From patchwork Thu Aug 11 05:50:58 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Slava Ovsiienko X-Patchwork-Id: 114817 X-Patchwork-Delegate: rasland@nvidia.com Return-Path: X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 9FC1CA0548; Thu, 11 Aug 2022 07:51:22 +0200 (CEST) Received: from [217.70.189.124] (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 59F4340DDA; Thu, 11 Aug 2022 07:51:22 +0200 (CEST) Received: from NAM12-DM6-obe.outbound.protection.outlook.com (mail-dm6nam12on2068.outbound.protection.outlook.com [40.107.243.68]) by mails.dpdk.org (Postfix) with ESMTP id 0ED9240A87; Thu, 11 Aug 2022 07:51:20 +0200 (CEST) ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=TGYW5/HQS79p+lcnj7bvLXoMrB2fvGxPjSm38AnkvrJwnR+4Iix4fBu7abxakDPKGC4kLZm4n5LOd3XaiGxew8xxzTMRweRuMFP0YAa/mEl0PKOKc2OLKNspbfPt/peRYmhSYj0B8YW4Vz6KJIwPh4DtaD4s1ZHnEKDc2CF+GOR07oQPFL+tcCn58jsm2ixhxUGP0y7kFU9Qoez7v3xI5IM8rT4JB2NoSN8+dTUDoMsxr/B4VtGrL0IwFH9sN/dGunGrEtXeBjz+bYIthiw5seAyKUkpssiyfzD3VRoiHeBcgkF3PQ1/cw59HHK83dPiwY3fYILIQm372WMNWA37pw== 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=EIhSPyIIOf0BshqaQ2CMWvm6LANQIagB+M0XU+ALWS8=; b=givTtCEKIbqa+bbAVb9siB7nXs6s78J/lriIoUL21t+C9GYORYwnMzL77v2JlgS24r7dEQN/o6AB2vOfv2aq/PR0tTG1pFSt9Sr1tG24sXrrBNi5e+0KdVD3MgPp0NIs7savdGSnTy75Yh3vHgO+hC/g8DVI4uA3z0+OhUQNmnXeWlRzCgwrxiKzLKE5tiMFLcdABj3yHpgZuZiZ9tbh1NTDlHaNJi2Th0n6MP5F+a7k5ed/f3nV4wvEmgxKgoWnZcATOeK7pzhd30X1kL0JtBEtNW2b5My/cR433KgQ3Glqc3PW508ZAMoiOs4hc/As+wuzl06W1/Cg7jVejkv9Vw== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass (sender ip is 12.22.5.235) smtp.rcpttodomain=dpdk.org smtp.mailfrom=nvidia.com; dmarc=pass (p=reject sp=reject pct=100) action=none header.from=nvidia.com; dkim=none (message not signed); arc=none DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=Nvidia.com; s=selector2; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=EIhSPyIIOf0BshqaQ2CMWvm6LANQIagB+M0XU+ALWS8=; b=A5vxuYpyGWGXpeg5LViNBJWiIfKw4bHPqx7WyTUP0b3WnphZVt0eaoObhb/+t/EirDxckxfi+mqHl++Pq8tJ3k7X3R07eVn75ak6HhTXIZU24alCD+cyqBMf3PsQuPTrRo8INo3Wkx74me8YT1D6bmF34MfEyobmncNS9RKPjTKvFdLd43VZGNtrWdrTMLVEU1DOoAWyitP9VLdCGTnbmt/tE2qk53mk6Ug5lYGnrmFK6IvRNGdEVGl4KvIbRTeSaoMeWOcwAKvhe2fQv/NcXbjRK8cxRQhpueP844z2+jw3CCAuVg6Fx72DtSOTtQPa/fOcemPo0w2k+Rr3d98ukg== Received: from MW4PR03CA0277.namprd03.prod.outlook.com (2603:10b6:303:b5::12) by PH7PR12MB5903.namprd12.prod.outlook.com (2603:10b6:510:1d7::14) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.5504.19; Thu, 11 Aug 2022 05:51:18 +0000 Received: from CO1NAM11FT061.eop-nam11.prod.protection.outlook.com (2603:10b6:303:b5:cafe::ef) by MW4PR03CA0277.outlook.office365.com (2603:10b6:303:b5::12) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.5525.11 via Frontend Transport; Thu, 11 Aug 2022 05:51:17 +0000 X-MS-Exchange-Authentication-Results: spf=pass (sender IP is 12.22.5.235) smtp.mailfrom=nvidia.com; dkim=none (message not signed) header.d=none;dmarc=pass action=none header.from=nvidia.com; Received-SPF: Pass (protection.outlook.com: domain of nvidia.com designates 12.22.5.235 as permitted sender) receiver=protection.outlook.com; client-ip=12.22.5.235; helo=mail.nvidia.com; pr=C Received: from mail.nvidia.com (12.22.5.235) by CO1NAM11FT061.mail.protection.outlook.com (10.13.175.200) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA384) id 15.20.5525.11 via Frontend Transport; Thu, 11 Aug 2022 05:51:17 +0000 Received: from rnnvmail201.nvidia.com (10.129.68.8) by DRHQMAIL107.nvidia.com (10.27.9.16) with Microsoft SMTP Server (TLS) id 15.0.1497.32; Thu, 11 Aug 2022 05:51:14 +0000 Received: from nvidia.com (10.126.230.35) by rnnvmail201.nvidia.com (10.129.68.8) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.986.26; Wed, 10 Aug 2022 22:51:12 -0700 From: Viacheslav Ovsiienko To: CC: , , , Subject: [PATCH] net/mlx5: fix check for orphan wait descriptor Date: Thu, 11 Aug 2022 08:50:58 +0300 Message-ID: <20220811055058.29957-1-viacheslavo@nvidia.com> X-Mailer: git-send-email 2.18.1 MIME-Version: 1.0 X-Originating-IP: [10.126.230.35] X-ClientProxiedBy: rnnvmail201.nvidia.com (10.129.68.8) To rnnvmail201.nvidia.com (10.129.68.8) X-EOPAttributedMessage: 0 X-MS-PublicTrafficType: Email X-MS-Office365-Filtering-Correlation-Id: aec8dfa5-11db-463d-ec4b-08da7b5d8269 X-MS-TrafficTypeDiagnostic: PH7PR12MB5903:EE_ 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:12.22.5.235; CTRY:US; LANG:en; SCL:1; SRV:; IPV:NLI; SFV:NSPM; H:mail.nvidia.com; PTR:InfoNoRecords; CAT:NONE; SFS:(13230016)(4636009)(39860400002)(136003)(396003)(346002)(376002)(36840700001)(40470700004)(46966006)(6666004)(7696005)(26005)(6286002)(41300700001)(82740400003)(1076003)(186003)(83380400001)(40460700003)(336012)(356005)(16526019)(47076005)(426003)(36860700001)(5660300002)(8936002)(81166007)(2616005)(86362001)(70586007)(70206006)(55016003)(4326008)(40480700001)(8676002)(2906002)(36756003)(82310400005)(54906003)(316002)(6916009)(478600001)(36900700001); DIR:OUT; SFP:1101; X-OriginatorOrg: Nvidia.com X-MS-Exchange-CrossTenant-OriginalArrivalTime: 11 Aug 2022 05:51:17.5407 (UTC) X-MS-Exchange-CrossTenant-Network-Message-Id: aec8dfa5-11db-463d-ec4b-08da7b5d8269 X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=43083d15-7273-40c1-b7db-39efd9ccc17a; Ip=[12.22.5.235]; Helo=[mail.nvidia.com] X-MS-Exchange-CrossTenant-AuthSource: CO1NAM11FT061.eop-nam11.prod.protection.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Anonymous X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem X-MS-Exchange-Transport-CrossTenantHeadersStamped: PH7PR12MB5903 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 The mlx5 PMD supports send scheduling feature, it allows to send packets at specified moment of time, to do that PMD pushes special wait descriptor (WQE) to the hardware queue and then pushes descriptor for packet data as usual. If queue is close to be full or there is no enough elts buffers to store mbufs being sent the data descriptors might be not pushed and the orphan wait WQE (not followed by the data) might reside in queue on tx_burst routine exit. To avoid orphan wait WQEs there was the check for enough free space in the queue WQE buffer and enough amount of the free elts in queue mbuf storage. This check was incomplete and did not cover all the cases for Enhanced Multi-Packet Write descriptors. Fixes: 2f827f5ea6e1 ("net/mlx5: support scheduling on send routine template") Cc: stable@dpdk.org Signed-off-by: Viacheslav Ovsiienko --- drivers/net/mlx5/mlx5_tx.h | 74 +++++++++++++++++++++----------------- 1 file changed, 