X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=examples%2Fip_fragmentation%2Fmain.c;h=d3b1da6c0937435bfc37a213e15b7d0ad4d45f20;hb=c64b9121a9637e02e62b791c88d556cee1c269a1;hp=3172ad5a45ae06579efe828c96651628512f9e9a;hpb=324bcf45e51bf372de0b16cdeaa90524eaa00499;p=dpdk.git diff --git a/examples/ip_fragmentation/main.c b/examples/ip_fragmentation/main.c index 3172ad5a45..d3b1da6c09 100644 --- a/examples/ip_fragmentation/main.c +++ b/examples/ip_fragmentation/main.c @@ -1,34 +1,5 @@ -/*- - * BSD LICENSE - * - * Copyright(c) 2010-2014 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. +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2014 Intel Corporation */ #include @@ -48,10 +19,7 @@ #include #include #include -#include -#include #include -#include #include #include #include @@ -60,12 +28,10 @@ #include #include #include -#include #include #include #include #include -#include #include #include #include @@ -75,12 +41,8 @@ #include -#include "main.h" - #define RTE_LOGTYPE_IP_FRAG RTE_LOGTYPE_USER1 -#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM) - /* allow max jumbo frame 9.5 KB */ #define JUMBO_FRAME_MAX_SIZE 0x2600 @@ -106,25 +68,6 @@ #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_US 100 /* TX drain every ~100us */ @@ -134,8 +77,8 @@ /* * Configurable number of RX/TX ring descriptors */ -#define RTE_TEST_RX_DESC_DEFAULT 128 -#define RTE_TEST_TX_DESC_DEFAULT 512 +#define RTE_TEST_RX_DESC_DEFAULT 1024 +#define RTE_TEST_TX_DESC_DEFAULT 1024 static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT; static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT; @@ -180,7 +123,7 @@ struct rx_queue { struct rte_mempool *indirect_pool; struct rte_lpm *lpm; struct rte_lpm6 *lpm6; - uint8_t portid; + uint16_t portid; }; #define MAX_RX_QUEUE_PER_LCORE 16 @@ -193,39 +136,22 @@ struct lcore_queue_conf { } __rte_cache_aligned; struct lcore_queue_conf lcore_queue_conf[RTE_MAX_LCORE]; -static const struct rte_eth_conf port_conf = { +static struct rte_eth_conf port_conf = { .rxmode = { .max_rx_pkt_len = JUMBO_FRAME_MAX_SIZE, .split_hdr_size = 0, - .header_split = 0, /**< Header Split disabled */ - .hw_ip_checksum = 1, /**< IP checksum offload enabled */ - .hw_vlan_filter = 0, /**< VLAN filtering disabled */ - .jumbo_frame = 1, /**< Jumbo Frame Support enabled */ - .hw_strip_crc = 0, /**< CRC stripped by hardware */ + .ignore_offload_bitfield = 1, + .offloads = (DEV_RX_OFFLOAD_CHECKSUM | + DEV_RX_OFFLOAD_JUMBO_FRAME | + DEV_RX_OFFLOAD_CRC_STRIP), }, .txmode = { .mq_mode = ETH_MQ_TX_NONE, + .offloads = (DEV_TX_OFFLOAD_IPV4_CKSUM | + DEV_TX_OFFLOAD_MULTI_SEGS), }, }; -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 */ -}; - /* * IPv4 forwarding table */ @@ -284,7 +210,7 @@ static struct rte_lpm6 *socket_lpm6[RTE_MAX_NUMA_NODES]; /* Send burst of packets on an output interface */ static inline int -send_burst(struct lcore_queue_conf *qconf, uint16_t n, uint8_t port) +send_burst(struct lcore_queue_conf *qconf, uint16_t n, uint16_t port) { struct rte_mbuf **m_table; int ret; @@ -305,11 +231,12 @@ send_burst(struct lcore_queue_conf *qconf, uint16_t n, uint8_t port) static inline void l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf, - uint8_t queueid, uint8_t port_in) + uint8_t queueid, uint16_t port_in) { struct rx_queue *rxq; - uint32_t i, len; - uint8_t next_hop, port_out, ipv6; + uint32_t i, len, next_hop; + uint8_t ipv6; + uint16_t port_out; int32_t len2; ipv6 = 0; @@ -325,7 +252,7 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf, len = qconf->tx_mbufs[port_out].len; /* if this is an IPv4 packet */ - if (m->ol_flags & PKT_RX_IPV4_HDR) { + if (RTE_ETH_IS_IPV4_HDR(m->packet_type)) { struct ipv4_hdr *ip_hdr; uint32_t ip_dst; /* Read the lookup key (i.e. ip_dst) from