/*-
* BSD LICENSE
*
- * Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
#include <ctype.h>
#include <errno.h>
#include <getopt.h>
+#include <signal.h>
+#include <stdbool.h>
#include <rte_common.h>
#include <rte_log.h>
+#include <rte_malloc.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_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"
+static volatile bool force_quit;
+
+/* MAC updating enabled by default */
+static int mac_updating = 1;
#define RTE_LOGTYPE_L2FWD RTE_LOGTYPE_USER1
-#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_US 100 /* TX drain every ~100us */
+#define MEMPOOL_CACHE_SIZE 256
/*
* Configurable number of RX/TX ring descriptors
static unsigned int l2fwd_rx_queue_per_lcore = 1;
-struct mbuf_table {
- unsigned 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 {
unsigned n_rx_port;
unsigned rx_port_list[MAX_RX_QUEUE_PER_LCORE];
- struct mbuf_table tx_mbufs[RTE_MAX_ETHPORTS];
-
} __rte_cache_aligned;
struct lcore_queue_conf lcore_queue_conf[RTE_MAX_LCORE];
+static struct rte_eth_dev_tx_buffer *tx_buffer[RTE_MAX_ETHPORTS];
+
static const struct rte_eth_conf port_conf = {
.rxmode = {
.split_hdr_size = 0,
.hw_ip_checksum = 0, /**< IP checksum offload disabled */
.hw_vlan_filter = 0, /**< VLAN filtering disabled */
.jumbo_frame = 0, /**< Jumbo Frame Support disabled */
- .hw_strip_crc = 0, /**< CRC stripped by hardware */
+ .hw_strip_crc = 1, /**< CRC stripped by hardware */
},
.txmode = {
.mq_mode = ETH_MQ_TX_NONE,
},
};
-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 */
- /*
- * As the example won't handle mult-segments and offload cases,
- * set the flag by default.
- */
- .txq_flags = ETH_TXQ_FLAGS_NOMULTSEGS | ETH_TXQ_FLAGS_NOOFFLOADS,
-};
-
struct rte_mempool * l2fwd_pktmbuf_pool = NULL;
/* Per-port statistics struct */
} __rte_cache_aligned;
struct l2fwd_port_statistics port_statistics[RTE_MAX_ETHPORTS];
-/* A tsc-based timer responsible for triggering statistics printout */
-#define TIMER_MILLISECOND 2000000ULL /* around 1ms at 2 Ghz */
#define MAX_TIMER_PERIOD 86400 /* 1 day max */
-static int64_t timer_period = 10 * TIMER_MILLISECOND * 1000; /* default period is 10 seconds */
+/* A tsc-based timer responsible for triggering statistics printout */
+static uint64_t timer_period = 10; /* default period is 10 seconds */
/* Print out statistics on packets dropped */
static void
printf("\n====================================================\n");
}
-/* Send the burst of packets 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 =0;
-
- 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;
-}
-
-/* Enqueue packets for TX and prepare them to be sent */
-static int
-l2fwd_send_packet(struct rte_mbuf *m, uint8_t port)
+static void
+l2fwd_mac_updating(struct rte_mbuf *m, unsigned dest_portid)
{
- unsigned lcore_id, len;
- struct lcore_queue_conf *qconf;
+ struct ether_hdr *eth;
+ void *tmp;
- lcore_id = rte_lcore_id();
+ eth = rte_pktmbuf_mtod(m, struct ether_hdr *);
- 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;
- }
+ /* 02:00:00:00:00:xx */
+ tmp = ð->d_addr.addr_bytes[0];
+ *((uint64_t *)tmp) = 0x000000000002 + ((uint64_t)dest_portid << 40);
- qconf->tx_mbufs[port].len = len;
- return 0;
+ /* src addr */
+ ether_addr_copy(&l2fwd_ports_eth_addr[dest_portid], ð->s_addr);
}
static void
l2fwd_simple_forward(struct rte_mbuf *m, unsigned portid)
{
- struct ether_hdr *eth;
- void *tmp;
unsigned dst_port;
+ int sent;
+ struct rte_eth_dev_tx_buffer *buffer;
dst_port = l2fwd_dst_ports[portid];
- eth = rte_pktmbuf_mtod(m, struct ether_hdr *);
- /* 02:00:00:00:00:xx */
- tmp = ð->d_addr.addr_bytes[0];
