#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 <unistd.h>
#include <signal.h>
#define RTE_LOGTYPE_L3FWD_POWER RTE_LOGTYPE_USER1
#define MAX_PKT_BURST 32
#define MIN_ZERO_POLL_COUNT 10
#define TIMER_RESOLUTION_CYCLES 200000000ULL
#define TIMER_NUMBER_PER_SECOND 10
#define SCALING_PERIOD (1000000/TIMER_NUMBER_PER_SECOND)
#define SCALING_DOWN_TIME_RATIO_THRESHOLD 0.25
#define APP_LOOKUP_EXACT_MATCH 0
#define APP_LOOKUP_LPM 1
#define DO_RFC_1812_CHECKS
#ifndef APP_LOOKUP_METHOD
#define APP_LOOKUP_METHOD APP_LOOKUP_LPM
#endif
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
#elif (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
#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
#define MAX_JUMBO_PKT_LEN 9600
#define IPV6_ADDR_LEN 16
#define MEMPOOL_CACHE_SIZE 256
#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 BURST_TX_DRAIN_US 100
#define NB_SOCKETS 8
#define PREFETCH_OFFSET 3
#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 struct ether_addr ports_eth_addr[RTE_MAX_ETHPORTS];
static uint32_t enabled_port_mask = 0;
static int promiscuous_on = 0;
static int numa_on = 1;
enum freq_scale_hint_t
{
FREQ_LOWER = -1,
FREQ_CURRENT = 0,
FREQ_HIGHER = 1,
FREQ_HIGHEST = 2
};
struct mbuf_table {
uint16_t len;
struct rte_mbuf *m_table[MAX_PKT_BURST];
};
struct lcore_rx_queue {
uint8_t port_id;
uint8_t queue_id;
enum freq_scale_hint_t freq_up_hint;
uint32_t zero_rx_packet_count;
uint32_t idle_hint;
#define MAX_RX_QUEUE_PER_LCORE 16
#define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS
#define MAX_RX_QUEUE_PER_PORT 128
#define MAX_RX_QUEUE_INTERRUPT_PER_PORT 16
#define MAX_LCORE_PARAMS 1024
struct lcore_params {
uint8_t port_id;
uint8_t queue_id;
uint8_t lcore_id;
static struct lcore_params lcore_params_array[MAX_LCORE_PARAMS];
static struct lcore_params lcore_params_array_default[] = {
{0, 0, 2},
{0, 1, 2},
{0, 2, 2},
{1, 0, 2},
{1, 1, 2},
{1, 2, 2},
{2, 0, 2},
{3, 0, 3},
{3, 1, 3},
};
static struct lcore_params * lcore_params = lcore_params_array_default;
static uint16_t nb_lcore_params = sizeof(lcore_params_array_default) /
sizeof(lcore_params_array_default[0]);
.split_hdr_size = 0,
.header_split = 0,
.hw_ip_checksum = 1,
.hw_vlan_filter = 0,
.jumbo_frame = 0,
.hw_strip_crc = 0,
},
.rx_adv_conf = {
.rss_conf = {
.rss_key = NULL,
.rss_hf = ETH_RSS_UDP,
},
},
.txmode = {
},
.intr_conf = {
.lsc = 1,
.rxq = 1,
},
};
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
#define DEFAULT_HASH_FUNC rte_hash_crc
#else
#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;
};
struct ipv6_l3fwd_route {
struct ipv6_5tuple key;
uint8_t if_out;
};
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 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
#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]))
#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[] = {
};
#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;
struct lcore_stats {
uint32_t sleep_time;
uint32_t nb_long_sleep;
uint32_t trend;
uint64_t nb_rx_processed;
uint64_t nb_iteration_looped;
