X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=examples%2Fl3fwd%2Fmain.c;h=b0a700ab15bc428411d742662f904c5e17c72b07;hb=6d13ea8e8e49ab957deae2bba5ecf4a4bfe747d1;hp=a6c04320d69eff1e9daa94f02afe0f0012c2902c;hpb=5c95261dbf79b5b03314b5477a3f3088a6934796;p=dpdk.git diff --git a/examples/l3fwd/main.c b/examples/l3fwd/main.c old mode 100755 new mode 100644 index a6c04320d6..b0a700ab15 --- a/examples/l3fwd/main.c +++ b/examples/l3fwd/main.c @@ -1,35 +1,5 @@ -/*- - * BSD LICENSE - * - * Copyright(c) 2010-2013 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) 2010-2016 Intel Corporation */ #include @@ -42,16 +12,16 @@ #include #include #include +#include +#include #include +#include #include #include #include #include -#include -#include #include -#include #include #include #include @@ -60,132 +30,72 @@ #include #include #include -#include #include #include #include #include -#include #include #include #include #include #include #include +#include -#include "main.h" - -#define APP_LOOKUP_EXACT_MATCH 0 -#define APP_LOOKUP_LPM 1 -#define DO_RFC_1812_CHECKS - -//#define APP_LOOKUP_METHOD APP_LOOKUP_EXACT_MATCH -#ifndef APP_LOOKUP_METHOD -#define APP_LOOKUP_METHOD APP_LOOKUP_LPM -#endif - -#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) -#include -#elif (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) -#include -#else -#error "APP_LOOKUP_METHOD set to incorrect value" -#endif - -#ifndef IPv6_BYTES -#define IPv6_BYTES_FMT "%02x%02x:%02x%02x:%02x%02x:%02x%02x:"\ - "%02x%02x:%02x%02x:%02x%02x:%02x%02x" -#define IPv6_BYTES(addr) \ - addr[0], addr[1], addr[2], addr[3], \ - addr[4], addr[5], addr[6], addr[7], \ - addr[8], addr[9], addr[10], addr[11],\ - addr[12], addr[13],addr[14], addr[15] -#endif - +#include +#include -#define RTE_LOGTYPE_L3FWD RTE_LOGTYPE_USER1 - -#define MAX_JUMBO_PKT_LEN 9600 - -#define IPV6_ADDR_LEN 16 - -#define MEMPOOL_CACHE_SIZE 256 - -#define MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM) +#include "l3fwd.h" /* - * This expression is used to calculate the number of mbufs needed depending on user input, taking - * into account memory for rx and tx hardware rings, cache per lcore and mtable per port per lcore. - * RTE_MAX is used to ensure that NB_MBUF never goes below a minimum value of 8192 + * Configurable number of RX/TX ring descriptors */ +#define RTE_TEST_RX_DESC_DEFAULT 1024 +#define RTE_TEST_TX_DESC_DEFAULT 1024 -#define NB_MBUF RTE_MAX ( \ - (nb_ports*nb_rx_queue*RTE_TEST_RX_DESC_DEFAULT + \ - nb_ports*nb_lcores*MAX_PKT_BURST + \ - nb_ports*n_tx_queue*RTE_TEST_TX_DESC_DEFAULT + \ - nb_lcores*MEMPOOL_CACHE_SIZE), \ - (unsigned)8192) +#define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS +#define MAX_RX_QUEUE_PER_PORT 128 -/* - * 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. */ +#define MAX_LCORE_PARAMS 1024 -/* - * 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. */ +/* Static global variables used within this file. */ +static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT; +static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT; -#define MAX_PKT_BURST 32 -#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ +/**< Ports set in promiscuous mode off by default. */ +static int promiscuous_on; -#define NB_SOCKETS 8 +/* Select Longest-Prefix or Exact match. */ +static int l3fwd_lpm_on; +static int l3fwd_em_on; -/* Configure how many packets ahead to prefetch, when reading packets */ -#define PREFETCH_OFFSET 3 +/* Global variables. */ -/* - * 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; +static int numa_on = 1; /**< NUMA is enabled by default. */ +static int parse_ptype; /**< Parse packet type using rx callback, and */ + /**< disabled by default */ +static int per_port_pool; /**< Use separate buffer pools per port; disabled */ + /**< by default */ + +volatile bool force_quit; /* ethernet addresses of ports */ -static struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS]; +uint64_t dest_eth_addr[RTE_MAX_ETHPORTS]; +struct rte_ether_addr ports_eth_addr[RTE_MAX_ETHPORTS]; -/* mask of enabled ports */ -static uint32_t enabled_port_mask = 0; -static int promiscuous_on = 0; /**< Ports set in promiscuous mode off by default. */ -static int numa_on = 1; /**< NUMA is enabled by default. */ +xmm_t val_eth[RTE_MAX_ETHPORTS]; -struct mbuf_table { - uint16_t len; - struct rte_mbuf *m_table[MAX_PKT_BURST]; -}; +/* mask of enabled ports */ +uint32_t enabled_port_mask; -struct lcore_rx_queue { - uint8_t port_id; - uint8_t queue_id; -} __rte_cache_aligned; +/* Used only in exact match mode. */ +int ipv6; /**< ipv6 is false by default. */ +uint32_t hash_entry_number = HASH_ENTRY_NUMBER_DEFAULT; -#define MAX_RX_QUEUE_PER_LCORE 16 -#define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS -#define MAX_RX_QUEUE_PER_PORT 128 +struct lcore_conf lcore_conf[RTE_MAX_LCORE]; -#define MAX_LCORE_PARAMS 1024 struct lcore_params { - uint8_t port_id; + uint16_t port_id; uint8_t queue_id; uint8_t lcore_id; } __rte_cache_aligned; @@ -209,18 +119,15 @@ static uint16_t nb_lcore_params = sizeof(lcore_params_array_default) / static struct rte_eth_conf port_conf = { .rxmode = { + .mq_mode = ETH_MQ_RX_RSS, .max_rx_pkt_len = ETHER_MAX_LEN, .