X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;ds=sidebyside;f=examples%2Fioat%2Fioatfwd.c;h=7255ff3c9e5e0d978ca9d321889cb84eed69d4a7;hb=2299c8d8e7319035819904e4ba99ca6e279018a6;hp=b33c1eeb40cf57973de5e6d581a34b88b602cef1;hpb=c8e6ceecebc1cf195fa64980f47da37a2c91b8d8;p=dpdk.git

diff --git a/examples/ioat/ioatfwd.c b/examples/ioat/ioatfwd.c
index b33c1eeb40..7255ff3c9e 100644
--- a/examples/ioat/ioatfwd.c
+++ b/examples/ioat/ioatfwd.c
@@ -48,6 +48,23 @@ struct rxtx_transmission_config {
 	uint16_t nb_lcores;
 };
 
+/* per-port statistics struct */
+struct ioat_port_statistics {
+	uint64_t rx[RTE_MAX_ETHPORTS];
+	uint64_t tx[RTE_MAX_ETHPORTS];
+	uint64_t tx_dropped[RTE_MAX_ETHPORTS];
+	uint64_t copy_dropped[RTE_MAX_ETHPORTS];
+};
+struct ioat_port_statistics port_statistics;
+
+struct total_statistics {
+	uint64_t total_packets_dropped;
+	uint64_t total_packets_tx;
+	uint64_t total_packets_rx;
+	uint64_t total_successful_enqueues;
+	uint64_t total_failed_enqueues;
+};
+
 typedef enum copy_mode_t {
 #define COPY_MODE_SW "sw"
 	COPY_MODE_SW_NUM,
@@ -89,6 +106,457 @@ static struct rte_ether_addr ioat_ports_eth_addr[RTE_MAX_ETHPORTS];
 static struct rte_eth_dev_tx_buffer *tx_buffer[RTE_MAX_ETHPORTS];
 struct rte_mempool *ioat_pktmbuf_pool;
 
+/* Print out statistics for one port. */
+static void
+print_port_stats(uint16_t port_id)
+{
+	printf("\nStatistics for port %u ------------------------------"
+		"\nPackets sent: %34"PRIu64
+		"\nPackets received: %30"PRIu64
+		"\nPackets dropped on tx: %25"PRIu64
+		"\nPackets dropped on copy: %23"PRIu64,
+		port_id,
+		port_statistics.tx[port_id],
+		port_statistics.rx[port_id],
+		port_statistics.tx_dropped[port_id],
+		port_statistics.copy_dropped[port_id]);
+}
+
+/* Print out statistics for one IOAT rawdev device. */
+static void
+print_rawdev_stats(uint32_t dev_id, uint64_t *xstats,
+	unsigned int *ids_xstats, uint16_t nb_xstats,
+	struct rte_rawdev_xstats_name *names_xstats)
+{
+	uint16_t i;
+
+	printf("\nIOAT channel %u", dev_id);
+	for (i = 0; i < nb_xstats; i++)
+		printf("\n\t %s: %*"PRIu64,
+			names_xstats[ids_xstats[i]].name,
+			(int)(37 - strlen(names_xstats[ids_xstats[i]].name)),
+			xstats[i]);
+}
+
+static void
+print_total_stats(struct total_statistics *ts)
+{
+	printf("\nAggregate statistics ==============================="
+		"\nTotal packets Tx: %24"PRIu64" [pps]"
+		"\nTotal packets Rx: %24"PRIu64" [pps]"
+		"\nTotal packets dropped: %19"PRIu64" [pps]",
+		ts->total_packets_tx,
+		ts->total_packets_rx,
+		ts->total_packets_dropped);
+
+	if (copy_mode == COPY_MODE_IOAT_NUM) {
+		printf("\nTotal IOAT successful enqueues: %8"PRIu64" [enq/s]"
+			"\nTotal IOAT failed enqueues: %12"PRIu64" [enq/s]",
+			ts->total_successful_enqueues,
+			ts->total_failed_enqueues);
+	}
+
+	printf("\n====================================================\n");
+}
+
+/* Print out statistics on packets dropped. */
+static void
+print_stats(char *prgname)
+{
+	struct total_statistics ts, delta_ts;
+	uint32_t i, port_id, dev_id;
+	struct rte_rawdev_xstats_name *names_xstats;
+	uint64_t *xstats;
+	unsigned int *ids_xstats, nb_xstats;
+	char status_string[120]; /* to print at the top of the output */
+	int status_strlen;
+	int ret;
+
+	const char clr[] = { 27, '[', '2', 'J', '\0' };
+	const char topLeft[] = { 27, '[', '1', ';', '1', 'H', '\0' };
+
+	status_strlen = snprintf(status_string, sizeof(status_string),
+		"%s, ", prgname);
+	status_strlen += snprintf(status_string + status_strlen,
+		sizeof(status_string) - status_strlen,
+		"Worker Threads = %d, ",
+		rte_lcore_count() > 2 ? 2 : 1);
+	status_strlen += snprintf(status_string + status_strlen,
+		sizeof(status_string) - status_strlen,
+		"Copy Mode = %s,\n", copy_mode == COPY_MODE_SW_NUM ?
+		COPY_MODE_SW : COPY_MODE_IOAT);
+	status_strlen += snprintf(status_string + status_strlen,
+		sizeof(status_string) - status_strlen,
+		"Updating MAC = %s, ", mac_updating ?
+		"enabled" : "disabled");
+	status_strlen += snprintf(status_string + status_strlen,
+		sizeof(status_string) - status_strlen,
+		"Rx Queues = %d, ", nb_queues);
+	status_strlen += snprintf(status_string + status_strlen,
+		sizeof(status_string) - status_strlen,
+		"Ring Size = %d\n", ring_size);
+
+	/* Allocate memory for xstats names and values */
+	ret = rte_rawdev_xstats_names_get(
+		cfg.ports[0].ioat_ids[0], NULL, 0);
+	if (ret < 0)
+		return;
+	nb_xstats = (unsigned int)ret;
+
+	names_xstats = malloc(sizeof(*names_xstats) * nb_xstats);
+	if (names_xstats == NULL) {
+		rte_exit(EXIT_FAILURE,
+			"Error allocating xstat names memory\n");
+	}
+	rte_rawdev_xstats_names_get(cfg.ports[0].ioat_ids[0],
+		names_xstats, nb_xstats);
+
+	ids_xstats = malloc(sizeof(*ids_xstats) * 2);
+	if (ids_xstats == NULL) {
+		rte_exit(EXIT_FAILURE,
+			"Error allocating xstat ids_xstats memory\n");
+	}
+
+	xstats = malloc(sizeof(*xstats) * 2);
+	if (xstats == NULL) {
+		rte_exit(EXIT_FAILURE,
+			"Error allocating xstat memory\n");
+	}
+
+	/* Get failed/successful enqueues stats index */
+	ids_xstats[0] = ids_xstats[1] = nb_xstats;
+	for (i = 0; i < nb_xstats; i++) {
+		if (!strcmp(names_xstats[i].name, "failed_enqueues"))
+			ids_xstats[0] = i;
+		else if (!strcmp(names_xstats[i].name, "successful_enqueues"))
+			ids_xstats[1] = i;
+		if (ids_xstats[0] < nb_xstats && ids_xstats[1] < nb_xstats)
+			break;
+	}
+	if (ids_xstats[0] == nb_xstats || ids_xstats[1] == nb_xstats) {
+		rte_exit(EXIT_FAILURE,
+			"Error getting failed/successful enqueues stats index\n");
+	}
+
+	memset(&ts, 0, sizeof(struct total_statistics));
