From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga11.intel.com (mga11.intel.com [192.55.52.93]) by dpdk.org (Postfix) with ESMTP id 18FC62E81 for ; Mon, 6 Jun 2016 07:48:23 +0200 (CEST) Received: from fmsmga002.fm.intel.com ([10.253.24.26]) by fmsmga102.fm.intel.com with ESMTP; 05 Jun 2016 22:48:23 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.26,425,1459839600"; d="scan'208";a="995947430" Received: from shvmail01.sh.intel.com ([10.239.29.42]) by fmsmga002.fm.intel.com with ESMTP; 05 Jun 2016 22:48:22 -0700 Received: from shecgisg004.sh.intel.com (shecgisg004.sh.intel.com [10.239.29.89]) by shvmail01.sh.intel.com with ESMTP id u565mKc0030592; Mon, 6 Jun 2016 13:48:20 +0800 Received: from shecgisg004.sh.intel.com (localhost [127.0.0.1]) by shecgisg004.sh.intel.com (8.13.6/8.13.6/SuSE Linux 0.8) with ESMTP id u565mG6h028693; Mon, 6 Jun 2016 13:48:18 +0800 Received: (from wenzhuol@localhost) by shecgisg004.sh.intel.com (8.13.6/8.13.6/Submit) id u565mG6W028689; Mon, 6 Jun 2016 13:48:16 +0800 From: Wenzhuo Lu To: dev@dpdk.org Cc: Wenzhuo Lu Date: Mon, 6 Jun 2016 13:48:13 +0800 Message-Id: <1465192093-28651-2-git-send-email-wenzhuo.lu@intel.com> X-Mailer: git-send-email 1.7.4.1 In-Reply-To: <1465192093-28651-1-git-send-email-wenzhuo.lu@intel.com> References: <1465192093-28651-1-git-send-email-wenzhuo.lu@intel.com> Subject: [dpdk-dev] [PATCH] examples: add a new example for link reset X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 06 Jun 2016 05:48:25 -0000 Add a new example to show when the PF is down and up, VF port can be reset and recover. Signed-off-by: Wenzhuo Lu --- MAINTAINERS | 4 + doc/guides/sample_app_ug/link_reset.rst | 177 ++++++++ examples/link_reset/Makefile | 50 +++ examples/link_reset/main.c | 769 ++++++++++++++++++++++++++++++++ 4 files changed, 1000 insertions(+) create mode 100644 doc/guides/sample_app_ug/link_reset.rst create mode 100644 examples/link_reset/Makefile create mode 100644 examples/link_reset/main.c diff --git a/MAINTAINERS b/MAINTAINERS index 3e8558f..76879c3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -650,3 +650,7 @@ F: examples/tep_termination/ F: examples/vmdq/ F: examples/vmdq_dcb/ F: doc/guides/sample_app_ug/vmdq_dcb_forwarding.rst + +M: Wenzhuo Lu +F: examples/link_reset/ +F: doc/guides/sample_app_ug/link_reset.rst diff --git a/doc/guides/sample_app_ug/link_reset.rst b/doc/guides/sample_app_ug/link_reset.rst new file mode 100644 index 0000000..fecae6d --- /dev/null +++ b/doc/guides/sample_app_ug/link_reset.rst @@ -0,0 +1,177 @@ +.. BSD LICENSE + Copyright(c) 2010-2016 Intel Corporation. All rights reserved. + All rights reserved. + + Redistribution and use in source and binary forms, with or without + modification, are permitted provided that the following conditions + are met: + + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + * Redistributions in binary form must reproduce the above copyright + notice, this list of conditions and the following disclaimer in + the documentation and/or other materials provided with the + distribution. + * Neither the name of Intel Corporation nor the names of its + contributors may be used to endorse or promote products derived + from this software without specific prior written permission. + + THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +Link Reset Sample Application (in Virtualized Environments) +=========================================================== + +The Link Reset sample application is a simple example of VF traffic recovery +using the Data Plane Development Kit (DPDK) which also takes advantage of Single +Root I/O Virtualization (SR-IOV) features in a virtualized environment. + +Overview +-------- + +The Link Reset sample application, which should operate in virtualized +environments, performs L2 forwarding for each packet that is received on an +RX_PORT. +This