diff options
Diffstat (limited to 'src/spdk/dpdk/examples/l2fwd-keepalive')
| -rw-r--r-- | src/spdk/dpdk/examples/l2fwd-keepalive/Makefile | 58 | ||||
| -rw-r--r-- | src/spdk/dpdk/examples/l2fwd-keepalive/ka-agent/Makefile | 21 | ||||
| -rw-r--r-- | src/spdk/dpdk/examples/l2fwd-keepalive/ka-agent/main.c | 120 | ||||
| -rw-r--r-- | src/spdk/dpdk/examples/l2fwd-keepalive/main.c | 799 | ||||
| -rw-r--r-- | src/spdk/dpdk/examples/l2fwd-keepalive/meson.build | 13 | ||||
| -rw-r--r-- | src/spdk/dpdk/examples/l2fwd-keepalive/shm.c | 112 | ||||
| -rw-r--r-- | src/spdk/dpdk/examples/l2fwd-keepalive/shm.h | 69 |
7 files changed, 1192 insertions, 0 deletions
diff --git a/src/spdk/dpdk/examples/l2fwd-keepalive/Makefile b/src/spdk/dpdk/examples/l2fwd-keepalive/Makefile new file mode 100644 index 00000000..4ab67db4 --- /dev/null +++ b/src/spdk/dpdk/examples/l2fwd-keepalive/Makefile @@ -0,0 +1,58 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2010-2016 Intel Corporation + +# binary name +APP = l2fwd-keepalive + +# all source are stored in SRCS-y +SRCS-y := main.c shm.c + +# Build using pkg-config variables if possible +$(shell pkg-config --exists libdpdk) +ifeq ($(.SHELLSTATUS),0) + +all: shared +.PHONY: shared static +shared: build/$(APP)-shared + ln -sf $(APP)-shared build/$(APP) +static: build/$(APP)-static + ln -sf $(APP)-static build/$(APP) + +LDFLAGS += -pthread -lrt + +PC_FILE := $(shell pkg-config --path libdpdk) +CFLAGS += -O3 $(shell pkg-config --cflags libdpdk) +LDFLAGS_SHARED = $(shell pkg-config --libs libdpdk) +LDFLAGS_STATIC = -Wl,-Bstatic $(shell pkg-config --static --libs libdpdk) + +build/$(APP)-shared: $(SRCS-y) Makefile $(PC_FILE) | build + $(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_SHARED) + +build/$(APP)-static: $(SRCS-y) Makefile $(PC_FILE) | build + $(CC) $(CFLAGS) $(SRCS-y) -o $@ $(LDFLAGS) $(LDFLAGS_STATIC) + +build: + @mkdir -p $@ + +.PHONY: clean +clean: + rm -f build/$(APP) build/$(APP)-static build/$(APP)-shared + rmdir --ignore-fail-on-non-empty build + +else # Build using legacy build system + +ifeq ($(RTE_SDK),) +$(error "Please define RTE_SDK environment variable") +endif + +# Default target, can be overridden by command line or environment +RTE_TARGET ?= x86_64-native-linuxapp-gcc + +include $(RTE_SDK)/mk/rte.vars.mk + +CFLAGS += -O3 +CFLAGS += $(WERROR_FLAGS) +LDFLAGS += -lrt + +include $(RTE_SDK)/mk/rte.extapp.mk +endif diff --git a/src/spdk/dpdk/examples/l2fwd-keepalive/ka-agent/Makefile b/src/spdk/dpdk/examples/l2fwd-keepalive/ka-agent/Makefile new file mode 100644 index 00000000..ddb6e83f --- /dev/null +++ b/src/spdk/dpdk/examples/l2fwd-keepalive/ka-agent/Makefile @@ -0,0 +1,21 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2016 Intel Corporation + +ifeq ($(RTE_SDK),) +$(error "Please define RTE_SDK environment variable") +endif + +# Default target, can be overridden by command line or environment +RTE_TARGET ?= x86_64-native-linuxapp-gcc + +include $(RTE_SDK)/mk/rte.vars.mk + +# binary name +APP = ka-agent + +# all source are stored in SRCS-y +SRCS-y := main.c + +CFLAGS += $(WERROR_FLAGS) -I$(SRCDIR)/../ +LDFLAGS += -lrt +include $(RTE_SDK)/mk/rte.extapp.mk diff --git a/src/spdk/dpdk/examples/l2fwd-keepalive/ka-agent/main.c b/src/spdk/dpdk/examples/l2fwd-keepalive/ka-agent/main.c new file mode 100644 index 00000000..b8a755db --- /dev/null +++ b/src/spdk/dpdk/examples/l2fwd-keepalive/ka-agent/main.c @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016 Intel Corporation + */ + +#include <stdio.h> +#include <string.h> +#include <stdint.h> +#include <errno.h> +#include <unistd.h> +#include <fcntl.h> +#include <sys/wait.h> +#include <sys/queue.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <time.h> + +#include <rte_keepalive.h> + +#include <shm.h> + +#define MAX_TIMEOUTS 4 +#define SEM_TIMEOUT_SECS 2 + +static struct rte_keepalive_shm *ka_shm_create(void) +{ + int fd = shm_open(RTE_KEEPALIVE_SHM_NAME, O_RDWR, 0666); + size_t size = sizeof(struct rte_keepalive_shm); + struct rte_keepalive_shm *shm; + + if (fd < 0) + printf("Failed to open %s as SHM:%s\n", + RTE_KEEPALIVE_SHM_NAME, + strerror(errno)); + else { + shm = (struct rte_keepalive_shm *) mmap( + 0, size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + close(fd); + if (shm == MAP_FAILED) + printf("Failed to mmap SHM:%s\n", strerror(errno)); + else + return shm; + } + + /* Reset to zero, as it was set to MAP_FAILED aka: (void *)-1 */ + shm = 0; + return NULL; +} + +int main(void) +{ + struct rte_keepalive_shm *shm = ka_shm_create(); + struct timespec timeout = { .tv_nsec = 0 }; + int idx_core; + int cnt_cores; + uint64_t last_seen_alive_time = 0; + uint64_t most_recent_alive_time; + int cnt_timeouts = 0; + int sem_errno; + + if (shm == NULL) { + printf("Unable to access shared core state\n"); + return 1; + } + while (1) { + most_recent_alive_time = 0; + for (idx_core = 0; idx_core < RTE_KEEPALIVE_MAXCORES; + idx_core++) + if (shm->core_last_seen_times[idx_core] > + most_recent_alive_time) + most_recent_alive_time = + shm->core_last_seen_times[idx_core]; + + timeout.tv_sec = time(NULL) + SEM_TIMEOUT_SECS; + if (sem_timedwait(&shm->core_died, &timeout) == -1) { + /* Assume no core death signals and no change in any + * last-seen times is the keepalive monitor itself + * failing. + */ + sem_errno = errno; + last_seen_alive_time = most_recent_alive_time; + if (sem_errno == ETIMEDOUT) { + if (last_seen_alive_time == + most_recent_alive_time && + cnt_timeouts++ > + MAX_TIMEOUTS) { + printf("No updates. Exiting..\n"); + break; + } + } else + printf("sem_timedwait() error (%s)\n", + strerror(sem_errno)); + continue; + } + cnt_timeouts = 0; + + cnt_cores = 0; + for (idx_core = 0; idx_core < RTE_KEEPALIVE_MAXCORES; + idx_core++) + if (shm->core_state[idx_core] == RTE_KA_STATE_DEAD) + cnt_cores++; + if (cnt_cores == 0) { + /* Can happen if core was restarted since Semaphore + * was sent, due to agent being offline. + */ + printf("Warning: Empty dead core report\n"); + continue; + } + + printf("%i dead cores: ", cnt_cores); + for (idx_core = 0; + idx_core < RTE_KEEPALIVE_MAXCORES; + idx_core++) + if (shm->core_state[idx_core] == RTE_KA_STATE_DEAD) + printf("%d, ", idx_core); + printf("\b\b\n"); + } + if (munmap(shm, sizeof(struct rte_keepalive_shm)) != 0) + printf("Warning: munmap() failed\n"); + return 0; +} diff --git a/src/spdk/dpdk/examples/l2fwd-keepalive/main.c b/src/spdk/dpdk/examples/l2fwd-keepalive/main.c new file mode 100644 index 00000000..2d8b4d1c --- /dev/null +++ b/src/spdk/dpdk/examples/l2fwd-keepalive/main.c @@ -0,0 +1,799 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2010-2016 Intel Corporation + */ + +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <stdint.h> +#include <inttypes.h> +#include <sys/types.h> +#include <sys/queue.h> +#include <netinet/in.h> +#include <setjmp.h> +#include <stdarg.h> +#include <ctype.h> +#include <errno.h> +#include <getopt.h> +#include <signal.h> + +#include <rte_common.h> +#include <rte_log.h> +#include <rte_malloc.