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 = 0, /**< Jumbo Frame Support disabled */ - .hw_strip_crc = 0, /**< CRC stripped by hardware */ + .offloads = DEV_RX_OFFLOAD_CHECKSUM, }, .rx_adv_conf = { .rss_conf = { .rss_key = NULL, - .rss_hf = ETH_RSS_IPV4 | ETH_RSS_IPV6, + .rss_hf = ETH_RSS_IP, }, }, .txmode = { @@ -228,508 +135,52 @@ static struct rte_eth_conf port_conf = { }, }; -static const struct rte_eth_rxconf rx_conf = { - .rx_thresh = { - .pthresh = RX_PTHRESH, - .hthresh = RX_HTHRESH, - .wthresh = RX_WTHRESH, - }, - .rx_free_thresh = 32, -}; +static struct rte_mempool *pktmbuf_pool[RTE_MAX_ETHPORTS][NB_SOCKETS]; +static uint8_t lkp_per_socket[NB_SOCKETS]; -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 */ - .txq_flags = 0x0, +struct l3fwd_lkp_mode { + void (*setup)(int); + int (*check_ptype)(int); + rte_rx_callback_fn cb_parse_ptype; + int (*main_loop)(void *); + void* (*get_ipv4_lookup_struct)(int); + void* (*get_ipv6_lookup_struct)(int); }; -static struct rte_mempool * pktmbuf_pool[NB_SOCKETS]; - - -#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) - -#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 -#include -#define DEFAULT_HASH_FUNC rte_hash_crc -#else -#include -#define DEFAULT_HASH_FUNC rte_jhash -#endif - -struct ipv4_5tuple { - uint32_t ip_dst; - uint32_t ip_src; - uint16_t port_dst; - uint16_t port_src; - uint8_t proto; -} __attribute__((__packed__)); - -struct ipv6_5tuple { - uint8_t ip_dst[IPV6_ADDR_LEN]; - uint8_t ip_src[IPV6_ADDR_LEN]; - uint16_t port_dst; - uint16_t port_src; - uint8_t proto; -} __attribute__((__packed__)); - -struct ipv4_l3fwd_route { - struct ipv4_5tuple key; - uint8_t if_out; -}; +static struct l3fwd_lkp_mode l3fwd_lkp; -struct ipv6_l3fwd_route { - struct ipv6_5tuple key; - uint8_t if_out; +static struct l3fwd_lkp_mode l3fwd_em_lkp = { + .setup = setup_hash, + .check_ptype = em_check_ptype, + .cb_parse_ptype = em_cb_parse_ptype, + .main_loop = em_main_loop, + .get_ipv4_lookup_struct = em_get_ipv4_l3fwd_lookup_struct, + .get_ipv6_lookup_struct = em_get_ipv6_l3fwd_lookup_struct, }; -static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = { - {{IPv4(100,10,0,1), IPv4(200,10,0,1), 101, 11, IPPROTO_TCP}, 0}, - {{IPv4(100,20,0,2), IPv4(200,20,0,2), 102, 12, IPPROTO_TCP}, 1}, - {{IPv4(100,30,0,3), IPv4(200,30,0,3), 103, 13, IPPROTO_TCP}, 2}, - {{IPv4(100,40,0,4), IPv4(200,40,0,4), 104, 14, IPPROTO_TCP}, 3}, +static struct l3fwd_lkp_mode l3fwd_lpm_lkp = { + .setup = setup_lpm, + .check_ptype = lpm_check_ptype, + .cb_parse_ptype = lpm_cb_parse_ptype, + .main_loop = lpm_main_loop, + .get_ipv4_lookup_struct = lpm_get_ipv4_l3fwd_lookup_struct, + .get_ipv6_lookup_struct = lpm_get_ipv6_l3fwd_lookup_struct, }; -static struct ipv6_l3fwd_route ipv6_l3fwd_route_array[] = { - { - { - {0xfe, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x02, 0x1b, 0x21, 0xff, 0xfe, 0x91, 0x38, 0x05}, - {0xfe, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x02, 0x1e, 0x67, 0xff, 0xfe, 0x0d, 0xb6, 0x0a}, - 1, 10, IPPROTO_UDP - }, 4 - }, -}; - -typedef struct rte_hash lookup_struct_t; -static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS]; -static lookup_struct_t *ipv6_l3fwd_lookup_struct[NB_SOCKETS]; - -#define L3FWD_HASH_ENTRIES 1024 - -struct rte_hash_parameters ipv4_l3fwd_hash_params = { - .name = "ipv4_l3fwd_hash_0", - .entries = L3FWD_HASH_ENTRIES, - .bucket_entries = 4, - .key_len = sizeof(struct ipv4_5tuple), - .hash_func = DEFAULT_HASH_FUNC, - .hash_func_init_val = 0, - .socket_id = 0, -}; - -struct rte_hash_parameters ipv6_l3fwd_hash_params = { - .name = "ipv6_l3fwd_hash_0", - .entries = L3FWD_HASH_ENTRIES, - .bucket_entries = 4, - .key_len = sizeof(struct ipv6_5tuple), - .hash_func = DEFAULT_HASH_FUNC, - .hash_func_init_val = 0, - .socket_id = 0, -}; - -#define IPV4_L3FWD_NUM_ROUTES \ - (sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0])) - -#define IPV6_L3FWD_NUM_ROUTES \ - (sizeof(ipv6_l3fwd_route_array) / sizeof(ipv6_l3fwd_route_array[0])) - -static uint8_t ipv4_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned; -static uint8_t ipv6_l3fwd_out_if[L3FWD_HASH_ENTRIES] __rte_cache_aligned; -#endif - -#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) -struct ipv4_l3fwd_route { - uint32_t ip; - uint8_t depth; - uint8_t if_out; -}; - -static struct ipv4_l3fwd_route ipv4_l3fwd_route_array[] = { - {IPv4(1,1,1,0), 24, 0}, - {IPv4(2,1,1,0), 24, 1}, - {IPv4(3,1,1,0), 24, 2}, - {IPv4(4,1,1,0), 24, 3}, - {IPv4(5,1,1,0), 24, 4}, - {IPv4(6,1,1,0), 24, 5}, - {IPv4(7,1,1,0), 24, 6}, - {IPv4(8,1,1,0), 24, 7}, -}; - -#define IPV4_L3FWD_NUM_ROUTES \ - (sizeof(ipv4_l3fwd_route_array) / sizeof(ipv4_l3fwd_route_array[0])) - -#define IPV4_L3FWD_LPM_MAX_RULES 1024 - -typedef struct rte_lpm lookup_struct_t; -static lookup_struct_t *ipv4_l3fwd_lookup_struct[NB_SOCKETS]; -#endif - -struct lcore_conf { - uint16_t n_rx_queue; - struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE]; - uint16_t tx_queue_id[RTE_MAX_ETHPORTS]; - struct mbuf_table tx_mbufs[RTE_MAX_ETHPORTS]; - lookup_struct_t * ipv4_lookup_struct; - lookup_struct_t * ipv6_lookup_struct; -} __rte_cache_aligned; - -static struct lcore_conf lcore_conf[RTE_MAX_LCORE]; - -/* Send burst of packets on an output interface */ -static inline int -send_burst(struct lcore_conf *qconf, uint16_t n, uint8_t port) -{ - struct rte_mbuf **m_table; - int ret; - uint16_t queueid; - - queueid = qconf->tx_queue_id[port]; - m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table; - - ret = rte_eth_tx_burst(port, queueid, m_table, n); - if (unlikely(ret < n)) { - do { - rte_pktmbuf_free(m_table[ret]); - } while (++ret < n); - } - - return 0; -} - -/* Enqueue a single packet, and send burst if queue is filled */ -static inline int -send_single_packet(struct rte_mbuf *m, uint8_t port) -{ - uint32_t lcore_id; - uint16_t len; - struct lcore_conf *qconf; - - lcore_id = rte_lcore_id(); - - qconf = &lcore_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)) { - send_burst(qconf, MAX_PKT_BURST, port); - len = 