example is extended from the L2 forwarding example. Please reference the +example of L2 forwarding in virtualized environments for more details and +explanation about the behavior of forwarding and how to setup the test. +The purpose of this example is to show when the PF port is down and up, the VF +port can recover and the traffic can recover too. + +Virtual Function Setup Instructions +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +This application can use the virtual function available in the system and +therefore can be used in a virtual machine without passing through +the whole Network Device into a guest machine in a virtualized scenario. +The virtual functions can be enabled in the host machine or the hypervisor +with the respective physical function driver. + +For example, in a Linux* host machine, it is possible to enable a virtual +function using the following command: + +.. code-block:: console + + modprobe ixgbe max_vfs=2,2 + +This command enables two Virtual Functions on each of Physical Function of the +NIC, with two physical ports in the PCI configuration space. +It is important to note that enabled Virtual Function 0 and 2 would belong to +Physical Function 0 and Virtual Function 1 and 3 would belong to Physical +Function 1, in this case enabling a total of four Virtual Functions. + +Compiling the Application +------------------------- + +#. Go to the example directory: + + .. code-block:: console + + export RTE_SDK=/path/to/rte_sdk + cd ${RTE_SDK}/examples/link_reset + +#. Set the target (a default target is used if not specified). For example: + + .. code-block:: console + + export RTE_TARGET=x86_64-native-linuxapp-gcc + + *See the DPDK Getting Started Guide* for possible RTE_TARGET values. + +#. Build the application: + + .. code-block:: console + + make + +Running the Application +----------------------- + +The application requires a number of command line options: + +.. code-block:: console + + ./build/link_reset [EAL options] -- -p PORTMASK [-q NQ] + +where, + +* p PORTMASK: A hexadecimal bitmask of the ports to configure + +* q NQ: A number of queues (=ports) per lcore (default is 1) + +To run the application in linuxapp environment with 4 lcores, 16 ports and 8 RX +queues per lcore, issue the command: + +.. code-block:: console + + $ ./build/link_reset -c f -n 4 -- -q 8 -p ffff + +Refer to the *DPDK Getting Started Guide* for general information on running applications +and the Environment Abstraction Layer (EAL) options. + +Explanation +----------- + +Handle VF link reset event +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +In main function, when initialising each port, register a callback for reset +event. + +.. code-block:: c + + /* Initialise each port */ + for (portid = 0; portid < nb_ports; portid++) { + ...... + /* register reset interrupt callback */ + rte_eth_dev_callback_register(portid, + RTE_ETH_EVENT_INTR_RESET, reset_event_callback, NULL); + ...... + } + +The callback function *reset_event_callback* will be executed in the +interruption thread. But we want the event to be handled in the management +thread. So in the callback function only a reset flag *stop_forwarding* is set. + +.. code-block:: c + + static void + reset_event_callback(uint8_t port_id, enum rte_eth_event_type type, void *param) + { + RTE_SET_USED(param); + + printf("\n\nIn registered callback...