-/*-
- * BSD LICENSE
- *
- * Copyright(c) 2010-2012 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 <stdio.h>
#include <getopt.h>
#include <netinet/in.h>
-#include <linux/if.h>
+#include <net/if.h>
+#ifdef RTE_EXEC_ENV_LINUXAPP
#include <linux/if_tun.h>
+#endif
#include <fcntl.h>
#include <sys/ioctl.h>
#include <unistd.h>
#include <rte_log.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_lcore.h>
#include <rte_branch_prediction.h>
#include <rte_interrupts.h>
-#include <rte_pci.h>
#include <rte_debug.h>
#include <rte_ether.h>
#include <rte_ethdev.h>
-#include <rte_ring.h>
-#include <rte_log.h>
#include <rte_mempool.h>
#include <rte_mbuf.h>
#include <rte_string_fns.h>
+#include <rte_cycles.h>
/* Macros for printing using RTE_LOG */
#define RTE_LOGTYPE_APP RTE_LOGTYPE_USER1
#define FATAL_ERROR(fmt, args...) rte_exit(EXIT_FAILURE, fmt "\n", ##args)
#define PRINT_INFO(fmt, args...) RTE_LOG(INFO, APP, fmt "\n", ##args)
-/* NUMA socket to allocate mbuf pool on */
-#define SOCKET 0
-
/* Max ports than can be used (each port is associated with two lcores) */
#define MAX_PORTS (RTE_MAX_LCORE / 2)
/* Max size of a single packet */
-#define MAX_PACKET_SZ 2048
+#define MAX_PACKET_SZ (2048)
-/* Number of bytes needed for each mbuf */
-#define MBUF_SZ \
- (MAX_PACKET_SZ + sizeof(struct rte_mbuf) + RTE_PKTMBUF_HEADROOM)
+/* Size of the data buffer in each mbuf */
+#define MBUF_DATA_SZ (MAX_PACKET_SZ + RTE_PKTMBUF_HEADROOM)
/* Number of mbufs in mempool that is created */
#define NB_MBUF 8192
#define MEMPOOL_CACHE_SZ PKT_BURST_SZ
/* Number of RX ring descriptors */
-#define NB_RXD 128
+#define NB_RXD 1024
/* Number of TX ring descriptors */
-#define NB_TXD 512
+#define NB_TXD 1024
/*
* RX and TX Prefetch, Host, and Write-back threshold values should be
* controller's datasheet and supporting DPDK documentation for guidance
* on how these parameters should be set.
*/
-/* RX ring configuration */
-static const struct rte_eth_rxconf rx_conf = {
- .rx_thresh = {
- .pthresh = 8, /* Ring prefetch threshold */
- .hthresh = 8, /* Ring host threshold */
- .wthresh = 4, /* Ring writeback threshold */
- },
- .rx_free_thresh = 0, /* Immediately free RX descriptors */
-};
-
-/*
- * 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.
- */
-/* TX ring configuration */
-static const struct rte_eth_txconf tx_conf = {
- .tx_thresh = {
- .pthresh = 36, /* Ring prefetch threshold */
- .hthresh = 0, /* Ring host threshold */
- .wthresh = 0, /* Ring writeback threshold */
- },
- .tx_free_thresh = 0, /* Use PMD default values */
- .tx_rs_thresh = 0, /* Use PMD default values */
-};
/* Options for configuring ethernet port */
-static const struct rte_eth_conf port_conf = {
+static struct rte_eth_conf port_conf = {
.rxmode = {
- .header_split = 0, /* Header Split disabled */
- .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 */
+ .ignore_offload_bitfield = 1,
+ .offloads = DEV_RX_OFFLOAD_CRC_STRIP,
},
.txmode = {
- .mq_mode = ETH_DCB_NONE,
+ .mq_mode = ETH_MQ_TX_NONE,
},
};
static uint32_t ports_mask = 0;
/* Mask of cores that read from NIC and write to tap */
-static uint32_t input_cores_mask = 0;
+static uint64_t input_cores_mask = 0;
/* Mask of cores that read from tap and write to NIC */
-static uint32_t output_cores_mask = 0;
+static uint64_t output_cores_mask = 0;
/* Array storing port_id that is associated with each lcore */
-static uint8_t port_ids[RTE_MAX_LCORE];
+static uint16_t port_ids[RTE_MAX_LCORE];
/* Structure type for recording lcore-specific stats */
struct stats {
}
}
+#ifdef RTE_EXEC_ENV_LINUXAPP
/*
* Create a tap network interface, or use existing one with same name.