uint32_t padding[9];
static struct lcore_conf lcore_conf[RTE_MAX_LCORE] __rte_cache_aligned;
static struct lcore_stats stats[RTE_MAX_LCORE] __rte_cache_aligned;
static struct rte_timer power_timers[RTE_MAX_LCORE];
static inline uint32_t power_idle_heuristic(uint32_t zero_rx_packet_count);
static inline enum freq_scale_hint_t power_freq_scaleup_heuristic( \
unsigned lcore_id, uint8_t port_id, uint16_t queue_id);
static void
signal_exit_now(int sigtype)
{
unsigned lcore_id;
int ret;
if (sigtype == SIGINT) {
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
continue;
if (ret)
rte_exit(EXIT_FAILURE,
"Power management "
"library de-initialization failed on "
"core%u\n", lcore_id);
}
}
rte_exit(EXIT_SUCCESS,
"User forced exit\n");
}
static void
power_timer_cb(__attribute__((unused))
struct rte_timer *tim,
__attribute__((unused))
void *
arg)
{
uint64_t hz;
float sleep_time_ratio;
sleep_time_ratio = (float)(stats[lcore_id].sleep_time) /
(float)SCALING_PERIOD;
if (sleep_time_ratio >= SCALING_DOWN_TIME_RATIO_THRESHOLD) {
}
else if ( (unsigned)(stats[lcore_id].nb_rx_processed /
stats[lcore_id].nb_iteration_looped) < MAX_PKT_BURST) {
if (rte_power_freq_down)
}
SINGLE, lcore_id, power_timer_cb, NULL);
stats[lcore_id].nb_rx_processed = 0;
stats[lcore_id].nb_iteration_looped = 0;
stats[lcore_id].sleep_time = 0;
}
static inline int
send_burst(
struct lcore_conf *qconf, uint16_t n, uint8_t
port)
{
int ret;
uint16_t queueid;
queueid = qconf->tx_queue_id[
port];
m_table = (
struct rte_mbuf **)qconf->tx_mbufs[port].m_table;
do {
} while (++ret < n);
}
return 0;
}
static inline int
send_single_packet(
struct rte_mbuf *m, uint8_t port)
{
uint32_t lcore_id;
uint16_t len;
struct lcore_conf *qconf;
qconf = &lcore_conf[lcore_id];
len = qconf->tx_mbufs[port].len;
qconf->tx_mbufs[port].m_table[len] = m;
len++;
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)
{
return -1;
return -3;
return -4;
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);
}
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
lookup_struct_t * ipv4_l3fwd_lookup_struct)
{
struct ipv4_5tuple key;
int ret = 0;
case IPPROTO_TCP:
tcp = (
struct tcp_hdr *)((
unsigned char *)ipv4_hdr +
sizeof(struct ipv4_hdr));
break;
case IPPROTO_UDP:
udp = (
struct udp_hdr *)((
unsigned char *)ipv4_hdr +
sizeof(struct ipv4_hdr));
break;
default:
key.port_dst = 0;
key.port_src = 0;
break;
}
return (uint8_t)((ret < 0)? portid : ipv4_l3fwd_out_if[ret]);
}
static inline uint8_t
lookup_struct_t *ipv6_l3fwd_lookup_struct)
{
struct ipv6_5tuple key;
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));
break;
case IPPROTO_UDP:
udp = (
struct udp_hdr *)((
unsigned char *) ipv6_hdr +
sizeof(struct ipv6_hdr));
break;
default:
key.port_dst = 0;
key.port_src = 0;
break;
}
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;
next_hop : portid);
}
#endif
static inline void
l3fwd_simple_forward(
struct rte_mbuf *m, uint8_t portid,
struct lcore_conf *qconf)
{
struct ipv4_hdr *ipv4_hdr;
void *d_addr_bytes;
uint8_t dst_port;
ipv4_hdr =
#ifdef DO_RFC_1812_CHECKS