the input packet */ @@ -342,7 +269,7 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf, } /* if we don't need to do any fragmentation */ - if (likely (IPV4_MTU_DEFAULT >= m->pkt.pkt_len)) { + if (likely (IPV4_MTU_DEFAULT >= m->pkt_len)) { qconf->tx_mbufs[port_out].m_table[len] = m; len2 = 1; } else { @@ -359,9 +286,8 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf, if (unlikely (len2 < 0)) return; } - } - /* if this is an IPv6 packet */ - else if (m->ol_flags & PKT_RX_IPV6_HDR) { + } else if (RTE_ETH_IS_IPV6_HDR(m->packet_type)) { + /* if this is an IPv6 packet */ struct ipv6_hdr *ip_hdr; ipv6 = 1; @@ -370,7 +296,8 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf, ip_hdr = rte_pktmbuf_mtod(m, struct ipv6_hdr *); /* Find destination port */ - if (rte_lpm6_lookup(rxq->lpm6, ip_hdr->dst_addr, &next_hop) == 0 && + if (rte_lpm6_lookup(rxq->lpm6, ip_hdr->dst_addr, + &next_hop) == 0 && (enabled_port_mask & 1 << next_hop) != 0) { port_out = next_hop; @@ -379,7 +306,7 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf, } /* if we don't need to do any fragmentation */ - if (likely (IPV6_MTU_DEFAULT >= m->pkt.pkt_len)) { + if (likely (IPV6_MTU_DEFAULT >= m->pkt_len)) { qconf->tx_mbufs[port_out].m_table[len] = m; len2 = 1; } else { @@ -413,7 +340,7 @@ l3fwd_simple_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf, rte_panic("No headroom in mbuf.\n"); } - m->pkt.vlan_macip.f.l2_len = sizeof(struct ether_hdr); + m->l2_len = sizeof(struct ether_hdr); /* 02:00:00:00:00:xx */ d_addr_bytes = ð_hdr->d_addr.addr_bytes[0]; @@ -447,7 +374,7 @@ main_loop(__attribute__((unused)) void *dummy) unsigned lcore_id; uint64_t prev_tsc, diff_tsc, cur_tsc; int i, j, nb_rx; - uint8_t portid; + uint16_t portid; 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; @@ -467,7 +394,7 @@ main_loop(__attribute__((unused)) void *dummy) portid = qconf->rx_queue_list[i].portid; RTE_LOG(INFO, IP_FRAG, " -- lcoreid=%u portid=%d\n", lcore_id, - (int) portid); + portid); } while (1) { @@ -630,29 +557,26 @@ parse_args(int argc, char **argv) argv[optind-1] = prgname; ret = optind-1; - optind = 0; /* reset getopt lib */ + optind = 1; /* reset getopt lib */ return ret; } static void print_ethaddr(const char *name, struct ether_addr *eth_addr) { - printf("%s%02X:%02X:%02X:%02X:%02X:%02X", name, - eth_addr->addr_bytes[0], - eth_addr->addr_bytes[1], - eth_addr->addr_bytes[2], - eth_addr->addr_bytes[3], - eth_addr->addr_bytes[4], - eth_addr->addr_bytes[5]); + char buf[ETHER_ADDR_FMT_SIZE]; + ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, eth_addr); + printf("%s%s", name, buf); } /* 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) +check_all_ports_link_status(uint16_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; + uint16_t portid; + uint8_t count, all_ports_up, print_flag = 0; struct rte_eth_link link; printf("\nChecking link status"); @@ -667,18 +591,17 @@ check_all_ports_link_status(uint8_t port_num, uint32_t port_mask) /* 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, + printf( + "Port%d Link Up .Speed %u Mbps - %s\n", + portid, 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); + printf("Port %d Link Down\n", portid); continue; } /* clear all_ports_up flag if any link down */ - if (link.link_status == 0) { + if (link.link_status == ETH_LINK_DOWN) { all_ports_up = 0; break; } @@ -701,6 +624,74 @@ check_all_ports_link_status(uint8_t port_num, uint32_t port_mask) } } +/* Check L3 packet type detection capablity of the NIC port */ +static int +check_ptype(int portid) +{ + int i, ret; + int ptype_l3_ipv4 = 0, ptype_l3_ipv6 = 0; + uint32_t ptype_mask = RTE_PTYPE_L3_MASK; + + ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, NULL, 0); + if (ret <= 0) + return 0; + + uint32_t