* If name[0]='\0' then a name is automatically assigned and returned in name.
ifr.ifr_flags = IFF_TAP | IFF_NO_PI;
if (name && *name)
- rte_snprintf(ifr.ifr_name, IFNAMSIZ, name);
+ snprintf(ifr.ifr_name, IFNAMSIZ, "%s", name);
ret = ioctl(fd, TUNSETIFF, (void *) &ifr);
if (ret < 0) {
}
if (name)
- rte_snprintf(name, IFNAMSIZ, ifr.ifr_name);
+ snprintf(name, IFNAMSIZ, "%s", ifr.ifr_name);
+
+ return fd;
+}
+#else
+/*
+ * Find a free tap network interface, or create a new one.
+ * The name is automatically assigned and returned in name.
+ */
+static int tap_create(char *name)
+{
+ int i, fd = -1;
+ char devname[PATH_MAX];
+
+ for (i = 0; i < 255; i++) {
+ snprintf(devname, sizeof(devname), "/dev/tap%d", i);
+ fd = open(devname, O_RDWR);
+ if (fd >= 0 || errno != EBUSY)
+ break;
+ }
+
+ if (name)
+ snprintf(name, IFNAMSIZ, "tap%d", i);
return fd;
}
+#endif
/* Main processing loop */
-static __attribute__((noreturn)) int
+static int
main_loop(__attribute__((unused)) void *arg)
{
const unsigned lcore_id = rte_lcore_id();
char tap_name[IFNAMSIZ];
int tap_fd;
- /* Create new tap interface */
- rte_snprintf(tap_name, IFNAMSIZ, "tap_dpdk_%.2u", lcore_id);
- tap_fd = tap_create(tap_name);
- if (tap_fd < 0)
- FATAL_ERROR("Could not create tap interface \"%s\" (%d)",
- tap_name, tap_fd);
+ if ((1ULL << lcore_id) & input_cores_mask) {
+ /* Create new tap interface */
+ snprintf(tap_name, IFNAMSIZ, "tap_dpdk_%.2u", lcore_id);
+ tap_fd = tap_create(tap_name);
+ if (tap_fd < 0)
+ FATAL_ERROR("Could not create tap interface \"%s\" (%d)",
+ tap_name, tap_fd);
- if ((1 << lcore_id) & input_cores_mask) {
PRINT_INFO("Lcore %u is reading from port %u and writing to %s",
lcore_id, (unsigned)port_ids[lcore_id], tap_name);
fflush(stdout);
}
}
}
- else if ((1 << lcore_id) & output_cores_mask) {
+ else if ((1ULL << lcore_id) & output_cores_mask) {
+ /* Create new tap interface */
+ snprintf(tap_name, IFNAMSIZ, "tap_dpdk_%.2u", lcore_id);
+ tap_fd = tap_create(tap_name);
+ if (tap_fd < 0)
+ FATAL_ERROR("Could not create tap interface \"%s\" (%d)",
+ tap_name, tap_fd);
+
PRINT_INFO("Lcore %u is reading from %s and writing to port %u",
lcore_id, tap_name, (unsigned)port_ids[lcore_id]);
fflush(stdout);
if (m == NULL)
continue;
- ret = read(tap_fd, m->pkt.data, MAX_PACKET_SZ);
+ ret = read(tap_fd, rte_pktmbuf_mtod(m, void *),
+ MAX_PACKET_SZ);
lcore_stats[lcore_id].rx++;
if (unlikely(ret < 0)) {
FATAL_ERROR("Reading from %s interface failed",
tap_name);
}
- m->pkt.nb_segs = 1;
- m->pkt.next = NULL;
- m->pkt.pkt_len = (uint16_t)ret;
- m->pkt.data_len = (uint16_t)ret;
+ m->nb_segs = 1;
+ m->next = NULL;
+ m->pkt_len = (uint16_t)ret;
+ m->data_len = (uint16_t)ret;
ret = rte_eth_tx_burst(port_ids[lcore_id], 0, &m, 1);
if (unlikely(ret < 1)) {
rte_pktmbuf_free(m);
}
else {
PRINT_INFO("Lcore %u has nothing to do", lcore_id);
- for (;;)
- ; /* loop doing nothing */
+ return 0;
}
/*
* Tap file is closed automatically when program exits. Putting close()
}
/* Convert string to unsigned number. 0 is returned if error occurs */
