase_data_addr + offset), > + (uint64_t *)(uintptr_t)src, size_to_copy); > + src +=3D size_to_copy; > + dst +=3D size_to_copy; > + align_bytes -=3D size_to_copy; > + } > + > + if (align_bytes >=3D DWORD_BYTES) { > + /* Write out remaining DWORD */ > + switch_ase_page(ctx, dst); > + offset =3D dst & DMA_ASE_WINDOW_MASK; > + rte_write32(*(uint32_t *)(uintptr_t)src, > + ctx->ase_data_addr + offset); > + src +=3D DWORD_BYTES; > + dst +=3D DWORD_BYTES; > + align_bytes -=3D DWORD_BYTES; > + } > + > + *src_ptr =3D src; > + *dst_ptr =3D dst; > + *count =3D align_bytes; > + > + return 0; > +} > + > +static int ase_host_to_fpga(struct dma_afu_ctx *ctx, uint64_t *dst_ptr, > + uint64_t *src_ptr, uint64_t count) > +{ > + uint64_t dst =3D *dst_ptr; > + uint64_t src =3D *src_ptr; > + uint64_t count_left =3D count; > + uint64_t unaligned_size =3D 0; > + int ret =3D 0; > + > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" --> 0x%"PRIx64" > (0x%"PRIx64")", src, dst, > + count); > + > + /* aligns address to 8 byte using dst masking method */ > + if (!IS_ALIGNED_DWORD(dst) && !IS_ALIGNED_QWORD(dst)) { > + unaligned_size =3D QWORD_BYTES - (dst % QWORD_BYTES); > + if (unaligned_size > count_left) > + unaligned_size =3D count_left; > + ret =3D ase_write_unaligned(ctx, dst, src, unaligned_size); > + if (ret) > + return ret; > + count_left -=3D unaligned_size; > + src +=3D unaligned_size; > + dst +=3D unaligned_size; > + } > + > + /* Handles 8/4 byte MMIO transfer */ > + ret =3D ase_write(ctx, &dst, &src, &count_left); > + if (ret) > + return ret; > + > + /* Left over unaligned bytes transferred using dst masking method > */ > + unaligned_size =3D QWORD_BYTES - (dst % QWORD_BYTES); > + if (unaligned_size > count_left) > + unaligned_size =3D count_left; > + > + ret =3D ase_write_unaligned(ctx, dst, src, unaligned_size); > + if (ret) > + return ret; > + > + count_left -=3D unaligned_size; > + *dst_ptr =3D dst + unaligned_size; > + *src_ptr =3D src + unaligned_size; > + > + return 0; > +} > + > +static int ase_read_unaligned(struct dma_afu_ctx *ctx, uint64_t dev_addr= , > + uint64_t host_addr, uint32_t count) > +{ > + uint64_t dev_aligned_addr =3D 0; > + uint64_t shift =3D 0; > + uint64_t val =3D 0; > + uintptr_t addr =3D (uintptr_t)host_addr; /* transfer to pointer size *= / > + > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" <-- 0x%"PRIx64" > (0x%x)", host_addr, > + dev_addr, count); > + > + if (!ctx || (count >=3D QWORD_BYTES)) > + return -EINVAL; > + > + if (!count) > + return 0; > + > + switch_ase_page(ctx, dev_addr); > + > + shift =3D dev_addr % QWORD_BYTES; > + dev_aligned_addr =3D (dev_addr - shift) & DMA_ASE_WINDOW_MASK; > + val =3D rte_read64(ctx->ase_data_addr + dev_aligned_addr); > + rte_memcpy((void *)addr, ((char *)(&val)) + shift, count); > + > + return 0; > +} > + > +static int ase_read(struct dma_afu_ctx *ctx, uint64_t *src_ptr, > + uint64_t *dst_ptr, uint64_t *count) > +{ > + uint64_t src =3D *src_ptr; > + uint64_t dst =3D *dst_ptr; > + uint64_t align_bytes =3D *count; > + uint64_t offset =3D 0; > + uint64_t left_in_page =3D DMA_ASE_WINDOW; > + uint64_t size_to_copy =3D 0; > + > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" <-- 0x%"PRIx64" > (0x%"PRIx64")", dst, src, > + align_bytes); > + > + if (!ctx || !IS_ALIGNED_DWORD(src)) > + return -EINVAL; > + > + if (align_bytes < DWORD_BYTES) > + return 0; > + > + if (!IS_ALIGNED_QWORD(src)) { > + /* Read a single DWORD to get QWORD aligned */ > + switch_ase_page(ctx, src); > + offset =3D src & DMA_ASE_WINDOW_MASK; > + *(uint32_t *)(uintptr_t)dst =3D > + rte_read32(ctx->ase_data_addr + offset); > + src +=3D DWORD_BYTES; > + dst +=3D DWORD_BYTES; > + align_bytes -=3D DWORD_BYTES; > + } > + > + if (!align_bytes) > + return 0; > + > + /* Read blocks of 64-bit values */ > + while (align_bytes >=3D QWORD_BYTES) { > + left_in_page -=3D src & DMA_ASE_WINDOW_MASK; > + size_to_copy =3D > + MIN(left_in_page, (align_bytes & ~(QWORD_BYTES - > 1))); > + if (size_to_copy < QWORD_BYTES) > + break; > + switch_ase_page(ctx, src); > + offset =3D src & DMA_ASE_WINDOW_MASK; > + blk_read64((uint64_t *)(ctx->ase_data_addr + offset), > + (uint64_t *)(uintptr_t)dst, size_to_copy); > + src +=3D size_to_copy; > + dst +=3D size_to_copy; > + align_bytes -=3D size_to_copy; > + } > + > + if (align_bytes >=3D DWORD_BYTES) { > + /* Read remaining DWORD */ > + switch_ase_page(ctx, src); > + offset =3D src & DMA_ASE_WINDOW_MASK; > + *(uint32_t *)(uintptr_t)dst =3D > + rte_read32(ctx->ase_data_addr + offset); > + src +=3D DWORD_BYTES; > + dst +=3D DWORD_BYTES; > + align_bytes -=3D DWORD_BYTES; > + } > + > + *src_ptr =3D src; > + *dst_ptr =3D dst; > + *count =3D align_bytes; > + > + return 0; > +} > + > +static int ase_fpga_to_host(struct dma_afu_ctx *ctx, uint64_t *src_ptr, > + uint64_t *dst_ptr, uint64_t count) > +{ > + uint64_t src =3D *src_ptr; > + uint64_t dst =3D *dst_ptr; > + uint64_t count_left =3D count; > + uint64_t unaligned_size =3D 0; > + int ret =3D 0; > + > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" --> 0x%"PRIx64" > (0x%"PRIx64")", src, dst, > + count); > + > + /* Aligns address to 8 byte using src masking method */ > + if (!IS_ALIGNED_DWORD(src) && !IS_ALIGNED_QWORD(src)) { > + unaligned_size =3D QWORD_BYTES - (src % QWORD_BYTES); > + if (unaligned_size > count_left) > + unaligned_size =3D count_left; > + ret =3D ase_read_unaligned(ctx, src, dst, unaligned_size); > + if (ret) > + return ret; > + count_left -=3D unaligned_size; > + dst +=3D unaligned_size; > + src +=3D unaligned_size; > + } > + > + /* Handles 8/4 byte MMIO transfer */ > + ret =3D ase_read(ctx, &src, &dst, &count_left); > + if (ret) > + return ret; > + > + /* Left over unaligned bytes transferred using src masking method */ > + unaligned_size =3D QWORD_BYTES - (src % QWORD_BYTES); > + if (unaligned_size > count_left) > + unaligned_size =3D count_left; > + > + ret =3D ase_read_unaligned(ctx, src, dst, unaligned_size); > + if (ret) > + return ret; > + > + count_left -=3D unaligned_size; > + *dst_ptr =3D dst + unaligned_size; > + *src_ptr =3D src + unaligned_size; > + > + return 0; > +} > + > +static void clear_interrupt(struct dma_afu_ctx *ctx) > +{ > + /* clear interrupt by writing 1 to IRQ bit in status register */ > + msgdma_status status; > + > + if (!ctx) > + return; > + > + status.csr =3D 0; > + status.irq =3D 1; > + rte_write32(status.csr, CSR_STATUS(ctx->csr_addr)); > +} > + > +static int poll_interrupt(struct dma_afu_ctx *ctx) > +{ > + struct pollfd pfd =3D {0}; > + uint64_t count =3D 0; > + ssize_t bytes_read =3D 0; > + int poll_ret =3D 0; > + int ret =3D 0; > + > + if (!ctx || (ctx->event_fd < 0)) > + return -EINVAL; > + > + pfd.fd =3D ctx->event_fd; > + pfd.events =3D POLLIN; > + poll_ret =3D poll(&pfd, 1, DMA_TIMEOUT_MSEC); > + if (poll_ret < 0) { > + IFPGA_RAWDEV_PMD_ERR("Error %s", strerror(errno)); > + ret =3D -EFAULT; > + goto out; > + } else if (poll_ret =3D=3D 0) { > + IFPGA_RAWDEV_PMD_ERR("Timeout"); > + ret =3D -ETIMEDOUT; > + } else { > + bytes_read =3D read(pfd.fd, &count, sizeof(count)); > + if (bytes_read > 0) { > + if (ctx->verbose) > + IFPGA_RAWDEV_PMD_DEBUG("Successful, > ret %d, cnt %"PRIu64, > + poll_ret, count); > + ret =3D 0; > + } else { > + IFPGA_RAWDEV_PMD_ERR("Failed %s", bytes_read > > 0 ? > + strerror(errno) : "zero bytes read"); > + ret =3D -EIO; > + } > + } > +out: > + clear_interrupt(ctx); > + return ret; > +} > + > +static void send_descriptor(struct dma_afu_ctx *ctx, msgdma_ext_desc > *desc) > +{ > + msgdma_status status; > + uint64_t fpga_queue_full =3D 0; > + > + if (!ctx) > + return; > + > + if (ctx->verbose) { > + IFPGA_RAWDEV_PMD_DEBUG("descriptor.rd_address =3D > 0x%x%08x", > + desc->rd_address_ext, desc->rd_address); > + IFPGA_RAWDEV_PMD_DEBUG("descriptor.wr_address =3D > 0x%x%08x", > + desc->wr_address_ext, desc->wr_address); > + IFPGA_RAWDEV_PMD_DEBUG("descriptor.len =3D %u", desc- > >len); > + IFPGA_RAWDEV_PMD_DEBUG("descriptor.wr_burst_count > =3D %u", > + desc->wr_burst_count); > + IFPGA_RAWDEV_PMD_DEBUG("descriptor.rd_burst_count > =3D %u", > + desc->rd_burst_count); > + IFPGA_RAWDEV_PMD_DEBUG("descriptor.wr_stride %u", > desc->wr_stride); > + IFPGA_RAWDEV_PMD_DEBUG("descriptor.rd_stride %u", > desc->rd_stride); > + } > + > + do { > + status.csr =3D rte_read32(CSR_STATUS(ctx->csr_addr)); > + if (fpga_queue_full++ > 100000000) { > + IFPGA_RAWDEV_PMD_DEBUG("DMA queue full > retry"); > + fpga_queue_full =3D 0; > + } > + } while (status.desc_buf_full); > + > + blk_write64((uint64_t *)ctx->desc_addr, (uint64_t *)desc, > + sizeof(*desc)); > +} > + > +static int do_dma(struct dma_afu_ctx *ctx, uint64_t dst, uint64_t src, > + int count, int is_last_desc, fpga_dma_type type, int intr_en) > +{ > + msgdma_ext_desc *desc =3D NULL; > + int alignment_offset =3D 0; > + int segment_size =3D 0; > + > + if (!ctx) > + return -EINVAL; > + > + /* src, dst and count must be 64-byte aligned */ > + if (!IS_DMA_ALIGNED(src) || !IS_DMA_ALIGNED(dst) || > + !IS_DMA_ALIGNED(count)) > + return -EINVAL; > + memset(ctx->desc_buf, 0, sizeof(msgdma_ext_desc)); > + > + /* these fields are fixed for all DMA transfers */ > + desc =3D ctx->desc_buf; > + desc->seq_num =3D 0; > + desc->wr_stride =3D 1; > + desc->rd_stride =3D 1; > + desc->control.go =3D 1; > + if (intr_en) > + desc->control.transfer_irq_en =3D 1; > + else > + desc->control.transfer_irq_en =3D 0; > + > + if (!is_last_desc) > + desc->control.early_done_en =3D 1; > + else > + desc->control.early_done_en =3D 0; > + > + if (type =3D=3D FPGA_TO_FPGA) { > + desc->rd_address =3D src & DMA_MASK_32_BIT; > + desc->wr_address =3D dst & DMA_MASK_32_BIT; > + desc->len =3D count; > + desc->wr_burst_count =3D 4; > + desc->rd_burst_count =3D 4; > + desc->rd_address_ext =3D (src >> 32) & DMA_MASK_32_BIT; > + desc->wr_address_ext =3D (dst >> 32) & DMA_MASK_32_BIT; > + send_descriptor(ctx, desc); > + } else { > + /* check CCIP (host) address is aligned to 4CL (256B) */ > + alignment_offset =3D (type =3D=3D HOST_TO_FPGA) > + ? (src % CCIP_ALIGN_BYTES) : (dst % > CCIP_ALIGN_BYTES); > + /* performing a short transfer to get aligned */ > + if (alignment_offset !=3D 0) { > + desc->rd_address =3D src & DMA_MASK_32_BIT; > + desc->wr_address =3D dst & DMA_MASK_32_BIT; > + desc->wr_burst_count =3D 1; > + desc->rd_burst_count =3D 1; > + desc->rd_address_ext =3D (src >> 32) & > DMA_MASK_32_BIT; > + desc->wr_address_ext =3D (dst >> 32) & > DMA_MASK_32_BIT; > + /* count isn't large enough to hit next 4CL boundary > */ > + if ((CCIP_ALIGN_BYTES - alignment_offset) >=3D count) > { > + segment_size =3D count; > + count =3D 0; > + } else { > + segment_size =3D CCIP_ALIGN_BYTES > + - alignment_offset; > + src +=3D segment_size; > + dst +=3D segment_size; > + count -=3D segment_size; > + desc->control.transfer_irq_en =3D 0; > + } > + /* post short transfer to align to a 4CL (256 byte) */ > + desc->len =3D segment_size; > + send_descriptor(ctx, desc); > + } > + /* at this point we are 4CL (256 byte) aligned */ > + if (count >=3D CCIP_ALIGN_BYTES) { > + desc->rd_address =3D src & DMA_MASK_32_BIT; > + desc->wr_address =3D dst & DMA_MASK_32_BIT; > + desc->wr_burst_count =3D 4; > + desc->rd_burst_count =3D 4; > + desc->rd_address_ext =3D (src >> 32) & > DMA_MASK_32_BIT; > + desc->wr_address_ext =3D (dst >> 32) & > DMA_MASK_32_BIT; > + /* buffer ends on 4CL boundary */ > + if ((count % CCIP_ALIGN_BYTES) =3D=3D 0) { > + segment_size =3D count; > + count =3D 0; > + } else { > + segment_size =3D count > + - (count % CCIP_ALIGN_BYTES); > + src +=3D segment_size; > + dst +=3D segment_size; > + count -=3D segment_size; > + desc->control.transfer_irq_en =3D 0; > + } > + desc->len =3D segment_size; > + send_descriptor(ctx, desc); > + } > + /* post short transfer to handle the remainder */ > + if (count > 0) { > + desc->rd_address =3D src & DMA_MASK_32_BIT; > + desc->wr_address =3D dst & DMA_MASK_32_BIT; > + desc->len =3D count; > + desc->wr_burst_count =3D 1; > + desc->rd_burst_count =3D 1; > + desc->rd_address_ext =3D (src >> 32) & > DMA_MASK_32_BIT; > + desc->wr_address_ext =3D (dst >> 32) & > DMA_MASK_32_BIT; > + if (intr_en) > + desc->control.transfer_irq_en =3D 1; > + send_descriptor(ctx, desc); > + } > + } > + > + return 0; > +} > + > +static int issue_magic(struct dma_afu_ctx *ctx) > +{ > + *(ctx->magic_buf) =3D 0ULL; > + return do_dma(ctx, DMA_WF_HOST_ADDR(ctx->magic_iova), > + DMA_WF_MAGIC_ROM, 64, 1, FPGA_TO_HOST, 1); > +} > + > +static void wait_magic(struct dma_afu_ctx *ctx) > +{ > + int magic_timeout =3D 0; > + > + if (!ctx) > + return; > + > + poll_interrupt(ctx); > + while (*(ctx->magic_buf) !=3D DMA_WF_MAGIC) { > + if (magic_timeout++ > 1000) { > + IFPGA_RAWDEV_PMD_ERR("DMA magic operation > timeout"); > + magic_timeout =3D 0; > + break; > + } > + } > + *(ctx->magic_buf) =3D 0ULL; > +} > + > +static int dma_tx_buf(struct dma_afu_ctx *ctx, uint64_t dst, uint64_t sr= c, > + uint64_t chunk, int is_last_chunk, int *intr_issued) > +{ > + int intr_en =3D 0; > + int ret =3D 0; > + > + if (!ctx || !intr_issued) > + return -EINVAL; > + > + src +=3D chunk * ctx->dma_buf_size; > + dst +=3D chunk * ctx->dma_buf_size; > + > + if (((chunk % HALF_DMA_BUF) =3D=3D (HALF_DMA_BUF - 1)) || > is_last_chunk) { > + if (*intr_issued) { > + ret =3D poll_interrupt(ctx); > + if (ret) > + return ret; > + } > + intr_en =3D 1; > + } > + > + chunk %=3D NUM_DMA_BUF; > + rte_memcpy(ctx->dma_buf[chunk], (void *)(uintptr_t)src, > + ctx->dma_buf_size); > + ret =3D do_dma(ctx, dst, DMA_HOST_ADDR(ctx->dma_iova[chunk]), > + ctx->dma_buf_size, 0, HOST_TO_FPGA, intr_en); > + if (intr_en) > + *intr_issued =3D 1; > + > + return ret; > +} > + > +static int dma_host_to_fpga(struct dma_afu_ctx *ctx, uint64_t dst, > uint64_t src, > + size_t count) > +{ > + uint64_t i =3D 0; > + uint64_t count_left =3D count; > + uint64_t aligned_addr =3D 0; > + uint64_t align_bytes =3D 0; > + uint64_t dma_chunks =3D 0; > + uint64_t dma_tx_bytes =3D 0; > + uint64_t offset =3D 0; > + int issued_intr =3D 0; > + int