if (is_valid_ipv4_pkt(ipv4_hdr, m->
pkt_len) < 0) {
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;
*((uint64_t *)d_addr_bytes) =
0x000000000002 + ((uint64_t)dst_port << 40);
#ifdef DO_RFC_1812_CHECKS
#endif
send_single_packet(m, dst_port);
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
struct ipv6_hdr *ipv6_hdr;
ipv6_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;
*((uint64_t *)d_addr_bytes) =
0x000000000002 + ((uint64_t)dst_port << 40);
send_single_packet(m, dst_port);
#else
#endif
}
}
#define MINIMUM_SLEEP_TIME 1
#define SUSPEND_THRESHOLD 300
static inline uint32_t
power_idle_heuristic(uint32_t zero_rx_packet_count)
{
if (zero_rx_packet_count < SUSPEND_THRESHOLD)
return MINIMUM_SLEEP_TIME;
else
return SUSPEND_THRESHOLD;
return 0;
}
static inline enum freq_scale_hint_t
power_freq_scaleup_heuristic(unsigned lcore_id,
uint8_t port_id,
uint16_t queue_id)
{
#define FREQ_GEAR1_RX_PACKET_THRESHOLD MAX_PKT_BURST
#define FREQ_GEAR2_RX_PACKET_THRESHOLD (MAX_PKT_BURST*2)
#define FREQ_GEAR3_RX_PACKET_THRESHOLD (MAX_PKT_BURST*3)
#define FREQ_UP_TREND1_ACC 1
#define FREQ_UP_TREND2_ACC 100
#define FREQ_UP_THRESHOLD 10000
FREQ_GEAR3_RX_PACKET_THRESHOLD) > 0)) {
stats[lcore_id].trend = 0;
return FREQ_HIGHEST;
FREQ_GEAR2_RX_PACKET_THRESHOLD) > 0))
stats[lcore_id].trend += FREQ_UP_TREND2_ACC;
FREQ_GEAR1_RX_PACKET_THRESHOLD) > 0))
stats[lcore_id].trend += FREQ_UP_TREND1_ACC;
if (
likely(stats[lcore_id].trend > FREQ_UP_THRESHOLD)) {
stats[lcore_id].trend = 0;
return FREQ_HIGHER;
}
return FREQ_CURRENT;
}
static int
sleep_until_rx_interrupt(int num)
{
struct rte_epoll_event event[num];
int n, i;
uint8_t port_id, queue_id;
void *data;
"lcore %u sleeps until interrupt triggers\n",
n = rte_epoll_wait(RTE_EPOLL_PER_THREAD, event, num, -1);
for (i = 0; i < n; i++) {
data = event[i].epdata.data;
port_id = ((uintptr_t)data) >> CHAR_BIT;
queue_id = ((uintptr_t)data) &
"lcore %u is waked up from rx interrupt on"
" port %d queue %d\n",
}
return 0;
}
static void turn_on_intr(struct lcore_conf *qconf)
{
int i;
struct lcore_rx_queue *rx_queue;
uint8_t port_id, queue_id;
for (i = 0; i < qconf->n_rx_queue; ++i) {
rx_queue = &(qconf->rx_queue_list[i]);
port_id = rx_queue->port_id;
queue_id = rx_queue->queue_id;
}
}
static int event_register(struct lcore_conf *qconf)
{
struct lcore_rx_queue *rx_queue;
uint8_t portid, queueid;
uint32_t data;
int ret;
int i;
for (i = 0; i < qconf->n_rx_queue; ++i) {
rx_queue = &(qconf->rx_queue_list[i]);
portid = rx_queue->port_id;
queueid = rx_queue->queue_id;
data = portid << CHAR_BIT | queueid;
RTE_EPOLL_PER_THREAD,
RTE_INTR_EVENT_ADD,
(void *)((uintptr_t)data));
if (ret)
return ret;
}
return 0;
}
static 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;
uint64_t prev_tsc_power = 0, cur_tsc_power, diff_tsc_power;
int i, j, nb_rx;
uint8_t portid, queueid;
struct lcore_conf *qconf;
struct lcore_rx_queue *rx_queue;
enum freq_scale_hint_t lcore_scaleup_hint;
uint32_t lcore_rx_idle_count = 0;
uint32_t lcore_idle_hint = 0;
int intr_en = 0;
const uint64_t drain_tsc = (