\n"); + printf("Event type: %s on port %d\n", + type == RTE_ETH_EVENT_INTR_RESET ? "RESET interrupt" : + "unknown event", port_id); + reset_port = port_id; + rte_compiler_barrier(); /* prevent compiler reordering */ + stop_forwarding = 1; + } + +The management thread keeps checking the reset flag *stop_forwarding* to see +if VF port reset is needed. If so, it should call the API *rte_eth_dev_reset* +to reset VF port. After that, the traffic will recover. + +.. code-block:: c + + while (1) { + rte_delay_ms(1000); + printf(".."); + if (stop_forwarding == 1) { + printf("\nreset\n"); + rte_eth_dev_reset(reset_port); + stop_forwarding = 0; + } + if (force_quit) + break; + } diff --git a/examples/link_reset/Makefile b/examples/link_reset/Makefile new file mode 100644 index 0000000..6a63256 --- /dev/null +++ b/examples/link_reset/Makefile @@ -0,0 +1,50 @@ +# BSD LICENSE +# +# Copyright(c) 2010-2016 Intel Corporation. All rights reserved. +# All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions +# are met: +# +# * Redistributions of source code must retain the above copyright +# notice, this list of conditions and the following disclaimer. +# * Redistributions in binary form must reproduce the above copyright +# notice, this list of conditions and the following disclaimer in +# the documentation and/or other materials provided with the +# distribution. +# * Neither the name of Intel Corporation nor the names of its +# contributors may be used to endorse or promote products derived +# from this software without specific prior written permission. +# +# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +# OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +ifeq ($(RTE_SDK),) +$(error "Please define RTE_SDK environment variable") +endif + +# Default target, can be overridden by command line or environment +RTE_TARGET ?= x86_64-native-linuxapp-gcc + +include $(RTE_SDK)/mk/rte.vars.mk + +# binary name +APP = link_reset + +# all source are stored in SRCS-y +SRCS-y := main.c + +CFLAGS += -O3 +CFLAGS += $(WERROR_FLAGS) + +include $(RTE_SDK)/mk/rte.extapp.mk diff --git a/examples/link_reset/main.c b/examples/link_reset/main.c new file mode 100644 index 0000000..f151a83 --- /dev/null +++ b/examples/link_reset/main.c @@ -0,0 +1,769 @@ +/*- + * BSD LICENSE + * + * Copyright(c) 2010-2016 Intel Corporation. All rights reserved. + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static volatile bool force_quit; + +#define RTE_LOGTYPE_L2FWD RTE_LOGTYPE_USER1 + +#define NB_MBUF 8192 + +#define MAX_PKT_BURST 32 +#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ + +/* + * Configurable number of RX/TX ring descriptors + */ +#define RTE_TEST_RX_DESC_DEFAULT 128 +#define RTE_TEST_TX_DESC_DEFAULT 512 +static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT; +static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT; + +/* ethernet addresses of ports */ +static struct ether_addr l2fwd_ports_eth_addr[RTE_MAX_ETHPORTS]; + +/* mask of enabled ports */ +static uint32_t l2fwd_enabled_port_mask; + +/* list of enabled ports */ +static uint32_t l2fwd_dst_ports[RTE_MAX_ETHPORTS]; + +static unsigned int l2fwd_rx_queue_per_lcore = 1; + +#define MAX_RX_QUEUE_PER_LCORE 16 +#define MAX_TX_QUEUE_PER_PORT 16 +struct lcore_queue_conf { + unsigned n_rx_port; + unsigned rx_port_list[MAX_RX_QUEUE_PER_LCORE]; +} __rte_cache_aligned; +struct lcore_queue_conf lcore_queue_conf[RTE_MAX_LCORE]; + +static struct rte_eth_dev_tx_buffer *tx_buffer[RTE_MAX_ETHPORTS]; + +static const struct rte_eth_conf port_conf = { + .rxmode = { + .split_hdr_size = 0, + .header_split = 0, /**< Header Split disabled */ + .hw_ip_checksum = 0, /**< IP checksum offload disabled */ + .hw_vlan_filter = 0, /**< VLAN filtering disabled */ + .jumbo_frame = 0, /**< Jumbo Frame Support disabled */ + .hw_strip_crc = 0, /**< CRC stripped by hardware */ + .lock_mode = 1, /**< Use lock mode in RX */ + }, + .txmode = { + .mq_mode = ETH_MQ_TX_NONE, + .lock_mode = 1, /**< Use lock mode in TX */ + }, +}; + +struct rte_mempool *l2fwd_pktmbuf_pool; + +/* Per-port statistics struct */ +struct l2fwd_port_statistics { + uint64_t tx; + uint64_t rx; + uint64_t dropped; +} __rte_cache_aligned; +struct l2fwd_port_statistics port_statistics[RTE_MAX_ETHPORTS]; + +/* A tsc-based timer responsible for triggering statistics printout */ +#define