ptypes[ret]; + + ret = rte_eth_dev_get_supported_ptypes(portid, ptype_mask, ptypes, ret); + for (i = 0; i < ret; ++i) { + if (ptypes[i] & RTE_PTYPE_L3_IPV4) + ptype_l3_ipv4 = 1; + if (ptypes[i] & RTE_PTYPE_L3_IPV6) + ptype_l3_ipv6 = 1; + } + + if (ptype_l3_ipv4 == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV4\n", portid); + + if (ptype_l3_ipv6 == 0) + printf("port %d cannot parse RTE_PTYPE_L3_IPV6\n", portid); + + if (ptype_l3_ipv4 && ptype_l3_ipv6) + return 1; + + return 0; + +} + +/* Parse packet type of a packet by SW */ +static inline void +parse_ptype(struct rte_mbuf *m) +{ + struct ether_hdr *eth_hdr; + uint32_t packet_type = RTE_PTYPE_UNKNOWN; + uint16_t ether_type; + + eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); + ether_type = eth_hdr->ether_type; + if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv4)) + packet_type |= RTE_PTYPE_L3_IPV4_EXT_UNKNOWN; + else if (ether_type == rte_cpu_to_be_16(ETHER_TYPE_IPv6)) + packet_type |= RTE_PTYPE_L3_IPV6_EXT_UNKNOWN; + + m->packet_type = packet_type; +} + +/* callback function to detect packet type for a queue of a port */ +static uint16_t +cb_parse_ptype(uint16_t port __rte_unused, uint16_t queue __rte_unused, + struct rte_mbuf *pkts[], uint16_t nb_pkts, + uint16_t max_pkts __rte_unused, + void *user_param __rte_unused) +{ + uint16_t i; + + for (i = 0; i < nb_pkts; ++i) + parse_ptype(pkts[i]); + + return nb_pkts; +} + static int init_routing_table(void) { @@ -768,6 +759,7 @@ init_mem(void) struct rte_mempool *mp; struct rte_lpm *lpm; struct rte_lpm6 *lpm6; + struct rte_lpm_config lpm_config; int socket; unsigned lcore_id; @@ -786,14 +778,10 @@ init_mem(void) if (socket_direct_pool[socket] == NULL) { RTE_LOG(INFO, IP_FRAG, "Creating direct mempool on socket %i\n", socket); - rte_snprintf(buf, sizeof(buf), "pool_direct_%i", socket); - - mp = rte_mempool_create(buf, NB_MBUF, - MBUF_SIZE, 32, - sizeof(struct rte_pktmbuf_pool_private), - rte_pktmbuf_pool_init, NULL, - rte_pktmbuf_init, NULL, - socket, 0); + snprintf(buf, sizeof(buf), "pool_direct_%i", socket); + + mp = rte_pktmbuf_pool_create(buf, NB_MBUF, 32, + 0, RTE_MBUF_DEFAULT_BUF_SIZE, socket); if (mp == NULL) { RTE_LOG(ERR, IP_FRAG, "Cannot create direct mempool\n"); return -1; @@ -804,14 +792,10 @@ init_mem(void) if (socket_indirect_pool[socket] == NULL) { RTE_LOG(INFO, IP_FRAG, "Creating indirect mempool on socket %i\n", socket); - rte_snprintf(buf, sizeof(buf), "pool_indirect_%i", socket); - - mp = rte_mempool_create(buf, NB_MBUF, - sizeof(struct rte_mbuf), 32, - 0, - NULL, NULL, - rte_pktmbuf_init, NULL, - socket, 0); + snprintf(buf, sizeof(buf), "pool_indirect_%i", socket); + + mp = rte_pktmbuf_pool_create(buf, NB_MBUF, 32, 0, 0, + socket); if (mp == NULL) { RTE_LOG(ERR, IP_FRAG, "Cannot create indirect mempool\n"); return -1; @@ -821,9 +805,13 @@ init_mem(void) if (socket_lpm[socket] == NULL) { RTE_LOG(INFO, IP_FRAG, "Creating LPM table on socket %i\n", socket); - rte_snprintf(buf, sizeof(buf), "IP_FRAG_LPM_%i", socket); + snprintf(buf, sizeof(buf), "IP_FRAG_LPM_%i", socket); - lpm = rte_lpm_create(buf, socket, LPM_MAX_RULES, 0); + lpm_config.max_rules = LPM_MAX_RULES; + lpm_config.number_tbl8s = 256; + lpm_config.flags = 0; + + lpm = rte_lpm_create(buf, socket, &lpm_config); if (lpm == NULL) { RTE_LOG(ERR, IP_FRAG, "Cannot create LPM table\n"); return -1; @@ -833,9 +821,9 @@ init_mem(void) if (socket_lpm6[socket] == NULL) { RTE_LOG(INFO, IP_FRAG, "Creating LPM6 table on socket %i\n", socket); - rte_snprintf(buf, sizeof(buf), "IP_FRAG_LPM_%i", socket); + snprintf(buf, sizeof(buf), "IP_FRAG_LPM_%i", socket); - lpm6 = rte_lpm6_create("IP_FRAG_LPM6", socket, &lpm6_config); + lpm6 = rte_lpm6_create(buf, socket, &lpm6_config); if (lpm6 == NULL) { RTE_LOG(ERR, IP_FRAG, "Cannot