0; - } - - qconf->tx_mbufs[port].len = len; - return 0; -} - -#ifdef DO_RFC_1812_CHECKS -static inline int -is_valid_ipv4_pkt(struct ipv4_hdr *pkt, uint32_t link_len) -{ - /* From http://www.rfc-editor.org/rfc/rfc1812.txt section 5.2.2 */ - /* - * 1. The packet length reported by the Link Layer must be large - * enough to hold the minimum length legal IP datagram (20 bytes). - */ - if (link_len < sizeof(struct ipv4_hdr)) - return -1; - - /* 2. The IP checksum must be correct. */ - /* this is checked in H/W */ - - /* - * 3. The IP version number must be 4. If the version number is not 4 - * then the packet may be another version of IP, such as IPng or - * ST-II. - */ - if (((pkt->version_ihl) >> 4) != 4) - return -3; - /* - * 4. The IP header length field must be large enough to hold the - * minimum length legal IP datagram (20 bytes = 5 words). - */ - if ((pkt->version_ihl & 0xf) < 5) - return -4; - - /* - * 5. The IP total length field must be large enough to hold the IP - * datagram header, whose length is specified in the IP header length - * field. - */ - if (rte_cpu_to_be_16(pkt->total_length) < sizeof(struct ipv4_hdr)) - return -5; - - return 0; -} -#endif - -#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) -static void -print_ipv4_key(struct ipv4_5tuple key) -{ - printf("IP dst = %08x, IP src = %08x, port dst = %d, port src = %d, proto = %d\n", - (unsigned)key.ip_dst, (unsigned)key.ip_src, key.port_dst, key.port_src, key.proto); -} +/* + * Setup lookup methods for forwarding. + * Currently exact-match and longest-prefix-match + * are supported ones. + */ static void -print_ipv6_key(struct ipv6_5tuple key) -{ - printf( "IP dst = " IPv6_BYTES_FMT ", IP src = " IPv6_BYTES_FMT ", " - "port dst = %d, port src = %d, proto = %d\n", - IPv6_BYTES(key.ip_dst), IPv6_BYTES(key.ip_src), - key.port_dst, key.port_src, key.proto); -} - -static inline uint8_t -get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint8_t portid, lookup_struct_t * ipv4_l3fwd_lookup_struct) -{ - struct ipv4_5tuple key; - struct tcp_hdr *tcp; - struct udp_hdr *udp; - int ret = 0; - - key.ip_dst = rte_be_to_cpu_32(ipv4_hdr->dst_addr); - key.ip_src = rte_be_to_cpu_32(ipv4_hdr->src_addr); - key.proto = ipv4_hdr->next_proto_id; - - switch (ipv4_hdr->next_proto_id) { - case IPPROTO_TCP: - tcp = (struct tcp_hdr *)((unsigned char *) ipv4_hdr + - sizeof(struct ipv4_hdr)); - key.port_dst = rte_be_to_cpu_16(tcp->dst_port); - key.port_src = rte_be_to_cpu_16(tcp->src_port); - break; - - case IPPROTO_UDP: - udp = (struct udp_hdr *)((unsigned char *) ipv4_hdr + - sizeof(struct ipv4_hdr)); - key.port_dst = rte_be_to_cpu_16(udp->dst_port); - key.port_src = rte_be_to_cpu_16(udp->src_port); - break; - - default: - key.port_dst = 0; - key.port_src = 0; - break; - } - - /* Find destination port */ - ret = rte_hash_lookup(ipv4_l3fwd_lookup_struct, (const void *)&key); - return (uint8_t)((ret < 0)? portid : ipv4_l3fwd_out_if[ret]); -} - -static inline uint8_t -get_ipv6_dst_port(struct ipv6_hdr *ipv6_hdr, uint8_t portid, lookup_struct_t * ipv6_l3fwd_lookup_struct) -{ - struct ipv6_5tuple key; - struct tcp_hdr *tcp; - struct udp_hdr *udp; - int ret = 0; - - memcpy(key.ip_dst, ipv6_hdr->dst_addr, IPV6_ADDR_LEN); - memcpy(key.ip_src, ipv6_hdr->src_addr, IPV6_ADDR_LEN); - - key.proto = ipv6_hdr->proto; - - switch (ipv6_hdr->proto) { - case IPPROTO_TCP: - tcp = (struct tcp_hdr *)((unsigned char *) ipv6_hdr + - sizeof(struct ipv6_hdr)); - key.port_dst = rte_be_to_cpu_16(tcp->dst_port); - key.port_src = rte_be_to_cpu_16(tcp->src_port); - break; - - case IPPROTO_UDP: - udp = (struct udp_hdr *)((unsigned char *) ipv6_hdr + - sizeof(struct ipv6_hdr)); - key.port_dst = rte_be_to_cpu_16(udp->dst_port); - key.port_src = rte_be_to_cpu_16(udp->src_port); - break; - - default: - key.port_dst = 0; - key.port_src = 0; - break; - } - - /* Find destination port */ - ret = rte_hash_lookup(ipv6_l3fwd_lookup_struct, (const void *)&key); - return (uint8_t)((ret < 0)? portid : ipv6_l3fwd_out_if[ret]); -} -#endif - -#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) -static inline uint8_t -get_ipv4_dst_port(struct ipv4_hdr *ipv4_hdr, uint8_t portid, lookup_struct_t * ipv4_l3fwd_lookup_struct) -{ - uint8_t next_hop; - - return (uint8_t) ((rte_lpm_lookup(ipv4_l3fwd_lookup_struct, - rte_be_to_cpu_32(ipv4_hdr->dst_addr), &next_hop) == 0)? - next_hop : portid); -} -#endif - -static inline void -l3fwd_simple_forward(struct rte_mbuf *m, uint8_t portid, struct lcore_conf *qconf) +setup_l3fwd_lookup_tables(void) { - struct ether_hdr *eth_hdr; - struct ipv4_hdr *ipv4_hdr; - void *d_addr_bytes; - uint8_t dst_port; - - eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *); - - if (m->ol_flags & PKT_RX_IPV4_HDR) { - /* Handle IPv4 headers.*/ - ipv4_hdr = (struct ipv4_hdr *)(rte_pktmbuf_mtod(m, unsigned char *) + - sizeof(struct ether_hdr)); - -#ifdef DO_RFC_1812_CHECKS - /* Check to make sure the packet is valid (RFC1812) */ - if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt.pkt_len) < 0) { - rte_pktmbuf_free(m); - return; - } -#endif - - dst_port = get_ipv4_dst_port(ipv4_hdr, portid, qconf->ipv4_lookup_struct); - if (dst_port >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port) == 0) - dst_port = portid; - - /* 02:00:00:00:00:xx */ - d_addr_bytes = ð_hdr->d_addr.addr_bytes[0]; - *((uint64_t *)d_addr_bytes) = 0x000000000002 + ((uint64_t)dst_port << 40); - -#ifdef DO_RFC_1812_CHECKS - /* Update time to live and header checksum */ - --(ipv4_hdr->time_to_live); - ++(ipv4_hdr->hdr_checksum); -#endif - - /* src addr */ - ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr); - - send_single_packet(m, dst_port); - } - else { - /* Handle IPv6 headers.