diff options
Diffstat (limited to 'examples/l2fwd-vf/main.c')
| -rw-r--r-- | examples/l2fwd-vf/main.c | 708 |
1 files changed, 708 insertions, 0 deletions
diff --git a/examples/l2fwd-vf/main.c b/examples/l2fwd-vf/main.c new file mode 100644 index 0000000..836e85a --- /dev/null +++ b/examples/l2fwd-vf/main.c @@ -0,0 +1,708 @@ +/*- + * BSD LICENSE + * + * Copyright(c) 2010-2012 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. + * + * version: DPDK.L.1.2.3-3 + */ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stdint.h> +#include <inttypes.h> +#include <sys/types.h> +#include <string.h> +#include <sys/queue.h> +#include <netinet/in.h> +#include <setjmp.h> +#include <stdarg.h> +#include <ctype.h> +#include <errno.h> +#include <getopt.h> + +#include <rte_common.h> +#include <rte_log.h> +#include <rte_memory.h> +#include <rte_memcpy.h> +#include <rte_memzone.h> +#include <rte_tailq.h> +#include <rte_eal.h> +#include <rte_per_lcore.h> +#include <rte_launch.h> +#include <rte_atomic.h> +#include <rte_cycles.h> +#include <rte_prefetch.h> +#include <rte_lcore.h> +#include <rte_per_lcore.h> +#include <rte_branch_prediction.h> +#include <rte_interrupts.h> +#include <rte_pci.h> +#include <rte_random.h> +#include <rte_debug.h> +#include <rte_ether.h> +#include <rte_ethdev.h> +#include <rte_ring.h> +#include <rte_mempool.h> +#include <rte_mbuf.h> + +#include "main.h" + +#define RTE_LOGTYPE_L2FWD RTE_LOGTYPE_USER1 + +#define L2FWD_MAX_PORTS 32 + +#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM) +#define NB_MBUF 8192 + +/* + * RX and TX Prefetch, Host, and Write-back threshold values should be + * carefully set for optimal performance. Consult the network + * controller's datasheet and supporting DPDK documentation for guidance + * on how these parameters should be set. + */ +#define RX_PTHRESH 8 /**< Default values of RX prefetch threshold reg. */ +#define RX_HTHRESH 8 /**< Default values of RX host threshold reg. */ +#define RX_WTHRESH 4 /**< Default values of RX write-back threshold reg. */ + +/* + * These default values are optimized for use with the Intel(R) 82599 10 GbE + * Controller and the DPDK ixgbe PMD. Consider using other values for other + * network controllers and/or network drivers. + */ +#define TX_PTHRESH 36 /**< Default values of TX prefetch threshold reg. */ +#define TX_HTHRESH 0 /**< Default values of TX host threshold reg. */ +#define TX_WTHRESH 0 /**< Default values of TX write-back threshold reg. */ + +#define MAX_PKT_BURST 32 +#define BURST_TX_DRAIN 200000ULL /* around 100us at 2 Ghz */ + +#define SOCKET0 0 + +/* + * 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[L2FWD_MAX_PORTS]; + +/* mask of enabled ports */ +static uint32_t l2fwd_enabled_port_mask = 0; + +/* list of enabled ports */ +static uint32_t l2fwd_dst_ports[L2FWD_MAX_PORTS]; + +static unsigned int l2fwd_rx_queue_per_lcore = 1; + +#define MAX_PKT_BURST 32 +struct mbuf_table { + unsigned len; + struct rte_mbuf *m_table[MAX_PKT_BURST]; +}; + +#define MAX_RX_QUEUE_PER_LCORE 16 + +/* Each VF(port) has one Rx/Tx queue (with queueid: 0) */ +struct lcore_queue_conf { + + unsigned n_rx_queue; + unsigned rx_queue_list[MAX_RX_QUEUE_PER_LCORE]; + unsigned tx_queue_id; + struct mbuf_table tx_mbufs[L2FWD_MAX_PORTS]; + +} __rte_cache_aligned; +struct lcore_queue_conf lcore_queue_conf[RTE_MAX_LCORE]; + +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 = 1, /**< CRC stripped by hardware */ + }, + .txmode = { + }, +}; + +static const struct rte_eth_rxconf rx_conf = { + .rx_thresh = { + .pthresh = RX_PTHRESH, + .hthresh = RX_HTHRESH, + .wthresh = RX_WTHRESH, + }, +}; + +static const struct rte_eth_txconf tx_conf = { + .tx_thresh = { + .pthresh = TX_PTHRESH, + .hthresh = TX_HTHRESH, + .wthresh = TX_WTHRESH, + }, + .tx_free_thresh = 0, /* Use PMD default values */ + .tx_rs_thresh = 0, /* Use PMD default values */ +}; + +struct rte_mempool * l2fwd_pktmbuf_pool = NULL; + +/* 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[L2FWD_MAX_PORTS]; + +/* 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 */ +static int64_t timer_period = 10 * TIMER_MILLISECOND * 1000; /* default period is 10 seconds */ + +/* 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 < L2FWD_MAX_PORTS; portid++) { + /* skip ports that are not enabled */ + 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"); +} + +/* Send the packet on an output interface */ +static int +l2fwd_send_burst(struct lcore_queue_conf *qconf, unsigned n, uint8_t port) +{ + struct rte_mbuf **m_table; + unsigned ret; + unsigned queueid; + + queueid = (uint16_t) qconf->tx_queue_id; + m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table; + + ret = rte_eth_tx_burst(port, (uint16_t) queueid, m_table, (uint16_t) n); + + port_statistics[port].tx += ret; + if (unlikely(ret < n)) { + port_statistics[port].dropped += (n - ret); + do { + rte_pktmbuf_free(m_table[ret]); + } while (++ret < n); + } + + return 0; +} + +/* Send the packet on an output interface */ +static int +l2fwd_send_packet(struct rte_mbuf *m, uint8_t port) +{ + unsigned lcore_id, len; + struct lcore_queue_conf *qconf; + + lcore_id = rte_lcore_id(); + + qconf = &lcore_queue_conf[lcore_id]; + len = qconf->tx_mbufs[port].len; + qconf->tx_mbufs[port].m_table[len] = m; + len++; + + /* enough pkts to be sent */ + if (unlikely(len == MAX_PKT_BURST)) { + l2fwd_send_burst(qconf, MAX_PKT_BURST, port); + len = 0; + } + + qconf->tx_mbufs[port].len = len; + return 0; +} + +static void +l2fwd_simple_forward(struct rte_mbuf *m, unsigned portid) +{ + struct ether_hdr *eth; + void *tmp; + unsigned dst_port; + + dst_port = l2fwd_dst_ports[portid]; + eth = rte_pktmbuf_mtod(m, struct ether_hdr *); + + /* 00:09:c0:00:00:xx */ + tmp = ð->d_addr.addr_bytes[0]; + *((uint64_t *)tmp) = 0x000000c00900 + (dst_port << 24); + + /* src addr */ + ether_addr_copy(&l2fwd_ports_eth_addr[dst_port], ð->s_addr); + + l2fwd_send_packet(m, (uint8_t) dst_port); +} + +/* main processing loop */ +static void +l2fwd_main_loop(void) +{ + struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; + struct rte_mbuf *m; + unsigned lcore_id; + unsigned int nb_ports; + uint64_t prev_tsc = 0; + uint64_t diff_tsc, cur_tsc, timer_tsc; + unsigned i, j, portid, nb_rx; + struct lcore_queue_conf *qconf; + + timer_tsc = 0; + + lcore_id = rte_lcore_id(); + qconf = &lcore_queue_conf[lcore_id]; + + nb_ports = rte_eth_dev_count(); + if (nb_ports > L2FWD_MAX_PORTS) + nb_ports = L2FWD_MAX_PORTS; + + if (qconf->n_rx_queue == 0) { + RTE_LOG(INFO, L2FWD, "lcore %u has nothing to do\n", lcore_id); + while(1); + } + + RTE_LOG(INFO, L2FWD, "entering main loop on lcore %u\n", lcore_id); + + for (i = 0; i < qconf->n_rx_queue; i++) { + + portid = qconf->rx_queue_list[i]; + RTE_LOG(INFO, L2FWD, " -- lcoreid=%u portid=%u\n", lcore_id, + portid); + } + + while (1) { + + cur_tsc = rte_rdtsc(); + + /* + * TX burst queue drain + */ + diff_tsc = cur_tsc - prev_tsc; + if (unlikely(diff_tsc > BURST_TX_DRAIN)) { + + for (portid = 0; portid < nb_ports; portid++) { + if (qconf->tx_mbufs[portid].len == 0) + continue; + l2fwd_send_burst(&lcore_queue_conf[lcore_id], + qconf->tx_mbufs[portid].len, + (uint8_t) portid); + qconf->tx_mbufs[portid].len = 0; + } + + /* 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_queue; i++) { + + portid = qconf->rx_queue_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; +} + +int +MAIN(int argc, char **argv) +{ + struct lcore_queue_conf *qconf; + int ret; + unsigned