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 4E0EF4624E; Mon, 17 Feb 2025 17:15:47 +0100 (CET) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id D88E7400EF; Mon, 17 Feb 2025 17:15:46 +0100 (CET) Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.16]) by mails.dpdk.org (Postfix) with ESMTP id 03874400D6 for ; Mon, 17 Feb 2025 17:15:43 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1739808944; x=1771344944; h=from:to:cc:subject:date:message-id:references: in-reply-to:mime-version; bh=BqPvd8hmyO5yn8cP+OyaHfJ48ID9aymuJ2QbVM1Ymh8=; b=UC07C+npnEmoqrm8SENDmcreOT4GEwEZd1bSQlVxhnx3q//di6lo16bY eKeTgWCiupwFqKLtWpyKnRHU3UtjJljUR2vOHsdo4xnGFHw6/wm/IWQ37 ZwyAMUj3On/0JqKeW5AfmgxpnqcfvvpKGAK8+9TX7dUIhxwQ+VJpcxUUK 7mNuiFz7nGsM7nUw3urn0O1XlJ9h5fRYNoL/CR6o/DYpcJKAxaOcqVon/ t9mhL1Sql0VAdAbxWirEfcUNzgxMuVoD1CzOQ3NKT7hIINoFmZ2G8npOT dLk1EtMfpLFJpWGNmAsWSCvyS3BVhyyNVoBRUZPrWFu462kaNfjb0vMaU g==; X-CSE-ConnectionGUID: Hp2pbT9nQ1KMarKjNPazKw== X-CSE-MsgGUID: AXrRmPLhTgi//UtfYZ4mFQ== X-IronPort-AV: E=McAfee;i="6700,10204,11348"; a="40620988" X-IronPort-AV: E=Sophos;i="6.13,293,1732608000"; d="scan'208,217";a="40620988" Received: from orviesa007.jf.intel.com ([10.64.159.147]) by orvoesa108.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 17 Feb 2025 08:15:42 -0800 X-CSE-ConnectionGUID: hWnfd786RRaNZ2UTUbfSJg== X-CSE-MsgGUID: sUfTvalQRuKzoH8XzyTEWA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.12,224,1728975600"; d="scan'208,217";a="114632263" Received: from orsmsx601.amr.corp.intel.com ([10.22.229.14]) by orviesa007.jf.intel.com with ESMTP/TLS/AES256-GCM-SHA384; 17 Feb 2025 08:15:42 -0800 Received: from ORSMSX902.amr.corp.intel.com (10.22.229.24) by ORSMSX601.amr.corp.intel.com (10.22.229.14) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.44; Mon, 17 Feb 2025 08:15:41 -0800 Received: from orsedg603.ED.cps.intel.com (10.7.248.4) by ORSMSX902.amr.corp.intel.com (10.22.229.24) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.1544.14 via Frontend Transport; Mon, 17 Feb 2025 08:15:41 -0800 Received: from NAM02-BN1-obe.outbound.protection.outlook.com (104.47.51.48) by edgegateway.intel.com (134.134.137.100) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.1.2507.44; Mon, 17 Feb 2025 08:15:41 -0800 ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=o77wrjRqJkNhYY9cg2S/PgIfQlt9p9AEoX4RidSZwpy9frGoJy/1jU2ktAIJv2men27jiFUDx0bBHE2JMF7f2GDAFvoP6FJwhgiTfMP3pMQ72cirKvxja1b/39a46OGiEylkGamXJAB4JpqG0KV2VIgGmiK2E51wKRUy50Tb4AQYWsGc58m8iyZTRD2VPuSq0MwN1vicDmu25VQRV46+2Tx3ogs4gCgjtpebvEHCC0AkkSdX07iqRtrSVjydd0qG2OsOwBqmdlf8LNiDqj19HB+1N85WdKNXWp17aaJwtQ01Rc74eXVHydBY+0ZJUfIcqBkw5GX+dX6d7hCZSnjNkA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; 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=NWJ1ya4/F4zA1RCd/5uOlAJP/2jY+e0xADqLu/AKzpQ=; b=ndKazthLce2EANwstm7kIXenTt0jzB6bwQsgi7PRafX1fF0WKTLk9W0b+a1ry6TB6m3cDQyvYJnM4UtJNGx4IY+vjxe4GSbHj6kCa02PA9wge1IUygMByk5AOsI1+UaLX9Y4UnYr7Ijab6Hz/xZkeu2n86K8qwXHnRKTwfDtKQhrk/Iwg6LuD0AnwIwWd/+HENQBeWoD/m3c1l4+0Am2XaiVwN1KbETLPrx8AMVNHeH9rK/ZD7W7WFm76iOWTdPRcs3592siXHRRMlH22mUIKkPdjghkqnplLXw+RoV8P7GKVOZyC+oEnlsC7uJwUd0AgZheURBy7bDAkp2BCZt+ug== 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 SN7PR11MB7044.namprd11.prod.outlook.com (2603:10b6:806:29b::5) by SJ2PR11MB8500.namprd11.prod.outlook.com (2603:10b6:a03:574::17) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.8445.18; Mon, 17 Feb 2025 16:15:38 +0000 Received: from SN7PR11MB7044.namprd11.prod.outlook.com ([fe80::79ff:96e:c439:d42e]) by SN7PR11MB7044.namprd11.prod.outlook.com ([fe80::79ff:96e:c439:d42e%3]) with mapi id 15.20.8445.017; Mon, 17 Feb 2025 16:15:38 +0000 From: "Naga Harish K, S V" To: Shijith Thotton , "jerinj@marvell.com" CC: "pbhagavatula@marvell.com" , "dev@dpdk.org" , "Pathak, Pravin" , Hemant Agrawal , Sachin Saxena , "Mattias R_nnblom" , Liang Ma , "Mccarthy, Peter" , "Van Haaren, Harry" , "Carrillo, Erik G" , "Gujjar, Abhinandan S" , Amit Prakash Shukla , "Burakov, Anatoly" Subject: Re: [PATCH 1/3] eventdev/eth_rx: add API to burst add queues to Rx adapter Thread-Topic: [PATCH 1/3] eventdev/eth_rx: add API to burst add queues to Rx adapter Thread-Index: AQHbeWoMB+ePS4d2NESAWuOpKtIhxrNLulAf Date: Mon, 17 Feb 2025 16:15:38 +0000 Message-ID: References: <20250207140910.721374-1-sthotton@marvell.com> <20250207140910.721374-2-sthotton@marvell.com> In-Reply-To: <20250207140910.721374-2-sthotton@marvell.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: msip_labels: authentication-results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=intel.com; x-ms-publictraffictype: Email x-ms-traffictypediagnostic: SN7PR11MB7044:EE_|SJ2PR11MB8500:EE_ x-ms-office365-filtering-correlation-id: 6598d2f2-47b8-4103-a761-08dd4f6e5108 x-ms-exchange-senderadcheck: 1 x-ms-exchange-antispam-relay: 0 x-microsoft-antispam: BCL:0; ARA:13230040|1800799024|376014|366016|8096899003|7053199007|38070700018; x-microsoft-antispam-message-info: =?iso-8859-1?Q?InC5hWKBXnva6/n953Q90mwniznNySSV6QCtQkR+SonyB2eA4vSJIB5oKv?= =?iso-8859-1?Q?UPEXREGES3hdfs0sSw54FBHiIK/+6zIK/dCxouWTYhF60SCS9+dkDApsZ2?= =?iso-8859-1?Q?+mAqZC8OcgVnLgfLV/e8Q8OYLJWfrgK8FBngcsqm7pjVwKltPalVHy6O1J?= =?iso-8859-1?Q?kYhwNMRzL1sytWqURQcMQ04ISo82zJpsHf22YJyCNFqyTefN7bijGNm+1V?= =?iso-8859-1?Q?dLv0AWAuQWohQxvPLF0R+u8yx+KpzA9guRvGpuqOea/CJs3i9j+A1aBhU3?= =?iso-8859-1?Q?C8LxatIvRC03mg4GM0llA8U0DrjvPwMhFEZfynuYHzUd0lnbERyU6DLPVx?= =?iso-8859-1?Q?bjJi0jEfobsOySmr9oIFTUQ+aHD0hE1Jl09o87t5ch8oqKL1Oq9Ejgd/fj?= =?iso-8859-1?Q?/g4neimxGG3w/6m/YwbMBoS57CORXHUgDMU8Wd/gXVZCXf79vM2VdJ3OSR?= =?iso-8859-1?Q?sfY3UnzT5aw+2IHPhx1H3Ah0GZ2CCV7gr9KVxt7rPEQlIG8E5E68Z0bses?