*/ -#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) - struct ipv6_hdr *ipv6_hdr; - - ipv6_hdr = (struct ipv6_hdr *)(rte_pktmbuf_mtod(m, unsigned char *) + - sizeof(struct ether_hdr)); - - dst_port = get_ipv6_dst_port(ipv6_hdr, portid, qconf->ipv6_lookup_struct); - - if (dst_port >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port) == 0) - dst_port = portid; - - /* 02:00:00:00:00:xx */ - d_addr_bytes = ð_hdr->d_addr.addr_bytes[0]; - *((uint64_t *)d_addr_bytes) = 0x000000000002 + ((uint64_t)dst_port << 40); - - /* src addr */ - ether_addr_copy(&ports_eth_addr[dst_port], ð_hdr->s_addr); - - send_single_packet(m, dst_port); -#else - /* We don't currently handle IPv6 packets in LPM mode. */ - rte_pktmbuf_free(m); -#endif - } - -} - -/* main processing loop */ -static __attribute__((noreturn)) int -main_loop(__attribute__((unused)) void *dummy) -{ - struct rte_mbuf *pkts_burst[MAX_PKT_BURST]; - unsigned lcore_id; - uint64_t prev_tsc, diff_tsc, cur_tsc; - int i, j, nb_rx; - uint8_t portid, queueid; - struct lcore_conf *qconf; - const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US; - - prev_tsc = 0; - - lcore_id = rte_lcore_id(); - qconf = &lcore_conf[lcore_id]; - - if (qconf->n_rx_queue == 0) { - RTE_LOG(INFO, L3FWD, "lcore %u has nothing to do\n", lcore_id); - while(1); - } - - RTE_LOG(INFO, L3FWD, "entering main loop on lcore %u\n", lcore_id); - - for (i = 0; i < qconf->n_rx_queue; i++) { - - portid = qconf->rx_queue_list[i].port_id; - queueid = qconf->rx_queue_list[i].queue_id; - RTE_LOG(INFO, L3FWD, " -- lcoreid=%u portid=%hhu rxqueueid=%hhu\n", lcore_id, - portid, queueid); - } - - while (1) { - - cur_tsc = rte_rdtsc(); - - /* - * TX burst queue drain - */ - diff_tsc = cur_tsc - prev_tsc; - if (unlikely(diff_tsc > drain_tsc)) { - - /* - * This could be optimized (use queueid instead of - * portid), but it is not called so often - */ - for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) { - if (qconf->tx_mbufs[portid].len == 0) - continue; - send_burst(&lcore_conf[lcore_id], - qconf->tx_mbufs[portid].len, - portid); - qconf->tx_mbufs[portid].len = 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].port_id; - queueid = qconf->rx_queue_list[i].queue_id; - nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst, MAX_PKT_BURST); - - /* Prefetch first packets */ - for (j = 0; j < PREFETCH_OFFSET && j < nb_rx; j++) { - rte_prefetch0(rte_pktmbuf_mtod( - pkts_burst[j], void *)); - } - - /* Prefetch and forward already prefetched packets */ - for (j = 0; j < (nb_rx - PREFETCH_OFFSET); j++) { - rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[ - j + PREFETCH_OFFSET], void *)); - l3fwd_simple_forward(pkts_burst[j], portid, qconf); - } - - /* Forward remaining prefetched packets */ - for (; j < nb_rx; j++) { - l3fwd_simple_forward(pkts_burst[j], portid, qconf); - } - } - } + /* Setup HASH lookup functions. */ + if (l3fwd_em_on) + l3fwd_lkp = l3fwd_em_lkp; + /* Setup LPM lookup functions. */ + else + l3fwd_lkp = l3fwd_lpm_lkp; } static int @@ -760,9 +211,9 @@ check_lcore_params(void) } static int -check_port_config(const unsigned nb_ports) +check_port_config(void) { - unsigned portid; + uint16_t portid; uint16_t i; for (i = 0; i < nb_lcore_params; ++i) { @@ -771,7 +222,7 @@ check_port_config(const unsigned nb_ports) printf("port %u is not enabled in port mask\n", portid); return -1; } - if (portid >= nb_ports) { + if (!rte_eth_dev_is_valid_port(portid)) { printf("port %u is not present on the board\n", portid); return -1; } @@ -780,14 +231,20 @@ check_port_config(const unsigned nb_ports) } static uint8_t -get_port_n_rx_queues(const uint8_t port) +get_port_n_rx_queues(const uint16_t port) { int queue = -1; uint16_t i; for (i = 0; i < nb_lcore_params; ++i) { - if (lcore_params[i].port_id == port && lcore_params[i].queue_id > queue) - queue = lcore_params[i].queue_id; + if (lcore_params[i].port_id == port) { + if (lcore_params[i].queue_id == queue+1) + queue = lcore_params[i].queue_id; + else + rte_exit(EXIT_FAILURE, "queue ids of the port %d must be" + " in sequence and must start with 0\n", + lcore_params[i].port_id); + } } return (uint8_t)(++queue); } @@ -820,19 +277,39 @@ init_lcore_rx_queues(void) static void print_usage(const char *prgname) { - printf ("%s [EAL options] -- -p PORTMASK -P" - " [--config (port,queue,lcore)[,(port,queue,lcore]]" - " [--enable-jumbo [--max-pkt-len PKTLEN]]\n" - " -p PORTMASK: hexadecimal bitmask of ports to configure\n" - " -P : enable promiscuous mode\n" - " --config (port,queue,lcore): rx queues configuration\n" - " --no-numa: optional, disable numa awareness\n" - " --enable-jumbo: enable jumbo frame" - " which max packet len is PKTLEN in decimal (64-9600)\n", + fprintf(stderr, "%s [EAL options] --" + " -p PORTMASK" + " [-P]" + " [-E]" + " [-L]" + " --config (port,queue,lcore)[,(port,queue,lcore)]" + " [--eth-dest=X,MM:MM:MM:MM:MM:MM]" + " [--enable-jumbo [--max-pkt-len PKTLEN]]" + " [--no-numa]" + " [--hash-entry-num]" + " [--ipv6]" + " [--parse-ptype]" + " [--per-port-pool]\n\n" + + " -p PORTMASK: Hexadecimal bitmask of ports to configure\n" + " -P : Enable promiscuous mode\n" + " -E : Enable exact match\n" + " -L : Enable longest prefix match (default)\n" + " --config (port,queue,lcore): Rx queue configuration\n" + " --eth-dest=X,MM:MM:MM:MM:MM:MM: Ethernet destination for port X\n" + " --enable-jumbo: Enable jumbo frames\n" + " --max-pkt-len: Under the premise of enabling jumbo,\n" + " maximum packet length in decimal (64-9600)\n" + " --no-numa: Disable numa