create LPM table\n"); return -1; @@ -848,16 +836,18 @@ init_mem(void) } int -MAIN(int argc, char **argv) +main(int argc, char **argv) { struct lcore_queue_conf *qconf; + struct rte_eth_dev_info dev_info; + struct rte_eth_txconf *txconf; struct rx_queue *rxq; int socket, ret; unsigned nb_ports; uint16_t queueid = 0; unsigned lcore_id = 0, rx_lcore_id = 0; uint32_t n_tx_queue, nb_lcores; - uint8_t portid; + uint16_t portid; /* init EAL */ ret = rte_eal_init(argc, argv); @@ -871,13 +861,8 @@ MAIN(int argc, char **argv) if (ret < 0) rte_exit(EXIT_FAILURE, "Invalid arguments"); - if (rte_eal_pci_probe() < 0) - rte_panic("Cannot probe PCI\n"); - nb_ports = rte_eth_dev_count(); - if (nb_ports > RTE_MAX_ETHPORTS) - nb_ports = RTE_MAX_ETHPORTS; - else if (nb_ports == 0) + if (nb_ports == 0) rte_exit(EXIT_FAILURE, "No ports found!\n"); nb_lcores = rte_lcore_count(); @@ -892,6 +877,9 @@ MAIN(int argc, char **argv) /* initialize all ports */ for (portid = 0; portid < nb_ports; portid++) { + struct rte_eth_conf local_port_conf = port_conf; + struct rte_eth_rxconf rxq_conf; + /* skip ports that are not enabled */ if ((enabled_port_mask & (1 << portid)) == 0) { printf("Skipping disabled port %d\n", portid); @@ -900,6 +888,12 @@ MAIN(int argc, char **argv) qconf = &lcore_queue_conf[rx_lcore_id]; + /* limit the frame size to the maximum supported by NIC */ + rte_eth_dev_info_get(portid, &dev_info); + local_port_conf.rxmode.max_rx_pkt_len = RTE_MIN( + dev_info.max_rx_pktlen, + local_port_conf.rxmode.max_rx_pkt_len); + /* get the lcore_id for this port */ while (rte_lcore_is_enabled(rx_lcore_id) == 0 || qconf->n_rx_queue == (unsigned)rx_queue_per_lcore) { @@ -931,8 +925,11 @@ MAIN(int argc, char **argv) n_tx_queue = nb_lcores; if (n_tx_queue > MAX_TX_QUEUE_PER_PORT) n_tx_queue = MAX_TX_QUEUE_PER_PORT; + if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE) + local_port_conf.txmode.offloads |= + DEV_TX_OFFLOAD_MBUF_FAST_FREE; ret = rte_eth_dev_configure(portid, 1, (uint16_t)n_tx_queue, - &port_conf); + &local_port_conf); if (ret < 0) { printf("\n"); rte_exit(EXIT_FAILURE, "Cannot configure device: " @@ -940,9 +937,19 @@ MAIN(int argc, char **argv) ret, portid); } + ret = rte_eth_dev_adjust_nb_rx_tx_desc(portid, &nb_rxd, + &nb_txd); + if (ret < 0) { + printf("\n"); + rte_exit(EXIT_FAILURE, "Cannot adjust number of " + "descriptors: err=%d, port=%d\n", ret, portid); + } + /* init one RX queue */ + rxq_conf = dev_info.default_rxconf; + rxq_conf.offloads = local_port_conf.rxmode.offloads; ret = rte_eth_rx_queue_setup(portid, 0, nb_rxd, - socket, &rx_conf, + socket, &rxq_conf, socket_direct_pool[socket]); if (ret < 0) { printf("\n"); @@ -964,8 +971,12 @@ MAIN(int argc, char **argv) socket = (int) rte_lcore_to_socket_id(lcore_id); printf("txq=%u,%d ", lcore_id, queueid); fflush(stdout); + + txconf = &dev_info.default_txconf; + txconf->txq_flags = ETH_TXQ_FLAGS_IGNORE; + txconf->offloads = local_port_conf.txmode.offloads; ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd, - socket, &tx_conf); + socket, txconf); if (ret < 0) { printf("\n"); rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup: " @@ -994,12 +1005,18 @@ MAIN(int argc, char **argv) ret, portid); rte_eth_promiscuous_enable(portid); + + if (check_ptype(portid) == 0) { + rte_eth_add_rx_callback(portid, 0, cb_parse_ptype, NULL); + printf("Add Rx callback function to detect L3 packet type by SW :" + " port = %d\n", portid); + } } if (init_routing_table() < 0) rte_exit(EXIT_FAILURE, "Cannot init routing table\n"); - check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask); + check_all_ports_link_status(nb_ports, enabled_port_mask); /* launch per-lcore init on every lcore */ rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER);