From patchwork Wed Jul 17 08:08:46 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: "A.McLoughlin" X-Patchwork-Id: 56582 X-Patchwork-Delegate: ferruh.yigit@amd.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 2B7E0276C; Wed, 17 Jul 2019 10:08:55 +0200 (CEST) Received: from mga03.intel.com (mga03.intel.com [134.134.136.65]) by dpdk.org (Postfix) with ESMTP id BEFF0152A for ; Wed, 17 Jul 2019 10:08:53 +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 orsmga103.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 17 Jul 2019 01:08:51 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.64,273,1559545200"; d="scan'208";a="175644295" Received: from silpixa00389822.ir.intel.com (HELO silpixa00389822.ger.corp.intel.com) ([10.237.223.42]) by FMSMGA003.fm.intel.com with ESMTP; 17 Jul 2019 01:08:49 -0700 From: "A.McLoughlin" To: Ferruh Yigit , Bruce Richardson , John McNamara , Marko Kovacevic Cc: dev@dpdk.org, cian.ferriter@intel.com, "A.McLoughlin" Date: Wed, 17 Jul 2019 09:08:46 +0100 Message-Id: <20190717080846.19871-1-aideen.mcloughlin@intel.com> X-Mailer: git-send-email 2.17.1 In-Reply-To: <20190716154331.15651-1-aideen.mcloughlin@intel.com> References: <20190716154331.15651-1-aideen.mcloughlin@intel.com> MIME-Version: 1.0 Subject: [dpdk-dev] [PATCH v3] net/pcap: create null Rx function 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 in the PCAP PMD it was only possibe to specify an rxq which uses an iface or a pcap file. This patch creates a 'dummy Rx' function which is used when no rx_pcap or rx_iface is passed but a tx queue is passed. This function can be polled and receives no packets. Signed-off-by: A.McLoughlin Acked-by: Ferruh Yigit --- v1 -> v2: * This patch supports single_iface once http://patches.dpdk.org/patch/56509/ is applied * Updated documentation to document patch behavior * Syntax fix on lines 148 to 149 * Fixed unpermitted driver aborting on line 152 v2 -> v3: * Update release notes to reflect functionality --- doc/guides/nics/pcap_ring.rst | 8 ++++ doc/guides/rel_notes/release_19_08.rst | 6 +++ drivers/net/pcap/rte_eth_pcap.c | 65 +++++++++++++++++++------- 3 files changed, 63 insertions(+), 16 deletions(-) diff --git a/doc/guides/nics/pcap_ring.rst b/doc/guides/nics/pcap_ring.rst index fb88fa64e..cf230ae40 100644 --- a/doc/guides/nics/pcap_ring.rst +++ b/doc/guides/nics/pcap_ring.rst @@ -126,6 +126,14 @@ Runtime Config Options In this case, one tx drop queue is created for each rxq on that device. + - Receive no packets on Rx + + The user may want to run without receiving any packets on Rx. This can be done by not providing a rx_pcap or rx_iface, for example:: + + --vdev 'net_pcap0,tx_pcap=file_tx.pcap' + +In this case, one dummy rx queue is created for each tx queue argument passed + Examples of Usage ^^^^^^^^^^^^^^^^^ diff --git a/doc/guides/rel_notes/release_19_08.rst b/doc/guides/rel_notes/release_19_08.rst index 4a1fd8dd8..7fd73e4ab 100644 --- a/doc/guides/rel_notes/release_19_08.rst +++ b/doc/guides/rel_notes/release_19_08.rst @@ -141,6 +141,12 @@ New Features device to be received repeatedly at a high rate. This can be useful for quick performance testing of DPDK apps. +* **Enabled Receiving no packets on Rx.** + + Added function to allow users to run without receiving any packets on Rx. + When function is called, a dummy queue is created for each Tx queue argument + passed. + * **Added a FPGA_LTE_FEC bbdev PMD.