TIMER_MILLISECOND 2000000ULL /* around 1ms at 2 Ghz */ +#define MAX_TIMER_PERIOD 86400 /* 1 day max */ +/* default period is 10 seconds */ +static int64_t timer_period = 10 * TIMER_MILLISECOND * 1000; + +static uint32_t stop_forwarding; +static uint8_t reset_port; + +/* Print out statistics on packets dropped */ +static void +print_stats(void) +{ + uint64_t total_packets_dropped, total_packets_tx, total_packets_rx; + unsigned portid; + + total_packets_dropped = 0; + total_packets_tx = 0; + total_packets_rx = 0; + + const char clr[] = { 27, '[', '2', 'J', '\0' }; + const char topLeft[] = { 27, '[', '1', ';', '1', 'H', '\0' }; + + /* Clear screen and move to top left */ + printf("%s%s", clr, topLeft); + + printf("\nPort statistics ===================================="); + + for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) { + /* skip disabled ports */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) + continue; + printf("\nStatistics for port %u ------------------------------" + "\nPackets sent: %24"PRIu64 + "\nPackets received: %20"PRIu64 + "\nPackets dropped: %21"PRIu64, + portid, + port_statistics[portid].tx, + port_statistics[portid].rx, + port_statistics[portid].dropped); + + total_packets_dropped += port_statistics[portid].dropped; + total_packets_tx += port_statistics[portid].tx; + total_packets_rx += port_statistics[portid].rx; + } + printf("\nAggregate statistics ===============================" + "\nTotal packets sent: %18"PRIu64 + "\nTotal packets received: %14"PRIu64 + "\nTotal packets dropped: %15"PRIu64, + total_packets_tx, + total_packets_rx, + total_packets_dropped); + printf("\n====================================================\n"); +} + +static void +l2fwd_simple_forward(struct rte_mbuf *m, unsigned portid) +{ + struct ether_hdr *eth; + void *tmp; + unsigned dst_port; + int sent; + struct rte_eth_dev_tx_buffer *buffer; + + dst_port = l2fwd_dst_ports[portid]; + eth = rte_pktmbuf_mtod(m, struct ether_hdr *); + + /* 02:00:00:00:00:xx */ + tmp = ð->d_addr.addr_bytes[0]; + *((uint64_t *)tmp) = 0x000000000002 + ((uint64_t)dst_port << 40); + + /* src addr */ + ether_addr_copy(&l2fwd_ports_eth_addr[dst_port], ð->s_addr); + + buffer = tx_buffer[dst_port]; + sent = rte_eth_tx_buffer(dst_port, 0, buffer, m); + if (sent) + port_statistics[dst_port].tx += sent; +} + +/* main processing loop */ +static void +l2fwd_main_loop(void) +{ + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; + struct rte_mbuf *m; + int sent; + unsigned lcore_id; + uint64_t prev_tsc, diff_tsc, cur_tsc, timer_tsc; + unsigned i, j, portid, nb_rx; + struct lcore_queue_conf *qconf; + const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / + US_PER_S * BURST_TX_DRAIN_US; + struct rte_eth_dev_tx_buffer *buffer; + + prev_tsc = 0; + timer_tsc = 0; + + lcore_id = rte_lcore_id(); + qconf = &lcore_queue_conf[lcore_id]; + + if (qconf->n_rx_port == 0) { + RTE_LOG(INFO, L2FWD, "lcore %u has nothing to do\n", lcore_id); + return; + } + + RTE_LOG(INFO, L2FWD, "entering main loop on lcore %u\n", lcore_id); + + for (i = 0; i < qconf->n_rx_port; i++) { + + portid = qconf->rx_port_list[i]; + RTE_LOG(INFO, L2FWD, " -- lcoreid=%u portid=%u\n", lcore_id, + portid); + + } + + while (!force_quit) { + + cur_tsc = rte_rdtsc(); + + /* + * TX burst queue drain + */ + diff_tsc = cur_tsc - prev_tsc; + if (unlikely(diff_tsc > drain_tsc)) { + + for (i = 0; i < qconf->n_rx_port; i++) { + portid = + l2fwd_dst_ports[qconf->rx_port_list[i]]; + buffer = tx_buffer[portid]; + + sent = rte_eth_tx_buffer_flush(portid, + 0, + buffer); + if (sent) + port_statistics[portid].tx += sent; + } + + /* if timer is enabled */ + if (timer_period > 0) { + + /* advance the timer */ + timer_tsc += diff_tsc; + + /* if timer has reached its timeout */ + if (unlikely(timer_tsc >= + (uint64_t) timer_period)) { + /* do this only on master core */ + if (lcore_id == + rte_get_master_lcore()) { + print_stats(); + /* reset the timer */ + timer_tsc = 0; + } + } + } + + prev_tsc = cur_tsc; + } + + /* + * Read packet from RX queues + */ + for (i = 0; i < qconf->n_rx_port; i++) { + + portid = qconf->rx_port_list[i]; + nb_rx = rte_eth_rx_burst((uint8_t) portid, 0, + pkts_burst, MAX_PKT_BURST); + + port_statistics[portid].rx += nb_rx; + + for (j = 0; j < nb_rx; j++) { + m = pkts_burst[j]; + rte_prefetch0(rte_pktmbuf_mtod(m, void *)); + l2fwd_simple_forward(m, portid); + } + } + } +} + +static int +l2fwd_launch_one_lcore(__attribute__((unused)) void *dummy) +{ + l2fwd_main_loop(); + return 0; +} + +/* display usage */ +static void +l2fwd_usage(const char *prgname) +{ + printf("%s [EAL options] -- -p PORTMASK [-q NQ]\n" + " -p PORTMASK: hexadecimal bitmask of ports to configure\n" + " -q NQ: number of queue (=ports) per lcore (default is 1)\n" + " -T PERIOD: statistics will be refreshed each PERIOD seconds (0 to disable, 10 default, 86400 maximum)\n", + prgname); +} + +static int +l2fwd_parse_portmask(const char *portmask) +{ + char *end = NULL; + unsigned long pm; + + /* parse hexadecimal string */ + pm = strtoul(portmask, &end, 16); + if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (pm == 0) + return -1; + + return pm; +} + +static unsigned int +l2fwd_parse_nqueue(const char *q_arg) +{ + char *end = NULL; + unsigned long n; + + /* parse hexadecimal string */ + n = strtoul(q_arg, &end, 10); + if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0')) + return 0; + if (n == 0) + return 0; + if (n >= MAX_RX_QUEUE_PER_LCORE) + return 0; + + return n; +} + +static int +l2fwd_parse_timer_period(const char *q_arg) +{ + char *end = NULL; + int n; + + /* parse number string */ + n = strtol(q_arg, &end, 10); + if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + if (n >= MAX_TIMER_PERIOD) + return -1; + + return n; +} + +/* Parse the argument given in the command line of the application */ +static int +l2fwd_parse_args(int argc, char **argv) +{ + int opt, ret; + char **argvopt; + int option_index; + char *prgname = argv[0]; + static struct option lgopts[] = { + {NULL, 0, 0, 0} + }; + + argvopt = argv; + + while ((opt = getopt_long(argc, argvopt, "p:q:T:", + lgopts, &option_index)) != EOF) { + + switch (opt) { + /* portmask */ + case 'p': + l2fwd_enabled_port_mask = l2fwd_parse_portmask(optarg); + if (l2fwd_enabled_port_mask == 0) { + printf("invalid portmask\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* nqueue */ + case 'q': + l2fwd_rx_queue_per_lcore = l2fwd_parse_nqueue(optarg); + if (l2fwd_rx_queue_per_lcore == 0) { + printf("invalid queue number\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* timer period */ + case 'T': + timer_period = l2fwd_parse_timer_period(optarg) * + 1000 * TIMER_MILLISECOND; + if (timer_period < 0) { + printf("invalid timer period\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* long options */ + case 0: + l2fwd_usage(prgname); + return -1; + + default: + l2fwd_usage(prgname); + return -1; + } + } + + if (optind >= 0) + argv[optind-1] = prgname; + + ret = optind-1; + optind = 0; /* reset getopt lib */ + return ret; +} + +/* Check the link status of all ports in up to 9s, and print them finally */ +static void +check_all_ports_link_status(uint8_t port_num, uint32_t port_mask) +{ +#define CHECK_INTERVAL 100 /* 100ms */ +#define MAX_CHECK_TIME 90 /* 9s (90 * 100ms) in total */ + uint8_t portid, count, all_ports_up, print_flag = 0; + struct rte_eth_link link; + + printf("\nChecking link status"); + fflush(stdout); + for (count = 0; count <= MAX_CHECK_TIME; count++) { + if (force_quit) + return; + all_ports_up = 1; + for (portid = 0; portid < port_num; portid++) { + if (force_quit) + return; + if ((port_mask & (1 << portid)) == 0) + continue; + memset(&link, 0, sizeof(link)); + rte_eth_link_get_nowait(portid, &link); + /* print