rte_get_tsc_hz() + US_PER_S - 1) / US_PER_S * BURST_TX_DRAIN_US;
prev_tsc = 0;
qconf = &lcore_conf[lcore_id];
if (qconf->n_rx_queue == 0) {
RTE_LOG(INFO, L3FWD_POWER,
"lcore %u has nothing to do\n", lcore_id);
return 0;
}
RTE_LOG(INFO, L3FWD_POWER,
"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_POWER,
" -- lcoreid=%u portid=%hhu "
"rxqueueid=%hhu\n", lcore_id, portid, queueid);
}
if (event_register(qconf) == 0)
intr_en = 1;
else
RTE_LOG(INFO, L3FWD_POWER,
"RX interrupt won't enable.\n");
while (1) {
stats[lcore_id].nb_iteration_looped++;
cur_tsc = rte_rdtsc();
cur_tsc_power = cur_tsc;
diff_tsc = cur_tsc - prev_tsc;
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;
}
diff_tsc_power = cur_tsc_power - prev_tsc_power;
if (diff_tsc_power > TIMER_RESOLUTION_CYCLES) {
prev_tsc_power = cur_tsc_power;
}
start_rx:
lcore_scaleup_hint = FREQ_CURRENT;
lcore_rx_idle_count = 0;
for (i = 0; i < qconf->n_rx_queue; ++i) {
rx_queue = &(qconf->rx_queue_list[i]);
rx_queue->idle_hint = 0;
portid = rx_queue->port_id;
queueid = rx_queue->queue_id;
MAX_PKT_BURST);
stats[lcore_id].nb_rx_processed += nb_rx;
rx_queue->zero_rx_packet_count++;
if (rx_queue->zero_rx_packet_count <=
MIN_ZERO_POLL_COUNT)
continue;
rx_queue->idle_hint = power_idle_heuristic(\
rx_queue->zero_rx_packet_count);
lcore_rx_idle_count++;
} else {
rx_queue->zero_rx_packet_count = 0;
rx_queue->freq_up_hint =
power_freq_scaleup_heuristic(lcore_id,
portid, queueid);
}
for (j = 0; j < PREFETCH_OFFSET && j < nb_rx; j++) {
pkts_burst[j], void *));
}
for (j = 0; j < (nb_rx - PREFETCH_OFFSET); j++) {
j + PREFETCH_OFFSET], void *));
l3fwd_simple_forward(pkts_burst[j], portid,
qconf);
}
for (; j < nb_rx; j++) {
l3fwd_simple_forward(pkts_burst[j], portid,
qconf);
}
}
if (
likely(lcore_rx_idle_count != qconf->n_rx_queue)) {
for (i = 1, lcore_scaleup_hint =
qconf->rx_queue_list[0].freq_up_hint;
i < qconf->n_rx_queue; ++i) {
rx_queue = &(qconf->rx_queue_list[i]);
if (rx_queue->freq_up_hint >
lcore_scaleup_hint)
lcore_scaleup_hint =
rx_queue->freq_up_hint;
}
if (lcore_scaleup_hint == FREQ_HIGHEST) {
} else if (lcore_scaleup_hint == FREQ_HIGHER) {
}
} else {
for (i = 1, lcore_idle_hint =
qconf->rx_queue_list[0].idle_hint;
i < qconf->n_rx_queue; ++i) {
rx_queue = &(qconf->rx_queue_list[i]);
if (rx_queue->idle_hint < lcore_idle_hint)
lcore_idle_hint = rx_queue->idle_hint;
}
if (lcore_idle_hint < SUSPEND_THRESHOLD)
else {
if (intr_en) {
turn_on_intr(qconf);
sleep_until_rx_interrupt(
qconf->n_rx_queue);
}
goto start_rx;
}
stats[lcore_id].sleep_time += lcore_idle_hint;
}
}
}
static int
check_lcore_params(void)
{
uint8_t queue, lcore;
uint16_t i;
int socketid;
for (i = 0; i < nb_lcore_params; ++i) {
queue = lcore_params[i].queue_id;
if (queue >= MAX_RX_QUEUE_PER_PORT) {
printf("invalid queue number: %hhu\n", queue);
return -1;
}
lcore = lcore_params[i].lcore_id;
printf("error: lcore %hhu is not enabled in lcore "
"mask\n", lcore);
return -1;
}
(numa_on == 0)) {
printf("warning: lcore %hhu is on socket %d with numa "
"off\n", lcore, socketid);