** Added the new ``fpga_lte_fec`` bbdev driver for the Intel® FPGA PAC diff --git a/drivers/net/pcap/rte_eth_pcap.c b/drivers/net/pcap/rte_eth_pcap.c index 26e85183e..c66e8cd8a 100644 --- a/drivers/net/pcap/rte_eth_pcap.c +++ b/drivers/net/pcap/rte_eth_pcap.c @@ -112,6 +112,8 @@ struct pmd_devargs_all { int single_iface; unsigned int is_tx_pcap; unsigned int is_tx_iface; + unsigned int is_rx_pcap; + unsigned int is_rx_iface; unsigned int infinite_rx; }; @@ -295,6 +297,14 @@ eth_pcap_rx(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts) return num_rx; } +static uint16_t +eth_null_rx(void *queue __rte_unused, + struct rte_mbuf **bufs __rte_unused, + uint16_t nb_pkts __rte_unused) +{ + return 0; +} + static inline void calculate_timestamp(struct timeval *ts) { uint64_t cycles; @@ -1316,8 +1326,11 @@ eth_from_pcaps(struct rte_vdev_device *vdev, /* Assign rx ops. */ if (infinite_rx) eth_dev->rx_pkt_burst = eth_pcap_rx_infinite; - else + else if (devargs_all->is_rx_pcap || devargs_all->is_rx_iface || + single_iface) eth_dev->rx_pkt_burst = eth_pcap_rx; + else + eth_dev->rx_pkt_burst = eth_null_rx; /* Assign tx ops. */ if (devargs_all->is_tx_pcap) @@ -1335,13 +1348,12 @@ static int pmd_pcap_probe(struct rte_vdev_device *dev) { const char *name; - unsigned int is_rx_pcap = 0; struct rte_kvargs *kvlist; struct pmd_devargs pcaps = {0}; struct pmd_devargs dumpers = {0}; struct rte_eth_dev *eth_dev = NULL; struct pmd_internals *internal; - int ret; + int ret = 0; struct pmd_devargs_all devargs_all = { .single_iface = 0, @@ -1404,13 +1416,22 @@ pmd_pcap_probe(struct rte_vdev_device *dev) } /* - * We check whether we want to open a RX stream from a real NIC or a - * pcap file + * We check whether we want to open a RX stream from a real NIC, a + * pcap file or open a dummy RX stream */ - is_rx_pcap = rte_kvargs_count(kvlist, ETH_PCAP_RX_PCAP_ARG) ? 1 : 0; + devargs_all.is_rx_pcap = + rte_kvargs_count(kvlist, ETH_PCAP_RX_PCAP_ARG) ? 1 : 0; + devargs_all.is_rx_iface = + rte_kvargs_count(kvlist, ETH_PCAP_RX_IFACE_ARG) ? 1 : 0; pcaps.num_of_queue = 0; - if (is_rx_pcap) { + devargs_all.is_tx_pcap = + rte_kvargs_count(kvlist, ETH_PCAP_TX_PCAP_ARG) ? 1 : 0; + devargs_all.is_tx_iface = + rte_kvargs_count(kvlist, ETH_PCAP_TX_IFACE_ARG) ? 1 : 0; + dumpers.num_of_queue = 0; + + if (devargs_all.is_rx_pcap) { /* * We check whether we want to infinitely rx the pcap file. */ @@ -1436,11 +1457,29 @@ pmd_pcap_probe(struct rte_vdev_device *dev) ret = rte_kvargs_process(kvlist, ETH_PCAP_RX_PCAP_ARG, &open_rx_pcap, &pcaps); - } else { + } else if (devargs_all.is_rx_iface) { ret = rte_kvargs_process(kvlist, NULL, &rx_iface_args_process, &pcaps); - } + } else if (devargs_all.is_tx_iface || devargs_all.is_tx_pcap) { + unsigned int i; + + /* Count number of tx queue args passed before dummy rx queue + * creation so a dummy rx queue can be created for each tx queue + */ + unsigned int num_tx_queues = + (rte_kvargs_count(kvlist, ETH_PCAP_TX_PCAP_ARG) + + rte_kvargs_count(kvlist, ETH_PCAP_TX_IFACE_ARG)); + PMD_LOG(INFO, "Creating null rx queue since no rx queues were provided."); + + /* Creating a dummy rx queue for each tx queue passed */ + for (i = 0; i < num_tx_queues; i++) + ret = add_queue(&pcaps, "dummy_rx", "rx_null", NULL, + NULL); + } else { + PMD_LOG(ERR, "Error - No rx or tx queues provided"); + ret = -ENOENT; + } if (ret < 0) goto free_kvlist; @@ -1448,12 +1487,6 @@ pmd_pcap_probe(struct rte_vdev_device *dev) * We check whether we want to open a TX stream to a real NIC, * a pcap file, or drop packets on tx */ - devargs_all.is_tx_pcap = - rte_kvargs_count(kvlist, ETH_PCAP_TX_PCAP_ARG) ? 1 : 0; - devargs_all.is_tx_iface = - rte_kvargs_count(kvlist, ETH_PCAP_TX_IFACE_ARG) ? 1 : 0; - dumpers.num_of_queue = 0; - if (devargs_all.is_tx_pcap) { ret = rte_kvargs_process(kvlist, ETH_PCAP_TX_PCAP_ARG, &open_tx_pcap, &dumpers); @@ -1467,7 +1500,7 @@ pmd_pcap_probe(struct rte_vdev_device *dev) /* Add 1 dummy queue per rxq which counts and drops packets. */ for (i = 0; i < pcaps.num_of_queue; i++) - ret = add_queue(&dumpers, "dummy", "tx_drop", NULL, + ret = add_queue(&dumpers, "dummy_tx", "tx_drop", NULL, NULL); }