int nb_ports; + unsigned portid; + unsigned lcore_id, rx_lcore_id; + unsigned last_port; + unsigned nb_ports_in_mask = 0; + + /* init EAL */ + ret = rte_eal_init(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid EAL parameters\n"); + argc -= ret; + argv += ret; + + /* parse application arguments (after the EAL ones) */ + ret = l2fwd_parse_args(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid L2FWD-VF parameters\n"); + + /* create the mbuf pool */ + l2fwd_pktmbuf_pool = + rte_mempool_create("mbuf_pool", NB_MBUF, + MBUF_SIZE, 32, + sizeof(struct rte_pktmbuf_pool_private), + rte_pktmbuf_pool_init, NULL, + rte_pktmbuf_init, NULL, + SOCKET0, 0); + if (l2fwd_pktmbuf_pool == NULL) + rte_exit(EXIT_FAILURE, "Cannot init mbuf pool\n"); + + /* init driver(s) */ +#ifdef RTE_LIBRTE_IGB_PMD + if (rte_igb_pmd_init() < 0) + rte_exit(EXIT_FAILURE, "Cannot init igb pmd\n"); +#endif +#ifdef RTE_LIBRTE_IXGBE_PMD + if (rte_ixgbe_pmd_init() < 0) + rte_exit(EXIT_FAILURE, "Cannot init ixgbe pmd\n"); + + if (rte_ixgbevf_pmd_init() < 0) + rte_exit(EXIT_FAILURE, "Cannot init ixgbevf pmd\n"); +#endif + + if (rte_eal_pci_probe() < 0) + rte_exit(EXIT_FAILURE, "Cannot probe PCI\n"); + + nb_ports = rte_eth_dev_count(); + if (nb_ports == 0) + rte_exit(EXIT_FAILURE, "No Ethernet port - bye\n"); + + if (nb_ports > L2FWD_MAX_PORTS) + nb_ports = L2FWD_MAX_PORTS; + + /* reset l2fwd_dst_ports */ + for (portid = 0; portid < L2FWD_MAX_PORTS; portid++) + l2fwd_dst_ports[portid] = 0; + last_port = 0; + + rx_lcore_id = 0; + qconf = &lcore_queue_conf[rx_lcore_id]; + + /* + * Initialize the lcore/port-rx-queue configuration of each lcore. + * NOTE: Each logical core sends packets out to all port-tx-queues + */ + 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++; + + while (rte_lcore_is_enabled(rx_lcore_id) == 0 || + lcore_queue_conf[rx_lcore_id].n_rx_queue == + l2fwd_rx_queue_per_lcore) { + + rx_lcore_id++; + if (rx_lcore_id >= RTE_MAX_LCORE) + rte_exit(EXIT_FAILURE, "Not enough cores\n"); + } + + qconf = &lcore_queue_conf[rx_lcore_id]; + qconf->tx_queue_id = 0; + qconf->rx_queue_list[qconf->n_rx_queue] = portid; + qconf->n_rx_queue++; + + printf("Lcore %u: RX port %u\n", rx_lcore_id, portid); + + } + + /* 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", portid); + continue; + } + + /* init port */ + printf("Initializing port %u... ", portid); + fflush(stdout); + ret = rte_eth_dev_configure((uint8_t) portid, 1, 1, &port_conf); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Cannot configure device: err=%d, port=%u\n", + ret, portid); + + rte_eth_macaddr_get((uint8_t) portid, + &l2fwd_ports_eth_addr[portid]); + + /* init one RX queue */ + fflush(stdout); + ret = rte_eth_rx_queue_setup((uint8_t) portid, 0, nb_rxd, + SOCKET0, &rx_conf, + l2fwd_pktmbuf_pool); + if (ret < 0) + rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup: err=%d, port=%u\n", + ret, portid); + + /* init one TX queue */ + fflush(stdout); + ret = rte_eth_tx_queue_setup((uint8_t) portid, 0, nb_txd, + SOCKET0, &tx_conf); + if (ret < 0) + rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup: err=%d, port=%u\n", + ret, portid); + + /* Start device */ + ret = rte_eth_dev_start((uint8_t) portid); + if (ret < 0) + rte_exit(EXIT_FAILURE, "rte_eth_dev_start: err=%d, port=%u\n", + ret, portid); + + printf("done: "); + fflush(stdout); + + printf("Port %u, MAC address: %02X:%02X:%02X:%02X:%02X:%02X\n\n", + 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)); + } + + /* launch per-lcore init on every lcore */ + rte_eal_mp_remote_launch(l2fwd_launch_one_lcore, NULL, CALL_MASTER); + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + if (rte_eal_wait_lcore(lcore_id) < 0) + return -1; + } + + return 0; +} |