From patchwork Fri Oct 26 06:33:27 2018 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Xing, Beilei" X-Patchwork-Id: 47459 X-Patchwork-Delegate: qi.z.zhang@intel.com Return-Path: X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [127.0.0.1]) by dpdk.org (Postfix) with ESMTP id 1B2965F0F; Fri, 26 Oct 2018 08:32:17 +0200 (CEST) Received: from mga01.intel.com (mga01.intel.com [192.55.52.88]) by dpdk.org (Postfix) with ESMTP id 90A6658F6; Fri, 26 Oct 2018 08:32:14 +0200 (CEST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by fmsmga101.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 25 Oct 2018 23:32:13 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.54,426,1534834800"; d="scan'208";a="91375282" Received: from unknown (HELO dpdk9.sh.intel.com) ([10.67.118.52]) by FMSMGA003.fm.intel.com with ESMTP; 25 Oct 2018 23:32:13 -0700 From: Beilei Xing To: qi.z.zhang@intel.com Cc: dev@dpdk.org, stable@dpdk.org Date: Fri, 26 Oct 2018 14:33:27 +0800 Message-Id: <1540535607-115720-1-git-send-email-beilei.xing@intel.com> X-Mailer: git-send-email 2.5.5 In-Reply-To: <1540453252-128654-1-git-send-email-beilei.xing@intel.com> References: <1540453252-128654-1-git-send-email-beilei.xing@intel.com> Subject: [dpdk-dev] [PATCH v2] net/i40e: fix Rx instability with vector mode X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Previously, there is instability during vector Rx if descriptor number is not power of 2, e.g. process hang and some Rx packets are unexpectedly empty. That's because vector Rx mode assumes Rx descriptor number is power of 2 when doing bit mask. This patch allows vector mode only when the number of Rx descriptor is power of 2. Fixes: 8e109464c022 ("i40e: allow vector Rx and Tx usage") Fixes: a3c83a2527e1 ("net/i40e: enable runtime queue setup") Cc: stable@dpdk.org Signed-off-by: Beilei Xing --- v2 changes: - rx_vec_allowed is global configuration, avoid overwrite. doc/guides/nics/i40e.rst | 7 +++++++ drivers/net/i40e/i40e_rxtx.c | 13 ++++++++++++- 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/doc/guides/nics/i40e.rst b/doc/guides/nics/i40e.rst index ab3928a..bfacbd1 100644 --- a/doc/guides/nics/i40e.rst +++ b/doc/guides/nics/i40e.rst @@ -172,6 +172,13 @@ Runtime Config Options -w 84:00.0,use-latest-supported-vec=1 +Vector RX Pre-conditions +~~~~~~~~~~~~~~~~~~~~~~~~ +For Vector RX it is assumed that the number of descriptor rings will be a power +of 2. With this pre-condition, the ring pointer can easily scroll back to the +head after hitting the tail without a conditional check. In addition Vector RX +can use this assumption to do a bit mask using ``ring_size - 1``. + Driver compilation and testing ------------------------------ diff --git a/drivers/net/i40e/i40e_rxtx.c b/drivers/net/i40e/i40e_rxtx.c index a827456..f6dcca0 100644 --- a/drivers/net/i40e/i40e_rxtx.c +++ b/drivers/net/i40e/i40e_rxtx.c @@ -1735,10 +1735,14 @@ i40e_dev_rx_queue_setup_runtime(struct rte_eth_dev *dev, * i40e_set_rx_function. */ ad->rx_bulk_alloc_allowed = true; - ad->rx_vec_allowed = true; dev->data->scattered_rx = use_scattered_rx; if (use_def_burst_func) ad->rx_bulk_alloc_allowed = false; + /** + * Vector mode is allowed only when number of Rx queue + * descriptor is a power of 2. + */ + ad->rx_vec_allowed = !(rxq->nb_rx_desc & (rxq->nb_rx_desc - 1)); i40e_set_rx_function(dev); return 0; } @@ -1811,6 +1815,13 @@ i40e_dev_rx_queue_setup(struct rte_eth_dev *dev, return -EINVAL; } + /** + * Vector mode is allowed only when number of Rx queue + * descriptor is a power of 2. + */ + if (ad->rx_vec_allowed) + ad->rx_vec_allowed = !(nb_desc & (nb_desc - 1)); + /* Free memory if needed */ if (dev->data->rx_queues[queue_idx]) { i40e_dev_rx_queue_release(dev->data->rx_queues[queue_idx]);