/*-
* BSD LICENSE
- *
- * Copyright(c) 2010-2013 Intel Corporation. All rights reserved.
+ *
+ * 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
+ *
+ * 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
+ *
+ * * 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
+ * * 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
+ * * 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
+ *
+ * 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.
- *
*/
#include <stdio.h>
#include <stdarg.h>
#include <errno.h>
#include <getopt.h>
+#include <signal.h>
#include <rte_common.h>
#include <rte_byteorder.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_spinlock.h>
#include <rte_cycles.h>
#include <rte_prefetch.h>
#include <rte_lcore.h>
#include <rte_udp.h>
#include <rte_string_fns.h>
-#include "main.h"
-
#define APP_LOOKUP_EXACT_MATCH 0
#define APP_LOOKUP_LPM 1
#define DO_RFC_1812_CHECKS
#define RTE_LOGTYPE_L3FWD RTE_LOGTYPE_USER1
-#define MAX_PORTS 32
+#define MEMPOOL_CACHE_SIZE 256
+
+/*
+ * 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 MBUF_SIZE (2048 + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM)
-#define NB_MBUF 8192
+#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)
/*
* RX and TX Prefetch, Host, and Write-back threshold values should be
#define TX_WTHRESH 0 /**< Default values of TX write-back threshold reg. */
#define MAX_PKT_BURST 32
-#define BURST_TX_DRAIN 200000ULL /* around 100us at 2 Ghz */
+#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */
#define NB_SOCKETS 8
static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT;
/* ethernet addresses of ports */
-static struct ether_addr ports_eth_addr[MAX_PORTS];
+static struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS];
/* mask of enabled ports */
static uint32_t enabled_port_mask = 0;
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 = 1, /**< CRC stripped by hardware */
+ .hw_strip_crc = 0, /**< CRC stripped by hardware */
},
.rx_adv_conf = {
.rss_conf = {
.rss_key = NULL,
- .rss_hf = ETH_RSS_IPV4 | ETH_RSS_IPV6,
+ .rss_hf = ETH_RSS_IP,
},
},
.txmode = {
},
};
-static const struct rte_eth_rxconf rx_conf = {
- .rx_thresh = {
- .pthresh = RX_PTHRESH,
- .hthresh = RX_HTHRESH,
- .wthresh = RX_WTHRESH,
- },
-};
-
-static const struct rte_eth_txconf tx_conf = {
- .tx_thresh = {
- .pthresh = TX_PTHRESH,
- .hthresh = TX_HTHRESH,
- .wthresh = TX_WTHRESH,
- },
- .tx_free_thresh = 0, /* Use PMD default values */
- .tx_rs_thresh = 0, /* Use PMD default values */
-};
-
static struct rte_mempool * pktmbuf_pool[NB_SOCKETS];
uint16_t n_rx_queue;
struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE];
uint16_t tx_queue_id;
- struct mbuf_table tx_mbufs[MAX_PORTS];
+ struct mbuf_table tx_mbufs[RTE_MAX_ETHPORTS];
lookup_struct_t * lookup_struct;
} __rte_cache_aligned;
static struct lcore_conf lcore_conf[RTE_MAX_LCORE];
-
+static rte_spinlock_t spinlock_conf[RTE_MAX_ETHPORTS] = {RTE_SPINLOCK_INITIALIZER};
/* Send burst of packets on an output interface */
static inline int
send_burst(struct lcore_conf *qconf, uint16_t n, uint8_t port)
queueid = qconf->tx_queue_id;
m_table = (struct rte_mbuf **)qconf->tx_mbufs[port].m_table;
+ rte_spinlock_lock(&spinlock_conf[port]);
ret = rte_eth_tx_burst(port, queueid, m_table, n);
+ rte_spinlock_unlock(&spinlock_conf[port]);
+
if (unlikely(ret < n)) {
do {
rte_pktmbuf_free(m_table[ret]);
eth_hdr = rte_pktmbuf_mtod(m, struct ether_hdr *);
- ipv4_hdr = (struct ipv4_hdr *)(rte_pktmbuf_mtod(m, unsigned char *) +
- sizeof(struct ether_hdr));
+ ipv4_hdr = rte_pktmbuf_mtod_offset(m, struct ipv4_hdr *,
+ 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) {
+ if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len) < 0) {
rte_pktmbuf_free(m);
return;
}
#endif
dst_port = get_dst_port(ipv4_hdr, portid, l3fwd_lookup_struct);
- if (dst_port >= MAX_PORTS || (enabled_port_mask & 1 << dst_port) == 0)
+ if (dst_port >= RTE_MAX_ETHPORTS || (enabled_port_mask & 1 << dst_port) == 0)
dst_port = portid;
/* 02:00:00:00:00:xx */
}
/* main processing loop */
-static __attribute__((noreturn)) int
+static int
main_loop(__attribute__((unused)) void *dummy)
{
struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
unsigned lcore_id;
- uint64_t prev_tsc = 0;
- uint64_t diff_tsc, cur_tsc;
+ 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);
+ return 0;
}
RTE_LOG(INFO, L3FWD, "entering main loop on lcore %u\n", lcore_id);
* TX burst queue drain
*/
diff_tsc = cur_tsc - prev_tsc;