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_timer.h> +#include <rte_keepalive.h> + +#include "shm.h" + +#define RTE_LOGTYPE_L2FWD RTE_LOGTYPE_USER1 + +#define NB_MBUF 8192 + +#define MAX_PKT_BURST 32 +#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */ + +/* + * 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 ether_addr l2fwd_ports_eth_addr[RTE_MAX_ETHPORTS]; + +/* mask of enabled ports */ +static uint32_t l2fwd_enabled_port_mask; + +/* list of enabled ports */ +static uint32_t l2fwd_dst_ports[RTE_MAX_ETHPORTS]; + +static unsigned int l2fwd_rx_queue_per_lcore = 1; + +#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]; +} __rte_cache_aligned; +struct lcore_queue_conf lcore_queue_conf[RTE_MAX_LCORE]; + +struct rte_eth_dev_tx_buffer *tx_buffer[RTE_MAX_ETHPORTS]; + +static struct rte_eth_conf port_conf = { + .rxmode = { + .split_hdr_size = 0, + .offloads = DEV_RX_OFFLOAD_CRC_STRIP, + }, + .txmode = { + .mq_mode = ETH_MQ_TX_NONE, + }, +}; + +struct rte_mempool *l2fwd_pktmbuf_pool = NULL; + +/* Per-port statistics struct */ +struct l2fwd_port_statistics { + uint64_t tx; + uint64_t rx; + uint64_t dropped; +} __rte_cache_aligned; +struct l2fwd_port_statistics port_statistics[RTE_MAX_ETHPORTS]; + +/* A tsc-based timer responsible for triggering statistics printout */ +#define TIMER_MILLISECOND 1 +#define MAX_TIMER_PERIOD 86400 /* 1 day max */ +static int64_t timer_period = 10 * TIMER_MILLISECOND * 1000; /* 10 seconds */ +static int64_t check_period = 5; /* default check cycle is 5ms */ + +/* Keepalive structure */ +struct rte_keepalive *rte_global_keepalive_info; + +/* Termination signalling */ +static int terminate_signal_received; + +/* Termination signal handler */ +static void handle_sigterm(__rte_unused int value) +{ + terminate_signal_received = 1; +} + +/* Print out statistics on packets dropped */ +static void +print_stats(__attribute__((unused)) struct rte_timer *ptr_timer, + __attribute__((unused)) void *ptr_data) +{ + uint64_t total_packets_dropped, total_packets_tx, total_packets_rx; + uint16_t portid; + + total_packets_dropped = 0; + total_packets_tx = 0; + total_packets_rx = 0; + + const char clr[] = { 27, '[', '2', 'J', '\0' }; + const char topLeft[] = { 27, '[', '1', ';', '1', 'H', '\0' }; + + /* Clear screen and move to top left */ + printf("%s%s", clr, topLeft); + + printf("\nPort statistics ===================================="); + + for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) { + /* skip disabled ports */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) + continue; + printf("\nStatistics for port %u ------------------------------" + "\nPackets sent: %24"PRIu64 + "\nPackets received: %20"PRIu64 + "\nPackets dropped: %21"PRIu64, + portid, + port_statistics[portid].tx, + port_statistics[portid].rx, + port_statistics[portid].dropped); + + total_packets_dropped += port_statistics[portid].dropped; + total_packets_tx += port_statistics[portid].tx; + total_packets_rx += port_statistics[portid].rx; + } + printf("\nAggregate statistics ===============================" + "\nTotal packets sent: %18"PRIu64 + "\nTotal packets received: %14"PRIu64 + "\nTotal packets dropped: %15"PRIu64, + total_packets_tx, + total_packets_rx, + total_packets_dropped); + printf("\n====================================================\n"); +} + +static void +l2fwd_simple_forward(struct rte_mbuf *m, unsigned portid) +{ + struct ether_hdr *eth; + void *tmp; + int sent; + unsigned dst_port; + 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); + + 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 */ +static void +l2fwd_main_loop(void) +{ + 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; + 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; + struct rte_eth_dev_tx_buffer *buffer; + + prev_tsc = 0; + + lcore_id = rte_lcore_id(); + qconf = &lcore_queue_conf[lcore_id]; + + if (qconf->n_rx_port == 0) { + RTE_LOG(INFO, L2FWD, "lcore %u has nothing to do\n", lcore_id); + return; + } + + RTE_LOG(INFO, L2FWD, "entering main loop on lcore %u\n", lcore_id); + + for (i = 0; i < qconf->n_rx_port; i++) { + + portid = qconf->rx_port_list[i]; + RTE_LOG(INFO, L2FWD, " -- lcoreid=%u portid=%u\n", lcore_id, + portid); + } + + uint64_t tsc_initial = rte_rdtsc(); + uint64_t tsc_lifetime = (rand()&0x07) * rte_get_tsc_hz(); + + while (!terminate_signal_received) { + /* Keepalive heartbeat */ + rte_keepalive_mark_alive(rte_global_keepalive_info); + + cur_tsc = rte_rdtsc(); + + /* + * Die randomly within 7 secs for demo purposes if + * keepalive enabled + */ + if (check_period > 0 && cur_tsc - tsc_initial > tsc_lifetime) + break; + + /* + * TX burst queue drain + */ + diff_tsc = cur_tsc - prev_tsc; + if (unlikely(diff_tsc > drain_tsc)) { + + 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; + + } + + prev_tsc = cur_tsc; + } + + /* + * Read packet from RX queues + */ + for (i = 0; i < qconf->n_rx_port; i++) { + + portid = qconf->rx_port_list[i]; + nb_rx = rte_eth_rx_burst(portid, 0, + pkts_burst, MAX_PKT_BURST); + + port_statistics[portid].rx += nb_rx; + + for (j = 0; j < nb_rx; j++) { + m = pkts_burst[j]; + rte_prefetch0(rte_pktmbuf_mtod(m, void *)); + l2fwd_simple_forward(m, portid); + } + } + } +} + +static int +l2fwd_launch_one_lcore(__attribute__((unused)) void *dummy) +{ + l2fwd_main_loop(); + return 0; +} + +/* display usage */ +static void +l2fwd_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" + " -K PERIOD: Keepalive check period (5 default; 86400 max)\n" + " -T PERIOD: statistics will be refreshed each PERIOD seconds (0 to disable, 10 default, 86400 maximum)\n", + prgname); +} + +static int +l2fwd_parse_portmask(const char *portmask) +{ + char *end = NULL; + unsigned long pm; + + /* parse hexadecimal string */ + pm = strtoul(portmask, &end, 16); + if ((portmask[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + + if (pm == 0) + return -1; + + return pm; +} + +static unsigned int +l2fwd_parse_nqueue(const char *q_arg) +{ + char *end = NULL; + unsigned long n; + + /* parse hexadecimal string */ + n = strtoul(q_arg, &end, 10); + if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0')) + return 0; + if (n == 0) + return 0; + if (n >= MAX_RX_QUEUE_PER_LCORE) + return 0; + + return n; +} + +static int +l2fwd_parse_timer_period(const char *q_arg) +{ + char *end = NULL; + int n; + + /* parse number string */ + n = strtol(q_arg, &end, 10); + if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + if (n >= MAX_TIMER_PERIOD) + return -1; + + return n; +} + +static int +l2fwd_parse_check_period(const char *q_arg) +{ + char *end = NULL; + int n; + + /* parse number string */ + n = strtol(q_arg, &end, 10); + if ((q_arg[0] == '\0') || (end == NULL) || (*end != '\0')) + return -1; + if (n >= MAX_TIMER_PERIOD) + return -1; + + return n; +} + +/* Parse the argument given in the command line of the application */ +static int +l2fwd_parse_args(int argc, char **argv) +{ + int opt, ret; + 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:K:", + lgopts, &option_index)) != EOF) { + + switch (opt) { + /* portmask */ + case 'p': + l2fwd_enabled_port_mask = l2fwd_parse_portmask(optarg); + if (l2fwd_enabled_port_mask == 0) { + printf("invalid portmask\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* nqueue */ + case 'q': + l2fwd_rx_queue_per_lcore = l2fwd_parse_nqueue(optarg); + if (l2fwd_rx_queue_per_lcore == 0) { + printf("invalid queue number\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* timer period */ + case 'T': + timer_period = l2fwd_parse_timer_period(optarg) + * (int64_t)(1000 * TIMER_MILLISECOND); + if (timer_period < 0) { + printf("invalid timer period\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* Check period */ + case 'K': + check_period = l2fwd_parse_check_period(optarg); + if (check_period < 0) { + printf("invalid check period\n"); + l2fwd_usage(prgname); + return -1; + } + break; + + /* long options */ + case 0: + l2fwd_usage(prgname); + return -1; + + default: + l2fwd_usage(prgname); + return -1; + } + } + + if (optind >= 0) + argv[optind-1] = prgname; + + ret = optind-1; + optind = 1; /* reset getopt lib */ + return ret; +} + +/* Check the link status of all ports in up to 9s, and print them finally */ +static void +check_all_ports_link_status(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; + RTE_ETH_FOREACH_DEV(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"); + } + } +} + +static void +dead_core(__rte_unused void *ptr_data, const int id_core) +{ + if (terminate_signal_received) + return; + printf("Dead core %i - restarting..\n", id_core); + if (rte_eal_get_lcore_state(id_core) == FINISHED) { + rte_eal_wait_lcore(id_core); + rte_eal_remote_launch(l2fwd_launch_one_lcore, NULL, id_core); + } else { + printf("..false positive!\n"); + } +} + +static void +relay_core_state(void *ptr_data, const int id_core, + const enum rte_keepalive_state core_state, uint64_t last_alive) +{ + rte_keepalive_relayed_state((struct rte_keepalive_shm *)ptr_data, + id_core, core_state, last_alive); +} + +int +main(int argc, char **argv) +{ + struct lcore_queue_conf *qconf; + int ret; + uint16_t nb_ports; + uint16_t nb_ports_available = 0; + uint16_t portid, last_port; + unsigned lcore_id, rx_lcore_id; + unsigned nb_ports_in_mask = 0; + struct sigaction signal_handler; + struct rte_keepalive_shm *ka_shm; + + memset(&signal_handler, 0, sizeof(signal_handler)); + terminate_signal_received = 0; + signal_handler.sa_handler = &handle_sigterm; + if (sigaction(SIGINT, &signal_handler, NULL) == -1 || + sigaction(SIGTERM, &signal_handler, NULL) == -1) + rte_exit(EXIT_FAILURE, "SIGNAL\n"); + + + /* init EAL */ + ret = rte_eal_init(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid EAL arguments\n"); + argc -= ret; + argv += ret; + + l2fwd_enabled_port_mask = 0; + + /* parse application arguments (after the EAL ones) */ + ret = l2fwd_parse_args(argc, argv); + if (ret < 0) + rte_exit(EXIT_FAILURE, "Invalid L2FWD arguments\n"); + + /* create the mbuf pool */ + l2fwd_pktmbuf_pool = rte_pktmbuf_pool_create("mbuf_pool", NB_MBUF, 32, + 0, RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id()); + if (l2fwd_pktmbuf_pool == NULL) + rte_exit(EXIT_FAILURE, "Cannot init mbuf pool\n"); + + nb_ports = rte_eth_dev_count_avail(); + if (nb_ports == 0) + rte_exit(EXIT_FAILURE, "No Ethernet ports - bye\n"); + + /* reset l2fwd_dst_ports */ + for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) + l2fwd_dst_ports[portid] = 0; + last_port = 0; + + /* + * Each logical core is assigned a dedicated TX queue on each port. + */ + RTE_ETH_FOREACH_DEV(portid) { + /* skip ports that are not enabled */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) + continue; + + if (nb_ports_in_mask % 2) { + l2fwd_dst_ports[portid] = last_port; + l2fwd_dst_ports[last_port] = portid; + } else + last_port = portid; + + nb_ports_in_mask++; + } + if (nb_ports_in_mask % 2) { + printf("Notice: odd number of ports in portmask.