link status if flag set */ + if (print_flag == 1) { + if (link.link_status) + printf("Port %d Link Up - speed %u " + "Mbps - %s\n", (uint8_t)portid, + (unsigned)link.link_speed, + (link.link_duplex == ETH_LINK_FULL_DUPLEX) ? + ("full-duplex") : ("half-duplex\n")); + else + printf("Port %d Link Down\n", + (uint8_t)portid); + continue; + } + /* clear all_ports_up flag if any link down */ + if (link.link_status == ETH_LINK_DOWN) { + all_ports_up = 0; + break; + } + } + /* after finally printing all link status, get out */ + if (print_flag == 1) + break; + + if (all_ports_up == 0) { + printf("."); + fflush(stdout); + rte_delay_ms(CHECK_INTERVAL); + } + + /* set the print_flag if all ports up or timeout */ + if (all_ports_up == 1 || count == (MAX_CHECK_TIME - 1)) { + print_flag = 1; + printf("done\n"); + } + } +} + +static void +signal_handler(int signum) +{ + if (signum == SIGINT || signum == SIGTERM) { + printf("\n\nSignal %d received, preparing to exit...\n", + signum); + force_quit = true; + } +} + +static void +reset_event_callback(uint8_t port_id, enum rte_eth_event_type type, void *param) +{ + RTE_SET_USED(param); + + printf("\n\nIn registered callback...\n"); + printf("Event type: %s on port %d\n", + type == RTE_ETH_EVENT_INTR_RESET ? "RESET interrupt" : + "unknown event", port_id); + reset_port = port_id; + rte_compiler_barrier(); /* prevent compiler reordering */ + stop_forwarding = 1; +} + +int +main(int argc, char **argv) +{ + struct lcore_queue_conf *qconf; + struct rte_eth_dev_info dev_info; + int ret; + uint8_t nb_ports; + uint8_t nb_ports_available; + uint8_t portid, last_port; + unsigned lcore_id, rx_lcore_id; + unsigned nb_ports_in_mask = 0; + + /* init EAL */ + ret = rte_eal_init(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid EAL arguments\n"); + argc -= ret; + argv += ret; + + force_quit = false; + signal(SIGINT, signal_handler); + signal(SIGTERM, signal_handler); + + /* parse application arguments (after the EAL ones) */ + ret = l2fwd_parse_args(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid L2FWD arguments\n"); + + /* create the mbuf pool */ + l2fwd_pktmbuf_pool = rte_pktmbuf_pool_create("mbuf_pool", NB_MBUF, 32, + 0, RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id()); + if (l2fwd_pktmbuf_pool == NULL) + rte_exit(EXIT_FAILURE, "Cannot init mbuf pool\n"); + + nb_ports = rte_eth_dev_count(); + if (nb_ports == 0) + rte_exit(EXIT_FAILURE, "No Ethernet ports - bye\n"); + + if (nb_ports > RTE_MAX_ETHPORTS) + nb_ports = RTE_MAX_ETHPORTS; + + /* reset l2fwd_dst_ports */ + for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) + l2fwd_dst_ports[portid] = 0; + last_port = 0; + + /* + * Each logical core is assigned a dedicated TX queue on each port. + */ + for (portid = 0; portid < nb_ports; portid++) { + /* skip ports that are not enabled */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) + continue; + + if (nb_ports_in_mask % 2) { + l2fwd_dst_ports[portid] = last_port; + l2fwd_dst_ports[last_port] = portid; + } else + last_port = portid; + + nb_ports_in_mask++; + + rte_eth_dev_info_get(portid, &dev_info); + } + if (nb_ports_in_mask % 2) { + printf("Notice: odd number of ports in portmask.\n"); + l2fwd_dst_ports[last_port] = last_port; + } + + rx_lcore_id = 1; + qconf = NULL; + + /* Initialize the port/queue configuration of each logical core */ + for (portid = 0; portid < nb_ports; portid++) { + /* skip ports that are not enabled */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) + continue; + + /* get the lcore_id for this port */ + while (rte_lcore_is_enabled(rx_lcore_id) == 0 || + lcore_queue_conf[rx_lcore_id].n_rx_port == + l2fwd_rx_queue_per_lcore) { + rx_lcore_id++; + if (rx_lcore_id >= RTE_MAX_LCORE) + rte_exit(EXIT_FAILURE, "Not enough cores\n"); + } + + if (qconf != &lcore_queue_conf[rx_lcore_id]) + /* Assigned