}
}
return 0;
}
static int
check_port_config(const unsigned nb_ports)
{
unsigned portid;
uint16_t i;
for (i = 0; i < nb_lcore_params; ++i) {
portid = lcore_params[i].port_id;
if ((enabled_port_mask & (1 << portid)) == 0) {
printf("port %u is not enabled in port mask\n",
portid);
return -1;
}
if (portid >= nb_ports) {
printf("port %u is not present on the board\n",
portid);
return -1;
}
}
return 0;
}
static uint8_t
get_port_n_rx_queues(const uint8_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;
}
return (uint8_t)(++queue);
}
static int
init_lcore_rx_queues(void)
{
uint16_t i, nb_rx_queue;
uint8_t lcore;
for (i = 0; i < nb_lcore_params; ++i) {
lcore = lcore_params[i].lcore_id;
nb_rx_queue = lcore_conf[lcore].n_rx_queue;
if (nb_rx_queue >= MAX_RX_QUEUE_PER_LCORE) {
printf("error: too many queues (%u) for lcore: %u\n",
(unsigned)nb_rx_queue + 1, (unsigned)lcore);
return -1;
} else {
lcore_conf[lcore].rx_queue_list[nb_rx_queue].port_id =
lcore_params[i].port_id;
lcore_conf[lcore].rx_queue_list[nb_rx_queue].queue_id =
lcore_params[i].queue_id;
lcore_conf[lcore].n_rx_queue++;
}
}
return 0;
}
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",
prgname);
}
static int parse_max_pkt_len(const char *pktlen)
{
char *end = NULL;
unsigned long len;
len = strtoul(pktlen, &end, 10);
if ((pktlen[0] == '\0') || (end == NULL) || (*end != '\0'))
return -1;
if (len == 0)
return -1;
return len;
}
static int
parse_portmask(const char *portmask)
{
char *end = NULL;
unsigned long pm;
pm = strtoul(portmask, &end, 16);
if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0'))
return -1;
if (pm == 0)
return -1;
return pm;
}
static int
parse_config(const char *q_arg)
{
char s[256];
const char *p, *p0 = q_arg;
char *end;
enum fieldnames {
FLD_PORT = 0,
FLD_QUEUE,
FLD_LCORE,
_NUM_FLD
};
unsigned long int_fld[_NUM_FLD];
char *str_fld[_NUM_FLD];
int i;
unsigned size;
nb_lcore_params = 0;
while ((p = strchr(p0,'(')) != NULL) {
++p;
if((p0 = strchr(p,')')) == NULL)
return -1;
size = p0 - p;
if(size >= sizeof(s))
return -1;
snprintf(s, sizeof(s), "%.*s", size, p);
_NUM_FLD)
return -1;
for (i = 0; i < _NUM_FLD; i++){
errno = 0;
int_fld[i] = strtoul(str_fld[i], &end, 0);
if (errno != 0 || end == str_fld[i] || int_fld[i] >
255)
return -1;
}
if (nb_lcore_params >= MAX_LCORE_PARAMS) {
printf("exceeded max number of lcore params: %hu\n",
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];
++nb_lcore_params;
}
lcore_params = lcore_params_array;
return 0;
}
static int
parse_args(int argc, char **argv)
{
int opt, ret;
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",
lgopts, &option_index)) != EOF) {
switch (opt) {
case 'p':
enabled_port_mask = parse_portmask(optarg);
if (enabled_port_mask == 0) {
printf("invalid portmask\n");
print_usage(prgname);
return -1;
}
break;
case 'P':
printf("Promiscuous mode selected\n");
promiscuous_on = 1;
break;
case 0:
if (!strncmp(lgopts[option_index].name, "config", 6)) {
ret = parse_config(optarg);
if (ret) {
printf("invalid config\n");
print_usage(prgname);