-static uint32_t
+static uint64_t
parse_unsigned(const char *portmask)
{
char *end = NULL;
- unsigned long num;
+ uint64_t num;
- num = strtoul(portmask, &end, 16);
+ num = strtoull(portmask, &end, 16);
if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0'))
return 0;
- return (uint32_t)num;
+ return (uint64_t)num;
}
/* Record affinities between ports and lcores in global port_ids[] array */
static void
setup_port_lcore_affinities(void)
{
- unsigned i;
- uint8_t tx_port = 0;
- uint8_t rx_port = 0;
+ unsigned long i;
+ uint16_t tx_port = 0;
+ uint16_t rx_port = 0;
/* Setup port_ids[] array, and check masks were ok */
RTE_LCORE_FOREACH(i) {
- if (input_cores_mask & (1 << i)) {
+ if (input_cores_mask & (1ULL << i)) {
/* Skip ports that are not enabled */
while ((ports_mask & (1 << rx_port)) == 0) {
rx_port++;
}
port_ids[i] = rx_port++;
- }
- else if (output_cores_mask & (1 << i)) {
+ } else if (output_cores_mask & (1ULL << (i & 0x3f))) {
/* Skip ports that are not enabled */
while ((ports_mask & (1 << tx_port)) == 0) {
tx_port++;
/* Initialise a single port on an Ethernet device */
static void
-init_port(uint8_t port)
+init_port(uint16_t port)
{
- struct rte_eth_link link;
int ret;
+ uint16_t nb_rxd = NB_RXD;
+ uint16_t nb_txd = NB_TXD;
+ struct rte_eth_dev_info dev_info;
+ struct rte_eth_rxconf rxq_conf;
+ struct rte_eth_txconf txq_conf;
+ struct rte_eth_conf local_port_conf = port_conf;
/* Initialise device and RX/TX queues */
- PRINT_INFO("Initialising port %u ...", (unsigned)port);
+ PRINT_INFO("Initialising port %u ...", port);
fflush(stdout);
- ret = rte_eth_dev_configure(port, 1, 1, &port_conf);
+ rte_eth_dev_info_get(port, &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;
+ ret = rte_eth_dev_configure(port, 1, 1, &local_port_conf);
if (ret < 0)
- FATAL_ERROR("Could not configure port%u (%d)",
- (unsigned)port, ret);
+ FATAL_ERROR("Could not configure port%u (%d)", port, ret);
- ret = rte_eth_rx_queue_setup(port, 0, NB_RXD, SOCKET, &rx_conf,
- pktmbuf_pool);
+ ret = rte_eth_dev_adjust_nb_rx_tx_desc(port, &nb_rxd, &nb_txd);
+ if (ret < 0)
+ FATAL_ERROR("Could not adjust number of descriptors for port%u (%d)",
+ port, ret);
+
+ rxq_conf = dev_info.default_rxconf;
+ rxq_conf.offloads = local_port_conf.rxmode.offloads;
+ ret = rte_eth_rx_queue_setup(port, 0, nb_rxd,
+ rte_eth_dev_socket_id(port),
+ &rxq_conf,
+ pktmbuf_pool);
if (ret < 0)
FATAL_ERROR("Could not setup up RX queue for port%u (%d)",
- (unsigned)port, ret);
-
- ret = rte_eth_tx_queue_setup(port, 0, NB_TXD, SOCKET, &tx_conf);
+ port, ret);
+
+ txq_conf = dev_info.default_txconf;
+ txq_conf.txq_flags = ETH_TXQ_FLAGS_IGNORE;
+ txq_conf.offloads = local_port_conf.txmode.offloads;
+ ret = rte_eth_tx_queue_setup(port, 0, nb_txd,
+ rte_eth_dev_socket_id(port),
+ &txq_conf);
if (ret < 0)
FATAL_ERROR("Could not setup up TX queue for port%u (%d)",
- (unsigned)port, ret);
+ port, ret);
ret = rte_eth_dev_start(port);
if (ret < 0)
- FATAL_ERROR("Could not start port%u (%d)", (unsigned)port, ret);
-
- /* Everything is setup and started, print link status */