ret =3D 0; > + > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" ---> 0x%"PRIx64" > (%zu)", src, dst, > + count); > + > + if (!ctx) > + return -EINVAL; > + > + if (!IS_DMA_ALIGNED(dst)) { > + if (count_left < DMA_ALIGN_BYTES) > + return ase_host_to_fpga(ctx, &dst, &src, count_left); > + > + aligned_addr =3D ((dst / DMA_ALIGN_BYTES) + 1) > + * DMA_ALIGN_BYTES; > + align_bytes =3D aligned_addr - dst; > + ret =3D ase_host_to_fpga(ctx, &dst, &src, align_bytes); > + if (ret) > + return ret; > + count_left =3D count_left - align_bytes; > + } > + > + if (count_left) { > + dma_chunks =3D count_left / ctx->dma_buf_size; > + offset =3D dma_chunks * ctx->dma_buf_size; > + count_left -=3D offset; > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" ---> > 0x%"PRIx64 > + " (%"PRIu64"...0x%"PRIx64")", > + src, dst, dma_chunks, count_left); > + for (i =3D 0; i < dma_chunks; i++) { > + ret =3D dma_tx_buf(ctx, dst, src, i, > + i =3D=3D (dma_chunks - 1), &issued_intr); > + if (ret) > + return ret; > + } > + > + if (issued_intr) { > + ret =3D poll_interrupt(ctx); > + if (ret) > + return ret; > + } > + > + if (count_left) { > + i =3D count_left / DMA_ALIGN_BYTES; > + if (i > 0) { > + dma_tx_bytes =3D i * DMA_ALIGN_BYTES; > + IFPGA_RAWDEV_PMD_DEBUG("left over > 0x%"PRIx64" to DMA", > + dma_tx_bytes); > + rte_memcpy(ctx->dma_buf[0], > + (void *)(uintptr_t)(src + offset), > + dma_tx_bytes); > + ret =3D do_dma(ctx, dst + offset, > + DMA_HOST_ADDR(ctx- > >dma_iova[0]), > + dma_tx_bytes, 1, HOST_TO_FPGA, 1); > + if (ret) > + return ret; > + ret =3D poll_interrupt(ctx); > + if (ret) > + return ret; > + } > + > + count_left -=3D dma_tx_bytes; > + if (count_left) { > + IFPGA_RAWDEV_PMD_DEBUG("left over > 0x%"PRIx64" to ASE", > + count_left); > + dst +=3D offset + dma_tx_bytes; > + src +=3D offset + dma_tx_bytes; > + ret =3D ase_host_to_fpga(ctx, &dst, &src, > + count_left); > + } > + } > + } > + > + return ret; > +} > + > +static int dma_rx_buf(struct dma_afu_ctx *ctx, uint64_t dst, uint64_t sr= c, > + uint64_t chunk, int is_last_chunk, uint64_t *rx_count, int *wf_issued) > +{ > + uint64_t i =3D chunk % NUM_DMA_BUF; > + uint64_t n =3D *rx_count; > + uint64_t num_pending =3D 0; > + int ret =3D 0; > + > + if (!ctx || !wf_issued) > + return -EINVAL; > + > + ret =3D do_dma(ctx, DMA_HOST_ADDR(ctx->dma_iova[i]), > + src + chunk * ctx->dma_buf_size, > + ctx->dma_buf_size, 1, FPGA_TO_HOST, 0); > + if (ret) > + return ret; > + > + num_pending =3D chunk - n + 1; > + if (num_pending =3D=3D HALF_DMA_BUF) { > + ret =3D issue_magic(ctx); > + if (ret) { > + IFPGA_RAWDEV_PMD_DEBUG("Magic issue failed"); > + return ret; > + } > + *wf_issued =3D 1; > + } > + > + if ((num_pending > (NUM_DMA_BUF - 1)) || is_last_chunk) { > + if (*wf_issued) { > + wait_magic(ctx); > + for (i =3D 0; i < HALF_DMA_BUF; i++) { > + rte_memcpy((void *)(uintptr_t)(dst + > + n * ctx->dma_buf_size), > + ctx->dma_buf[n % NUM_DMA_BUF], > + ctx->dma_buf_size); > + n++; > + } > + *wf_issued =3D 0; > + *rx_count =3D n; > + } > + ret =3D issue_magic(ctx); > + if (ret) { > + IFPGA_RAWDEV_PMD_DEBUG("Magic issue failed"); > + return ret; > + } > + *wf_issued =3D 1; > + } > + > + return ret; > +} > + > +static int dma_fpga_to_host(struct dma_afu_ctx *ctx, uint64_t dst, > uint64_t src, > + size_t count) > +{ > + uint64_t i =3D 0; > + uint64_t count_left =3D count; > + uint64_t aligned_addr =3D 0; > + uint64_t align_bytes =3D 0; > + uint64_t dma_chunks =3D 0; > + uint64_t pending_buf =3D 0; > + uint64_t dma_rx_bytes =3D 0; > + uint64_t offset =3D 0; > + int wf_issued =3D 0; > + int ret =3D 0; > + > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" ---> 0x%"PRIx64" > (%zu)", src, dst, > + count); > + > + if (!ctx) > + return -EINVAL; > + > + if (!IS_DMA_ALIGNED(src)) { > + if (count_left < DMA_ALIGN_BYTES) > + return ase_fpga_to_host(ctx, &src, &dst, count_left); > + > + aligned_addr =3D ((src / DMA_ALIGN_BYTES) + 1) > + * DMA_ALIGN_BYTES; > + align_bytes =3D aligned_addr - src; > + ret =3D ase_fpga_to_host(ctx, &src, &dst, align_bytes); > + if (ret) > + return ret; > + count_left =3D count_left - align_bytes; > + } > + > + if (count_left) { > + dma_chunks =3D count_left / ctx->dma_buf_size; > + offset =3D dma_chunks * ctx->dma_buf_size; > + count_left -=3D offset; > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" ---> > 0x%"PRIx64 > + " (%"PRIu64"...0x%"PRIx64")", > + src, dst, dma_chunks, count_left); > + for (i =3D 0; i < dma_chunks; i++) { > + ret =3D dma_rx_buf(ctx, dst, src, i, > + i =3D=3D (dma_chunks - 1), > + &pending_buf, &wf_issued); > + if (ret) > + return ret; > + } > + > + if (wf_issued) > + wait_magic(ctx); > + > + /* clear out final dma memcpy operations */ > + while (pending_buf < dma_chunks) { > + /* constant size transfer; no length check required */ > + rte_memcpy((void *)(uintptr_t)(dst + > + pending_buf * ctx->dma_buf_size), > + ctx->dma_buf[pending_buf % > NUM_DMA_BUF], > + ctx->dma_buf_size); > + pending_buf++; > + } > + > + if (count_left > 0) { > + i =3D count_left / DMA_ALIGN_BYTES; > + if (i > 0) { > + dma_rx_bytes =3D i * DMA_ALIGN_BYTES; > + IFPGA_RAWDEV_PMD_DEBUG("left over > 0x%"PRIx64" to DMA", > + dma_rx_bytes); > + ret =3D do_dma(ctx, > + DMA_HOST_ADDR(ctx- > >dma_iova[0]), > + src + offset, > + dma_rx_bytes, 1, FPGA_TO_HOST, 0); > + if (ret) > + return ret; > + ret =3D issue_magic(ctx); > + if (ret) > + return ret; > + wait_magic(ctx); > + rte_memcpy((void *)(uintptr_t)(dst + offset), > + ctx->dma_buf[0], dma_rx_bytes); > + } > + > + count_left -=3D dma_rx_bytes; > + if (count_left) { > + IFPGA_RAWDEV_PMD_DEBUG("left over > 0x%"PRIx64" to ASE", > + count_left); > + dst +=3D offset + dma_rx_bytes; > + src +=3D offset + dma_rx_bytes; > + ret =3D ase_fpga_to_host(ctx, &src, &dst, > + count_left); > + } > + } > + } > + > + return ret; > +} > + > +static int dma_fpga_to_fpga(struct dma_afu_ctx *ctx, uint64_t dst, > uint64_t src, > + size_t count) > +{ > + uint64_t i =3D 0; > + uint64_t count_left =3D count; > + uint64_t dma_chunks =3D 0; > + uint64_t offset =3D 0; > + uint32_t tx_chunks =3D 0; > + uint64_t *tmp_buf =3D NULL; > + int ret =3D 0; > + > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" ---> 0x%"PRIx64" > (%zu)", src, dst, > + count); > + > + if (!ctx) > + return -EINVAL; > + > + if (IS_DMA_ALIGNED(dst) && IS_DMA_ALIGNED(src) > + && IS_DMA_ALIGNED(count_left)) { > + dma_chunks =3D count_left / ctx->dma_buf_size; > + offset =3D dma_chunks * ctx->dma_buf_size; > + count_left -=3D offset; > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" ---> > 0x%"PRIx64 > + " (%"PRIu64"...0x%"PRIx64")", > + src, dst, dma_chunks, count_left); > + for (i =3D 0; i < dma_chunks; i++) { > + ret =3D do_dma(ctx, dst + i * ctx->dma_buf_size, > + src + i * ctx->dma_buf_size, > + ctx->dma_buf_size, 0, FPGA_TO_FPGA, 0); > + if (ret) > + return ret; > + if ((((i + 1) % NUM_DMA_BUF) =3D=3D 0) || > + (i =3D=3D (dma_chunks - 1))) { > + ret =3D issue_magic(ctx); > + if (ret) > + return ret; > + wait_magic(ctx); > + } > + } > + > + if (count_left > 0) { > + IFPGA_RAWDEV_PMD_DEBUG("left over > 0x%"PRIx64" to DMA", count_left); > + ret =3D do_dma(ctx, dst + offset, src + offset, > + count_left, 1, FPGA_TO_FPGA, 0); > + if (ret) > + return ret; > + ret =3D issue_magic(ctx); > + if (ret) > + return ret; > + wait_magic(ctx); > + } > + } else { > + if ((src < dst) && (src + count_left > dst)) { > + IFPGA_RAWDEV_PMD_ERR("Overlapping: > 0x%"PRIx64 > + " -> 0x%"PRIx64" (0x%"PRIx64")", > + src, dst, count_left); > + return -EINVAL; > + } > + tx_chunks =3D count_left / ctx->dma_buf_size; > + offset =3D tx_chunks * ctx->dma_buf_size; > + count_left -=3D offset; > + IFPGA_RAWDEV_PMD_DEBUG("0x%"PRIx64" --> > 0x%"PRIx64 > + " (%u...0x%"PRIx64")", > + src, dst, tx_chunks, count_left); > + tmp_buf =3D (uint64_t *)rte_malloc(NULL, ctx->dma_buf_size, > + DMA_ALIGN_BYTES); > + for (i =3D 0; i < tx_chunks; i++) { > + ret =3D dma_fpga_to_host(ctx, (uint64_t)tmp_buf, > + src + i * ctx->dma_buf_size, > + ctx->dma_buf_size); > + if (ret) > + goto free_buf; > + ret =3D dma_host_to_fpga(ctx, > + dst + i * ctx->dma_buf_size, > + (uint64_t)tmp_buf, ctx->dma_buf_size); > + if (ret) > + goto free_buf; > + } > + > + if (count_left > 0) { > + ret =3D dma_fpga_to_host(ctx, (uint64_t)tmp_buf, > + src + offset, count_left); > + if (ret) > + goto free_buf; > + ret =3D dma_host_to_fpga(ctx, dst + offset, > + (uint64_t)tmp_buf, count_left); > + if (ret) > + goto free_buf; > + } > +free_buf: > + rte_free(tmp_buf); > + } > + > + return ret; > +} > + > +static int dma_transfer_sync(struct dma_afu_ctx *ctx, uint64_t dst, > + uint64_t src, size_t count, fpga_dma_type type) > +{ > + int ret =3D 0; > + > + if (!ctx) > + return -EINVAL; > + > + if (type =3D=3D HOST_TO_FPGA) > + ret =3D dma_host_to_fpga(ctx, dst, src, count); > + else if (type =3D=3D FPGA_TO_HOST) > + ret =3D dma_fpga_to_host(ctx, dst, src, count); > + else if (type =3D=3D FPGA_TO_FPGA) > + ret =3D dma_fpga_to_fpga(ctx, dst, src, count); > + else > + return -EINVAL; > + > + return ret; > +} > + > +static double getTime(struct timespec start, struct timespec end) > +{ > + uint64_t diff =3D 1000000000L * (end.tv_sec - start.tv_sec) > + + end.tv_nsec - start.tv_nsec; > + return (double)diff / (double)1000000000L; > +} > + Pls rename this function as DPDK program guide. > +#define SWEEP_ITERS 1 > +static int sweep_test(struct dma_afu_ctx *ctx, uint32_t length, > + uint64_t ddr_offset, uint64_t buf_offset, uint64_t size_decrement) > +{ > + struct timespec start, end; > + uint64_t test_size =3D 0; > + uint64_t *dma_buf_ptr =3D NULL; > + double throughput, total_time =3D 0.0; > + int i =3D 0; > + int ret =3D 0; > + > + if (!ctx || !ctx->data_buf || !ctx->ref_buf) { > + IFPGA_RAWDEV_PMD_ERR("Buffer for DMA test is not > allocated"); > + return -EINVAL; > + } > + > + if (length < (buf_offset + size_decrement)) { > + IFPGA_RAWDEV_PMD_ERR("Test length does not match > unaligned parameter"); > + return -EINVAL; > + } > + test_size =3D length - (buf_offset + size_decrement); > + if ((ddr_offset + test_size) > ctx->mem_size) { > + IFPGA_RAWDEV_PMD_ERR("Test is out of DDR memory > space"); > + return -EINVAL; > + } > + > + dma_buf_ptr =3D (uint64_t *)((uint8_t *)ctx->data_buf + buf_offset); > + printf("Sweep Host %p to FPGA 0x%"PRIx64 > + " with 0x%"PRIx64" bytes ...\n", > + (void *)dma_buf_ptr, ddr_offset, test_size); > + > + for (i =3D 0; i < SWEEP_ITERS; i++) { > + clock_gettime(CLOCK_MONOTONIC, &start); > + ret =3D dma_transfer_sync(ctx, ddr_offset, > (uint64_t)dma_buf_ptr, > + test_size, HOST_TO_FPGA); > + clock_gettime(CLOCK_MONOTONIC, &end); > + if (ret) { > + IFPGA_RAWDEV_PMD_ERR("Failed"); > + return ret; > + } > + total_time +=3D getTime(start, end); > + } > + throughput =3D (test_size * SWEEP_ITERS) / (total_time * 1000000); > + printf("Measured bandwidth =3D %lf MB/s\n", throughput); > + > + printf("Sweep FPGA 0x%"PRIx64" to Host %p with 0x%"PRIx64" > bytes ...\n", > + ddr_offset, (void *)dma_buf_ptr, test_size); > + > + total_time =3D 0.0; > + memset((char *)dma_buf_ptr, 0, test_size); > + for (i =3D 0; i < SWEEP_ITERS; i++) { > + clock_gettime(CLOCK_MONOTONIC, &start); > + ret =3D dma_transfer_sync(ctx, (uint64_t)dma_buf_ptr, > ddr_offset, > + test_size, FPGA_TO_HOST); > + clock_gettime(CLOCK_MONOTONIC, &end); > + if (ret) { > + IFPGA_RAWDEV_PMD_ERR("Failed"); > + return ret; > + } > + total_time +=3D getTime(start, end); > + } > + throughput =3D (test_size * SWEEP_ITERS) / (total_time * 1000000); > + printf("Measured bandwidth =3D %lf MB/s\n", throughput); > + > + printf("Verifying buffer ...\n"); > + return dma_afu_buf_verify(ctx, test_size); > +} > + > +static int dma_afu_test(struct afu_rawdev *dev) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + struct dma_afu_ctx *ctx =3D NULL; > + struct rte_pmd_afu_dma_cfg *cfg =3D NULL; > + msgdma_ctrl ctrl; > + uint64_t offset =3D 0; > + uint32_t i =3D 0; > + int ret =3D 0; > + > + if (!dev) > + return -EINVAL; > + > + if (!dev->priv) > + return -ENOENT; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + cfg =3D &priv->dma_cfg; > + if (cfg->index >=3D NUM_N3000_DMA) > + return -EINVAL; > + ctx =3D &priv->dma_ctx[cfg->index]; > + > + ctx->pattern =3D (int)cfg->pattern; > + ctx->verbose =3D (int)cfg->verbose; > + ctx->dma_buf_size =3D cfg->size; > + > + ret =3D dma_afu_buf_alloc(ctx, cfg); > + if (ret) > + goto free; > + > + printf("Initialize test buffer\n"); > + dma_afu_buf_init(ctx, cfg->length); > + > + /* enable interrupt */ > + ctrl.csr =3D 0; > + ctrl.global_intr_en_mask =3D 1; > + rte_write32(ctrl.csr, CSR_CONTROL(ctx->csr_addr)); > + > + printf("Host %p to FPGA 0x%x with 0x%x bytes\n", ctx->data_buf, > + cfg->offset, cfg->length); > + ret =3D dma_transfer_sync(ctx, cfg->offset, (uint64_t)ctx->data_buf, > + cfg->length, HOST_TO_FPGA); > + if (ret) { > + IFPGA_RAWDEV_PMD_ERR("Failed to transfer data from > host to FPGA"); > + goto end; > + } > + memset(ctx->data_buf, 0, cfg->length); > + > + printf("FPGA 0x%x to Host %p with 0x%x bytes\n", cfg->offset, > + ctx->data_buf, cfg->length); > + ret =3D dma_transfer_sync(ctx, (uint64_t)ctx->data_buf, cfg->offset, > + cfg->length, FPGA_TO_HOST); > + if (ret) { > + IFPGA_RAWDEV_PMD_ERR("Failed to transfer data from > FPGA to host"); > + goto end; > + } > + ret =3D dma_afu_buf_verify(ctx, cfg->length); > + if (ret) > + goto end; > + > + if ((cfg->offset + cfg->length * 2) <=3D ctx->mem_size) > + offset =3D cfg->offset + cfg->length; > + else if (cfg->offset > cfg->length) > + offset =3D 0; > + else > + goto end; > + > + printf("FPGA 0x%x to FPGA 0x%"PRIx64" with 0x%x bytes\n", > + cfg->offset, offset, cfg->length); > + ret =3D dma_transfer_sync(ctx, offset, cfg->offset, cfg->length, > + FPGA_TO_FPGA); > + if (ret) { > + IFPGA_RAWDEV_PMD_ERR("Failed to transfer data from > FPGA to FPGA"); > + goto end; > + } > + > + printf("FPGA 0x%"PRIx64" to Host %p with 0x%x bytes\n", offset, > + ctx->data_buf, cfg->length); > + ret =3D