examples/ipv4_multicast/main.c

/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2014 Intel Corporation
 */
 
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <inttypes.h>
#include <sys/types.h>
#include <string.h>
#include <sys/queue.h>
#include <stdarg.h>
#include <errno.h>
#include <getopt.h>
 
#include <rte_common.h>
#include <rte_byteorder.h>
#include <rte_log.h>
#include <rte_memory.h>
#include <rte_memcpy.h>
#include <rte_eal.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_random.h>
#include <rte_debug.h>
#include <rte_ether.h>
#include <rte_ethdev.h>
#include <rte_mempool.h>
#include <rte_mbuf.h>
#include <rte_malloc.h>
#include <rte_fbk_hash.h>
#include <rte_ip.h>
 
#define RTE_LOGTYPE_IPv4_MULTICAST RTE_LOGTYPE_USER1
 
#define MAX_PORTS 16
 
#define MCAST_CLONE_PORTS   2
#define MCAST_CLONE_SEGS    2
 
#define PKT_MBUF_DATA_SIZE  RTE_MBUF_DEFAULT_BUF_SIZE
#define NB_PKT_MBUF 8192
 
#define HDR_MBUF_DATA_SIZE  (2 * RTE_PKTMBUF_HEADROOM)
#define NB_HDR_MBUF (NB_PKT_MBUF * MAX_PORTS)
 
#define NB_CLONE_MBUF   (NB_PKT_MBUF * MCAST_CLONE_PORTS * MCAST_CLONE_SEGS * 2)
 
/* allow max jumbo frame 9.5 KB */
#define JUMBO_FRAME_MAX_SIZE    0x2600
 
#define MAX_PKT_BURST 32
#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */
 
/* Configure how many packets ahead to prefetch, when reading packets */
#define PREFETCH_OFFSET 3
 
/*
 * Construct Ethernet multicast address from IPv4 multicast address.
 * Citing RFC 1112, section 6.4:
 * "An IP host group address is mapped to an Ethernet multicast address
 * by placing the low-order 23-bits of the IP address into the low-order
 * 23 bits of the Ethernet multicast address 01-00-5E-00-00-00 (hex)."
 */
#define ETHER_ADDR_FOR_IPV4_MCAST(x)    \
    (rte_cpu_to_be_64(0x01005e000000ULL | ((x) & 0x7fffff)) >> 16)
 
/*
 * Configurable number of RX/TX ring descriptors
 */
#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;
 
/* ethernet addresses of ports */
static struct rte_ether_addr ports_eth_addr[MAX_PORTS];
 
/* mask of enabled ports */
static uint32_t enabled_port_mask = 0;
 
static uint16_t nb_ports;
 
static int rx_queue_per_lcore = 1;
 
struct mbuf_table {
    uint16_t len;
    struct rte_mbuf *m_table[MAX_PKT_BURST];
};
 
#define MAX_RX_QUEUE_PER_LCORE 16
#define MAX_TX_QUEUE_PER_PORT 16
struct lcore_queue_conf {
    uint64_t tx_tsc;
    uint16_t n_rx_queue;
    uint8_t rx_queue_list[MAX_RX_QUEUE_PER_LCORE];
    uint16_t tx_queue_id[MAX_PORTS];
    struct mbuf_table tx_mbufs[MAX_PORTS];
} __rte_cache_aligned;
static struct lcore_queue_conf lcore_queue_conf[RTE_MAX_LCORE];
 
static struct rte_eth_conf port_conf = {
    .rxmode = {
        .max_rx_pkt_len = JUMBO_FRAME_MAX_SIZE,
        .split_hdr_size = 0,
        .offloads = DEV_RX_OFFLOAD_JUMBO_FRAME,
    },
    .txmode = {
        .mq_mode = ETH_MQ_TX_NONE,
        .offloads = DEV_TX_OFFLOAD_MULTI_SEGS,
    },
};
 
static struct rte_mempool *packet_pool, *header_pool, *clone_pool;
 