= =?iso-8859-1?Q?tb/nmeRIkjObD8MJoIVn7T6BU4ThyC3LEaA62lw/WxLPoapWOpG8z72bH1?= =?iso-8859-1?Q?j4A7uTE5+g2FJ69l66FyE2t3Rb4/dUc5WikvlN+gX2vVr/DZJ+HADErXos?= =?iso-8859-1?Q?OzgJo/lvvf9bLHiB4cR5wWiX7jVCNDJ760MF9KmgrI3PaUMLYk1IbDizs0?= =?iso-8859-1?Q?xbVnhM8PUsOQPm2AjTmNCnX8VE7mSkMGdvYdlT3KMZ1FtnjFmP8Z3Oe/Zr?= =?iso-8859-1?Q?+wEzVD5C8jTSZkhI9YuKX4oaXXkeAtOdQV54QqKBx0+QrEfwmlgwVIdwLo?= =?iso-8859-1?Q?LS6FzJTZLp/abXqUVDeQhacyw+rDuAp4XCsPK2/33AdNUtDUzZpW6iwVfZ?= =?iso-8859-1?Q?1tcM3GebEtv3fVXOaor8f9qTsXyVbjceS6skbuUsOmf3cR32nfC57A8FZL?= =?iso-8859-1?Q?cb22p0CHapGCf45GHjb+S0R9VzIJuje9b+tQQV7gjnXd90g2ByKZ6GK+Jb?= =?iso-8859-1?Q?tlRLbVeZoRtxg5sd6OIonKXLVI9PeFzxT3KDxD3DpugSBD2nIoQQ2J9j80?= =?iso-8859-1?Q?I+QjhzRtHsRWtG4cNRiRYjoIGuM5Vv+vu1F8adtyYC3YrAgUueTZxS7TJE?= =?iso-8859-1?Q?pb4W7KovyI3I7CFJCh66WUNsm7lgEyUpicEzT5bdtIwGtGXD6aflnm+0Wm?= =?iso-8859-1?Q?4NwgJU+6+qB1VW1bT0v3cc/5DdvHnbx6/N39+B2HX9Rk4vpO2XyYFeeHeb?= =?iso-8859-1?Q?jqtDsJqXnsnlBmF3i2S4jSlNvKv2O8gv0Oyz0/6+BfDQYq/dlT7FBAz7NW?= =?iso-8859-1?Q?mzmd9TG1JL6PY351Rvh+x+nUKq+aAOBxBCwlp/M2sZqOeGZWV6Sp0fiMv1?= =?iso-8859-1?Q?aDziaoWipqYGqkIQcCuolj9HHHCJgEBLHz5Gq58Mwo3uuDCr3VjQyJlrHs?= =?iso-8859-1?Q?nJzOMd5G2OJyO66Pytl8XFNj99hwW6m2XBQlrnsS0xSquyB3da/CVXPwr0?= =?iso-8859-1?Q?j2dszsSwSkYKAjZGVJm92F?= x-forefront-antispam-report: CIP:255.255.255.255; CTRY:; LANG:en; SCL:1; SRV:; IPV:NLI; SFV:NSPM; H:SN7PR11MB7044.namprd11.prod.outlook.com; PTR:; CAT:NONE; SFS:(13230040)(1800799024)(376014)(366016)(8096899003)(7053199007)(38070700018); DIR:OUT; SFP:1101; x-ms-exchange-antispam-messagedata-chunkcount: 1 x-ms-exchange-antispam-messagedata-0: =?iso-8859-1?Q?6o6uopEXlt99cXqSBbvkelvmguyzByOIbHG+6pJJ05JntLrJWenooo57YH?= =?iso-8859-1?Q?yAm6ZcDp0OALF+it2T/JaB61dLdeEjCb7chvRvIHcIip4YhVTGc6jAzZau?= =?iso-8859-1?Q?STI1V2D0VNE91/7lg391MyGRgNuyQlcXonZFLdQYskqxPOUZC5W5W+94T4?= =?iso-8859-1?Q?FvYo2Pcaf6ZA1E5lGnXlPbipgkgOpXO8yECKWFWsI17naHXgjBRiFMXwSq?= =?iso-8859-1?Q?Ae0JLUGQwZNZ5KdDyD3ctRZoS1/YxCqWFGwVhvBpbCaGXpLPK/bvgcI71h?= =?iso-8859-1?Q?c7nP7xREi004q9NUSH4pQOlZyEU74J5ohDVD4nPNX66aqh0iH99ZmfObX/?= =?iso-8859-1?Q?RuHNciVtIvlE2BQSHRNC9Z/X9pMEB7pw4sh+xHgoFCecUbJFB9LTbjL86N?= =?iso-8859-1?Q?5G6wvYxcLlMjo//+cTJVL27CSxPkYLA+jJDoDpXMSyOXNTND74CL1uuFXO?= =?iso-8859-1?Q?lkpKkDth5PLuvgREuE0qd3E+jMwOEfPzQi148s7P1SOyT5WcoZg4zRadfU?= =?iso-8859-1?Q?IlqiEjVMEWuHhiRqgPDimwlV8XzREbhXSA+J0MpndwmPBKmumtWhT4EBi5?= =?iso-8859-1?Q?5TDzvI4gr4ue6uUm1zIgEhSXOw6vsAgdyeUMIIqjk/20XcPh37J5zwvWlv?= =?iso-8859-1?Q?5VKev9zZhV6lOvWCej8rmBRxUBx0kF20SFB/eSxY+gLinw0UZ0JC55A8qs?= =?iso-8859-1?Q?hmBj5QQtUqsDS0mS5Qxy0gimAK+lYgvVFmZuirxAKKwa7YstWL8nO6z6VC?= =?iso-8859-1?Q?ia9xvf2tUvW2+jyF6a+yvr9y8W8GGqRsec4HgL0LIBJBbylBiS7NOMpmmN?= =?iso-8859-1?Q?at9ynuhbkyU9XBvlQWvT3rcvpiuJDjNO9TCiEP5nj5YI4H36aoU/XDNlbU?= =?iso-8859-1?Q?f+65Yj4CeBypf96d1/QxLEsvfUgQZzVY2Eg931KYaJJGyAF6X8w6IJDA5a?= =?iso-8859-1?Q?AhTpU3WouyMR5SpYKSHSmfUILOyk7scCvsld5NwhhtVboMOL4Tznbila3C?= =?iso-8859-1?Q?npCGhtFUFVMRWYSKEgwsj8EwwOfrreUtvXNXg6MvGonLkfbMfs1UVSAUXb?= =?iso-8859-1?Q?Mj0OABgLZepUX16whD2O8HK/UE/16+E5q3O+TPTMbO6QDFECiFrHTqXwst?= =?iso-8859-1?Q?QR99AhGkl8C6NzGNQixziJwxSsdui+tqNMWMYKzy1EfkgGHzlDLQ9yy+ij?= =?iso-8859-1?Q?pLpATOtPyz7yv7FCezfxeGi7f08myVQaJRFhv+3LYnSPMvkcLrJ9Gi/F4W?= =?iso-8859-1?Q?C/wZpgmUg7i7EQQU4qJwOmR/l2HE1R1Yx+f+DKBbwgIioe4wKcxsh051gc?= =?iso-8859-1?Q?n2UFD5iBmSpqzB7TQEZrQ4uQSsn1wiWq2BIGBQwGkV385Ex8HL00kWL7Er?= =?iso-8859-1?Q?2gbII8KCP6ET8+O09LPx+O82BM+fRBzgqqgC5iiWD+Qw/N95cAVRjW9dy7?= =?iso-8859-1?Q?Y6fsC2cHcJFEO3HNWE0NoUaiW7TSqNhSL1pIED1l9IaXxUTuqnSyoTWN2F?= =?iso-8859-1?Q?tMV6iuOtZbVtLFbHBXXeJv/46DXG4DuijxfYGdKzhzjo88nT8dLozPNO/e?= =?iso-8859-1?Q?mcYHLkB2qClUSOLbi1aPmvn7F+liiOo/lc7Xq1VUwVyCMyTh15zaS4Lufs?= =?iso-8859-1?Q?vzzBwiMMEVFxdSY86a/MFggS97TuVZTQPk?= Content-Type: multipart/alternative; boundary="_000_SN7PR11MB7044CD7EEC9FCD8B2993561FA1FB2SN7PR11MB7044namp_" MIME-Version: 1.0 X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-AuthSource: SN7PR11MB7044.namprd11.prod.outlook.com X-MS-Exchange-CrossTenant-Network-Message-Id: 6598d2f2-47b8-4103-a761-08dd4f6e5108 X-MS-Exchange-CrossTenant-originalarrivaltime: 17 Feb 2025 16:15:38.0554 (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: KUFMGznAZbNP8jEThETJvny1NkL3jXKRKcniMaC0LLMvspGwclmsmz4YPlpXKuFpHcm8QxmW0skdqFTBn59lSreIQfV/8NaOxF0DvE68oek= X-MS-Exchange-Transport-CrossTenantHeadersStamped: SJ2PR11MB8500 X-OriginatorOrg: intel.com 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 --_000_SN7PR11MB7044CD7EEC9FCD8B2993561FA1FB2SN7PR11MB7044namp_ Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable ________________________________ From: Shijith Thotton Sent: Friday, February 7, 2025 7:39 PM To: jerinj@marvell.com Cc: pbhagavatula@marvell.com ; Shijith Thotton ; dev@dpdk.org ; Pathak, Pravin ; Hemant Agrawal ; Sachin Saxena ; Mattias R_nnblom ; Li= ang Ma ; Mccarthy, Peter ; = Van Haaren, Harry ; Carrillo, Erik G ; Gujjar, Abhinandan S ; Amit= Prakash Shukla ; Naga Harish K, S V ; Burakov, Anatoly Subject: [PATCH 1/3] eventdev/eth_rx: add API to burst add queues to Rx ada= pter This patch introduces a new API, rte_event_eth_rx_adapter_queues_add(), to allow bulk addition of multiple Rx queues in the eventdev Rx adapter. The existing rte_event_eth_rx_adapter_queue_add() API supports adding multiple queues by specifying rx_queue_id =3D -1, but it lacks the ability to apply specific configurations to each of the added queues. A new internal PMD operation, eventdev_eth_rx_adapter_queues_add_t, has been introduced to enable this functionality. It takes an array of receive queue IDs along with their