awareness\n" + " --hash-entry-num: Specify the hash entry number in hexadecimal to be setup\n" + " --ipv6: Set if running ipv6 packets\n" + " --parse-ptype: Set to use software to analyze packet type\n" + " --per-port-pool: Use separate buffer pool per port\n\n", prgname); } -static int parse_max_pkt_len(const char *pktlen) +static int +parse_max_pkt_len(const char *pktlen) { char *end = NULL; unsigned long len; @@ -865,6 +342,22 @@ parse_portmask(const char *portmask) return pm; } +static int +parse_hash_entry_number(const char *hash_entry_num) +{ + char *end = NULL; + unsigned long hash_en; + /* parse hexadecimal string */ + hash_en = strtoul(hash_entry_num, &end, 16); + if ((hash_entry_num[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (hash_en == 0) + return -1; + + return hash_en; +} + static int parse_config(const char *q_arg) { @@ -893,7 +386,7 @@ parse_config(const char *q_arg) if(size >= sizeof(s)) return -1; - rte_snprintf(s, sizeof(s), "%.*s", size, p); + snprintf(s, sizeof(s), "%.*s", size, p); if (rte_strsplit(s, sizeof(s), str_fld, _NUM_FLD, ',') != _NUM_FLD) return -1; for (i = 0; i < _NUM_FLD; i++){ @@ -907,15 +400,106 @@ parse_config(const char *q_arg) nb_lcore_params); return -1; } - lcore_params_array[nb_lcore_params].port_id = (uint8_t)int_fld[FLD_PORT]; - lcore_params_array[nb_lcore_params].queue_id = (uint8_t)int_fld[FLD_QUEUE]; - lcore_params_array[nb_lcore_params].lcore_id = (uint8_t)int_fld[FLD_LCORE]; + lcore_params_array[nb_lcore_params].port_id = + (uint8_t)int_fld[FLD_PORT]; + lcore_params_array[nb_lcore_params].queue_id = + (uint8_t)int_fld[FLD_QUEUE]; + lcore_params_array[nb_lcore_params].lcore_id = + (uint8_t)int_fld[FLD_LCORE]; ++nb_lcore_params; } lcore_params = lcore_params_array; return 0; } +static void +parse_eth_dest(const char *optarg) +{ + uint16_t portid; + char *port_end; + uint8_t c, *dest, peer_addr[6]; + + errno = 0; + portid = strtoul(optarg, &port_end, 10); + if (errno != 0 || port_end == optarg || *port_end++ != ',') + rte_exit(EXIT_FAILURE, + "Invalid eth-dest: %s", optarg); + if (portid >= RTE_MAX_ETHPORTS) + rte_exit(EXIT_FAILURE, + "eth-dest: port %d >= RTE_MAX_ETHPORTS(%d)\n", + portid, RTE_MAX_ETHPORTS); + + if (cmdline_parse_etheraddr(NULL, port_end, + &peer_addr, sizeof(peer_addr)) < 0) + rte_exit(EXIT_FAILURE, + "Invalid ethernet address: %s\n", + port_end); + dest = (uint8_t *)&dest_eth_addr[portid]; + for (c = 0; c < 6; c++) + dest[c] = peer_addr[c]; + *(uint64_t *)(val_eth + portid) = dest_eth_addr[portid]; +} + +#define MAX_JUMBO_PKT_LEN 9600 +#define MEMPOOL_CACHE_SIZE 256 + +static const char short_options[] = + "p:" /* portmask */ + "P" /* promiscuous */ + "L" /* enable long prefix match */ + "E" /* enable exact match */ + ; + +#define CMD_LINE_OPT_CONFIG "config" +#define CMD_LINE_OPT_ETH_DEST "eth-dest" +#define CMD_LINE_OPT_NO_NUMA "no-numa" +#define CMD_LINE_OPT_IPV6 "ipv6" +#define CMD_LINE_OPT_ENABLE_JUMBO "enable-jumbo" +#define CMD_LINE_OPT_HASH_ENTRY_NUM "hash-entry-num" +#define CMD_LINE_OPT_PARSE_PTYPE "parse-ptype" +#define CMD_LINE_OPT_PER_PORT_POOL "per-port-pool" +enum { + /* long options mapped to a short option */ + + /* first long only option value must be >= 256, so that we won't + * conflict with short options */ + CMD_LINE_OPT_MIN_NUM = 256, + CMD_LINE_OPT_CONFIG_NUM, + CMD_LINE_OPT_ETH_DEST_NUM, + CMD_LINE_OPT_NO_NUMA_NUM, + CMD_LINE_OPT_IPV6_NUM, + CMD_LINE_OPT_ENABLE_JUMBO_NUM, + CMD_LINE_OPT_HASH_ENTRY_NUM_NUM, + CMD_LINE_OPT_PARSE_PTYPE_NUM, + CMD_LINE_OPT_PARSE_PER_PORT_POOL, +}; + +static const struct option lgopts[] = { + {CMD_LINE_OPT_CONFIG, 1, 0, CMD_LINE_OPT_CONFIG_NUM}, + {CMD_LINE_OPT_ETH_DEST, 1, 0, CMD_LINE_OPT_ETH_DEST_NUM}, + {CMD_LINE_OPT_NO_NUMA, 0, 0, CMD_LINE_OPT_NO_NUMA_NUM}, + {CMD_LINE_OPT_IPV6, 0, 0, CMD_LINE_OPT_IPV6_NUM}, + {CMD_LINE_OPT_ENABLE_JUMBO, 0, 0, CMD_LINE_OPT_ENABLE_JUMBO_NUM}, + {CMD_LINE_OPT_HASH_ENTRY_NUM, 1, 0, CMD_LINE_OPT_HASH_ENTRY_NUM_NUM}, + {CMD_LINE_OPT_PARSE_PTYPE, 0, 0, CMD_LINE_OPT_PARSE_PTYPE_NUM}, + {CMD_LINE_OPT_PER_PORT_POOL, 0, 0, CMD_LINE_OPT_PARSE_PER_PORT_POOL}, + {NULL, 0, 0, 0} +}; + +/* + * This expression is used to calculate the number of mbufs needed + * depending on user input, taking into account memory for rx and + * tx hardware rings, cache per lcore and mtable per port per lcore. + * RTE_MAX is used to ensure that NB_MBUF never goes below a minimum + * value of 8192 + */ +#define NB_MBUF(nports) RTE_MAX( \ + (nports*nb_rx_queue*nb_rxd + \ + nports*nb_lcores*MAX_PKT_BURST + \ + nports*n_tx_queue*nb_txd + \ + nb_lcores*MEMPOOL_CACHE_SIZE), \ + (unsigned)8192) + /* Parse the argument given in the command line of the application */ static int parse_args(int argc, char **argv) @@ -924,16 +508,11 @@ parse_args(int argc, char **argv) char **argvopt; int option_index; char *prgname = argv[0]; - static struct option lgopts[] = { - {"config", 1, 0, 0}, - {"no-numa", 0, 0, 0}, - {"enable-jumbo", 0, 0, 0}, - {NULL, 0, 0, 0} - }; argvopt = argv; - while ((opt = getopt_long(argc, argvopt, "p:P", + /* Error or normal output strings. */ + while ((opt = getopt_long(argc, argvopt, short_options, lgopts, &option_index)) != EOF) { switch (opt) { @@ -941,52 +520,91 @@ parse_args(int argc, char **argv) case 'p': enabled_port_mask = parse_portmask(optarg); if (enabled_port_mask == 0) { - printf("invalid portmask\n"); + fprintf(stderr, "Invalid portmask\n"); print_usage(prgname); return -1; } break; + case 'P': - printf("Promiscuous mode selected\n"); promiscuous_on = 1; break; + case 'E': + l3fwd_em_on = 1; + break; + + case 'L': + l3fwd_lpm_on = 1; + break; + /* long options */ - case 0: - if (!strncmp(lgopts[option_index].name, "config", 6)) { - ret = parse_config(optarg); - if (ret) { - printf("invalid config\n"); + case CMD_LINE_OPT_CONFIG_NUM: + ret = parse_config(optarg); + if (ret) { + fprintf(stderr, "Invalid config\n"); + print_usage(prgname); + return -1; + } + break; + + case CMD_LINE_OPT_ETH_DEST_NUM: + parse_eth_dest(optarg); + break; + + case CMD_LINE_OPT_NO_NUMA_NUM: + numa_on = 0; + break; + + case CMD_LINE_OPT_IPV6_NUM: + ipv6 = 1; + break; + + case CMD_LINE_OPT_ENABLE_JUMBO_NUM: { + const struct option lenopts = { + "max-pkt-len", required_argument, 0, 0 + }; + + port_conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME; + port_conf.txmode.offloads |= DEV_TX_OFFLOAD_MULTI_SEGS; + + /* + * if no max-pkt-len set, use the default + * value ETHER_MAX_LEN. + */ + if (getopt_long(argc, argvopt, "", + &lenopts, &option_index) == 0) { + ret = parse_max_pkt_len(optarg); + if (ret < 64 || ret > MAX_JUMBO_PKT_LEN) { + fprintf(stderr, + "invalid maximum packet length\n"); print_usage(prgname); return -1; } + port_conf.rxmode.max_rx_pkt_len = ret; } + break; + } - if (!strncmp(lgopts[option_index].name, "no-numa", 7)) { - printf("numa is disabled \n"); - numa_on = 0; - } - - if (!strncmp(lgopts[option_index].name, "enable-jumbo", 12)) { - struct option lenopts = {"max-pkt-len", required_argument, 0, 0}; - - printf("jumbo frame is enabled \n"); - port_conf.rxmode.jumbo_frame = 1; - - /* if no max-pkt-len set, use the default value ETHER_MAX_LEN */ - if (0 == getopt_long(argc, argvopt, "", &lenopts, &option_index)) { - ret = parse_max_pkt_len(optarg); - if ((ret < 64) || (ret > MAX_JUMBO_PKT_LEN)){ - printf("invalid packet length\n"); - print_usage(prgname); - return -1; - } - port_conf.rxmode.max_rx_pkt_len = ret; - } - printf("set jumbo frame max packet length to %u\n", - (unsigned int)port_conf.rxmode.max_rx_pkt_len); + case CMD_LINE_OPT_HASH_ENTRY_NUM_NUM: + ret = parse_hash_entry_number(optarg); + if ((ret > 0) && (ret <= L3FWD_HASH_ENTRIES)) { + hash_entry_number = ret; + } else { + fprintf(stderr, "invalid hash entry number\n"); + print_usage(prgname); + return -1; } - + break; + + case CMD_LINE_OPT_PARSE_PTYPE_NUM: + printf("soft parse-ptype is enabled\n"); + parse_ptype = 1; + break; + + case CMD_LINE_OPT_PARSE_PER_PORT_POOL: + printf("per port buffer pool is enabled\n"); + per_port_pool = 1; break; default: @@ -995,120 +613,49 @@ parse_args(int argc, char **argv) } } + /* If both LPM and EM are selected, return error. */ + if (l3fwd_lpm_on && l3fwd_em_on) { + fprintf(stderr, "LPM and EM are mutually exclusive, select only one\n"); + return -1; + } + + /* + * Nothing is selected, pick longest-prefix match + * as default match. + */ + if (!l3fwd_lpm_on && !l3fwd_em_on) { + fprintf(stderr, "LPM or EM none selected, default LPM on\n"); + l3fwd_lpm_on = 1; + } + + /* + * ipv6 and hash flags are valid only for + * exact macth, reset them to default for + * longest-prefix match. + */ + if (l3fwd_lpm_on) { + ipv6 = 0; + hash_entry_number = HASH_ENTRY_NUMBER_DEFAULT; + } + if (optind >= 0) 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, const 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]); -} - -#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) -static void -setup_hash(int socketid) +print_ethaddr(const char *name, const struct rte_ether_addr *eth_addr) { - unsigned i; - int ret; - char s[64]; - - /* create ipv4 hash */ - rte_snprintf(s, sizeof(s), "ipv4_l3fwd_hash_%d", socketid); - ipv4_l3fwd_hash_params.name = s; - ipv4_l3fwd_hash_params.socket_id = socketid; - ipv4_l3fwd_lookup_struct[socketid] = rte_hash_create(&ipv4_l3fwd_hash_params); - if (ipv4_l3fwd_lookup_struct[socketid] == NULL) - rte_exit(EXIT_FAILURE, "Unable to create the l3fwd hash on " - "socket %d\n", socketid); - - /* create ipv6 hash */ - rte_snprintf(s, sizeof(s), "ipv6_l3fwd_hash_%d", socketid); - ipv6_l3fwd_hash_params.name = s; - ipv6_l3fwd_hash_params.socket_id = socketid; - ipv6_l3fwd_lookup_struct[socketid] = rte_hash_create(&ipv6_l3fwd_hash_params); - if (ipv6_l3fwd_lookup_struct[socketid] == NULL) - rte_exit(EXIT_FAILURE, "Unable to create the l3fwd hash on " - "socket %d\n", socketid); - - - /* populate the ipv4 hash */ - for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) { - ret = rte_hash_add_key (ipv4_l3fwd_lookup_struct[socketid], - (void *) &ipv4_l3fwd_route_array[i].key); - if (ret < 0) { - rte_exit(EXIT_FAILURE, "Unable to add entry %u to the" - "l3fwd hash on socket %d\n", i, socketid); - } - ipv4_l3fwd_out_if[ret] = ipv4_l3fwd_route_array[i].if_out; - printf("Hash: Adding key\n"); - print_ipv4_key(ipv4_l3fwd_route_array[i].key); - } - - /* populate the ipv6 hash */ - for (i = 0; i < IPV6_L3FWD_NUM_ROUTES; i++) { - ret = rte_hash_add_key (ipv6_l3fwd_lookup_struct[socketid], - (void *) &ipv6_l3fwd_route_array[i].key); - if (ret < 0) { - rte_exit(EXIT_FAILURE, "Unable to add entry %u to the" - "l3fwd hash on socket %d\n", i, socketid); - } - ipv6_l3fwd_out_if[ret] = ipv6_l3fwd_route_array[i].if_out; - printf("Hash: Adding key\n"); - print_ipv6_key(ipv6_l3fwd_route_array[i].key); - } + char buf[ETHER_ADDR_FMT_SIZE]; + ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, eth_addr); + printf("%s%s", name, buf); } -#endif - -#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) -static void -setup_lpm(int socketid) -{ - unsigned i; - int ret; - char s[64]; - - /* create the LPM table */ - rte_snprintf(s, sizeof(s), "IPV4_L3FWD_LPM_%d", socketid); - ipv4_l3fwd_lookup_struct[socketid] = rte_lpm_create(s, socketid, - IPV4_L3FWD_LPM_MAX_RULES, 0); - if (ipv4_l3fwd_lookup_struct[socketid] == NULL) - rte_exit(EXIT_FAILURE, "Unable to create the l3fwd LPM table" - " on socket %d\n", socketid); - - /* populate the LPM table */ - for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) { - ret = rte_lpm_add(ipv4_l3fwd_lookup_struct[socketid], - ipv4_l3fwd_route_array[i].ip, - ipv4_l3fwd_route_array[i].depth, - ipv4_l3fwd_route_array[i].if_out); - - if (ret < 0) { - rte_exit(EXIT_FAILURE, "Unable to add entry %u to the " - "l3fwd LPM table on socket %d\n", - i, socketid); - } - - printf("LPM: Adding route 0x%08x / %d (%d)\n", - (unsigned)ipv4_l3fwd_route_array[i].ip, - ipv4_l3fwd_route_array[i].depth, - ipv4_l3fwd_route_array[i].if_out); - } -} -#endif static int -init_mem(unsigned nb_mbuf) +init_mem(uint16_t portid, unsigned int nb_mbuf) { struct lcore_conf *qconf; int socketid; @@ -1125,52 +672,62 @@ init_mem(unsigned nb_mbuf) socketid = 0; if (socketid >= NB_SOCKETS) { - rte_exit(EXIT_FAILURE, "Socket %d of lcore %u is out of range %d\n", + rte_exit(EXIT_FAILURE, + "Socket %d of lcore %u is out of range %d\n", socketid, lcore_id, NB_SOCKETS); } - if (pktmbuf_pool[socketid] == NULL) { - rte_snprintf(s, sizeof(s), "mbuf_pool_%d", socketid); - pktmbuf_pool[socketid] = - rte_mempool_create(s, nb_mbuf, MBUF_SIZE, MEMPOOL_CACHE_SIZE, - sizeof(struct rte_pktmbuf_pool_private), - rte_pktmbuf_pool_init, NULL, - rte_pktmbuf_init, NULL, - socketid, 0); - if (pktmbuf_pool[socketid] == NULL) + + if (pktmbuf_pool[portid][socketid] == NULL) { + snprintf(s, sizeof(s), "mbuf_pool_%d:%d", + portid, socketid); + pktmbuf_pool[portid][socketid] = + rte_pktmbuf_pool_create(s, nb_mbuf, + MEMPOOL_CACHE_SIZE, 0, + RTE_MBUF_DEFAULT_BUF_SIZE, socketid); + if (pktmbuf_pool[portid][socketid] == NULL) rte_exit(EXIT_FAILURE, - "Cannot init mbuf pool on socket %d\n", socketid); + "Cannot init mbuf pool on socket %d\n", + socketid); else - printf("Allocated mbuf pool on socket %d\n", socketid); + printf("Allocated mbuf pool on socket %d\n", + socketid); -#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM) - setup_lpm(socketid); -#else - setup_hash(socketid); -#endif + /* Setup either LPM or EM(f.e Hash). But, only once per + * available socket. + */ + if (!lkp_per_socket[socketid]) { + l3fwd_lkp.setup(socketid); + lkp_per_socket[socketid] = 1; + } } qconf = &lcore_conf[lcore_id]; - qconf->ipv4_lookup_struct = ipv4_l3fwd_lookup_struct[socketid]; -#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH) - qconf->ipv6_lookup_struct = ipv6_l3fwd_lookup_struct[socketid]; -#endif + qconf->ipv4_lookup_struct = + l3fwd_lkp.get_ipv4_lookup_struct(socketid); + qconf->ipv6_lookup_struct = + l3fwd_lkp.get_ipv6_lookup_struct(socketid); } return 0; } /* 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(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"); 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++) { + RTE_ETH_FOREACH_DEV(portid) { + if (force_quit) + return; if ((port_mask & (1 << portid)) == 0) continue; memset(&link, 0, sizeof(link)); @@ -1178,18 +735,17 @@ 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; } @@ -1212,16 +768,50 @@ check_all_ports_link_status(uint8_t port_num, uint32_t port_mask) } } +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 int +prepare_ptype_parser(uint16_t portid, uint16_t queueid) +{ + if (parse_ptype) { + printf("Port %d: softly parse packet type info\n", portid); + if (rte_eth_add_rx_callback(portid, queueid, + l3fwd_lkp.cb_parse_ptype, + NULL)) + return 1; + + printf("Failed to add rx callback: port=%d\n", portid); + return 0; + } + + if (l3fwd_lkp.check_ptype(portid)) + return 1; + + printf("port %d cannot parse packet type, please add --%s\n", + portid, CMD_LINE_OPT_PARSE_PTYPE); + return 0; +} + int -MAIN(int argc, char **argv) +main(int argc, char **argv) { struct lcore_conf *qconf; + struct rte_eth_dev_info dev_info; + struct rte_eth_txconf *txconf; int ret; unsigned nb_ports; - uint16_t queueid; + uint16_t queueid, portid; unsigned lcore_id; uint32_t n_tx_queue, nb_lcores; - uint8_t portid, nb_rx_queue, queue, socketid; + uint8_t nb_rx_queue, queue, socketid; /* init EAL */ ret = rte_eal_init(argc, argv); @@ -1230,6 +820,17 @@ MAIN(int argc, char **argv) argc -= ret; argv += ret; + force_quit = false; + signal(SIGINT, signal_handler); + signal(SIGTERM, signal_handler); + + /* pre-init dst MACs for all ports to 02:00:00:00:00:xx */ + for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) { + dest_eth_addr[portid] = + ETHER_LOCAL_ADMIN_ADDR + ((uint64_t)portid << 40); + *(uint64_t *)(val_eth + portid) = dest_eth_addr[portid]; + } + /* parse application arguments (after the EAL ones) */ ret = parse_args(argc, argv); if (ret < 0) @@ -1242,25 +843,20 @@ MAIN(int argc, char **argv) if (ret < 0) rte_exit(EXIT_FAILURE, "init_lcore_rx_queues failed\n"); + nb_ports = rte_eth_dev_count_avail(); - /* init driver(s) */ - if (rte_pmd_init_all() < 0) - rte_exit(EXIT_FAILURE, "Cannot init pmd\n"); - - if (rte_eal_pci_probe() < 0) - rte_exit(EXIT_FAILURE, "Cannot probe PCI\n"); - - nb_ports = rte_eth_dev_count(); - if (nb_ports > RTE_MAX_ETHPORTS) - nb_ports = RTE_MAX_ETHPORTS; - - if (check_port_config(nb_ports) < 0) + if (check_port_config() < 0) rte_exit(EXIT_FAILURE, "check_port_config failed\n"); nb_lcores = rte_lcore_count(); + /* Setup function pointers for lookup method. */ + setup_l3fwd_lookup_tables(); + /* initialize all ports */ - for (portid = 0; portid < nb_ports; portid++) { + RTE_ETH_FOREACH_DEV(portid) { + struct rte_eth_conf local_port_conf = port_conf; + /* skip ports that are not enabled */ if ((enabled_port_mask & (1 << portid)) == 