dma_transfer_sync(ctx, (uint64_t)ctx->data_buf, offset, > + cfg->length, FPGA_TO_HOST); > + if (ret) { > + IFPGA_RAWDEV_PMD_ERR("Failed to transfer data from > FPGA to host"); > + goto end; > + } > + ret =3D dma_afu_buf_verify(ctx, cfg->length); > + if (ret) > + goto end; > + > + printf("Sweep with aligned address and size\n"); > + ret =3D sweep_test(ctx, cfg->length, cfg->offset, 0, 0); > + if (ret) > + goto end; > + > + if (cfg->unaligned) { > + printf("Sweep with unaligned address and size\n"); > + struct unaligned_set { > + uint64_t addr_offset; > + uint64_t size_dec; > + } param[] =3D {{61, 5}, {3, 0}, {7, 3}, {0, 3}, {0, 61}, {0, 7}}; > + for (i =3D 0; i < ARRAY_SIZE(param); i++) { > + ret =3D sweep_test(ctx, cfg->length, cfg->offset, > + param[i].addr_offset, param[i].size_dec); > + if (ret) > + break; > + } > + } > + > +end: > + /* disable interrupt */ > + ctrl.global_intr_en_mask =3D 0; > + rte_write32(ctrl.csr, CSR_CONTROL(ctx->csr_addr)); > + > +free: > + dma_afu_buf_free(ctx); > + return ret; > +} > + > +static struct rte_pci_device *n3000_afu_get_pci_dev(struct afu_rawdev > *dev) > +{ > + struct rte_afu_device *afudev =3D NULL; > + > + if (!dev || !dev->rawdev || !dev->rawdev->device) > + return NULL; > + > + afudev =3D RTE_DEV_TO_AFU(dev->rawdev->device); > + if (!afudev->rawdev || !afudev->rawdev->device) > + return NULL; > + > + return RTE_DEV_TO_PCI(afudev->rawdev->device); > +} > + > +#ifdef VFIO_PRESENT > +static int dma_afu_set_irqs(struct afu_rawdev *dev, uint32_t vec_start, > + uint32_t count, int *efds) > +{ > + struct rte_pci_device *pci_dev =3D NULL; > + struct vfio_irq_set *irq_set =3D NULL; > + int vfio_dev_fd =3D 0; > + size_t sz =3D 0; > + int ret =3D 0; > + > + if (!dev || !efds || (count =3D=3D 0) || (count > MAX_MSIX_VEC)) > + return -EINVAL; > + > + pci_dev =3D n3000_afu_get_pci_dev(dev); > + if (!pci_dev) > + return -ENODEV; > + vfio_dev_fd =3D rte_intr_dev_fd_get(pci_dev->intr_handle); > + > + sz =3D sizeof(*irq_set) + sizeof(*efds) * count; > + irq_set =3D rte_zmalloc(NULL, sz, 0); > + if (!irq_set) > + return -ENOMEM; > + > + irq_set->argsz =3D (uint32_t)sz; > + irq_set->count =3D count; > + irq_set->flags =3D VFIO_IRQ_SET_DATA_EVENTFD | > + VFIO_IRQ_SET_ACTION_TRIGGER; > + irq_set->index =3D VFIO_PCI_MSIX_IRQ_INDEX; > + irq_set->start =3D vec_start; > + > + rte_memcpy(&irq_set->data, efds, sizeof(*efds) * count); > + ret =3D ioctl(vfio_dev_fd, VFIO_DEVICE_SET_IRQS, irq_set); > + if (ret) > + IFPGA_RAWDEV_PMD_ERR("Error enabling MSI-X > interrupts\n"); > + > + rte_free(irq_set); > + return ret; > +} > +#endif > + > +static void *n3000_afu_get_port_addr(struct afu_rawdev *dev) > +{ > + struct rte_pci_device *pci_dev =3D NULL; > + uint8_t *addr =3D NULL; > + uint64_t val =3D 0; > + uint32_t bar =3D 0; > + > + pci_dev =3D n3000_afu_get_pci_dev(dev); > + if (!pci_dev) > + return NULL; > + > + addr =3D (uint8_t *)pci_dev->mem_resource[0].addr; > + val =3D rte_read64(addr + PORT_ATTR_REG(dev->port)); > + if (!PORT_IMPLEMENTED(val)) { > + IFPGA_RAWDEV_PMD_INFO("FIU port %d is not > implemented", dev->port); > + return NULL; > + } > + > + bar =3D PORT_BAR(val); > + if (bar >=3D PCI_MAX_RESOURCE) { > + IFPGA_RAWDEV_PMD_ERR("BAR index %u is out of limit", > bar); > + return NULL; > + } > + > + addr =3D (uint8_t *)pci_dev->mem_resource[bar].addr + > PORT_OFFSET(val); > + return addr; > +} > + > +static int n3000_afu_get_irq_capability(struct afu_rawdev *dev, > + uint32_t *vec_start, uint32_t *vec_count) > +{ > + uint8_t *addr =3D NULL; > + uint64_t val =3D 0; > + uint64_t header =3D 0; > + uint64_t next_offset =3D 0; > + > + addr =3D (uint8_t *)n3000_afu_get_port_addr(dev); > + if (!addr) > + return -ENOENT; > + > + do { > + addr +=3D next_offset; > + header =3D rte_read64(addr); > + if ((DFH_TYPE(header) =3D=3D DFH_TYPE_PRIVATE) && > + (DFH_FEATURE_ID(header) =3D=3D > PORT_FEATURE_UINT_ID)) { > + val =3D rte_read64(addr + PORT_UINT_CAP_REG); > + if (vec_start) > + *vec_start =3D PORT_VEC_START(val); > + if (vec_count) > + *vec_count =3D PORT_VEC_COUNT(val); > + return 0; > + } > + next_offset =3D DFH_NEXT_OFFSET(header); > + if (((next_offset & 0xffff) =3D=3D 0xffff) || (next_offset =3D=3D 0)) > + break; > + } while (!DFH_EOL(header)); > + > + return -ENOENT; > +} > + > +static int nlb_afu_ctx_release(struct afu_rawdev *dev) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + struct nlb_afu_ctx *ctx =3D NULL; > + > + if (!dev) > + return -EINVAL; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + if (!priv) > + return -ENOENT; > + > + ctx =3D &priv->nlb_ctx; > + > + rte_free(ctx->dsm_ptr); > + ctx->dsm_ptr =3D NULL; > + ctx->status_ptr =3D NULL; > + > + rte_free(ctx->src_ptr); > + ctx->src_ptr =3D NULL; > + > + rte_free(ctx->dest_ptr); > + ctx->dest_ptr =3D NULL; > + > + return 0; > +} > + > +static int nlb_afu_ctx_init(struct afu_rawdev *dev, uint8_t *addr) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + struct nlb_afu_ctx *ctx =3D NULL; > + int ret =3D 0; > + > + if (!dev || !addr) > + return -EINVAL; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + if (!priv) > + return -ENOENT; > + > + ctx =3D &priv->nlb_ctx; > + ctx->addr =3D addr; > + > + ctx->dsm_ptr =3D (uint8_t *)rte_zmalloc(NULL, DSM_SIZE, > TEST_MEM_ALIGN); > + if (!ctx->dsm_ptr) > + return -ENOMEM; > + > + ctx->dsm_iova =3D rte_malloc_virt2iova(ctx->dsm_ptr); > + if (ctx->dsm_iova =3D=3D RTE_BAD_IOVA) { > + ret =3D -ENOMEM; > + goto release_dsm; > + } > + > + ctx->src_ptr =3D (uint8_t *)rte_zmalloc(NULL, NLB_BUF_SIZE, > + TEST_MEM_ALIGN); > + if (!ctx->src_ptr) { > + ret =3D -ENOMEM; > + goto release_dsm; > + } > + ctx->src_iova =3D rte_malloc_virt2iova(ctx->src_ptr); > + if (ctx->src_iova =3D=3D RTE_BAD_IOVA) { > + ret =3D -ENOMEM; > + goto release_src; > + } > + > + ctx->dest_ptr =3D (uint8_t *)rte_zmalloc(NULL, NLB_BUF_SIZE, > + TEST_MEM_ALIGN); > + if (!ctx->dest_ptr) { > + ret =3D -ENOMEM; > + goto release_src; > + } > + ctx->dest_iova =3D rte_malloc_virt2iova(ctx->dest_ptr); > + if (ctx->dest_iova =3D=3D RTE_BAD_IOVA) { > + ret =3D -ENOMEM; > + goto release_dest; > + } > + > + ctx->status_ptr =3D (struct nlb_dsm_status *)(ctx->dsm_ptr + > DSM_STATUS); > + return 0; > + > +release_dest: > + rte_free(ctx->dest_ptr); > + ctx->dest_ptr =3D NULL; > +release_src: > + rte_free(ctx->src_ptr); > + ctx->src_ptr =3D NULL; > +release_dsm: > + rte_free(ctx->dsm_ptr); > + ctx->dsm_ptr =3D NULL; > + return ret; > +} > + > +static int dma_afu_ctx_release(struct afu_rawdev *dev) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + struct dma_afu_ctx *ctx =3D NULL; > + > + if (!dev) > + return -EINVAL; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + if (!priv) > + return -ENOENT; > + > + ctx =3D &priv->dma_ctx[0]; > + > + rte_free(ctx->desc_buf); > + ctx->desc_buf =3D NULL; > + > + rte_free(ctx->magic_buf); > + ctx->magic_buf =3D NULL; > + > + close(ctx->event_fd); > + return 0; > +} > + > +static int dma_afu_ctx_init(struct afu_rawdev *dev, int index, uint8_t > *addr) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + struct dma_afu_ctx *ctx =3D NULL; > + uint64_t mem_sz[] =3D {0x100000000, 0x100000000, 0x40000000, > 0x1000000}; > + static int efds[1] =3D {0}; > + uint32_t vec_start =3D 0; > + int ret =3D 0; > + > + if (!dev || (index < 0) || (index >=3D NUM_N3000_DMA) || !addr) > + return -EINVAL; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + if (!priv) > + return -ENOENT; > + > + ctx =3D &priv->dma_ctx[index]; > + ctx->index =3D index; > + ctx->addr =3D addr; > + ctx->csr_addr =3D addr + DMA_CSR; > + ctx->desc_addr =3D addr + DMA_DESC; > + ctx->ase_ctrl_addr =3D addr + DMA_ASE_CTRL; > + ctx->ase_data_addr =3D addr + DMA_ASE_DATA; > + ctx->mem_size =3D mem_sz[ctx->index]; > + ctx->cur_ase_page =3D INVALID_ASE_PAGE; > + if (ctx->index =3D=3D 0) { > + ret =3D n3000_afu_get_irq_capability(dev, &vec_start, NULL); > + if (ret) > + return ret; > + > + efds[0] =3D eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC); > + if (efds[0] < 0) { > + IFPGA_RAWDEV_PMD_ERR("eventfd create failed"); > + return -EBADF; > + } > +#ifdef VFIO_PRESENT > + if (dma_afu_set_irqs(dev, vec_start, 1, efds)) > + IFPGA_RAWDEV_PMD_ERR("DMA interrupt setup > failed"); > +#endif > + } > + ctx->event_fd =3D efds[0]; > + > + ctx->desc_buf =3D (msgdma_ext_desc *)rte_zmalloc(NULL, > + sizeof(msgdma_ext_desc), DMA_ALIGN_BYTES); > + if (!ctx->desc_buf) { > + ret =3D -ENOMEM; > + goto release; > + } > + > + ctx->magic_buf =3D (uint64_t *)rte_zmalloc(NULL, MAGIC_BUF_SIZE, > + TEST_MEM_ALIGN); > + if (!ctx->magic_buf) { > + ret =3D -ENOMEM; > + goto release; > + } > + ctx->magic_iova =3D rte_malloc_virt2iova(ctx->magic_buf); > + if (ctx->magic_iova =3D=3D RTE_BAD_IOVA) { > + ret =3D -ENOMEM; > + goto release; > + } > + > + return 0; > + > +release: > + dma_afu_ctx_release(dev); > + return ret; > +} > + > +static int n3000_afu_ctx_init(struct afu_rawdev *dev) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + uint8_t *addr =3D NULL; > + uint64_t header =3D 0; > + uint64_t uuid_hi =3D 0; > + uint64_t uuid_lo =3D 0; > + uint64_t next_offset =3D 0; > + int ret =3D 0; > + > + if (!dev) > + return -EINVAL; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + if (!priv) > + return -ENOENT; > + > + addr =3D (uint8_t *)dev->addr; > + do { > + addr +=3D next_offset; > + header =3D rte_read64(addr); > + uuid_lo =3D rte_read64(addr + DFH_UUID_L_OFFSET); > + uuid_hi =3D rte_read64(addr + DFH_UUID_H_OFFSET); > + > + if ((DFH_TYPE(header) =3D=3D DFH_TYPE_AFU) && > + (uuid_lo =3D=3D N3000_NLB0_UUID_L) && > + (uuid_hi =3D=3D N3000_NLB0_UUID_H)) { > + IFPGA_RAWDEV_PMD_INFO("AFU NLB0 found > @ %p", (void *)addr); > + ret =3D nlb_afu_ctx_init(dev, addr); > + if (ret) > + return ret; > + } else if ((DFH_TYPE(header) =3D=3D DFH_TYPE_BBB) && > + (uuid_lo =3D=3D N3000_DMA_UUID_L) && > + (uuid_hi =3D=3D N3000_DMA_UUID_H) && > + (priv->num_dma < NUM_N3000_DMA)) { > + IFPGA_RAWDEV_PMD_INFO("AFU DMA%d found > @ %p", > + priv->num_dma, (void *)addr); > + ret =3D dma_afu_ctx_init(dev, priv->num_dma, addr); > + if (ret) > + return ret; > + priv->num_dma++; > + } else { > + IFPGA_RAWDEV_PMD_DEBUG("DFH: type %"PRIu64 > + ", uuid %016"PRIx64"%016"PRIx64, > + DFH_TYPE(header), uuid_hi, uuid_lo); > + } > + > + next_offset =3D DFH_NEXT_OFFSET(header); > + if (((next_offset & 0xffff) =3D=3D 0xffff) || (next_offset =3D=3D 0)) > + break; > + } while (!DFH_EOL(header)); > + > + return 0; > +} > + > +static int n3000_afu_init(struct afu_rawdev *dev) > +{ > + if (!dev) > + return -EINVAL; > + > + if (!dev->priv) { > + dev->priv =3D rte_zmalloc(NULL, sizeof(struct n3000_afu_priv), > 0); > + if (!dev->priv) > + return -ENOMEM; > + } > + > + return n3000_afu_ctx_init(dev); > +} > + > +static int n3000_afu_config(struct afu_rawdev *dev, void *config, > + size_t config_size) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + struct rte_pmd_afu_n3000_cfg *cfg =3D NULL; > + int i =3D 0; > + uint64_t top =3D 0; > + > + if (!dev || !config || !config_size) > + return -EINVAL; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + if (!priv) > + return -ENOENT; > + > + if (config_size !=3D sizeof(struct rte_pmd_afu_n3000_cfg)) > + return -EINVAL; > + > + cfg =3D (struct rte_pmd_afu_n3000_cfg *)config; > + if (cfg->type =3D=3D RTE_PMD_AFU_N3000_NLB) { > + if (cfg->nlb_cfg.mode !=3D NLB_MODE_LPBK) > + return -EINVAL; > + if ((cfg->nlb_cfg.read_vc > NLB_VC_RANDOM) || > + (cfg->nlb_cfg.write_vc > NLB_VC_RANDOM)) > + return -EINVAL; > + if (cfg->nlb_cfg.wrfence_vc > NLB_VC_VH1) > + return -EINVAL; > + if (cfg->nlb_cfg.cache_hint > NLB_RDLINE_MIXED) > + return -EINVAL; > + if (cfg->nlb_cfg.cache_policy > NLB_WRPUSH_I) > + return -EINVAL; > + if ((cfg->nlb_cfg.multi_cl !=3D 1) && > + (cfg->nlb_cfg.multi_cl !=3D 2) && > + (cfg->nlb_cfg.multi_cl !=3D 4)) > + return -EINVAL; > + if ((cfg->nlb_cfg.begin < MIN_CACHE_LINES) || > + (cfg->nlb_cfg.begin > MAX_CACHE_LINES)) > + return -EINVAL; > + if ((cfg->nlb_cfg.end < cfg->nlb_cfg.begin) || > + (cfg->nlb_cfg.end > MAX_CACHE_LINES)) > + return -EINVAL; > + rte_memcpy(&priv->nlb_cfg, &cfg->nlb_cfg, > + sizeof(struct rte_pmd_afu_nlb_cfg)); > + } else if (cfg->type =3D=3D RTE_PMD_AFU_N3000_DMA) { > + if (cfg->dma_cfg.index >=3D NUM_N3000_DMA) > + return -EINVAL; > + i =3D cfg->dma_cfg.index; > + if (cfg->dma_cfg.length > priv->dma_ctx[i].mem_size) > + return -EINVAL; > + if (cfg->dma_cfg.offset >=3D priv->dma_ctx[i].mem_size) > + return -EINVAL; > + top =3D cfg->dma_cfg.length + cfg->dma_cfg.offset; > + if ((top =3D=3D 0) || (top > priv->dma_ctx[i].mem_size)) > + return -EINVAL; > + if (i =3D=3D 3) { /* QDR connected to DMA3 */ > + if (cfg->dma_cfg.length & 0x3f) { > + cfg->dma_cfg.length &=3D ~0x3f; > + IFPGA_RAWDEV_PMD_INFO("Round size > to %x for QDR", > + cfg->dma_cfg.length); > + } > + } > + rte_memcpy(&priv->dma_cfg, &cfg->dma_cfg, > + sizeof(struct rte_pmd_afu_dma_cfg)); > + } else { > + IFPGA_RAWDEV_PMD_ERR("Invalid type of N3000 AFU"); > + return -EINVAL; > + } > + > + priv->cfg_type =3D cfg->type; > + return 0; > +} > + > +static int n3000_afu_test(struct afu_rawdev *dev) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + int ret =3D 0; > + > + if (!dev) > + return -EINVAL; > + > + if (!dev->priv) > + return -ENOENT; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + > + if (priv->cfg_type =3D=3D RTE_PMD_AFU_N3000_NLB) { > + IFPGA_RAWDEV_PMD_INFO("Test NLB"); > + ret =3D nlb_afu_test(dev); > + } else if (priv->cfg_type =3D=3D RTE_PMD_AFU_N3000_DMA) { > + IFPGA_RAWDEV_PMD_INFO("Test DMA%u", priv- > >dma_cfg.index); > + ret =3D dma_afu_test(dev); > + } else { > + IFPGA_RAWDEV_PMD_ERR("Please configure AFU before > test"); > + ret =3D -EINVAL; > + } > + > + return ret; > +} > + > +static int n3000_afu_close(struct afu_rawdev *dev) > +{ > + if (!dev) > + return -EINVAL; > + > + nlb_afu_ctx_release(dev); > + dma_afu_ctx_release(dev); > + > + rte_free(dev->priv); > + dev->priv =3D NULL; > + > + return 0; > +} > + > +static int n3000_afu_dump(struct afu_rawdev *dev, FILE *f) > +{ > + struct n3000_afu_priv *priv =3D NULL; > + > + if (!dev) > + return -EINVAL; > + > + priv =3D (struct n3000_afu_priv *)dev->priv; > + if (!priv) > + return -ENOENT; > + > + if (!f) > + f =3D stdout; > + > + if (priv->cfg_type =3D=3D RTE_PMD_AFU_N3000_NLB) { > + struct nlb_afu_ctx *ctx =3D &priv->nlb_ctx; > + fprintf(f, "addr:\t\t%p\n", (void *)ctx->addr); > + fprintf(f, "dsm_ptr:\t%p\n", (void *)ctx->dsm_ptr); > + fprintf(f, "dsm_iova:\t0x%"PRIx64"\n", ctx->dsm_iova); > + fprintf(f, "src_ptr:\t%p\n", (void *)ctx->src_ptr); > + fprintf(f, "src_iova:\t0x%"PRIx64"\n", ctx->src_iova); > + fprintf(f, "dest_ptr:\t%p\n", (void *)ctx->dest_ptr); > + fprintf(f, "dest_iova:\t0x%"PRIx64"\n", ctx->dest_iova); > + fprintf(f, "status_ptr:\t%p\n", (void *)ctx->status_ptr); > + } else if (priv->cfg_type =3D=3D RTE_PMD_AFU_N3000_DMA) { > + struct dma_afu_ctx *ctx =3D &priv->dma_ctx[priv- > >dma_cfg.index]; > + fprintf(f, "index:\t\t%d\n", ctx->index); > + fprintf(f, "addr:\t\t%p\n", (void *)ctx->addr); > + fprintf(f, "csr_addr:\t%p\n", (void *)ctx->csr_addr); > + fprintf(f, "desc_addr:\t%p\n", (void *)ctx->desc_addr); > + fprintf(f, "ase_ctrl_addr:\t%p\n", (void *)ctx->ase_ctrl_addr); > + fprintf(f, "ase_data_addr:\t%p\n", (void *)ctx- > >ase_data_addr); > + fprintf(f, "desc_buf:\t%p\n", (void *)ctx->desc_buf); > + fprintf(f, "magic_buf:\t%p\n", (void *)ctx->magic_buf); > + fprintf(f, "magic_iova:\t0x%"PRIx64"\n", ctx->magic_iova); > + } else { > + return -EINVAL; > + } > + > + return 0; > +} > + > +static int n3000_afu_reset(struct afu_rawdev *dev) > +{ > + uint8_t *addr =3D NULL; > + uint64_t val =3D 0; > + > + addr =3D (uint8_t *)n3000_afu_get_port_addr(dev); > + if (!addr) > + return -ENOENT; > + > + val =3D rte_read64(addr + PORT_CTRL_REG); > + val |=3D PORT_SOFT_RESET; > + rte_write64(val, addr + PORT_CTRL_REG); > + rte_delay_us(100); > + val &=3D ~PORT_SOFT_RESET; > + rte_write64(val, addr + PORT_CTRL_REG); > + > + return 0; > +} > + > +static struct afu_ops n3000_afu_ops =3D { > + .init =3D n3000_afu_init, > + .config =3D n3000_afu_config, > + .start =3D NULL, > + .stop =3D NULL, > + .test =3D n3000_afu_test, > + .close =3D n3000_afu_close, > + .dump =3D n3000_afu_dump, > + .reset =3D n3000_afu_reset > +}; > + > +static struct afu_rawdev_drv n3000_afu_drv =3D { > + .uuid =3D { N3000_AFU_UUID_L, N3000_AFU_UUID_H }, > + .ops =3D &n3000_afu_ops > +}; > + > +AFU_PMD_REGISTER(n3000_afu_drv); > diff --git a/drivers/raw/ifpga/afu_pmd_n3000.h > b/drivers/raw/ifpga/afu_pmd_n3000.h > new file mode 100644 > index 0000000..67e83fe > --- /dev/null > +++ b/drivers/raw/ifpga/afu_pmd_n3000.h > @@ -0,0 +1,339 @@ > +/* SPDX-License-Identifier: BSD-3-Clause > + * Copyright(c) 2022 Intel Corporation > + */ > + > +#ifndef _AFU_PMD_N3000_H_ > +#define _AFU_PMD_N3000_H_ > + > +#ifdef __cplusplus > +extern "C" { > +#endif > + > +#include "afu_pmd_core.h" > +#include "rte_pmd_afu.h" > + > +#define N3000_AFU_UUID_L 0xc000c9660d824272 > +#define N3000_AFU_UUID_H 0x9aeffe5f84570612 > +#define N3000_NLB0_UUID_L 0xf89e433683f9040b > +#define N3000_NLB0_UUID_H 0xd8424dc4a4a3c413 > +#define N3000_DMA_UUID_L 0xa9149a35bace01ea > +#define N3000_DMA_UUID_H 0xef82def7f6ec40fc > + > +#define NUM_N3000_DMA 4 > +#define MAX_MSIX_VEC 7 > + > +/* N3000 DFL definition */ > +#define DFH_UUID_L_OFFSET 8 > +#define DFH_UUID_H_OFFSET 16 > +#define DFH_TYPE(hdr) (((hdr) >> 60) & 0xf) > +#define DFH_TYPE_AFU 1 > +#define DFH_TYPE_BBB 2 > +#define DFH_TYPE_PRIVATE 3 > +#define DFH_EOL(hdr) (((hdr) >> 40) & 0x1) > +#define DFH_NEXT_OFFSET(hdr) (((hdr) >> 16) & 0xffffff) > +#define DFH_FEATURE_ID(hdr) ((hdr) & 0xfff) > +#define PORT_ATTR_REG(n) (((n) << 3) + 0x38) > +#define PORT_IMPLEMENTED(attr) (((attr) >> 60) & 0x1) > +#define PORT_BAR(attr) (((attr) >> 32) & 0x7) > +#define PORT_OFFSET(attr) ((attr) & 0xffffff) > +#define PORT_FEATURE_UINT_ID 0x12 > +#define PORT_UINT_CAP_REG 0x8 > +#define PORT_VEC_START(cap) (((cap) >> 12) & 0xfff) > +#define PORT_VEC_COUNT(cap) ((cap) >> 12 & 0xfff) > +#define PORT_CTRL_REG 0x38 > +#define PORT_SOFT_RESET (0x1 << 0) > + > +/* NLB registers definition */ > +#define CSR_SCRATCHPAD0 0x100 > +#define CSR_SCRATCHPAD1 0x108 > +#define CSR_AFU_DSM_BASEL 0x110 > +#define CSR_AFU_DSM_BASEH 0x114 > +#define CSR_SRC_ADDR 0x120 > +#define CSR_DST_ADDR 0x128 > +#define CSR_NUM_LINES 0x130 > +#define CSR_CTL 0x138 > +#define CSR_CFG 0x140 > +#define CSR_INACT_THRESH 0x148 > +#define CSR_INTERRUPT0 0x150 > +#define CSR_SWTEST_MSG 0x158 > +#define CSR_STATUS0 0x160 > +#define CSR_STATUS1 0x168 > +#define CSR_ERROR 0x170 > +#define CSR_STRIDE 0x178 > +#define CSR_HE_INFO0 0x180 > + > +#define DSM_SIZE 0x200000 > +#define DSM_STATUS 0x40 > +#define DSM_POLL_INTERVAL 5 /* ms */ > +#define DSM_TIMEOUT 1000 /* ms */ > + > +#define NLB_BUF_SIZE 0x400000 > +#define TEST_MEM_ALIGN 1024 > + > +struct nlb_csr_ctl { > + union { > + uint32_t csr; > + struct { > + uint32_t reset:1; > + uint32_t start:1; > + uint32_t force_completion:1; > + uint32_t reserved:29; > + }; > + }; > +}; > + > +struct nlb_csr_cfg { > + union { > + uint32_t csr; > + struct { > + uint32_t wrthru_en:1; > + uint32_t cont:1; > + uint32_t mode:3; > + uint32_t multicl_len:2; > + uint32_t rsvd1:1; > + uint32_t delay_en:1; > + uint32_t rdsel:2; > + uint32_t rsvd2:1; > + uint32_t chsel:3; > + uint32_t rsvd3:1; > + uint32_t wrpush_i:1; > + uint32_t wr_chsel:3; > + uint32_t rsvd4:3; > + uint32_t test_cfg:5; > + uint32_t interrupt_on_error:1; > + uint32_t interrupt_testmode:1; > + uint32_t wrfence_chsel:2; > + }; > + }; > +}; > + > +struct nlb_status0 { > + union { > + uint64_t csr; > + struct { > + uint32_t num_writes; > + uint32_t num_reads; > + }; > + }; > +}; > + > +struct nlb_status1 { > + union { > + uint64_t csr; > + struct { > + uint32_t num_pend_writes; > + uint32_t num_pend_reads; > + }; > + }; > +}; > + > +struct nlb_dsm_status { > + uint32_t test_complete; > + uint32_t test_error; > + uint64_t num_clocks; > + uint32_t num_reads; > + uint32_t num_writes; > + uint32_t start_overhead; > + uint32_t end_overhead; > +}; > + > +/* DMA registers definition */ > +#define DMA_CSR 0x40 > +#define DMA_DESC 0x60 > +#define DMA_ASE_CTRL 0x200 > +#define DMA_ASE_DATA 0x1000 > + > +#define DMA_ASE_WINDOW 4096 > +#define DMA_ASE_WINDOW_MASK ((uint64_t)(DMA_ASE_WINDOW - 1)) > +#define INVALID_ASE_PAGE 0xffffffffffffffffULL > + > +#define DMA_WF_MAGIC 0x5772745F53796E63ULL > +#define DMA_WF_MAGIC_ROM 0x1000000000000 > +#define DMA_HOST_ADDR(addr) ((addr) | 0x2000000000000) > +#define DMA_WF_HOST_ADDR(addr) ((addr) | 0x3000000000000) > + > +#define NUM_DMA_BUF 8 > +#define HALF_DMA_BUF (NUM_DMA_BUF / 2) > + > +#define DMA_MASK_32_BIT 0xFFFFFFFF > + > +#define DMA_CSR_BUSY 0x1 > +#define DMA_DESC_BUFFER_EMPTY 0x2 > +#define DMA_DESC_BUFFER_FULL 0x4 > + > +#define DWORD_BYTES 4 > +#define IS_ALIGNED_DWORD(addr) (((addr) % DWORD_BYTES) =3D=3D 0) > + > +#define QWORD_BYTES 8 > +#define IS_ALIGNED_QWORD(addr) (((addr) % QWORD_BYTES) =3D=3D 