\n"); + l2fwd_dst_ports[last_port] = last_port; + } + + rx_lcore_id = 1; + qconf = NULL; + + /* Initialize the port/queue configuration of each logical core */ + RTE_ETH_FOREACH_DEV(portid) { + /* skip ports that are not enabled */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) + continue; + + /* get the lcore_id for this port */ + while (rte_lcore_is_enabled(rx_lcore_id) == 0 || + lcore_queue_conf[rx_lcore_id].n_rx_port == + l2fwd_rx_queue_per_lcore) { + rx_lcore_id++; + if (rx_lcore_id >= RTE_MAX_LCORE) + rte_exit(EXIT_FAILURE, "Not enough cores\n"); + } + + if (qconf != &lcore_queue_conf[rx_lcore_id]) + /* Assigned a new logical core in the loop above. */ + qconf = &lcore_queue_conf[rx_lcore_id]; + + qconf->rx_port_list[qconf->n_rx_port] = portid; + qconf->n_rx_port++; + printf("Lcore %u: RX port %u\n", + rx_lcore_id, portid); + } + + /* Initialise each port */ + RTE_ETH_FOREACH_DEV(portid) { + 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; + + /* skip ports that are not enabled */ + if ((l2fwd_enabled_port_mask & (1 << portid)) == 0) { + printf("Skipping disabled port %u\n", portid); + continue; + } + nb_ports_available++; + + /* init port */ + printf("Initializing port %u... ", portid); + fflush(stdout); + rte_eth_dev_info_get(portid, &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(portid, 1, 1, &local_port_conf); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "Cannot configure device: err=%d, port=%u\n", + ret, 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, portid); + + rte_eth_macaddr_get(portid, &l2fwd_ports_eth_addr[portid]); + + /* init one RX queue */ + fflush(stdout); + rxq_conf = dev_info.default_rxconf; + rxq_conf.offloads = local_port_conf.rxmode.offloads; + ret = rte_eth_rx_queue_setup(portid, 0, nb_rxd, + rte_eth_dev_socket_id(portid), + &rxq_conf, + l2fwd_pktmbuf_pool); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_rx_queue_setup:err=%d, port=%u\n", + ret, portid); + + /* init one TX queue on each port */ + fflush(stdout); + txq_conf = dev_info.default_txconf; + txq_conf.offloads = local_port_conf.txmode.offloads; + ret = rte_eth_tx_queue_setup(portid, 0, nb_txd, + rte_eth_dev_socket_id(portid), + &txq_conf); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_tx_queue_setup:err=%d, port=%u\n", + ret, 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", + 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", + portid); + + /* Start device */ + ret = rte_eth_dev_start(portid); + if (ret < 0) + rte_exit(EXIT_FAILURE, + "rte_eth_dev_start:err=%d, port=%u\n", + ret, portid); + + rte_eth_promiscuous_enable(portid); + + printf("Port %u, MAC address: " + "%02X:%02X:%02X:%02X:%02X:%02X\n\n", + portid, + l2fwd_ports_eth_addr[portid].addr_bytes[0], + l2fwd_ports_eth_addr[portid].addr_bytes[1], + l2fwd_ports_eth_addr[portid].addr_bytes[2], + l2fwd_ports_eth_addr[portid].addr_bytes[3], + l2fwd_ports_eth_addr[portid].addr_bytes[4], + l2fwd_ports_eth_addr[portid].addr_bytes[5]); + + /* initialize port stats */ + memset(&port_statistics, 0, sizeof(port_statistics)); + } + + if (!nb_ports_available) { + rte_exit(EXIT_FAILURE, + "All available ports are disabled. Please set portmask.\n"); + } + + check_all_ports_link_status(l2fwd_enabled_port_mask); + + struct rte_timer hb_timer, stats_timer; + + rte_timer_subsystem_init(); + rte_timer_init(&stats_timer); + + ka_shm = NULL; + if (check_period > 0) { + ka_shm = rte_keepalive_shm_create(); + if (ka_shm == NULL) + rte_exit(EXIT_FAILURE, + "rte_keepalive_shm_create() failed"); + rte_global_keepalive_info = + rte_keepalive_create(&dead_core, ka_shm); + if (rte_global_keepalive_info == NULL) + rte_exit(EXIT_FAILURE, "init_keep_alive() failed"); + rte_keepalive_register_relay_callback(rte_global_keepalive_info, + relay_core_state, ka_shm); + rte_timer_init(&hb_timer); + if (rte_timer_reset(&hb_timer, + (check_period * rte_get_timer_hz()) / 1000, + PERIODICAL, + rte_lcore_id(), + (void(*)(struct rte_timer*, void*)) + &rte_keepalive_dispatch_pings, + rte_global_keepalive_info + ) != 0 ) + rte_exit(EXIT_FAILURE, "Keepalive setup failure.