+
+	while (!force_quit) {
+		/* Sleep for 1 second each round - init sleep allows reading
+		 * messages from app startup.
+		 */
+		sleep(1);
+
+		/* Clear screen and move to top left */
+		printf("%s%s", clr, topLeft);
+
+		memset(&delta_ts, 0, sizeof(struct total_statistics));
+
+		printf("%s", status_string);
+
+		for (i = 0; i < cfg.nb_ports; i++) {
+			port_id = cfg.ports[i].rxtx_port;
+			print_port_stats(port_id);
+
+			delta_ts.total_packets_dropped +=
+				port_statistics.tx_dropped[port_id]
+				+ port_statistics.copy_dropped[port_id];
+			delta_ts.total_packets_tx +=
+				port_statistics.tx[port_id];
+			delta_ts.total_packets_rx +=
+				port_statistics.rx[port_id];
+
+			if (copy_mode == COPY_MODE_IOAT_NUM) {
+				uint32_t j;
+
+				for (j = 0; j < cfg.ports[i].nb_queues; j++) {
+					dev_id = cfg.ports[i].ioat_ids[j];
+					rte_rawdev_xstats_get(dev_id,
+						ids_xstats, xstats, 2);
+
+					print_rawdev_stats(dev_id, xstats,
+						ids_xstats, 2, names_xstats);
+
+					delta_ts.total_failed_enqueues +=
+						xstats[ids_xstats[0]];
+					delta_ts.total_successful_enqueues +=
+						xstats[ids_xstats[1]];
+				}
+			}
+		}
+
+		delta_ts.total_packets_tx -= ts.total_packets_tx;
+		delta_ts.total_packets_rx -= ts.total_packets_rx;
+		delta_ts.total_packets_dropped -= ts.total_packets_dropped;
+		delta_ts.total_failed_enqueues -= ts.total_failed_enqueues;
+		delta_ts.total_successful_enqueues -=
+			ts.total_successful_enqueues;
+
+		printf("\n");
+		print_total_stats(&delta_ts);
+
+		ts.total_packets_tx += delta_ts.total_packets_tx;
+		ts.total_packets_rx += delta_ts.total_packets_rx;
+		ts.total_packets_dropped += delta_ts.total_packets_dropped;
+		ts.total_failed_enqueues += delta_ts.total_failed_enqueues;
+		ts.total_successful_enqueues +=
+			delta_ts.total_successful_enqueues;
+	}
+
+	free(names_xstats);
+	free(xstats);
+	free(ids_xstats);
+}
+
+static void
+update_mac_addrs(struct rte_mbuf *m, uint32_t dest_portid)
+{
+	struct rte_ether_hdr *eth;
+	void *tmp;
+
+	eth = rte_pktmbuf_mtod(m, struct rte_ether_hdr *);
+
+	/* 02:00:00:00:00:xx - overwriting 2 bytes of source address but
+	 * it's acceptable cause it gets overwritten by rte_ether_addr_copy
+	 */
+	tmp = &eth->d_addr.addr_bytes[0];
+	*((uint64_t *)tmp) = 0x000000000002 + ((uint64_t)dest_portid << 40);
+
+	/* src addr */
+	rte_ether_addr_copy(&ioat_ports_eth_addr[dest_portid], &eth->s_addr);
+}
+
+static inline void
+pktmbuf_sw_copy(struct rte_mbuf *src, struct rte_mbuf *dst)
+{
+	/* Copy packet metadata */
+	rte_memcpy(&dst->rearm_data,
+		&src->rearm_data,
+		offsetof(struct rte_mbuf, cacheline1)
+		- offsetof(struct rte_mbuf, rearm_data));
+
+	/* Copy packet data */
+	rte_memcpy(rte_pktmbuf_mtod(dst, char *),
+		rte_pktmbuf_mtod(src, char *), src->data_len);
+}
+
+static uint32_t
+ioat_enqueue_packets(struct rte_mbuf **pkts,
+	uint32_t nb_rx, uint16_t dev_id)
+{
+	int ret;
+	uint32_t i;
+	struct rte_mbuf *pkts_copy[MAX_PKT_BURST];
+
+	const uint64_t addr_offset = RTE_PTR_DIFF(pkts[0]->buf_addr,
+		&pkts[0]->rearm_data);
+
+	ret = rte_mempool_get_bulk(ioat_pktmbuf_pool,
+		(void *)pkts_copy, nb_rx);
+
+	if (unlikely(ret < 0))
+		rte_exit(EXIT_FAILURE, "Unable to allocate memory.\n");
+
+	for (i = 0; i < nb_rx; i++) {
+		/* Perform data copy */
+		ret = rte_ioat_enqueue_copy(dev_id,
+			pkts[i]->buf_iova
+			- addr_offset,
+			pkts_copy[i]->buf_iova
+			- addr_offset,
+			rte_pktmbuf_data_len(pkts[i])
+			+ addr_offset,
+			(uintptr_t)pkts[i],
+			(uintptr_t)pkts_copy[i],
+			0 /* nofence */);
+
+		if (ret != 1)
+			break;
+	}
+
+	ret = i;
+	/* Free any not enqueued packets. */
+	rte_mempool_put_bulk(ioat_pktmbuf_pool, (void *)&pkts[i], nb_rx - i);
+	rte_mempool_put_bulk(ioat_pktmbuf_pool, (void *)&pkts_copy[i],
+		nb_rx - i);
+
+	return ret;
+}
+
+/* Receive packets on one port and enqueue to IOAT rawdev or rte_ring. */
+static void
+ioat_rx_port(struct rxtx_port_config *rx_config)
+{
+	uint32_t nb_rx, nb_enq, i, j;
+	struct rte_mbuf *pkts_burst[MAX_PKT_BURST];
+
+	for (i = 0; i < rx_config->nb_queues; i++) {
+
+		nb_rx = rte_eth_rx_burst(rx_config->rxtx_port, i,
+			pkts_burst, MAX_PKT_BURST);
+
+		if (nb_rx == 0)
+			continue;
+
+		port_statistics.rx[rx_config->rxtx_port] += nb_rx;
+
+		if (copy_mode == COPY_MODE_IOAT_NUM) {