return -1;
}
}
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");
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;
}
}
printf("set jumbo frame "
"max packet length to %u\n",
}
break;
default:
print_usage(prgname);
return -1;
}
}
if (optind >= 0)
argv[optind-1] = prgname;
ret = optind-1;
optind = 0;
return ret;
}
static void
print_ethaddr(
const char *name,
const struct ether_addr *eth_addr)
{
char buf[ETHER_ADDR_FMT_SIZE];
printf("%s%s", name, buf);
}
#if (APP_LOOKUP_METHOD == APP_LOOKUP_EXACT_MATCH)
static void
setup_hash(int socketid)
{
.entries = L3FWD_HASH_ENTRIES,
.key_len = sizeof(struct ipv4_5tuple),
.hash_func = DEFAULT_HASH_FUNC,
.hash_func_init_val = 0,
};
.entries = L3FWD_HASH_ENTRIES,
.key_len = sizeof(struct ipv6_5tuple),
.hash_func = DEFAULT_HASH_FUNC,
.hash_func_init_val = 0,
};
unsigned i;
int ret;
char s[64];
snprintf(s, sizeof(s), "ipv4_l3fwd_hash_%d", socketid);
ipv4_l3fwd_hash_params.
name = s;
ipv4_l3fwd_lookup_struct[socketid] =
if (ipv4_l3fwd_lookup_struct[socketid] == NULL)
rte_exit(EXIT_FAILURE,
"Unable to create the l3fwd hash on "
"socket %d\n", socketid);
snprintf(s, sizeof(s), "ipv6_l3fwd_hash_%d", socketid);
ipv6_l3fwd_hash_params.
name = s;
ipv6_l3fwd_lookup_struct[socketid] =
if (ipv6_l3fwd_lookup_struct[socketid] == NULL)
rte_exit(EXIT_FAILURE,
"Unable to create the l3fwd hash on "
"socket %d\n", socketid);
for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) {
(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);
}
for (i = 0; i < IPV6_L3FWD_NUM_ROUTES; i++) {
(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);
}
}
#endif
#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
static void
setup_lpm(int socketid)
{
unsigned i;
int ret;
char s[64];
snprintf(s, sizeof(s), "IPV4_L3FWD_LPM_%d", 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);
for (i = 0; i < IPV4_L3FWD_NUM_ROUTES; i++) {
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)
{
struct lcore_conf *qconf;
int socketid;
unsigned lcore_id;
char s[64];
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
continue;
if (numa_on)
else
socketid = 0;
if (socketid >= NB_SOCKETS) {
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) {
snprintf(s, sizeof(s), "mbuf_pool_%d", socketid);
pktmbuf_pool[socketid] =
MEMPOOL_CACHE_SIZE, 0,
RTE_MBUF_DEFAULT_BUF_SIZE,
socketid);
if (pktmbuf_pool[socketid] == NULL)
"Cannot init mbuf pool on socket %d\n",
socketid);
else
printf("Allocated mbuf pool on socket %d\n",
socketid);
#if (APP_LOOKUP_METHOD == APP_LOOKUP_LPM)
setup_lpm(socketid);
#else
setup_hash(socketid);
#endif
}
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
}
return 0;
}
static void
check_all_ports_link_status(uint8_t port_num, uint32_t port_mask)
{
#define CHECK_INTERVAL 100
#define MAX_CHECK_TIME 90
uint8_t portid, count, all_ports_up, print_flag = 0;
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));
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,
("full-duplex") : ("half-duplex\n"));
else
printf("Port %d Link Down\n",
(uint8_t)portid);
continue;