- if (unlikely(diff_tsc > BURST_TX_DRAIN)) {
+ 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 < MAX_PORTS; portid++) {
+ for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) {
if (qconf->tx_mbufs[portid].len == 0)
continue;
send_burst(&lcore_conf[lcore_id],
prgname);
}
+/* Custom handling of signals to handle process terminal */
+static void
+signal_handler(int signum)
+{
+ uint8_t portid;
+ uint8_t nb_ports = rte_eth_dev_count();
+
+ /* When we receive a SIGINT signal */
+ if (signum == SIGINT) {
+ for (portid = 0; portid < nb_ports; portid++) {
+ /* skip ports that are not enabled */
+ if ((enabled_port_mask & (1 << portid)) == 0)
+ continue;
+ rte_eth_dev_close(portid);
+ }
+ }
+ rte_exit(EXIT_SUCCESS, "\n User forced exit\n");
+}
static int
parse_portmask(const char *portmask)
{
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++){
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]);
+ char buf[ETHER_ADDR_FMT_SIZE];
+ ether_format_addr(buf, ETHER_ADDR_FMT_SIZE, eth_addr);
+ printf("%s%s", name, buf);
}
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
char s[64];
/* create hashes */
- rte_snprintf(s, sizeof(s), "l3fwd_hash_%d", socketid);
+ snprintf(s, sizeof(s), "l3fwd_hash_%d", socketid);
l3fwd_hash_params.name = s;
l3fwd_hash_params.socket_id = socketid;
l3fwd_lookup_struct[socketid] = rte_hash_create(&l3fwd_hash_params);
char s[64];
/* create the LPM table */
- rte_snprintf(s, sizeof(s), "L3FWD_LPM_%d", socketid);
+ snprintf(s, sizeof(s), "L3FWD_LPM_%d", socketid);
l3fwd_lookup_struct[socketid] = rte_lpm_create(s, socketid,
L3FWD_LPM_MAX_RULES, 0);
if (l3fwd_lookup_struct[socketid] == NULL)
#endif
static int
-init_mem(void)
+init_mem(unsigned nb_mbuf)
{
struct lcore_conf *qconf;
int socketid;
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, 32,
- sizeof(struct rte_pktmbuf_pool_private),
- rte_pktmbuf_pool_init, NULL,
- rte_pktmbuf_init, NULL,
- socketid, 0);
+ snprintf(s, sizeof(s), "mbuf_pool_%d", socketid);
+ pktmbuf_pool[socketid] = rte_pktmbuf_pool_create(s,
+ nb_mbuf, MEMPOOL_CACHE_SIZE, 0,
+ RTE_MBUF_DEFAULT_BUF_SIZE, socketid);
if (pktmbuf_pool[socketid] == NULL)
rte_exit(EXIT_FAILURE, "Cannot init mbuf pool on socket %d\n", socketid);
else
}
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;
unsigned lcore_id;
+ uint32_t nb_lcores;
+ uint16_t n_tx_queue;
uint8_t portid, nb_rx_queue, queue, socketid;
+ signal(SIGINT, signal_handler);
/* init EAL */
ret = rte_eal_init(argc, argv);
if (ret < 0)
if (ret < 0)
rte_exit(EXIT_FAILURE, "init_lcore_rx_queues failed\n");
- ret = init_mem();
- if (ret < 0)
- rte_exit(EXIT_FAILURE, "init_mem failed\n");
-
- /* init driver */
- 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 > MAX_PORTS)
- nb_ports = MAX_PORTS;
+ if (nb_ports > RTE_MAX_ETHPORTS)
+ nb_ports = RTE_MAX_ETHPORTS;
if (check_port_config(nb_ports) < 0)
rte_exit(EXIT_FAILURE, "check_port_config failed\n");
+ nb_lcores = rte_lcore_count();
+
/* initialize all ports */
for (portid = 0; portid < nb_ports; portid++) {
/* skip ports that are not enabled */
/* must always equal(=1) */
nb_rx_queue = get_port_n_rx_queues(portid);
+ n_tx_queue = MAX_TX_QUEUE_PER_PORT;
printf("Creating queues: nb_rxq=%d nb_txq=%u... ",
nb_rx_queue, (unsigned)1 );
- ret = rte_eth_dev_configure(portid, nb_rx_queue, 1, &port_conf);
+ ret = rte_eth_dev_configure(portid, nb_rx_queue, n_tx_queue, &port_conf);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Cannot configure device: err=%d, port=%d\n",
ret, portid);
print_ethaddr(" Address:", &ports_eth_addr[portid]);
printf(", ");
+ ret = init_mem(NB_MBUF);
+ if (ret < 0)
+ rte_exit(EXIT_FAILURE, "init_mem failed\n");
+
/* init one TX queue */
- socketid = 0;
+ socketid = (uint8_t)rte_lcore_to_socket_id(rte_get_master_lcore());
- printf("txq=%d,%d ", 0, socketid);
+ printf("txq=%d,%d,%d ", portid, 0, socketid);
fflush(stdout);
+
+ rte_eth_dev_info_get(portid, &dev_info);
+ txconf = &dev_info.default_txconf;
+ if (port_conf.rxmode.jumbo_frame)
+ txconf->txq_flags = 0;
ret = rte_eth_tx_queue_setup(portid, 0, nb_txd,
- socketid, &tx_conf);
+ socketid, txconf);
if (ret < 0)
rte_exit(EXIT_FAILURE, "rte_eth_tx_queue_setup: err=%d, "
"port=%d\n", ret, portid);
fflush(stdout);
ret = rte_eth_rx_queue_setup(portid, queueid, nb_rxd,
- socketid, &rx_conf, pktmbuf_pool[socketid]);
+ socketid, NULL,
+ pktmbuf_pool[socketid]);
if (ret < 0)
rte_exit(EXIT_FAILURE, "rte_eth_rx_queue_setup: err=%d,"
"port=%d\n", ret, portid);