0) { printf("\nSkipping disabled port %d\n", portid); @@ -1277,18 +873,59 @@ MAIN(int argc, char **argv) n_tx_queue = MAX_TX_QUEUE_PER_PORT; printf("Creating queues: nb_rxq=%d nb_txq=%u... ", nb_rx_queue, (unsigned)n_tx_queue ); + + rte_eth_dev_info_get(portid, &dev_info); + if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE) + local_port_conf.txmode.offloads |= + DEV_TX_OFFLOAD_MBUF_FAST_FREE; + + local_port_conf.rx_adv_conf.rss_conf.rss_hf &= + dev_info.flow_type_rss_offloads; + if (local_port_conf.rx_adv_conf.rss_conf.rss_hf != + port_conf.rx_adv_conf.rss_conf.rss_hf) { + printf("Port %u modified RSS hash function based on hardware support," + "requested:%#"PRIx64" configured:%#"PRIx64"\n", + portid, + port_conf.rx_adv_conf.rss_conf.rss_hf, + local_port_conf.rx_adv_conf.rss_conf.rss_hf); + } + ret = rte_eth_dev_configure(portid, nb_rx_queue, - (uint16_t)n_tx_queue, &port_conf); + (uint16_t)n_tx_queue, &local_port_conf); if (ret < 0) - rte_exit(EXIT_FAILURE, "Cannot configure device: err=%d, port=%d\n", + rte_exit(EXIT_FAILURE, + "Cannot configure device: err=%d, port=%d\n", ret, portid); + ret = rte_eth_dev_adjust_nb_rx_tx_desc(portid, &nb_rxd, + &nb_txd); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "Cannot adjust number of descriptors: err=%d, " + "port=%d\n", ret, portid); + rte_eth_macaddr_get(portid, &ports_eth_addr[portid]); print_ethaddr(" Address:", &ports_eth_addr[portid]); printf(", "); + print_ethaddr("Destination:", + (const struct rte_ether_addr *)&dest_eth_addr[portid]); + printf(", "); + + /* + * prepare src MACs for each port. + */ + ether_addr_copy(&ports_eth_addr[portid], + (struct rte_ether_addr *)(val_eth + portid) + 1); /* init memory */ - ret = init_mem(NB_MBUF); + if (!per_port_pool) { + /* portid = 0; this is *not* signifying the first port, + * rather, it signifies that portid is ignored. + */ + ret = init_mem(0, NB_MBUF(nb_ports)); + } else { + ret = init_mem(portid, NB_MBUF(1)); + } if (ret < 0) rte_exit(EXIT_FAILURE, "init_mem failed\n"); @@ -1299,21 +936,29 @@ MAIN(int argc, char **argv) continue; if (numa_on) - socketid = (uint8_t)rte_lcore_to_socket_id(lcore_id); + socketid = + (uint8_t)rte_lcore_to_socket_id(lcore_id); else socketid = 0; printf("txq=%u,%d,%d ", lcore_id, queueid, socketid); fflush(stdout); + + txconf = &dev_info.default_txconf; + txconf->offloads = local_port_conf.txmode.offloads; ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd, - socketid, &tx_conf); + socketid, txconf); if (ret < 0) - rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup: err=%d, " + rte_exit(EXIT_FAILURE, + "rte_eth_tx_queue_setup: err=%d, " "port=%d\n", ret, portid); qconf = &lcore_conf[lcore_id]; qconf->tx_queue_id[portid] = queueid; queueid++; + + qconf->tx_port_id[qconf->n_tx_port] = portid; + qconf->n_tx_port++; } printf("\n"); } @@ -1326,36 +971,56 @@ MAIN(int argc, char **argv) fflush(stdout); /* init RX queues */ for(queue = 0; queue < qconf->n_rx_queue; ++queue) { + struct rte_eth_dev *dev; + struct rte_eth_conf *conf; + struct rte_eth_rxconf rxq_conf; + portid = qconf->rx_queue_list[queue].port_id; queueid = qconf->rx_queue_list[queue].queue_id; + dev = &rte_eth_devices[portid]; + conf = &dev->data->dev_conf; if (numa_on) - socketid = (uint8_t)rte_lcore_to_socket_id(lcore_id); + socketid = + (uint8_t)rte_lcore_to_socket_id(lcore_id); else socketid = 0; printf("rxq=%d,%d,%d ", portid, queueid, socketid); fflush(stdout); - ret = rte_eth_rx_queue_setup(portid, queueid, nb_rxd, - socketid, &rx_conf, pktmbuf_pool[socketid]); + rte_eth_dev_info_get(portid, &dev_info); + rxq_conf = dev_info.default_rxconf; + rxq_conf.offloads = conf->rxmode.offloads; + if (!per_port_pool) + ret = rte_eth_rx_queue_setup(portid, queueid, + nb_rxd, socketid, + &rxq_conf, + pktmbuf_pool[0][socketid]); + else + ret = rte_eth_rx_queue_setup(portid, queueid, + nb_rxd, socketid, + &rxq_conf, + pktmbuf_pool[portid][socketid]); if (ret < 0) - rte_exit(EXIT_FAILURE, "rte_eth_rx_queue_setup: err=%d," - "port=%d\n", ret, portid); + rte_exit(EXIT_FAILURE, + "rte_eth_rx_queue_setup: err=%d, port=%d\n", + ret, portid); } } printf("\n"); /* start ports */ - for (portid = 0; portid < nb_ports; portid++) { + RTE_ETH_FOREACH_DEV(portid) { if ((enabled_port_mask & (1 << portid)) == 0) { continue; } /* Start device */ ret = rte_eth_dev_start(portid); if (ret < 0) - rte_exit(EXIT_FAILURE, "rte_eth_dev_start: err=%d, port=%d\n", + rte_exit(EXIT_FAILURE, + "rte_eth_dev_start: err=%d, port=%d\n", ret, portid); /* @@ -1368,14 +1033,43 @@ MAIN(int argc, char **argv) rte_eth_promiscuous_enable(portid); } - check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask); + printf("\n"); + + for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) { + if (rte_lcore_is_enabled(lcore_id) == 0) + continue; + qconf = &lcore_conf[lcore_id]; + for (queue = 0; queue < qconf->n_rx_queue; ++queue) { + portid = qconf->rx_queue_list[queue].port_id; + queueid = qconf->rx_queue_list[queue].queue_id; + if (prepare_ptype_parser(portid, queueid) == 0) + rte_exit(EXIT_FAILURE, "ptype check fails\n"); + } + } + + check_all_ports_link_status(enabled_port_mask); + + ret = 0; /* launch per-lcore init on every lcore */ - rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER); + rte_eal_mp_remote_launch(l3fwd_lkp.main_loop, NULL, CALL_MASTER); RTE_LCORE_FOREACH_SLAVE(lcore_id) { - if (rte_eal_wait_lcore(lcore_id) < 0) - return -1; + if (rte_eal_wait_lcore(lcore_id) < 0) { + ret = -1; + break; + } } - return 0; + /* stop ports */ + RTE_ETH_FOREACH_DEV(portid) { + if ((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; }