corresponding queue configurations. Signed-off-by: Shijith Thotton --- lib/eventdev/eventdev_pmd.h | 34 ++++++ lib/eventdev/eventdev_trace.h | 14 +++ lib/eventdev/eventdev_trace_points.c | 3 + lib/eventdev/rte_event_eth_rx_adapter.c | 146 ++++++++++++++++++++++++ lib/eventdev/rte_event_eth_rx_adapter.h | 33 ++++++ lib/eventdev/version.map | 3 + 6 files changed, 233 insertions(+) diff --git a/lib/eventdev/eventdev_pmd.h b/lib/eventdev/eventdev_pmd.h index 36148f8d86..ad13ba5b03 100644 --- a/lib/eventdev/eventdev_pmd.h +++ b/lib/eventdev/eventdev_pmd.h @@ -25,6 +25,7 @@ #include #include "event_timer_adapter_pmd.h" +#include "rte_event_eth_rx_adapter.h" #include "rte_eventdev.h" #ifdef __cplusplus @@ -708,6 +709,37 @@ typedef int (*eventdev_eth_rx_adapter_queue_add_t)( int32_t rx_queue_id, const struct rte_event_eth_rx_adapter_queue_conf *queue_co= nf); +/** + * Add ethernet Rx queues to event device in burst. This callback is invok= ed if + * the caps returned from rte_eventdev_eth_rx_adapter_caps_get(, eth_port_= id) + * has RTE_EVENT_ETH_RX_ADAPTER_CAP_INTERNAL_PORT set. + * + * @param dev + * Event device pointer + * + * @param eth_dev + * Ethernet device pointer + * + * @param rx_queue_id + * Ethernet device receive queue index array + * + * @param queue_conf + * Additional configuration structure array + * + * @param nb_rx_queues + * Number of ethernet device receive queues + * + * @return + * - 0: Success, ethernet receive queues added successfully. + * - <0: Error code returned by the driver function. + */ +typedef int (*eventdev_eth_rx_adapter_queues_add_t)( + const struct rte_eventdev *dev, + const struct rte_eth_dev *eth_dev, + int32_t rx_queue_id[], + const struct rte_event_eth_rx_adapter_queue_conf queue_conf= [], + uint16_t nb_rx_queues); + /** * Delete ethernet Rx queues from event device. This callback is invoked i= f * the caps returned from eventdev_eth_rx_adapter_caps_get(, eth_port_id) @@ -1578,6 +1610,8 @@ struct eventdev_ops { /**< Get ethernet Rx adapter capabilities */ eventdev_eth_rx_adapter_queue_add_t eth_rx_adapter_queue_add; /**< Add Rx queues to ethernet Rx adapter */ + eventdev_eth_rx_adapter_queues_add_t eth_rx_adapter_queues_add; + /**< Add Rx queues to ethernet Rx adapter in burst */ eventdev_eth_rx_adapter_queue_del_t eth_rx_adapter_queue_del; /**< Delete Rx queues from ethernet Rx adapter */ eventdev_eth_rx_adapter_queue_conf_get_t eth_rx_adapter_queue_conf= _get; diff --git a/lib/eventdev/eventdev_trace.h b/lib/eventdev/eventdev_trace.h index 8ff8841729..6b334d8bd1 100644 --- a/lib/eventdev/eventdev_trace.h +++ b/lib/eventdev/eventdev_trace.h @@ -159,6 +159,20 @@ RTE_TRACE_POINT( rte_trace_point_emit_int(rc); ) +RTE_TRACE_POINT( + rte_eventdev_trace_eth_rx_adapter_queues_add, + RTE_TRACE_POINT_ARGS(uint8_t adptr_id, uint16_t eth_dev_id, + uint16_t nb_rx_queues, void *rx_queue_id, + const void *queue_conf, + int rc), + rte_trace_point_emit_u8(adptr_id); + rte_trace_point_emit_u16(eth_dev_id); + rte_trace_point_emit_u16(nb_rx_queues); + rte_trace_point_emit_ptr(rx_queue_id); + rte_trace_point_emit_ptr(queue_conf); + rte_trace_point_emit_int(rc); +) + RTE_TRACE_POINT( rte_eventdev_trace_eth_rx_adapter_queue_del, RTE_TRACE_POINT_ARGS(uint8_t adptr_id, uint16_t eth_dev_id, diff --git a/lib/eventdev/eventdev_trace_points.c b/lib/eventdev/eventdev_t= race_points.c index e7af1591f7..8caf6353a1 100644 --- a/lib/eventdev/eventdev_trace_points.c +++ b/lib/eventdev/eventdev_trace_points.c @@ -65,6 +65,9 @@ RTE_TRACE_POINT_REGISTER(rte_eventdev_trace_eth_rx_adapte= r_free, RTE_TRACE_POINT_REGISTER(rte_eventdev_trace_eth_rx_adapter_queue_add, lib.eventdev.rx.adapter.queue.add) +RTE_TRACE_POINT_REGISTER(rte_eventdev_trace_eth_rx_adapter_queues_add, + lib.eventdev.rx.adapter.queues.add) + RTE_TRACE_POINT_REGISTER(rte_eventdev_trace_eth_rx_adapter_queue_del, lib.eventdev.rx.adapter.queue.del) diff --git a/lib/eventdev/rte_event_eth_rx_adapter.c b/lib/eventdev/rte_eve= nt_eth_rx_adapter.c index 39674c4604..c5a357aa85 100644 --- a/lib/eventdev/rte_event_eth_rx_adapter.c +++ b/lib/eventdev/rte_event_eth_rx_adapter.c @@ -2793,6 +2793,152 @@ rte_event_eth_rx_adapter_queue_add(uint8_t id, return 0; } +int +rte_event_eth_rx_adapter_queues_add(uint8_t id, uint16_t eth_dev_id, int32= _t rx_queue_id[], + const struct rte_event_eth_rx_adapter_q= ueue_conf queue_conf[], + uint16_t nb_rx_queues) +{ + struct rte_event_eth_rx_adapter_vector_limits limits; + struct event_eth_rx_adapter *rx_adapter; + struct eth_device_info *dev_info; + struct rte_eventdev *dev; + uint32_t cap; + int32_t i; + int ret; + + if (rxa_memzone_lookup()) + return -ENOMEM; + + RTE_EVENT_ETH_RX_ADAPTER_ID_VALID_OR_ERR_RET(id, -EINVAL); + RTE_ETH_VALID_PORTID_OR_ERR_RET(eth_dev_id, -EINVAL); + + rx_adapter =3D rxa_id_to_adapter(id); + if ((rx_adapter =3D=3D NULL) || (queue_conf =3D=3D NULL)) + return -EINVAL; + + if (nb_rx_queues && rx_queue_id =3D=3D NULL) + return -EINVAL; + + if (nb_rx_queues > rte_eth_devices[eth_dev_id].data->nb_rx_queues) = { + RTE_EDEV_LOG_ERR("Invalid number of rx queues %" PRIu16, nb= _rx_queues); + return -EINVAL; + } + + ret =3D rte_event_eth_rx_adapter_caps_get(rx_adapter->eventdev_id, = eth_dev_id, &cap); + if (ret) { + RTE_EDEV_LOG_ERR("Failed to get adapter caps edev %" PRIu8 = "eth port %" PRIu16, id, + eth_dev_id); + return ret; + } + + for (i =3D 0; i < (nb_rx_queues ? nb_rx_queues : 1); i++) { + const struct rte_event_eth_rx_adapter_queue_conf *conf; + + conf =3D &queue_conf[i]; + if ((cap & RTE_EVENT_ETH_RX_ADAPTER_CAP_OVERRIDE_FLOW_ID) = =3D=3D 0 && + (conf->rx_queue_flags & RTE_EVENT_ETH_RX_ADAPTER_QUEUE_= FLOW_ID_VALID)) { + RTE_EDEV_LOG_ERR("Flow ID override is not supported= ," + " eth port: %" PRIu16 " adapter id= : %" PRIu8, + eth_dev_id, id); "rx_queue_id" can also be included in the error debug logs. Same is applicable to the following debug logs. + return -EINVAL; + } + RTE_EVENT_ETH_RX_ADAPTER_CAP_MULTI_EVENTQ validation is missing. + if (conf->rx_queue_flags & RTE_EVENT_ETH_RX_ADAPTER_QUEUE_E= VENT_VECTOR) { + if ((cap & RTE_EVENT_ETH_RX_ADAPTER_CAP_EVENT_VECTO= R) =3D=3D 0) { + RTE_EDEV_LOG_ERR("Event vectorization is no= t supported," + " eth port: %" PRIu16 " ad= apter id: %" PRIu8, + eth_dev_id, id); + return -EINVAL; + } + + ret =3D rte_event_eth_rx_adapter_vector_limits_get(= rx_adapter->eventdev_id, + et= h_dev_id, &limits); + if (ret < 0) { + RTE_EDEV_LOG_ERR("Failed to get event devic= e vector limits," + " eth port: %" PRIu16 " ad= apter id: %" PRIu8, + eth_dev_id, id); + return -EINVAL; + } + + if (conf->vector_sz < limits.min_sz || conf->vector= _sz > limits.max_sz || + conf->vector_timeout_ns < limits.min_timeout_ns= || + conf->vector_timeout_ns > limits.max_timeout_ns= || + conf->vector_mp =3D=3D NULL) { + RTE_EDEV_LOG_ERR("Invalid event vector conf= iguration," + " eth port: %" PRIu16 " ad= apter id: %" PRIu8, + eth_dev_id, id); + return -EINVAL; + } + + if (conf->vector_mp->elt_size < (sizeof(struct rte_= event_vector) + + (sizeof(uintptr_t)= * conf->vector_sz))) { + RTE_EDEV_LOG_ERR("Invalid event vector conf= iguration," + " eth port: %" PRIu16 " ad= apter id: %" PRIu8, + eth_dev_id, id); + return -EINVAL; + } + } + + if ((rx_adapter->use_queue_event_buf && conf->event_buf_siz= e =3D=3D 0) || + (!rx_adapter->use_queue_event_buf && conf->event_buf_si= ze !=3D 0)) { + RTE_EDEV_LOG_ERR("Invalid Event buffer size for the= queue"); + return -EINVAL; + } + } + + dev =3D &rte_eventdevs[rx_adapter->eventdev_id]; + dev_info =3D &rx_adapter->eth_devices[eth_dev_id]; + + if (cap & RTE_EVENT_ETH_RX_ADAPTER_CAP_INTERNAL_PORT) { + if (*dev->dev_ops->eth_rx_adapter_queues_add =3D=3D NULL) + return -ENOTSUP; + + if (dev_info->rx_queue =3D=3D NULL) { + dev_info->rx_queue =3D + rte_zmalloc_socket(rx_adapter->mem_name, + dev_info->dev->data->nb_= rx_queues * + sizeof(struct et= h_rx_queue_info), + 0, rx_adapter->socket_id= ); + if (dev_info->rx_queue =3D=3D NULL) + return -ENOMEM; + } + + ret =3D (*dev->dev_ops->eth_rx_adapter_queues_add)( + dev, &rte_eth_devices[eth_dev_id], rx_queue_id, que= ue_conf, nb_rx_queues); + if (ret =3D=3D 0) { + dev_info->internal_event_port =3D 1; + + if (nb_rx_queues =3D=3D 0) + rxa_update_queue(rx_adapter, dev_info, -1, = 1); + + for (i =3D 0; i < nb_rx_queues; i++) + rxa_update_queue(rx_adapter, dev_info, rx_q= ueue_id[i], 1); + } + } else { + rte_spinlock_lock(&rx_adapter->rx_lock); + dev_info->internal_event_port =3D 0; + ret =3D rxa_init_service(rx_adapter, id); + if (ret =3D=3D 0) { + uint32_t service_id =3D rx_adapter->service_id; + + if (nb_rx_queues =3D=3D 0) + ret =3D rxa_sw_add(rx_adapter, eth_dev_id, = -1, &queue_conf[0]); + + for (i =3D 0; i < nb_rx_queues; i++) + ret =3D rxa_sw_add(rx_adapter, eth_dev_id, = rx_queue_id[i], + &queue_conf[i]); + + rte_service_component_runstate_set(service_id, + rxa_sw_adapter_q= ueue_count(rx_adapter)); + } + rte_spinlock_unlock(&rx_adapter->rx_lock); + } + + rte_eventdev_trace_eth_rx_adapter_queues_add(id, eth_dev_id, nb_rx_= queues, rx_queue_id, + queue_conf, ret); + return ret; +} + static int rxa_sw_vector_limits(struct rte_event_eth_rx_adapter_vector_limits *limits= ) { diff --git a/lib/eventdev/rte_event_eth_rx_adapter.h b/lib/eventdev/rte_eve= nt_eth_rx_adapter.h index 9237e198a7..758e1c5f56 100644 --- a/lib/eventdev/rte_event_eth_rx_adapter.h +++ b/lib/eventdev/rte_event_eth_rx_adapter.h @@ -553,6 +553,39 @@ int rte_event_eth_rx_adapter_queue_add(uint8_t id, int32_t rx_queue_id, const struct rte_event_eth_rx_adapter_queue_conf *= conf); +/** + * Add multiple receive queues to an event adapter. + * + * @param id + * Adapter identifier. + * + * @param eth_dev_id + * Port identifier of Ethernet device. + * + * @param rx_queue_id + * Array of Ethernet device receive queue indices. + * If nb_rx_queues is 0, then rx_queue_id is ignored. + * + * @param conf + * Array of additional configuration structures of type + * *rte_event_eth_rx_adapter_queue_conf*. conf[i] is used for rx_queue_id= [i]. + * If nb_rx_queues is 0, then conf[0] is used for all Rx queues. + * + * @param nb_rx_queues + * Number of receive queues to add. + * If nb_rx_queues is 0, then all Rx queues configured for + * the device are added with the same configuration in conf[0]. + * @see RTE_EVENT_ETH_RX_ADAPTER_CAP_MULTI_EVENTQ + * + * @return + * - 0: Success, Receive queues added correctly. + * - <0: Error code on failure. + */ +__rte_experimental +int rte_event_eth_rx_adapter_queues_add(uint8_t id, uint16_t eth_dev_id, i= nt32_t rx_queue_id[], + const struct rte_event_eth_rx_adapt= er_queue_conf conf[], + uint16_t nb_rx_queues); + /** * Delete receive queue from an event adapter. * diff --git a/lib/eventdev/version.map b/lib/eventdev/version.map index 42a5867aba..44687255cb 100644 --- a/lib/eventdev/version.map +++ b/lib/eventdev/version.map @@ -153,6 +153,9 @@ EXPERIMENTAL { __rte_eventdev_trace_port_preschedule_modify; rte_event_port_preschedule; __rte_eventdev_trace_port_preschedule; + + # added in 25.03 + rte_event_eth_rx_adapter_queues_add; }; INTERNAL { -- 2.25.1 --_000_SN7PR11MB7044CD7EEC9FCD8B2993561FA1FB2SN7PR11MB7044namp_ Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable


From: Shijit= h Thotton <sthotton@marvell.com>
Sent: Friday, February 7, 2025 7:39 PM
To: jerinj@marvell.com <jerinj@marvell.com>
Cc: pbhagavatula@marvell.com <pbhagavatula@marvell.com>; = Shijith Thotton <sthotton@marvell.com>; dev@dpdk.org <dev@dpdk.org= >; Pathak, Pravin <pravin.pathak@intel.com>; Hemant Agrawal <he= mant.agrawal@nxp.com>; Sachin Saxena <sachin.saxena@nxp.com>; Matt= ias R_nnblom <mattias.ronnblom@ericsson.com>; Liang Ma <liangma@liang= bit.com>; Mccarthy, Peter <Peter.Mccarthy@intel.com>; Van Haaren, = Harry <harry.van.haaren@intel.com>; Carrillo, Erik G <Erik.G.Carri= llo@intel.com>; Gujjar, Abhinandan S <abhinandan.gujjar@intel.com>= ; Amit Prakash Shukla <amitprakashs@marvell.com>; Naga Harish K, S V &= lt;s.v.naga.harish.k@intel.com>; Burakov, Anatoly <anatoly.burakov@in= tel.com>
Subject: [PATCH 1/3] eventdev/eth_rx: add API to burst add queu= es to Rx adapter
 