+			/* Perform packet hardware copy */
+			nb_enq = ioat_enqueue_packets(pkts_burst,
+				nb_rx, rx_config->ioat_ids[i]);
+			if (nb_enq > 0)
+				rte_ioat_do_copies(rx_config->ioat_ids[i]);
+		} else {
+			/* Perform packet software copy, free source packets */
+			int ret;
+			struct rte_mbuf *pkts_burst_copy[MAX_PKT_BURST];
+
+			ret = rte_mempool_get_bulk(ioat_pktmbuf_pool,
+				(void *)pkts_burst_copy, nb_rx);
+
+			if (unlikely(ret < 0))
+				rte_exit(EXIT_FAILURE,
+					"Unable to allocate memory.\n");
+
+			for (j = 0; j < nb_rx; j++)
+				pktmbuf_sw_copy(pkts_burst[j],
+					pkts_burst_copy[j]);
+
+			rte_mempool_put_bulk(ioat_pktmbuf_pool,
+				(void *)pkts_burst, nb_rx);
+
+			nb_enq = rte_ring_enqueue_burst(
+				rx_config->rx_to_tx_ring,
+				(void *)pkts_burst_copy, nb_rx, NULL);
+
+			/* Free any not enqueued packets. */
+			rte_mempool_put_bulk(ioat_pktmbuf_pool,
+				(void *)&pkts_burst_copy[nb_enq],
+				nb_rx - nb_enq);
+		}
+
+		port_statistics.copy_dropped[rx_config->rxtx_port] +=
+			(nb_rx - nb_enq);
+	}
+}
+
+/* Transmit packets from IOAT rawdev/rte_ring for one port. */
+static void
+ioat_tx_port(struct rxtx_port_config *tx_config)
+{
+	uint32_t i, j, nb_dq = 0;
+	struct rte_mbuf *mbufs_src[MAX_PKT_BURST];
+	struct rte_mbuf *mbufs_dst[MAX_PKT_BURST];
+
+	for (i = 0; i < tx_config->nb_queues; i++) {
+		if (copy_mode == COPY_MODE_IOAT_NUM) {
+			/* Deque the mbufs from IOAT device. */
+			nb_dq = rte_ioat_completed_copies(
+				tx_config->ioat_ids[i], MAX_PKT_BURST,
+				(void *)mbufs_src, (void *)mbufs_dst);
+		} else {
+			/* Deque the mbufs from rx_to_tx_ring. */
+			nb_dq = rte_ring_dequeue_burst(
+				tx_config->rx_to_tx_ring, (void *)mbufs_dst,
+				MAX_PKT_BURST, NULL);
+		}
+
+		if ((int32_t) nb_dq <= 0)
+			return;
+
+		if (copy_mode == COPY_MODE_IOAT_NUM)
+			rte_mempool_put_bulk(ioat_pktmbuf_pool,
+				(void *)mbufs_src, nb_dq);
+
+		/* Update macs if enabled */
+		if (mac_updating) {
+			for (j = 0; j < nb_dq; j++)
+				update_mac_addrs(mbufs_dst[j],
+					tx_config->rxtx_port);
+		}
+
+		const uint16_t nb_tx = rte_eth_tx_burst(
+			tx_config->rxtx_port, 0,
+			(void *)mbufs_dst, nb_dq);
+
+		port_statistics.tx[tx_config->rxtx_port] += nb_tx;
+
+		/* Free any unsent packets. */
+		if (unlikely(nb_tx < nb_dq))
+			rte_mempool_put_bulk(ioat_pktmbuf_pool,
+			(void *)&mbufs_dst[nb_tx],
+				nb_dq - nb_tx);
+	}
+}
+
+/* Main rx processing loop for IOAT rawdev. */
+static void
+rx_main_loop(void)
+{
+	uint16_t i;
+	uint16_t nb_ports = cfg.nb_ports;
+
+	RTE_LOG(INFO, IOAT, "Entering main rx loop for copy on lcore %u\n",
+		rte_lcore_id());
+
+	while (!force_quit)
+		for (i = 0; i < nb_ports; i++)
+			ioat_rx_port(&cfg.ports[i]);
+}
+
+/* Main tx processing loop for hardware copy. */
+static void
+tx_main_loop(void)
+{
+	uint16_t i;
+	uint16_t nb_ports = cfg.nb_ports;
+
+	RTE_LOG(INFO, IOAT, "Entering main tx loop for copy on lcore %u\n",
+		rte_lcore_id());
+
+	while (!force_quit)
+		for (i = 0; i < nb_ports; i++)
+			ioat_tx_port(&cfg.ports[i]);
+}
+
+/* Main rx and tx loop if only one slave lcore available */
+static void
+rxtx_main_loop(void)
+{
+	uint16_t i;
+	uint16_t nb_ports = cfg.nb_ports;
+
+	RTE_LOG(INFO, IOAT, "Entering main rx and tx loop for copy on"
+		" lcore %u\n", rte_lcore_id());
+
+	while (!force_quit)
+		for (i = 0; i < nb_ports; i++) {
+			ioat_rx_port(&cfg.ports[i]);
+			ioat_tx_port(&cfg.ports[i]);
+		}
+}
+
+static void start_forwarding_cores(void)
+{
+	uint32_t lcore_id = rte_lcore_id();
+
+	RTE_LOG(INFO, IOAT, "Entering %s on lcore %u\n",
+		__func__, rte_lcore_id());
+
+	if (cfg.nb_lcores == 1) {
+		lcore_id = rte_get_next_lcore(lcore_id, true, true);
+		rte_eal_remote_launch((lcore_function_t *)rxtx_main_loop,
+			NULL, lcore_id);
+	} else if (cfg.nb_lcores > 1) {
+		lcore_id = rte_get_next_lcore(lcore_id, true, true);
+		rte_eal_remote_launch((lcore_function_t *)rx_main_loop,
+			NULL, lcore_id);
+
+		lcore_id = rte_get_next_lcore(lcore_id, true, true);
+		rte_eal_remote_launch((lcore_function_t *)tx_main_loop, NULL,
+			lcore_id);
+	}
+}
+
 /* Display usage */
 static void
 ioat_usage(const char *prgname)
@@ -229,7 +697,7 @@ check_link_status(uint32_t port_mask)
 {
 	uint16_t portid;
 	struct rte_eth_link link;
-	int retval = 0;
+	int ret, link_status = 0;
 
 	printf("\nChecking link status\n");
 	RTE_ETH_FOREACH_DEV(portid) {
@@ -237,7 +705,12 @@ check_link_status(uint32_t port_mask)
 			continue;
 
 		memset(&link, 0, sizeof(link));
-		rte_eth_link_get(portid, &link);
+		ret = rte_eth_link_get(portid, &link);
+		if (ret < 0) {
+			printf("Port %u link get failed: err=%d\n",
+					portid, ret);
+			continue;
+		}
 
 		/* Print link status */
 		if (link.link_status) {
@@ -246,11 +719,78 @@ check_link_status(uint32_t port_mask)
 				portid, link.link_speed,
 				(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
 				("full-duplex") : ("half-duplex\n"));
-			retval = 1;
+			link_status = 1;
 		} else
 			printf("Port %d Link Down\n", portid);
 	}
-	return retval;
+	return link_status;
+}
+
+static void
+configure_rawdev_queue(uint32_t dev_id)
+{
+	struct rte_ioat_rawdev_config dev_config = { .ring_size = ring_size };
+	struct rte_rawdev_info info = { .dev_private = &dev_config };
+
+	if (rte_rawdev_configure(dev_id, &info) != 0) {
+		rte_exit(EXIT_FAILURE,
+			"Error with rte_rawdev_configure()\n");
+	}
+	if (rte_rawdev_start(dev_id) != 0) {
+		rte_exit(EXIT_FAILURE,
+			"Error with rte_rawdev_start()\n");
+	}
+}
+
+static void
+assign_rawdevs(void)
+{
+	uint16_t nb_rawdev = 0, rdev_id = 0;
+	uint32_t i, j;
+
+	for (i = 0; i < cfg.nb_ports; i++) {
+		for (j = 0; j < cfg.ports[i].nb_queues; j++) {
+			struct rte_rawdev_info rdev_info = { 0 };
+
+			do {
+				if (rdev_id == rte_rawdev_count())
+					goto end;
+				rte_rawdev_info_get(rdev_id++, &rdev_info);
+			} while (rdev_info.driver_name == NULL ||
+					strcmp(rdev_info.driver_name,
+						IOAT_PMD_RAWDEV_NAME_STR) != 0);
+
+			cfg.ports[i].ioat_ids[j] = rdev_id - 1;
+			configure_rawdev_queue(cfg.ports[i].ioat_ids[j]);
+			++nb_rawdev;
+		}
+	}
+end:
+	if (nb_rawdev < cfg.nb_ports * cfg.ports[0].nb_queues)
+		rte_exit(EXIT_FAILURE,
+			"Not enough IOAT rawdevs (%u) for all queues (%u).\n",
+			nb_rawdev, cfg.nb_ports * cfg.ports[0].nb_queues);
+	RTE_LOG(INFO, IOAT, "Number of used rawdevs: %u.\n", nb_rawdev);
+}
+
+static void
+assign_rings(void)
+{
+	uint32_t i;
+
+	for (i = 0; i < cfg.nb_ports; i++) {
+		char ring_name[RTE_RING_NAMESIZE];
+
+		snprintf(ring_name, sizeof(ring_name), "rx_to_tx_ring_%u", i);
+		/* Create ring for inter core communication */
+		cfg.ports[i].rx_to_tx_ring = rte_ring_create(
+			ring_name, ring_size,
+			rte_socket_id(), RING_F_SP_ENQ | RING_F_SC_DEQ);
+
+		if (cfg.ports[i].rx_to_tx_ring == NULL)
+			rte_exit(EXIT_FAILURE, "Ring create failed: %s\n",
+				rte_strerror(rte_errno));
+	}
 }
 