\n"); + } + if (timer_period > 0) { + if (rte_timer_reset(&stats_timer, + (timer_period * rte_get_timer_hz()) / 1000, + PERIODICAL, + rte_lcore_id(), + &print_stats, NULL + ) != 0 ) + rte_exit(EXIT_FAILURE, "Stats setup failure.\n"); + } + /* launch per-lcore init on every slave lcore */ + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + struct lcore_queue_conf *qconf = &lcore_queue_conf[lcore_id]; + + if (qconf->n_rx_port == 0) + RTE_LOG(INFO, L2FWD, + "lcore %u has nothing to do\n", + lcore_id + ); + else { + rte_eal_remote_launch( + l2fwd_launch_one_lcore, + NULL, + lcore_id + ); + rte_keepalive_register_core(rte_global_keepalive_info, + lcore_id); + } + } + while (!terminate_signal_received) { + rte_timer_manage(); + rte_delay_ms(5); + } + + RTE_LCORE_FOREACH_SLAVE(lcore_id) { + if (rte_eal_wait_lcore(lcore_id) < 0) + return -1; + } + + if (ka_shm != NULL) + rte_keepalive_shm_cleanup(ka_shm); + return 0; +} diff --git a/src/spdk/dpdk/examples/l2fwd-keepalive/meson.build b/src/spdk/dpdk/examples/l2fwd-keepalive/meson.build new file mode 100644 index 00000000..6f7b007e --- /dev/null +++ b/src/spdk/dpdk/examples/l2fwd-keepalive/meson.build @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: BSD-3-Clause +# Copyright(c) 2017 Intel Corporation + +# meson file, for building this example as part of a main DPDK build. +# +# To build this example as a standalone application with an already-installed +# DPDK instance, use 'make' + +ext_deps += cc.find_library('rt') +deps += 'timer' +sources = files( + 'main.c', 'shm.c' +) diff --git a/src/spdk/dpdk/examples/l2fwd-keepalive/shm.c b/src/spdk/dpdk/examples/l2fwd-keepalive/shm.c new file mode 100644 index 00000000..7c7a9ea8 --- /dev/null +++ b/src/spdk/dpdk/examples/l2fwd-keepalive/shm.c @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016 Intel Corporation + */ + +#include <time.h> + +#include <rte_common.h> +#include <rte_log.h> +#include <rte_keepalive.h> + +#include "shm.h" + +struct rte_keepalive_shm *rte_keepalive_shm_create(void) +{ + int fd; + int idx_core; + struct rte_keepalive_shm *ka_shm; + + /* If any existing object is not unlinked, it makes it all too easy + * for clients to end up with stale shared memory blocks when + * restarted. Unlinking makes sure subsequent shm_open by clients + * will get the new block mapped below. + */ + if (shm_unlink(RTE_KEEPALIVE_SHM_NAME) == -1 && errno != ENOENT) + printf("Warning: Error unlinking stale %s (%s)\n", + RTE_KEEPALIVE_SHM_NAME, strerror(errno)); + + fd = shm_open(RTE_KEEPALIVE_SHM_NAME, + O_CREAT | O_TRUNC | O_RDWR, 0666); + if (fd < 0) + RTE_LOG(INFO, EAL, + "Failed to open %s as SHM (%s)\n", + RTE_KEEPALIVE_SHM_NAME, + strerror(errno)); + else if (ftruncate(fd, sizeof(struct rte_keepalive_shm)) != 0) + RTE_LOG(INFO, EAL, + "Failed to resize SHM (%s)\n", strerror(errno)); + else { + ka_shm = (struct rte_keepalive_shm *) mmap( + 0, sizeof(struct rte_keepalive_shm), + PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + close(fd); + if (ka_shm == MAP_FAILED) + RTE_LOG(INFO, EAL, + "Failed to mmap SHM (%s)\n", strerror(errno)); + else { + memset(ka_shm, 0, sizeof(struct rte_keepalive_shm)); + + /* Initialize the semaphores for IPC/SHM use */ + if (sem_init(&ka_shm->core_died, 1, 