This patch introdu= ces a new API, rte_event_eth_rx_adapter_queues_add(),
to allow bulk addition of multiple Rx queues in the eventdev Rx adapter.
The existing rte_event_eth_rx_adapter_queue_add() API supports adding
multiple queues by specifying rx_queue_id =3D -1, but it lacks the ability<= br> to apply specific configurations to each of the added queues.

A new internal PMD operation, eventdev_eth_rx_adapter_queues_add_t, has
been introduced to enable this functionality. It takes an array of
receive queue IDs along with their corresponding queue configurations.

Signed-off-by: Shijith Thotton <sthotton@marvell.com>
---
 lib/eventdev/eventdev_pmd.h       =       |  34 ++++++
 lib/eventdev/eventdev_trace.h      &nbs= p;    |  14 +++
 lib/eventdev/eventdev_trace_points.c    |   = 3 +
 lib/eventdev/rte_event_eth_rx_adapter.c | 146 +++++++++++++++++++++++= +
 lib/eventdev/rte_event_eth_rx_adapter.h |  33 ++++++
 lib/eventdev/version.map       &nb= sp;        |   3 +
 6 files changed, 233 insertions(+)

diff --git a/lib/eventdev/eventdev_pmd.h b/lib/eventdev/eventdev_pmd.h
index 36148f8d86..ad13ba5b03 100644
--- a/lib/eventdev/eventdev_pmd.h
+++ b/lib/eventdev/eventdev_pmd.h
@@ -25,6 +25,7 @@
 #include <rte_mbuf_dyn.h>
 
 #include "event_timer_adapter_pmd.h"
+#include "rte_event_eth_rx_adapter.h"
 #include "rte_eventdev.h"
 
 #ifdef __cplusplus
@@ -708,6 +709,37 @@ typedef int (*eventdev_eth_rx_adapter_queue_add_t)(             &nb= sp;    int32_t rx_queue_id,
            &nb= sp;    const struct rte_event_eth_rx_adapter_queue_conf *que= ue_conf);
 
+/**
+ * Add ethernet Rx queues to event device in burst. This callback is invok= ed if
+ * the caps returned from rte_eventdev_eth_rx_adapter_caps_get(, eth_port_= id)
+ * has RTE_EVENT_ETH_RX_ADAPTER_CAP_INTERNAL_PORT set.
+ *
+ * @param dev
+ *   Event device pointer
+ *
+ * @param eth_dev
+ *   Ethernet device pointer
+ *
+ * @param rx_queue_id
+ *   Ethernet device receive queue index array
+ *
+ * @param queue_conf
+ *   Additional configuration structure array
+ *
+ * @param nb_rx_queues
+ *   Number of ethernet device receive queues
+ *
+ * @return
+ *   - 0: Success, ethernet receive queues added successfully. + *   - <0: Error code returned by the driver function.
+ */
+typedef int (*eventdev_eth_rx_adapter_queues_add_t)(
+            &n= bsp;  const struct rte_eventdev *dev,
+            &n= bsp;  const struct rte_eth_dev *eth_dev,
+            &n= bsp;  int32_t rx_queue_id[],
+            &n= bsp;  const struct rte_event_eth_rx_adapter_queue_conf queue_conf[], +            &n= bsp;  uint16_t nb_rx_queues);
+
 /**
  * Delete ethernet Rx queues from event device. This callback is invo= ked if
  * the caps returned from eventdev_eth_rx_adapter_caps_get(, eth_port= _id)
@@ -1578,6 +1610,8 @@ struct eventdev_ops {
         /**< Get ethernet Rx ad= apter capabilities */
         eventdev_eth_rx_adapter_qu= eue_add_t eth_rx_adapter_queue_add;
         /**< Add Rx queues to e= thernet Rx adapter */
+       eventdev_eth_rx_adapter_queues_add_t = eth_rx_adapter_queues_add;
+       /**< Add Rx queues to ethernet Rx = adapter in burst */
         eventdev_eth_rx_adapter_qu= eue_del_t eth_rx_adapter_queue_del;
         /**< Delete Rx queues f= rom ethernet Rx adapter */
         eventdev_eth_rx_adapter_qu= eue_conf_get_t eth_rx_adapter_queue_conf_get;
diff --git a/lib/eventdev/eventdev_trace.h b/lib/eventdev/eventdev_trace.h<= br> index 8ff8841729..6b334d8bd1 100644
--- a/lib/eventdev/eventdev_trace.h
+++ b/lib/eventdev/eventdev_trace.h
@@ -159,6 +159,20 @@ RTE_TRACE_POINT(
         rte_trace_point_emit_int(r= c);
 )
 
+RTE_TRACE_POINT(
+       rte_eventdev_trace_eth_rx_adapter_que= ues_add,
+       RTE_TRACE_POINT_ARGS(uint8_t adptr_id= , uint16_t eth_dev_id,
+            &n= bsp;  uint16_t nb_rx_queues, void *rx_queue_id,
+            &n= bsp;  const void *queue_conf,
+            &n= bsp;  int rc),
+       rte_trace_point_emit_u8(adptr_id); +       rte_trace_point_emit_u16(eth_dev_id);=
+       rte_trace_point_emit_u16(nb_rx_queues= );
+       rte_trace_point_emit_ptr(rx_queue_id)= ;
+       rte_trace_point_emit_ptr(queue_conf);=
+       rte_trace_point_emit_int(rc);
+)
+
 RTE_TRACE_POINT(
         rte_eventdev_trace_eth_rx_= adapter_queue_del,
         RTE_TRACE_POINT_ARGS(uint8= _t adptr_id, uint16_t eth_dev_id,
diff --git a/lib/eventdev/eventdev_trace_points.c b/lib/eventdev/eventdev_t= race_points.c
index e7af1591f7..8caf6353a1 100644
--- a/lib/eventdev/eventdev_trace_points.c
+++ b/lib/eventdev/eventdev_trace_points.c
@@ -65,6 +65,9 @@ RTE_TRACE_POINT_REGISTER(rte_eventdev_trace_eth_rx_adapte= r_free,
 RTE_TRACE_POINT_REGISTER(rte_eventdev_trace_eth_rx_adapter_queue_add,=
         lib.eventdev.rx.adapter.qu= eue.add)
 