 
/* Multicast */
static struct rte_fbk_hash_params mcast_hash_params = {
    .name = "MCAST_HASH",
    .entries = 1024,
    .entries_per_bucket = 4,
    .socket_id = 0,
    .hash_func = NULL,
    .init_val = 0,
};
 
struct rte_fbk_hash_table *mcast_hash = NULL;
 
struct mcast_group_params {
    uint32_t ip;
    uint16_t port_mask;
};
 
static struct mcast_group_params mcast_group_table[] = {
        {RTE_IPV4(224,0,0,101), 0x1},
        {RTE_IPV4(224,0,0,102), 0x2},
        {RTE_IPV4(224,0,0,103), 0x3},
        {RTE_IPV4(224,0,0,104), 0x4},
        {RTE_IPV4(224,0,0,105), 0x5},
        {RTE_IPV4(224,0,0,106), 0x6},
        {RTE_IPV4(224,0,0,107), 0x7},
        {RTE_IPV4(224,0,0,108), 0x8},
        {RTE_IPV4(224,0,0,109), 0x9},
        {RTE_IPV4(224,0,0,110), 0xA},
        {RTE_IPV4(224,0,0,111), 0xB},
        {RTE_IPV4(224,0,0,112), 0xC},
        {RTE_IPV4(224,0,0,113), 0xD},
        {RTE_IPV4(224,0,0,114), 0xE},
        {RTE_IPV4(224,0,0,115), 0xF},
};
 
/* Send burst of packets on an output interface */
static void
send_burst(struct lcore_queue_conf *qconf, uint16_t port)
{
    struct rte_mbuf **m_table;
    uint16_t n, queueid;
    int ret;
 
    queueid = qconf->tx_queue_id[port];
    m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table;
    n = qconf->tx_mbufs[port].len;
 
    ret = rte_eth_tx_burst(port, queueid, m_table, n);
    while (unlikely (ret < n)) {
        rte_pktmbuf_free(m_table[ret]);
        ret++;
    }
 
    qconf->tx_mbufs[port].len = 0;
}
 
/* Get number of bits set. */
static inline uint32_t
bitcnt(uint32_t v)
{
    uint32_t n;
 
    for (n = 0; v != 0; v &= v - 1, n++)
        ;
 
    return n;
}
 
static inline struct rte_mbuf *
mcast_out_pkt(struct rte_mbuf *pkt, int use_clone)
{
    struct rte_mbuf *hdr;
 
    /* Create new mbuf for the header. */
    if (unlikely ((hdr = rte_pktmbuf_alloc(header_pool)) == NULL))
        return NULL;
 
    /* If requested, then make a new clone packet. */
    if (use_clone != 0 &&
        unlikely ((pkt = rte_pktmbuf_clone(pkt, clone_pool)) == NULL)) {
        rte_pktmbuf_free(hdr);
        return NULL;
    }
 
    /* prepend new header */
    hdr->next = pkt;
 
    /* update header's fields */
    hdr->pkt_len = (uint16_t)(hdr->data_len + pkt->pkt_len);
    hdr->nb_segs = pkt->nb_segs + 1;
 
    __rte_mbuf_sanity_check(hdr, 1);
    return hdr;
}
 
/*
 * Write new Ethernet header to the outgoing packet,
 * and put it into the outgoing queue for the given port.
 */
static inline void
mcast_send_pkt(struct rte_mbuf *pkt, struct rte_ether_addr *dest_addr,
        struct lcore_queue_conf *qconf, uint16_t port)
{
    struct rte_ether_hdr *ethdr;
    uint16_t len;
 
    /* Construct Ethernet header. */
    ethdr = (struct rte_ether_hdr *)
        rte_pktmbuf_prepend(pkt, (uint16_t)sizeof(*ethdr));
    RTE_ASSERT(ethdr != NULL);
 
    rte_ether_addr_copy(dest_addr, &ethdr->d_addr);
    rte_ether_addr_copy(&ports_eth_addr[port], &ethdr->s_addr);
    ethdr->ether_type = rte_be_to_cpu_16(RTE_ETHER_TYPE_IPV4);
 
    /* Put new packet into the output queue */
    len = qconf->tx_mbufs[port].len;
    qconf->tx_mbufs[port].m_table[len] = pkt;
    qconf->tx_mbufs[port].len = ++len;
 
    /* Transmit packets */
    if (unlikely(MAX_PKT_BURST == len))
        send_burst(qconf, port);
}
 