- rte_eth_link_get(port, &link);
- if (link.link_status)
- PRINT_INFO(" link up - %u Mbit/s - %s",
- (unsigned)link.link_speed,
- (link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex"));
- else
- PRINT_INFO(" link down");
+ FATAL_ERROR("Could not start port%u (%d)", port, ret);
rte_eth_promiscuous_enable(port);
}
+/* Check the link status of all ports in up to 9s, and print them finally */
+static void
+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 */
+ 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++) {
+ all_ports_up = 1;
+ for (portid = 0; portid < port_num; portid++) {
+ if ((port_mask & (1 << portid)) == 0)
+ continue;
+ memset(&link, 0, sizeof(link));
+ rte_eth_link_get_nowait(portid, &link);
+ /* print link status if flag set */
+ if (print_flag == 1) {
+ if (link.link_status)
+ 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", portid);
+ continue;
+ }
+ /* clear all_ports_up flag if any link down */
+ if (link.link_status == ETH_LINK_DOWN) {
+ all_ports_up = 0;
+ break;
+ }
+ }
+ /* after finally printing all link status, get out */
+ if (print_flag == 1)
+ break;
+
+ if (all_ports_up == 0) {
+ printf(".");
+ fflush(stdout);
+ rte_delay_ms(CHECK_INTERVAL);
+ }
+
+ /* set the print_flag if all ports up or timeout */
+ if (all_ports_up == 1 || count == (MAX_CHECK_TIME - 1)) {
+ print_flag = 1;
+ printf("done\n");
+ }
+ }
+}
+
/* Initialise ports/queues etc. and start main loop on each core */
int
main(int argc, char** argv)
{
int ret;
unsigned i,high_port;
- uint8_t nb_sys_ports, port;
+ uint16_t nb_sys_ports, port;
/* Associate signal_hanlder function with USR signals */
signal(SIGUSR1, signal_handler);
parse_args(argc, argv);
/* Create the mbuf pool */
- pktmbuf_pool = rte_mempool_create("mbuf_pool", NB_MBUF, MBUF_SZ,
- MEMPOOL_CACHE_SZ,
- sizeof(struct rte_pktmbuf_pool_private),
- rte_pktmbuf_pool_init, NULL, rte_pktmbuf_init, NULL,
- SOCKET, 0);
+ pktmbuf_pool = rte_pktmbuf_pool_create("mbuf_pool", NB_MBUF,
+ MEMPOOL_CACHE_SZ, 0, MBUF_DATA_SZ, rte_socket_id());
if (pktmbuf_pool == NULL) {
FATAL_ERROR("Could not initialise mbuf pool");
return -1;
}
- /* Initialise PMD driver(s) */
- ret = rte_pmd_init_all();
- if (ret < 0)
- FATAL_ERROR("Could not probe PMD (%d)", ret);
-
- /* Scan PCI bus for recognised devices */
- ret = rte_eal_pci_probe();
- if (ret < 0)
- FATAL_ERROR("Could not probe PCI (%d)", ret);
-
/* Get number of ports found in scan */
nb_sys_ports = rte_eth_dev_count();
if (nb_sys_ports == 0)
- FATAL_ERROR("No supported Ethernet devices found - check that "
- "CONFIG_RTE_LIBRTE_IGB_PMD=y and/or "
- "CONFIG_RTE_LIBRTE_IXGBE_PMD=y in the config file");
+ FATAL_ERROR("No supported Ethernet device found");
/* Find highest port set in portmask */
for (high_port = (sizeof(ports_mask) * 8) - 1;
(high_port != 0) && !(ports_mask & (1 << high_port));
}
init_port(port);
}
+ check_all_ports_link_status(nb_sys_ports, ports_mask);
/* Launch per-lcore function on every lcore */
rte_eal_mp_remote_launch(main_loop, NULL, CALL_MASTER);