+RTE_TRACE_POINT_REGISTER(rte_eventdev_trace_eth_rx_adapter_queues_add,
+       lib.eventdev.rx.adapter.queues.add) +
 RTE_TRACE_POINT_REGISTER(rte_eventdev_trace_eth_rx_adapter_queue_del,=
         lib.eventdev.rx.adapter.qu= eue.del)
 
diff --git a/lib/eventdev/rte_event_eth_rx_adapter.c b/lib/eventdev/rte_eve= nt_eth_rx_adapter.c
index 39674c4604..c5a357aa85 100644
--- a/lib/eventdev/rte_event_eth_rx_adapter.c
+++ b/lib/eventdev/rte_event_eth_rx_adapter.c
@@ -2793,6 +2793,152 @@ rte_event_eth_rx_adapter_queue_add(uint8_t id,
         return 0;
 }
 
+int
+rte_event_eth_rx_adapter_queues_add(uint8_t id, uint16_t eth_dev_id, int32= _t rx_queue_id[],
+            &n= bsp;            = ;          const struct rte_ev= ent_eth_rx_adapter_queue_conf queue_conf[],
+            &n= bsp;            = ;          uint16_t nb_rx_queu= es)
+{
+       struct rte_event_eth_rx_adapter_vecto= r_limits limits;
+       struct event_eth_rx_adapter *rx_adapt= er;
+       struct eth_device_info *dev_info;
+       struct rte_eventdev *dev;
+       uint32_t cap;
+       int32_t i;
+       int ret;
+
+       if (rxa_memzone_lookup())
+            &n= bsp;  return -ENOMEM;
+
+       RTE_EVENT_ETH_RX_ADAPTER_ID_VALID_OR_= ERR_RET(id, -EINVAL);
+       RTE_ETH_VALID_PORTID_OR_ERR_RET(eth_d= ev_id, -EINVAL);
+
+       rx_adapter =3D rxa_id_to_adapter(id);=
+       if ((rx_adapter =3D=3D NULL) || (queu= e_conf =3D=3D NULL))
+            &n= bsp;  return -EINVAL;
+
+       if (nb_rx_queues && rx_queue_= id =3D=3D NULL)
+            &n= bsp;  return -EINVAL;
+
+       if (nb_rx_queues > rte_eth_devices= [eth_dev_id].data->nb_rx_queues) {
+            &n= bsp;  RTE_EDEV_LOG_ERR("Invalid number of rx queues %" PRIu1= 6, nb_rx_queues);
+            &n= bsp;  return -EINVAL;
+       }
+
+       ret =3D rte_event_eth_rx_adapter_caps= _get(rx_adapter->eventdev_id, eth_dev_id, &cap);
+       if (ret) {
+            &n= bsp;  RTE_EDEV_LOG_ERR("Failed to get adapter caps edev %" P= RIu8 "eth port %" PRIu16, id,
+            &n= bsp;            = ;       eth_dev_id);
+            &n= bsp;  return ret;
+       }
+
+       for (i =3D 0; i < (nb_rx_queues ? = nb_rx_queues : 1); i++) {
+            &n= bsp;  const struct rte_event_eth_rx_adapter_queue_conf *conf;
+
+            &n= bsp;  conf =3D &queue_conf[i];
+            &n= bsp;  if ((cap & RTE_EVENT_ETH_RX_ADAPTER_CAP_OVERRIDE_FLOW_ID) = =3D=3D 0 &&
+            &n= bsp;      (conf->rx_queue_flags & RTE_EVENT= _ETH_RX_ADAPTER_QUEUE_FLOW_ID_VALID)) {
+            &n= bsp;          RTE_EDEV_LOG_ERR= ("Flow ID override is not supported,"
+            &n= bsp;            = ;            &n= bsp;  " eth port: %" PRIu16 " adapter id: %" PRIu8= ,
+            &n= bsp;            = ;            &n= bsp;  eth_dev_id, id);

"rx_queue_id&= quot; can also be included in the error debug logs. 
Same is applicable to the following debug logs.

+   = ;            &n= bsp;       return -EINVAL;
+            &n= bsp;  }
+

RTE_EVENT_ETH_RX_ADAPTER_CAP_MULTI_EVENTQ validation is missing.