- *((uint64_t *)tmp) = 0x000000000002 + ((uint64_t)dst_port << 40);
-
- /* src addr */
- ether_addr_copy(&l2fwd_ports_eth_addr[dst_port], ð->s_addr);
+ if (mac_updating)
+ l2fwd_mac_updating(m, dst_port);
- l2fwd_send_packet(m, (uint8_t) dst_port);
+ buffer = tx_buffer[dst_port];
+ sent = rte_eth_tx_buffer(dst_port, 0, buffer, m);
+ if (sent)
+ port_statistics[dst_port].tx += sent;
}
/* main processing loop */
{
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
struct rte_mbuf *m;
+ int sent;
unsigned lcore_id;
uint64_t prev_tsc, diff_tsc, cur_tsc, timer_tsc;
unsigned i, j, portid, nb_rx;
struct lcore_queue_conf *qconf;
- const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US;
+ const uint64_t drain_tsc = (rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S *
+ BURST_TX_DRAIN_US;
+ struct rte_eth_dev_tx_buffer *buffer;
prev_tsc = 0;
timer_tsc = 0;
portid = qconf->rx_port_list[i];
RTE_LOG(INFO, L2FWD, " -- lcoreid=%u portid=%u\n", lcore_id,
portid);
+
}
- while (1) {
+ while (!force_quit) {
cur_tsc = rte_rdtsc();
diff_tsc = cur_tsc - prev_tsc;
if (unlikely(diff_tsc > drain_tsc)) {
- for (portid = 0; portid < RTE_MAX_ETHPORTS; 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;
+ for (i = 0; i < qconf->n_rx_port; i++) {
+
+ portid = l2fwd_dst_ports[qconf->rx_port_list[i]];
+ buffer = tx_buffer[portid];
+
+ sent = rte_eth_tx_buffer_flush(portid, 0, buffer);
+ if (sent)
+ port_statistics[portid].tx += sent;
+
}
/* if timer is enabled */
timer_tsc += diff_tsc;
/* if timer has reached its timeout */
- if (unlikely(timer_tsc >= (uint64_t) timer_period)) {
+ if (unlikely(timer_tsc >= timer_period)) {
/* do this only on master core */
if (lcore_id == rte_get_master_lcore()) {
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",
+ " -T PERIOD: statistics will be refreshed each PERIOD seconds (0 to disable, 10 default, 86400 maximum)\n"
+ " --[no-]mac-updating: Enable or disable MAC addresses updating (enabled by default)\n"
+ " When enabled:\n"
+ " - The source MAC address is replaced by the TX port MAC address\n"
+ " - The destination MAC address is replaced by 02:00:00:00:00:TX_PORT_ID\n",
prgname);
}
return n;
}
+static const char short_options[] =
+ "p:" /* portmask */
+ "q:" /* number of queues */
+ "T:" /* timer period */
+ ;
+
+#define CMD_LINE_OPT_MAC_UPDATING "mac-updating"
+#define CMD_LINE_OPT_NO_MAC_UPDATING "no-mac-updating"
+
+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,
+};
+
+static const struct option lgopts[] = {
+ { CMD_LINE_OPT_MAC_UPDATING, no_argument, &mac_updating, 1},
+ { CMD_LINE_OPT_NO_MAC_UPDATING, no_argument, &mac_updating, 0},
+ {NULL, 0, 0, 0}
+};
+
/* Parse the argument given in the command line of the application */
static int
l2fwd_parse_args(int argc, char **argv)
{
- int opt, ret;
+ int opt, ret, timer_secs;
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:",
+ while ((opt = getopt_long(argc, argvopt, short_options,
lgopts, &option_index)) != EOF) {
switch (opt) {
/* timer period */
case 'T':
- timer_period = l2fwd_parse_timer_period(optarg) * 1000 * TIMER_MILLISECOND;
- if (timer_period < 0) {
+ timer_secs = l2fwd_parse_timer_period(optarg);
+ if (timer_secs < 0) {
printf("invalid timer period\n");
l2fwd_usage(prgname);
return -1;
}
+ timer_period = timer_secs;
break;
/* long options */
case 0:
- l2fwd_usage(prgname);
- return -1;
+ break;
default:
l2fwd_usage(prgname);
argv[optind-1] = prgname;
ret = optind-1;
- optind = 0; /* reset getopt lib */
+ optind = 1; /* reset getopt lib */
return ret;
}
printf("\nChecking link status");
fflush(stdout);