41 insertions(+), 33 deletions(-) diff --git a/drivers/net/mlx5/mlx5_tx.h b/drivers/net/mlx5/mlx5_tx.h index 20776919c2..f081921ffc 100644 --- a/drivers/net/mlx5/mlx5_tx.h +++ b/drivers/net/mlx5/mlx5_tx.h @@ -1642,6 +1642,9 @@ mlx5_tx_mseg_build(struct mlx5_txq_data *__rte_restrict txq, * Pointer to TX queue structure. * @param loc * Pointer to burst routine local context. + * @param elts + * Number of free elements in elts buffer to be checked, for zero + * value the check is optimized out by compiler. * @param olx * Configured Tx offloads mask. It is fully defined at * compile time and may be used for optimization. @@ -1655,6 +1658,7 @@ mlx5_tx_mseg_build(struct mlx5_txq_data *__rte_restrict txq, static __rte_always_inline enum mlx5_txcmp_code mlx5_tx_schedule_send(struct mlx5_txq_data *restrict txq, struct mlx5_txq_local *restrict loc, + uint16_t elts, unsigned int olx) { if (MLX5_TXOFF_CONFIG(TXPP) && @@ -1669,7 +1673,7 @@ mlx5_tx_schedule_send(struct mlx5_txq_data *restrict txq, * to the queue and we won't get the orphan WAIT WQE. */ if (loc->wqe_free <= MLX5_WQE_SIZE_MAX / MLX5_WQE_SIZE || - loc->elts_free < NB_SEGS(loc->mbuf)) + loc->elts_free < elts) return MLX5_TXCMP_CODE_EXIT; /* Convert the timestamp into completion to wait. */ ts = *RTE_MBUF_DYNFIELD(loc->mbuf, txq->ts_offset, uint64_t *); @@ -1735,11 +1739,12 @@ mlx5_tx_packet_multi_tso(struct mlx5_txq_data *__rte_restrict txq, struct mlx5_wqe *__rte_restrict wqe; unsigned int ds, dlen, inlen, ntcp, vlan = 0; + MLX5_ASSERT(loc->elts_free >= NB_SEGS(loc->mbuf)); if (MLX5_TXOFF_CONFIG(TXPP)) { enum mlx5_txcmp_code wret; /* Generate WAIT for scheduling if requested. */ - wret = mlx5_tx_schedule_send(txq, loc, olx); + wret = mlx5_tx_schedule_send(txq, loc, 0, olx); if (wret == MLX5_TXCMP_CODE_EXIT) return MLX5_TXCMP_CODE_EXIT; if (wret == MLX5_TXCMP_CODE_ERROR) @@ -1833,11 +1838,12 @@ mlx5_tx_packet_multi_send(struct mlx5_txq_data *__rte_restrict txq, unsigned int ds, nseg; MLX5_ASSERT(NB_SEGS(loc->mbuf) > 1); + MLX5_ASSERT(loc->elts_free >= NB_SEGS(loc->mbuf)); if (MLX5_TXOFF_CONFIG(TXPP)) { enum mlx5_txcmp_code wret; /* Generate WAIT for scheduling if requested. */ - wret = mlx5_tx_schedule_send(txq, loc, olx); + wret = mlx5_tx_schedule_send(txq, loc, 0, olx); if (wret == MLX5_TXCMP_CODE_EXIT) return MLX5_TXCMP_CODE_EXIT; if (wret == MLX5_TXCMP_CODE_ERROR) @@ -1948,16 +1954,7 @@ mlx5_tx_packet_multi_inline(struct mlx5_txq_data *__rte_restrict txq, MLX5_ASSERT(MLX5_TXOFF_CONFIG(INLINE)); MLX5_ASSERT(NB_SEGS(loc->mbuf) > 1); - if (MLX5_TXOFF_CONFIG(TXPP)) { - enum mlx5_txcmp_code wret; - - /* Generate WAIT for scheduling if requested. */ - wret = mlx5_tx_schedule_send(txq, loc, olx); - if (wret == MLX5_TXCMP_CODE_EXIT) - return MLX5_TXCMP_CODE_EXIT; - if (wret == MLX5_TXCMP_CODE_ERROR) - return MLX5_TXCMP_CODE_ERROR; - } + MLX5_ASSERT(loc->elts_free >= NB_SEGS(loc->mbuf)); /* * First calculate data length to be inlined * to estimate the required space for WQE. @@ -2063,6 +2060,16 @@ mlx5_tx_packet_multi_inline(struct mlx5_txq_data *__rte_restrict txq, * supposing no any mbufs is being freed during inlining. */ do_build: + if (MLX5_TXOFF_CONFIG(TXPP)) { + enum mlx5_txcmp_code wret; + + /* Generate WAIT for scheduling if requested. */ + wret = mlx5_tx_schedule_send(txq, loc, 0, olx); + if (wret == MLX5_TXCMP_CODE_EXIT) + return MLX5_TXCMP_CODE_EXIT; + if (wret == MLX5_TXCMP_CODE_ERROR) + return MLX5_TXCMP_CODE_ERROR; + } MLX5_ASSERT(inlen <= txq->inlen_send); ds = NB_SEGS(loc->mbuf) + 2 + (inlen - MLX5_ESEG_MIN_INLINE_SIZE + @@ -2223,7 +2230,7 @@ mlx5_tx_burst_tso(struct mlx5_txq_data *__rte_restrict txq, enum mlx5_txcmp_code wret; /* Generate WAIT for scheduling if requested. */ - wret = mlx5_tx_schedule_send(txq, loc, olx); + wret = mlx5_tx_schedule_send(txq, loc, 1, olx); if (wret == MLX5_TXCMP_CODE_EXIT) return MLX5_TXCMP_CODE_EXIT; if (wret == MLX5_TXCMP_CODE_ERROR) @@ -2601,16 +2608,6 @@ mlx5_tx_burst_empw_simple(struct mlx5_txq_data *__rte_restrict txq, next_empw: MLX5_ASSERT(NB_SEGS(loc->mbuf) == 1); - if (MLX5_TXOFF_CONFIG(TXPP)) { - enum mlx5_txcmp_code wret; - - /* Generate WAIT for scheduling if requested. */ - wret = mlx5_tx_schedule_send(txq, loc, olx); - if (wret == MLX5_TXCMP_CODE_EXIT) - return MLX5_TXCMP_CODE_EXIT; - if (wret == MLX5_TXCMP_CODE_ERROR) - return MLX5_TXCMP_CODE_ERROR; - } part = RTE_MIN(pkts_n, MLX5_TXOFF_CONFIG(MPW) ? MLX5_MPW_MAX_PACKETS : MLX5_EMPW_MAX_PACKETS); @@ -2621,6 +2618,16 @@ mlx5_tx_burst_empw_simple(struct mlx5_txq_data *__rte_restrict txq, /* But we still able to send at least minimal eMPW. */ part = loc->elts_free; } + if (MLX5_TXOFF_CONFIG(TXPP)) { + enum mlx5_txcmp_code wret; + + /* Generate WAIT for scheduling if requested. */ + wret = mlx5_tx_schedule_send(txq, loc, 0, olx); + if (wret == MLX5_TXCMP_CODE_EXIT) + return MLX5_TXCMP_CODE_EXIT; + if (wret == MLX5_TXCMP_CODE_ERROR) + return MLX5_TXCMP_CODE_ERROR; + } /* Check whether we have enough WQEs */ if (unlikely(loc->wqe_free < ((2 + part + 3) / 4))) { if (unlikely(loc->wqe_free < @@ -2775,23 +2782,23 @@ mlx5_tx_burst_empw_inline(struct mlx5_txq_data *__rte_restrict txq, unsigned int slen = 0; MLX5_ASSERT(NB_SEGS(loc->mbuf) == 1); + /* + * Limits the amount of packets in one WQE + * to improve CQE latency generation. + */ + nlim = RTE_MIN(pkts_n, MLX5_TXOFF_CONFIG(MPW) ? + MLX5_MPW_INLINE_MAX_PACKETS : + MLX5_EMPW_MAX_PACKETS); if (MLX5_TXOFF_CONFIG(TXPP)) { enum mlx5_txcmp_code wret; /* Generate WAIT for scheduling if requested. */ - wret = mlx5_tx_schedule_send(txq, loc, olx); + wret = mlx5_tx_schedule_send(txq, loc, nlim, olx); if (wret == MLX5_TXCMP_CODE_EXIT) return MLX5_TXCMP_CODE_EXIT; if (wret == MLX5_TXCMP_CODE_ERROR) return MLX5_TXCMP_CODE_ERROR; } - /* - * Limits the amount of packets in one WQE - * to improve CQE latency generation. - */ - nlim = RTE_MIN(pkts_n, MLX5_TXOFF_CONFIG(MPW) ? - MLX5_MPW_INLINE_MAX_PACKETS : - MLX5_EMPW_MAX_PACKETS); /* Check whether we have minimal amount WQEs */ if (unlikely(loc->wqe_free < ((2 + MLX5_EMPW_MIN_PACKETS + 3) / 4))) @@ -3074,11 +3081,12 @@ mlx5_tx_burst_single_send(struct mlx5_txq_data *__rte_restrict txq, enum mlx5_txcmp_code ret; MLX5_ASSERT(NB_SEGS(loc->mbuf) == 1); + MLX5_ASSERT(loc->elts_free); if (MLX5_TXOFF_CONFIG(TXPP)) { enum mlx5_txcmp_code wret; /* Generate WAIT for scheduling if requested. */ - wret = mlx5_tx_schedule_send(txq, loc, olx); + wret = mlx5_tx_schedule_send(txq, loc, 0, olx); if (wret == MLX5_TXCMP_CODE_EXIT) return MLX5_TXCMP_CODE_EXIT; if (wret == MLX5_TXCMP_CODE_ERROR)