+   = ;            if (con= f->rx_queue_flags & RTE_EVENT_ETH_RX_ADAPTER_QUEUE_EVENT_VECTOR) { +            &n= bsp;          if ((cap & R= TE_EVENT_ETH_RX_ADAPTER_CAP_EVENT_VECTOR) =3D=3D 0) {
+            &n= bsp;            = ;      RTE_EDEV_LOG_ERR("Event vectorization = is not supported,"
+            &n= bsp;            = ;            &n= bsp;          " eth port:= %" PRIu16 " adapter id: %" PRIu8,
+            &n= bsp;            = ;            &n= bsp;          eth_dev_id, id);=
+            &n= bsp;            = ;      return -EINVAL;
+            &n= bsp;          }
+
+            &n= bsp;          ret =3D rte_even= t_eth_rx_adapter_vector_limits_get(rx_adapter->eventdev_id,
+            &n= bsp;            = ;            &n= bsp;            = ;            &n= bsp;         eth_dev_id, &limit= s);
+            &n= bsp;          if (ret < 0) = {
+            &n= bsp;            = ;      RTE_EDEV_LOG_ERR("Failed to get event = device vector limits,"
+            &n= bsp;            = ;            &n= bsp;          " eth port:= %" PRIu16 " adapter id: %" PRIu8,
+            &n= bsp;            = ;            &n= bsp;          eth_dev_id, id);=
+            &n= bsp;            = ;      return -EINVAL;
+            &n= bsp;          }
+
+            &n= bsp;          if (conf->vec= tor_sz < limits.min_sz || conf->vector_sz > limits.max_sz ||
+            &n= bsp;            = ;  conf->vector_timeout_ns < limits.min_timeout_ns ||
+            &n= bsp;            = ;  conf->vector_timeout_ns > limits.max_timeout_ns ||
+            &n= bsp;            = ;  conf->vector_mp =3D=3D NULL) {
+            &n= bsp;            = ;      RTE_EDEV_LOG_ERR("Invalid event vector= configuration,"
+            &n= bsp;            = ;            &n= bsp;          " eth port:= %" PRIu16 " adapter id: %" PRIu8,
+            &n= bsp;            = ;            &n= bsp;          eth_dev_id, id);=
+            &n= bsp;            = ;      return -EINVAL;
+            &n= bsp;          }
+
+            &n= bsp;          if (conf->vec= tor_mp->elt_size < (sizeof(struct rte_event_vector) +
+            &n= bsp;            = ;            &n= bsp;            = ;      (sizeof(uintptr_t) * conf->vector_sz))) = {
+            &n= bsp;            = ;      RTE_EDEV_LOG_ERR("Invalid event vector= configuration,"
+            &n= bsp;            = ;            &n= bsp;          " eth port:= %" PRIu16 " adapter id: %" PRIu8,
+            &n= bsp;            = ;            &n= bsp;          eth_dev_id, id);=
+            &n= bsp;            = ;      return -EINVAL;
+            &n= bsp;          }
+            &n= bsp;  }
+
+            &n= bsp;  if ((rx_adapter->use_queue_event_buf && conf->even= t_buf_size =3D=3D 0) ||
+            &n= bsp;      (!rx_adapter->use_queue_event_buf &am= p;& conf->event_buf_size !=3D 0)) {
+            &n= bsp;          RTE_EDEV_LOG_ERR= ("Invalid Event buffer size for the queue");
+            &n= bsp;          return -EINVAL;<= br> +            &n= bsp;  }
+       }
+
+       dev =3D &rte_eventdevs[rx_adapter= ->eventdev_id];
+       dev_info =3D &rx_adapter->eth_= devices[eth_dev_id];
+
+       if (cap & RTE_EVENT_ETH_RX_ADAPTE= R_CAP_INTERNAL_PORT) {
+            &n= bsp;  if (*dev->dev_ops->eth_rx_adapter_queues_add =3D=3D NULL)<= br> +            &n= bsp;          return -ENOTSUP;=
+
+            &n= bsp;  if (dev_info->rx_queue =3D=3D NULL) {
+            &n= bsp;          dev_info->rx_= queue =3D
+            &n= bsp;            = ;      rte_zmalloc_socket(rx_adapter->mem_name,=
+            &n= bsp;            = ;            &n= bsp;            dev_= info->dev->data->nb_rx_queues *
+            &n= bsp;            = ;            &n= bsp;            = ;        sizeof(struct eth_rx_queue_info= ),
+            &n= bsp;            = ;            &n= bsp;            0, r= x_adapter->socket_id);
+            &n= bsp;          if (dev_info->= ;rx_queue =3D=3D NULL)
+            &n= bsp;            = ;      return -ENOMEM;
+            &n= bsp;  }
+
+            &n= bsp;  ret =3D (*dev->dev_ops->eth_rx_adapter_queues_add)(
+            &n= bsp;          dev, &rte_et= h_devices[eth_dev_id], rx_queue_id, queue_conf, nb_rx_queues);
+            &n= bsp;  if (ret =3D=3D 0) {
+            &n= bsp;          dev_info->int= ernal_event_port =3D 1;
+
+            &n= bsp;          if (nb_rx_queues= =3D=3D 0)
+            &n= bsp;            = ;      rxa_update_queue(rx_adapter, dev_info, -1, = 1);
+
+            &n= bsp;          for (i =3D 0; i = < nb_rx_queues; i++)
+            &n= bsp;            = ;      rxa_update_queue(rx_adapter, dev_info, rx_q= ueue_id[i], 1);
+            &n= bsp;  }
+       } else {
+            &n= bsp;  rte_spinlock_lock(&rx_adapter->rx_lock);
+            &n= bsp;  dev_info->internal_event_port =3D 0;
+            &n= bsp;  ret =3D rxa_init_service(rx_adapter, id);
+            &n= bsp;  if (ret =3D=3D 0) {
+            &n= bsp;          uint32_t service= _id =3D rx_adapter->service_id;
+
+            &n= bsp;          if (nb_rx_queues= =3D=3D 0)
+            &n= bsp;            = ;      ret =3D rxa_sw_add(rx_adapter, eth_dev_id, = -1, &queue_conf[0]);
+
+            &n= bsp;          for (i =3D 0; i = < nb_rx_queues; i++)
+            &n= bsp;            = ;      ret =3D rxa_sw_add(rx_adapter, eth_dev_id, = rx_queue_id[i],
+            &n= bsp;            = ;            &n= bsp;          &queue_conf[= i]);
+
+            &n= bsp;          rte_service_comp= onent_runstate_set(service_id,
+            &n= bsp;            = ;            &n= bsp;            = ;        rxa_sw_adapter_queue_count(rx_a= dapter));
+            &n= bsp;  }
+            &n= bsp;  rte_spinlock_unlock(&rx_adapter->rx_lock);
+       }
+
+       rte_eventdev_trace_eth_rx_adapter_que= ues_add(id, eth_dev_id, nb_rx_queues, rx_queue_id,
+            &n= bsp;            = ;            &n= bsp;            = ;  queue_conf, ret);
+       return ret;
+}
+
 static int
 rxa_sw_vector_limits(struct rte_event_eth_rx_adapter_vector_limits *l= imits)
 {
diff --git a/lib/eventdev/rte_event_eth_rx_adapter.h b/lib/eventdev/rte_eve= nt_eth_rx_adapter.h
index 9237e198a7..758e1c5f56 100644
--- a/lib/eventdev/rte_event_eth_rx_adapter.h
+++ b/lib/eventdev/rte_event_eth_rx_adapter.h
@@ -553,6 +553,39 @@ int rte_event_eth_rx_adapter_queue_add(uint8_t id,
            &nb= sp;            int32= _t rx_queue_id,
            &nb= sp;            const= struct rte_event_eth_rx_adapter_queue_conf *conf);
 
+/**
+ * Add multiple receive queues to an event adapter.
+ *
+ * @param id
+ *  Adapter identifier.
+ *
+ * @param eth_dev_id
+ *  Port identifier of Ethernet device.
+ *
+ * @param rx_queue_id
+ *  Array of Ethernet device receive queue indices.
+ *  If nb_rx_queues is 0, then rx_queue_id is ignored.
+ *
+ * @param conf
+ *  Array of additional configuration structures of type
+ *  *rte_event_eth_rx_adapter_queue_conf*. conf[i] is used for rx_que= ue_id[i].
+ *  If nb_rx_queues is 0, then conf[0] is used for all Rx queues.
+ *
+ * @param nb_rx_queues
+ *  Number of receive queues to add.
+ *  If nb_rx_queues is 0, then all Rx queues configured for
+ *  the device are added with the same configuration in conf[0].
+ * @see RTE_EVENT_ETH_RX_ADAPTER_CAP_MULTI_EVENTQ
+ *
+ * @return
+ *  - 0: Success, Receive queues added correctly.
+ *  - <0: Error code on failure.
+ */
+__rte_experimental
+int rte_event_eth_rx_adapter_queues_add(uint8_t id, uint16_t eth_dev_id, i= nt32_t rx_queue_id[],
+            &n= bsp;            = ;            &n= bsp; const struct rte_event_eth_rx_adapter_queue_conf conf[],
+            &n= bsp;            = ;            &n= bsp; uint16_t nb_rx_queues);
+
 /**
  * Delete receive queue from an event adapter.
  *
diff --git a/lib/eventdev/version.map b/lib/eventdev/version.map
index 42a5867aba..44687255cb 100644
--- a/lib/eventdev/version.map
+++ b/lib/eventdev/version.map
@@ -153,6 +153,9 @@ EXPERIMENTAL {
         __rte_eventdev_trace_port_= preschedule_modify;
         rte_event_port_preschedule= ;
         __rte_eventdev_trace_port_= preschedule;
+
+       # added in 25.03
+       rte_event_eth_rx_adapter_queues_add;<= br>  };
 
 INTERNAL {
--
2.25.1

--_000_SN7PR11MB7044CD7EEC9FCD8B2993561FA1FB2SN7PR11MB7044namp_--