0) > + > +#define DMA_ALIGN_BYTES 64 > +#define IS_DMA_ALIGNED(addr) (((addr) % DMA_ALIGN_BYTES) =3D=3D 0) > + > +#define CCIP_ALIGN_BYTES (DMA_ALIGN_BYTES << 2) > + > +#define DMA_TIMEOUT_MSEC 5000 > + > +#define MAGIC_BUF_SIZE 64 > +#define ERR_CHECK_LIMIT 64 > + > +#ifndef MIN > +#define MIN(a, b) ((a) < (b) ? (a) : (b)) > +#endif > + > +#ifndef ARRAY_SIZE > +#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) > +#endif > + > +typedef enum { > + HOST_TO_FPGA =3D 0, > + FPGA_TO_HOST, > + FPGA_TO_FPGA, > + FPGA_MAX_TRANSFER_TYPE, > +} fpga_dma_type; > + > +typedef union { > + uint32_t csr; > + struct { > + uint32_t tx_channel:8; > + uint32_t generate_sop:1; > + uint32_t generate_eop:1; > + uint32_t park_reads:1; > + uint32_t park_writes:1; > + uint32_t end_on_eop:1; > + uint32_t reserved_1:1; > + uint32_t transfer_irq_en:1; > + uint32_t early_term_irq_en:1; > + uint32_t trans_error_irq_en:8; > + uint32_t early_done_en:1; > + uint32_t reserved_2:6; > + uint32_t go:1; > + }; > +} msgdma_desc_ctrl; > + > +typedef struct __rte_packed { > + uint32_t rd_address; > + uint32_t wr_address; > + uint32_t len; > + uint16_t seq_num; > + uint8_t rd_burst_count; > + uint8_t wr_burst_count; > + uint16_t rd_stride; > + uint16_t wr_stride; > + uint32_t rd_address_ext; > + uint32_t wr_address_ext; > + msgdma_desc_ctrl control; > +} msgdma_ext_desc; > + > +typedef union { > + uint32_t csr; > + struct { > + uint32_t busy:1; > + uint32_t desc_buf_empty:1; > + uint32_t desc_buf_full:1; > + uint32_t rsp_buf_empty:1; > + uint32_t rsp_buf_full:1; > + uint32_t stopped:1; > + uint32_t resetting:1; > + uint32_t stopped_on_error:1; > + uint32_t stopped_on_early_term:1; > + uint32_t irq:1; > + uint32_t reserved:22; > + }; > +} msgdma_status; > + > +typedef union { > + uint32_t csr; > + struct { > + uint32_t stop_dispatcher:1; > + uint32_t reset_dispatcher:1; > + uint32_t stop_on_error:1; > + uint32_t stopped_on_early_term:1; > + uint32_t global_intr_en_mask:1; > + uint32_t stop_descriptors:1; > + uint32_t reserved:22; > + }; > +} msgdma_ctrl; > + > +typedef union { > + uint32_t csr; > + struct { > + uint32_t rd_fill_level:16; > + uint32_t wr_fill_level:16; > + }; > +} msgdma_fill_level; > + > +typedef union { > + uint32_t csr; > + struct { > + uint32_t rsp_fill_level:16; > + uint32_t reserved:16; > + }; > +} msgdma_rsp_level; > + > +typedef union { > + uint32_t csr; > + struct { > + uint32_t rd_seq_num:16; > + uint32_t wr_seq_num:16; > + }; > +} msgdma_seq_num; > + > +typedef struct __rte_packed { > + msgdma_status status; > + msgdma_ctrl ctrl; > + msgdma_fill_level fill_level; > + msgdma_rsp_level rsp; > + msgdma_seq_num seq_num; > +} msgdma_csr; > + > +#define CSR_STATUS(csr) (&(((msgdma_csr *)(csr))->status)) > +#define CSR_CONTROL(csr) (&(((msgdma_csr *)(csr))->ctrl)) > + > +struct nlb_afu_ctx { > + uint8_t *addr; > + uint8_t *dsm_ptr; > + uint64_t dsm_iova; > + uint8_t *src_ptr; > + uint64_t src_iova; > + uint8_t *dest_ptr; > + uint64_t dest_iova; > + struct nlb_dsm_status *status_ptr; > +}; > + > +struct dma_afu_ctx { > + int index; > + uint8_t *addr; > + uint8_t *csr_addr; > + uint8_t *desc_addr; > + uint8_t *ase_ctrl_addr; > + uint8_t *ase_data_addr; > + uint64_t mem_size; > + uint64_t cur_ase_page; > + int event_fd; > + int verbose; > + int pattern; > + void *data_buf; > + void *ref_buf; > + msgdma_ext_desc *desc_buf; > + uint64_t *magic_buf; > + uint64_t magic_iova; > + uint32_t dma_buf_size; > + uint64_t *dma_buf[NUM_DMA_BUF]; > + uint64_t dma_iova[NUM_DMA_BUF]; > +}; > + > +struct n3000_afu_priv { > + struct rte_pmd_afu_nlb_cfg nlb_cfg; > + struct rte_pmd_afu_dma_cfg dma_cfg; > + struct nlb_afu_ctx nlb_ctx; > + struct dma_afu_ctx dma_ctx[NUM_N3000_DMA]; > + int num_dma; > + int cfg_type; > +}; > + > +#ifdef __cplusplus > +} > +#endif > + > +#endif /* _AFU_PMD_N3000_H_ */ > diff --git a/drivers/raw/ifpga/meson.build b/drivers/raw/ifpga/meson.buil= d > index d9a6f29..2294ab5 100644 > --- a/drivers/raw/ifpga/meson.build > +++ b/drivers/raw/ifpga/meson.build > @@ -13,7 +13,8 @@ objs =3D [base_objs] > deps +=3D ['ethdev', 'rawdev', 'pci', 'bus_pci', 'kvargs', > 'bus_vdev', 'bus_ifpga', 'net', 'net_i40e', 'net_ipn3ke'] >=20 > -sources =3D files('ifpga_rawdev.c', 'rte_pmd_ifpga.c', 'afu_pmd_core.c') > +sources =3D files('ifpga_rawdev.c', 'rte_pmd_ifpga.c', 'afu_pmd_core.c', > + 'afu_pmd_n3000.c') >=20 > includes +=3D include_directories('base') > includes +=3D include_directories('../../net/ipn3ke') > diff --git a/drivers/raw/ifpga/rte_pmd_afu.h > b/drivers/raw/ifpga/rte_pmd_afu.h > new file mode 100644 > index 0000000..f14a053 > --- /dev/null > +++ b/drivers/raw/ifpga/rte_pmd_afu.h > @@ -0,0 +1,97 @@ > +/* SPDX-License-Identifier: BSD-3-Clause > + * Copyright 2022 Intel Corporation > + */ > + > +#ifndef __RTE_PMD_AFU_H__ > +#define __RTE_PMD_AFU_H__ > + > +/** > + * @file rte_pmd_afu.h > + * > + * AFU PMD specific definitions. > + * > + * @b EXPERIMENTAL: this API may change, or be removed, without prior > notice > + * > + */ > + > +#ifdef __cplusplus > +extern "C" { > +#endif > + > +#include > + > +#define RTE_PMD_AFU_N3000_NLB 1 > +#define RTE_PMD_AFU_N3000_DMA 2 > + > +#define NLB_MODE_LPBK 0 > +#define NLB_MODE_READ 1 > +#define NLB_MODE_WRITE 2 > +#define NLB_MODE_TRPUT 3 > + > +#define NLB_VC_AUTO 0 > +#define NLB_VC_VL0 1 > +#define NLB_VC_VH0 2 > +#define NLB_VC_VH1 3 > +#define NLB_VC_RANDOM 4 > + > +#define NLB_WRLINE_M 0 > +#define NLB_WRLINE_I 1 > +#define NLB_WRPUSH_I 2 > + > +#define NLB_RDLINE_S 0 > +#define NLB_RDLINE_I 1 > +#define NLB_RDLINE_MIXED 2 > + > +#define MIN_CACHE_LINES 1 > +#define MAX_CACHE_LINES 1024 > + > +#define MIN_DMA_BUF_SIZE 64 > +#define MAX_DMA_BUF_SIZE (1023 * 1024) > + > +/** > + * NLB AFU configuration data structure. > + */ > +struct rte_pmd_afu_nlb_cfg { > + uint32_t mode; > + uint32_t begin; > + uint32_t end; > + uint32_t multi_cl; > + uint32_t cont; > + uint32_t timeout; > + uint32_t cache_policy; > + uint32_t cache_hint; > + uint32_t read_vc; > + uint32_t write_vc; > + uint32_t wrfence_vc; > + uint32_t freq_mhz; > +}; > + > +/** > + * DMA AFU configuration data structure. > + */ > +struct rte_pmd_afu_dma_cfg { > + uint32_t index; /* index of DMA controller */ > + uint32_t length; /* total length of data to DMA */ > + uint32_t offset; /* address offset of target memory */ > + uint32_t size; /* size of transfer buffer */ > + uint32_t pattern; /* data pattern to fill in test buffer */ > + uint32_t unaligned; /* use unaligned address or length in sweep test > */ > + uint32_t verbose; /* enable verbose error information in test */ > +}; > + > +/** > + * N3000 AFU configuration data structure. > + */ > +struct rte_pmd_afu_n3000_cfg { > + int type; /* RTE_PMD_AFU_N3000_NLB or > RTE_PMD_AFU_N3000_DMA */ > + union { > + struct rte_pmd_afu_nlb_cfg nlb_cfg; > + struct rte_pmd_afu_dma_cfg dma_cfg; > + }; > +}; > + > +#ifdef __cplusplus > +} > +#endif > + > +#endif /* __RTE_PMD_AFU_H__ */ > -- > 1.8.3.1 Reviewed-by: Rosen Xu