0) != 0) { + RTE_LOG(INFO, EAL, + "Failed to setup SHM semaphore (%s)\n", + strerror(errno)); + munmap(ka_shm, + sizeof(struct rte_keepalive_shm)); + return NULL; + } + + /* Set all cores to 'not present' */ + for (idx_core = 0; + idx_core < RTE_KEEPALIVE_MAXCORES; + idx_core++) { + ka_shm->core_state[idx_core] = + RTE_KA_STATE_UNUSED; + ka_shm->core_last_seen_times[idx_core] = 0; + } + + return ka_shm; + } + } +return NULL; +} + +void rte_keepalive_relayed_state(struct rte_keepalive_shm *shm, + const int id_core, const enum rte_keepalive_state core_state, + __rte_unused uint64_t last_alive) +{ + int count; + + shm->core_state[id_core] = core_state; + shm->core_last_seen_times[id_core] = last_alive; + + if (core_state == RTE_KEEPALIVE_SHM_DEAD) { + /* Since core has died, also signal ka_agent. + * + * Limit number of times semaphore can be incremented, in case + * ka_agent is not active. + */ + if (sem_getvalue(&shm->core_died, &count) == -1) { + RTE_LOG(INFO, EAL, "Semaphore check failed(%s)\n", + strerror(errno)); + return; + } + if (count > 1) + return; + + if (sem_post(&shm->core_died) != 0) + RTE_LOG(INFO, EAL, + "Failed to increment semaphore (%s)\n", + strerror(errno)); + } +} + +void rte_keepalive_shm_cleanup(struct rte_keepalive_shm *ka_shm) +{ + if (shm_unlink(RTE_KEEPALIVE_SHM_NAME) == -1 && errno != ENOENT) + printf("Warning: Error unlinking %s (%s)\n", + RTE_KEEPALIVE_SHM_NAME, strerror(errno)); + + if (ka_shm && munmap(ka_shm, sizeof(struct rte_keepalive_shm)) != 0) + printf("Warning: munmap() failed\n"); +} diff --git a/src/spdk/dpdk/examples/l2fwd-keepalive/shm.h b/src/spdk/dpdk/examples/l2fwd-keepalive/shm.h new file mode 100644 index 00000000..7a9d5972 --- /dev/null +++ b/src/spdk/dpdk/examples/l2fwd-keepalive/shm.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright(c) 2016 Intel Corporation + */ + +#define RTE_KEEPALIVE_SHM_NAME "/dpdk_keepalive_shm_name" + +#define RTE_KEEPALIVE_SHM_ALIVE 1 +#define RTE_KEEPALIVE_SHM_DEAD 2 + +#include <fcntl.h> +#include <string.h> +#include <unistd.h> +#include <sys/mman.h> +#include <sys/stat.h> +#include <semaphore.h> +#include <rte_keepalive.h> + +/** + * Keepalive SHM structure. + * + * The shared memory allocated by the primary is this size, and contains the + * information as contained within this struct. A secondary may open the SHM, + * and read the contents. + */ +struct rte_keepalive_shm { + /** IPC semaphore. Posted when a core dies */ + sem_t core_died; + + /** + * Relayed status of each core. + */ + enum rte_keepalive_state core_state[RTE_KEEPALIVE_MAXCORES]; + + /** + * Last-seen-alive timestamps for the cores + */ + uint64_t core_last_seen_times[RTE_KEEPALIVE_MAXCORES]; +}; + +/** + * Create shared host memory keepalive object. + * @return + * Pointer to SHM keepalive structure, or NULL on failure. + */ +struct rte_keepalive_shm *rte_keepalive_shm_create(void); + +/** + * Relays state for given core + * @param *shm + * Pointer to SHM keepalive structure. + * @param id_core + * Id of core + * @param core_state + * State of core + * @param last_alive + * Last seen timestamp for core + */ +void rte_keepalive_relayed_state(struct rte_keepalive_shm *shm, + const int id_core, const enum rte_keepalive_state core_state, + uint64_t last_alive); + +/** Shutdown cleanup of shared host memory keepalive object. + * @param *shm + * Pointer to SHM keepalive structure. May be NULL. + * + * If *shm is NULL, this function will only attempt to remove the + * shared host memory handle and not unmap the underlying memory. + */ +void rte_keepalive_shm_cleanup(struct rte_keepalive_shm *ka_shm); |