for (count = 0; count <= MAX_CHECK_TIME; count++) {
+ if (force_quit)
+ return;
all_ports_up = 1;
for (portid = 0; portid < port_num; portid++) {
+ if (force_quit)
+ return;
if ((port_mask & (1 << portid)) == 0)
continue;
memset(&link, 0, sizeof(link));
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;
}
}
}
+static void
+signal_handler(int signum)
+{
+ if (signum == SIGINT || signum == SIGTERM) {
+ printf("\n\nSignal %d received, preparing to exit...\n",
+ signum);
+ force_quit = true;
+ }
+}
+
int
-MAIN(int argc, char **argv)
+main(int argc, char **argv)
{
struct lcore_queue_conf *qconf;
struct rte_eth_dev_info dev_info;
argc -= ret;
argv += ret;
+ force_quit = false;
+ signal(SIGINT, signal_handler);
+ signal(SIGTERM, signal_handler);
+
/* parse application arguments (after the EAL ones) */
ret = l2fwd_parse_args(argc, argv);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Invalid L2FWD arguments\n");
+ printf("MAC updating %s\n", mac_updating ? "enabled" : "disabled");
+
+ /* convert to number of cycles */
+ timer_period *= rte_get_timer_hz();
+
/* 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,
- rte_socket_id(), 0);
+ l2fwd_pktmbuf_pool = rte_pktmbuf_pool_create("mbuf_pool", NB_MBUF,
+ MEMPOOL_CACHE_SIZE, 0, RTE_MBUF_DEFAULT_BUF_SIZE,
+ rte_socket_id());
if (l2fwd_pktmbuf_pool == NULL)
rte_exit(EXIT_FAILURE, "Cannot init mbuf pool\n");
- 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 ports - bye\n");
- if (nb_ports > RTE_MAX_ETHPORTS)
- nb_ports = RTE_MAX_ETHPORTS;
-
/* reset l2fwd_dst_ports */
for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++)
l2fwd_dst_ports[portid] = 0;
rte_exit(EXIT_FAILURE, "Cannot configure device: err=%d, port=%u\n",
ret, (unsigned) 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=%u\n",
+ ret, (unsigned) portid);
+
rte_eth_macaddr_get(portid,&l2fwd_ports_eth_addr[portid]);
/* init one RX queue */
fflush(stdout);
ret = rte_eth_rx_queue_setup(portid, 0, nb_rxd,
- rte_eth_dev_socket_id(portid), &rx_conf,
+ rte_eth_dev_socket_id(portid),
+ NULL,
l2fwd_pktmbuf_pool);
if (ret < 0)
rte_exit(EXIT_FAILURE, "rte_eth_rx_queue_setup:err=%d, port=%u\n",
/* init one TX queue on each port */
fflush(stdout);
ret = rte_eth_tx_queue_setup(portid, 0, nb_txd,
- rte_eth_dev_socket_id(portid), &tx_conf);
+ rte_eth_dev_socket_id(portid),
+ NULL);
if (ret < 0)
rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup:err=%d, port=%u\n",
ret, (unsigned) portid);
+ /* Initialize TX buffers */
+ tx_buffer[portid] = rte_zmalloc_socket("tx_buffer",
+ RTE_ETH_TX_BUFFER_SIZE(MAX_PKT_BURST), 0,
+ rte_eth_dev_socket_id(portid));
+ if (tx_buffer[portid] == NULL)
+ rte_exit(EXIT_FAILURE, "Cannot allocate buffer for tx on port %u\n",
+ (unsigned) portid);
+
+ rte_eth_tx_buffer_init(tx_buffer[portid], MAX_PKT_BURST);
+
+ ret = rte_eth_tx_buffer_set_err_callback(tx_buffer[portid],
+ rte_eth_tx_buffer_count_callback,
+ &port_statistics[portid].dropped);
+ if (ret < 0)
+ rte_exit(EXIT_FAILURE, "Cannot set error callback for "
+ "tx buffer on port %u\n", (unsigned) portid);
+
/* Start device */
ret = rte_eth_dev_start(portid);
if (ret < 0)
check_all_ports_link_status(nb_ports, l2fwd_enabled_port_mask);
+ ret = 0;
/* launch per-lcore init on every lcore */
rte_eal_mp_remote_launch(l2fwd_launch_one_lcore, NULL, 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;
-}
+ for (portid = 0; portid < nb_ports; portid++) {
+ if ((l2fwd_enabled_port_mask & (1 << portid)) == 0)
+ continue;
+ printf("Closing port %d...", portid);
+ rte_eth_dev_stop(portid);
+ rte_eth_dev_close(portid);
+ printf(" Done\n");
+ }
+ printf("Bye...\n");
+ return ret;
+}