 /*
@@ -289,7 +829,11 @@ port_init(uint16_t portid, struct rte_mempool *mbuf_pool, uint16_t nb_queues)
 	/* Init port */
 	printf("Initializing port %u... ", portid);
 	fflush(stdout);
-	rte_eth_dev_info_get(portid, &dev_info);
+	ret = rte_eth_dev_info_get(portid, &dev_info);
+	if (ret < 0)
+		rte_exit(EXIT_FAILURE, "Cannot get device info: %s, port=%u\n",
+			rte_strerror(-ret), portid);
+
 	local_port_conf.rx_adv_conf.rss_conf.rss_hf &=
 		dev_info.flow_type_rss_offloads;
 	if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
@@ -344,6 +888,14 @@ port_init(uint16_t portid, struct rte_mempool *mbuf_pool, uint16_t nb_queues)
 
 	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.tx_dropped[portid]);
+	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)
@@ -420,6 +972,9 @@ main(int argc, char **argv)
 	RTE_ETH_FOREACH_DEV(portid)
 		port_init(portid, ioat_pktmbuf_pool, nb_queues);
 
+	/* Initialize port xstats */
+	memset(&port_statistics, 0, sizeof(port_statistics));
+
 	while (!check_link_status(ioat_enabled_port_mask) && !force_quit)
 		sleep(1);
 
@@ -428,10 +983,32 @@ main(int argc, char **argv)
 	if (cfg.nb_lcores < 1)
 		rte_exit(EXIT_FAILURE,
 			"There should be at least one slave lcore.\n");
+
+	if (copy_mode == COPY_MODE_IOAT_NUM)
+		assign_rawdevs();
+	else /* copy_mode == COPY_MODE_SW_NUM */
+		assign_rings();
+
+	start_forwarding_cores();
+	/* master core prints stats while other cores forward */
+	print_stats(argv[0]);
+
+	/* force_quit is true when we get here */
+	rte_eal_mp_wait_lcore();
+
+	uint32_t j;
 	for (i = 0; i < cfg.nb_ports; i++) {
 		printf("Closing port %d\n", cfg.ports[i].rxtx_port);
 		rte_eth_dev_stop(cfg.ports[i].rxtx_port);
 		rte_eth_dev_close(cfg.ports[i].rxtx_port);
+		if (copy_mode == COPY_MODE_IOAT_NUM) {
+			for (j = 0; j < cfg.ports[i].nb_queues; j++) {
+				printf("Stopping rawdev %d\n",
+					cfg.ports[i].ioat_ids[j]);
+				rte_rawdev_stop(cfg.ports[i].ioat_ids[j]);
+			}
+		} else /* copy_mode == COPY_MODE_SW_NUM */
+			rte_ring_free(cfg.ports[i].rx_to_tx_ring);
 	}
 
 	printf("Bye...\n");