a new logical core in the loop above. */ + qconf = &lcore_queue_conf[rx_lcore_id]; + + qconf->rx_port_list[qconf->n_rx_port] = portid; + qconf->n_rx_port++; + printf("Lcore %u: RX port %u\n", + rx_lcore_id, + (unsigned) portid); + } + + nb_ports_available = nb_ports; + + /* Initialise each port */ + for (portid = 0; portid < nb_ports; portid++) { + /* skip ports that are not enabled */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) { + printf("Skipping disabled port %u\n", + (unsigned) portid); + nb_ports_available--; + continue; + } + /* init port */ + printf("Initializing port %u... ", (unsigned) portid); + fflush(stdout); + ret = rte_eth_dev_configure(portid, 1, 1, &port_conf); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "Cannot configure device: err=%d, port=%u\n", + ret, (unsigned) portid); + + /* register reset interrupt callback */ + rte_eth_dev_callback_register(portid, + RTE_ETH_EVENT_INTR_RESET, reset_event_callback, NULL); + + rte_eth_macaddr_get(portid, &l2fwd_ports_eth_addr[portid]); + + /* init one RX queue */ + fflush(stdout); + ret = rte_eth_rx_queue_setup(portid, 0, nb_rxd, + rte_eth_dev_socket_id(portid), + NULL, + l2fwd_pktmbuf_pool); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_rx_queue_setup:err=%d, port=%u\n", + ret, (unsigned) portid); + + /* init one TX queue on each port */ + fflush(stdout); + ret = rte_eth_tx_queue_setup(portid, 0, nb_txd, + rte_eth_dev_socket_id(portid), + NULL); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_tx_queue_setup:err=%d, port=%u\n", + ret, (unsigned) portid); + + /* Initialize TX buffers */ + tx_buffer[portid] = rte_zmalloc_socket("tx_buffer", + RTE_ETH_TX_BUFFER_SIZE(MAX_PKT_BURST), 0, + rte_eth_dev_socket_id(portid)); + if (tx_buffer[portid] == NULL) + rte_exit(EXIT_FAILURE, + "Cannot allocate buffer for tx on port %u\n", + (unsigned) portid); + + rte_eth_tx_buffer_init(tx_buffer[portid], MAX_PKT_BURST); + + ret = rte_eth_tx_buffer_set_err_callback(tx_buffer[portid], + rte_eth_tx_buffer_count_callback, + &port_statistics[portid].dropped); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Cannot set error callback for " + "tx buffer on port %u\n", (unsigned) portid); + + /* Start device */ + ret = rte_eth_dev_start(portid); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_dev_start:err=%d, port=%u\n", + ret, (unsigned) portid); + + printf("done:\n"); + + rte_eth_promiscuous_enable(portid); + + printf("Port %u, MAC address: " + "%02X:%02X:%02X:%02X:%02X:%02X\n\n", + (unsigned) portid, + l2fwd_ports_eth_addr[portid].addr_bytes[0], + l2fwd_ports_eth_addr[portid].addr_bytes[1], + l2fwd_ports_eth_addr[portid].addr_bytes[2], + l2fwd_ports_eth_addr[portid].addr_bytes[3], + l2fwd_ports_eth_addr[portid].addr_bytes[4], + l2fwd_ports_eth_addr[portid].addr_bytes[5]); + + /* initialize port stats */ + memset(&port_statistics, 0, sizeof(port_statistics)); + } + + if (!nb_ports_available) { + rte_exit(EXIT_FAILURE, + "All available ports are disabled. Please set portmask.\n"); + } + + check_all_ports_link_status(nb_ports, l2fwd_enabled_port_mask); + + ret = 0; + /* launch per-lcore init on every lcore */ + rte_eal_mp_remote_launch(l2fwd_launch_one_lcore, NULL, SKIP_MASTER); + + printf("\nwaiting.."); + while (1) { + rte_delay_ms(1000); + printf(".."); + if (stop_forwarding == 1) { + printf("\nreset\n"); + rte_eth_dev_reset(reset_port); + stop_forwarding = 0; + } + if (force_quit) + break; + } + + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + if (rte_eal_wait_lcore(lcore_id) < 0) { + ret = -1; + break; + } + } + + for (portid = 0; portid < nb_ports; portid++) { + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) + continue; + printf("Closing port %d...", portid); + rte_eth_dev_stop(portid); + rte_eth_dev_close(portid); + printf(" Done\n"); + } + printf("Bye...\n"); + + return ret; +} -- 1.9.3