}
if (link.link_status == 0) {
all_ports_up = 0;
break;
}
}
if (print_flag == 1)
break;
if (all_ports_up == 0) {
printf(".");
fflush(stdout);
}
if (all_ports_up == 1 || count == (MAX_CHECK_TIME - 1)) {
print_flag = 1;
printf("done\n");
}
}
}
int
main(int argc, char **argv)
{
struct lcore_conf *qconf;
struct rte_eth_dev_info dev_info;
int ret;
unsigned nb_ports;
uint16_t queueid;
unsigned lcore_id;
uint64_t hz;
uint32_t n_tx_queue, nb_lcores;
uint32_t dev_rxq_num, dev_txq_num;
uint8_t portid, nb_rx_queue, queue, socketid;
signal(SIGINT, signal_exit_now);
if (ret < 0)
rte_exit(EXIT_FAILURE,
"Invalid EAL parameters\n");
argc -= ret;
argv += ret;
ret = parse_args(argc, argv);
if (ret < 0)
rte_exit(EXIT_FAILURE,
"Invalid L3FWD parameters\n");
if (check_lcore_params() < 0)
rte_exit(EXIT_FAILURE,
"check_lcore_params failed\n");
ret = init_lcore_rx_queues();
if (ret < 0)
rte_exit(EXIT_FAILURE,
"init_lcore_rx_queues failed\n");
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");
for (portid = 0; portid < nb_ports; portid++) {
if ((enabled_port_mask & (1 << portid)) == 0) {
printf("\nSkipping disabled port %d\n", portid);
continue;
}
printf("Initializing port %d ... ", portid );
fflush(stdout);
dev_rxq_num = dev_info.max_rx_queues;
dev_txq_num = dev_info.max_tx_queues;
nb_rx_queue = get_port_n_rx_queues(portid);
if (nb_rx_queue > dev_rxq_num)
"Cannot configure not existed rxq: "
"port=%d\n", portid);
n_tx_queue = nb_lcores;
if (n_tx_queue > dev_txq_num)
n_tx_queue = dev_txq_num;
printf("Creating queues: nb_rxq=%d nb_txq=%u... ",
nb_rx_queue, (unsigned)n_tx_queue );
(uint16_t)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");
queueid = 0;
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
continue;
if (queueid >= dev_txq_num)
continue;
if (numa_on)
socketid = \
else
socketid = 0;
printf("txq=%u,%d,%d ", lcore_id, queueid, socketid);
fflush(stdout);
txconf = &dev_info.default_txconf;
socketid, txconf);
if (ret < 0)
"rte_eth_tx_queue_setup: err=%d, "
"port=%d\n", ret, portid);
qconf = &lcore_conf[lcore_id];
qconf->tx_queue_id[portid] = queueid;
queueid++;
}
printf("\n");
}
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
continue;
if (ret)
"Library initialization failed on core %u\n", lcore_id);
hz/TIMER_NUMBER_PER_SECOND, SINGLE, lcore_id,
power_timer_cb, NULL);
qconf = &lcore_conf[lcore_id];
printf("\nInitializing rx queues on lcore %u ... ", lcore_id );
fflush(stdout);
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 (numa_on)
socketid = \
else
socketid = 0;
printf("rxq=%d,%d,%d ", portid, queueid, socketid);
fflush(stdout);
socketid, NULL,
pktmbuf_pool[socketid]);
if (ret < 0)
"rte_eth_rx_queue_setup: err=%d, "
"port=%d\n", ret, portid);
}
}
printf("\n");
for (portid = 0; portid < nb_ports; portid++) {
if ((enabled_port_mask & (1 << portid)) == 0) {
continue;
}
if (ret < 0)
rte_exit(EXIT_FAILURE,
"rte_eth_dev_start: err=%d, "
"port=%d\n", ret, portid);
if (promiscuous_on)
}
check_all_ports_link_status((uint8_t)nb_ports, enabled_port_mask);
return -1;
}
return 0;
}