/* Multicast forward of the input packet */
static inline void
mcast_forward(struct rte_mbuf *m, struct lcore_queue_conf *qconf)
{
    struct rte_mbuf *mc;
    struct rte_ipv4_hdr *iphdr;
    uint32_t dest_addr, port_mask, port_num, use_clone;
    int32_t hash;
    uint16_t port;
    union {
        uint64_t as_int;
        struct rte_ether_addr as_addr;
    } dst_eth_addr;
 
    /* Remove the Ethernet header from the input packet */
    iphdr = (struct rte_ipv4_hdr *)
        rte_pktmbuf_adj(m, (uint16_t)sizeof(struct rte_ether_hdr));
    RTE_ASSERT(iphdr != NULL);
 
    dest_addr = rte_be_to_cpu_32(iphdr->dst_addr);
 
    /*
     * Check that it is a valid multicast address and
     * we have some active ports assigned to it.
     */
    if (!RTE_IS_IPV4_MCAST(dest_addr) ||
        (hash = rte_fbk_hash_lookup(mcast_hash, dest_addr)) <= 0 ||
        (port_mask = hash & enabled_port_mask) == 0) {
        rte_pktmbuf_free(m);
        return;
    }
 
    /* Calculate number of destination ports. */
    port_num = bitcnt(port_mask);
 
    /* Should we use rte_pktmbuf_clone() or not. */
    use_clone = (port_num <= MCAST_CLONE_PORTS &&
        m->nb_segs <= MCAST_CLONE_SEGS);
 
    /* Mark all packet's segments as referenced port_num times */
    if (use_clone == 0)
        rte_pktmbuf_refcnt_update(m, (uint16_t)port_num);
 
    /* construct destination ethernet address */
    dst_eth_addr.as_int = ETHER_ADDR_FOR_IPV4_MCAST(dest_addr);
 
    for (port = 0; use_clone != port_mask; port_mask >>= 1, port++) {
 
        /* Prepare output packet and send it out. */
        if ((port_mask & 1) != 0) {
            if (likely ((mc = mcast_out_pkt(m, use_clone)) != NULL))
                mcast_send_pkt(mc, &dst_eth_addr.as_addr,
                        qconf, port);
            else if (use_clone == 0)
                rte_pktmbuf_free(m);
        }
    }
 
    /*
     * If we making clone packets, then, for the last destination port,
     * we can overwrite input packet's metadata.
     */
    if (use_clone != 0)
        mcast_send_pkt(m, &dst_eth_addr.as_addr, qconf, port);
    else
        rte_pktmbuf_free(m);
}
 
/* Send burst of outgoing packet, if timeout expires. */
static inline void
send_timeout_burst(struct lcore_queue_conf *qconf)
{
    uint64_t cur_tsc;
    uint16_t portid;
    const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US;
 
    cur_tsc = rte_rdtsc();
    if (likely (cur_tsc < qconf->tx_tsc + drain_tsc))
        return;
 
    for (portid = 0; portid < MAX_PORTS; portid++) {
        if (qconf->tx_mbufs[portid].len != 0)
            send_burst(qconf, portid);
    }
    qconf->tx_tsc = cur_tsc;
}
 
/* main processing loop */
static int
main_loop(__rte_unused void *dummy)
{
    struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
    unsigned lcore_id;
    int i, j, nb_rx;
    uint16_t portid;
    struct lcore_queue_conf *qconf;
 
    lcore_id = rte_lcore_id();
    qconf = &lcore_queue_conf[lcore_id];
 
 
    if (qconf->n_rx_queue == 0) {
        RTE_LOG(INFO, IPv4_MULTICAST, "lcore %u has nothing to do\n",
            lcore_id);
        return 0;
    }
 
    RTE_LOG(INFO, IPv4_MULTICAST, "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, IPv4_MULTICAST, " -- lcoreid=%u portid=%d\n",
            lcore_id, portid);
    }
 
    while (1) {
 
        /*
         * 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(portid, 0, 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 *));
                mcast_forward(pkts_burst[j], qconf);
            }
 
            /* Forward remaining prefetched packets */
            for (; j < nb_rx; j++) {
                mcast_forward(pkts_burst[j], qconf);
            }
        }
 
        /* Send out packets from TX queues */
        send_timeout_burst(qconf);
    }
}
 
/* display usage */
static void
print_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",
        prgname);
}
 
static uint32_t
parse_portmask(const char *portmask)
{
    char *end = NULL;
    unsigned long pm;
 
    /* pars