[dpdk-dev] [RFC PATCH 5/5] example/l3fwd_graph: l3fwd using graph architecture

[<jerinj@marvell.com>]

From: Nithin Dabilpuram <ndabilpuram@marvell.com>

This example application showcase the l3fwd implementation
using graph architecture.

The graphical topology representation of the l3fwd-graph is the following,
http://bit.ly/39UPPGm

Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
---
 examples/Makefile                |    3 +
 examples/l3fwd-graph/Makefile    |   58 ++
 examples/l3fwd-graph/main.c      | 1131 ++++++++++++++++++++++++++++++
 examples/l3fwd-graph/meson.build |   13 +
 examples/meson.build             |    6 +-
 5 files changed, 1209 insertions(+), 2 deletions(-)
 create mode 100644 examples/l3fwd-graph/Makefile
 create mode 100644 examples/l3fwd-graph/main.c
 create mode 100644 examples/l3fwd-graph/meson.build

diff --git a/examples/Makefile b/examples/Makefile
index feff79784..96a2b9575 100644
--- a/examples/Makefile
+++ b/examples/Makefile
@@ -51,6 +51,9 @@ DIRS-$(CONFIG_RTE_LIBRTE_ACL) += l3fwd-acl
 ifeq ($(CONFIG_RTE_LIBRTE_LPM)$(CONFIG_RTE_LIBRTE_HASH),yy)
 DIRS-$(CONFIG_RTE_LIBRTE_POWER) += l3fwd-power
 endif
+ifeq ($(CONFIG_RTE_LIBRTE_GRAPH), y)
+DIRS-y += l3fwd-graph
+endif
 DIRS-y += link_status_interrupt
 DIRS-y += multi_process
 DIRS-y += ntb
diff --git a/examples/l3fwd-graph/Makefile b/examples/l3fwd-graph/Makefile
new file mode 100644
index 000000000..7596de500
--- /dev/null
+++ b/examples/l3fwd-graph/Makefile
@@ -0,0 +1,58 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(C) 2020 Marvell International Ltd.
+
+# binary name
+APP = l3fwd-graph
+
+# all source are stored in SRCS-y
+SRCS-y := main.c 
+
+# Build using pkg-config variables if possible
+ifeq ($(shell pkg-config --exists libdpdk && echo 0),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)
+
+PKGCONF=pkg-config --define-prefix
+
+PC_FILE := $(shell $(PKGCONF) --path libdpdk)
+CFLAGS += -O3 $(shell $(PKGCONF) --cflags libdpdk) -DALLOW_EXPERIMENTAL_API
+LDFLAGS_SHARED = $(shell $(PKGCONF) --libs libdpdk)
+LDFLAGS_STATIC = -Wl,-Bstatic $(shell $(PKGCONF) --static --libs libdpdk)
+
+build/$(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
+	test -d build && rmdir -p build || true
+
+else # Build using legacy build system
+
+ifeq ($(RTE_SDK),)
+$(error "Please define RTE_SDK environment variable")
+endif
+
+# Default target, detect a build directory, by looking for a path with a .config
+RTE_TARGET ?= $(notdir $(abspath $(dir $(firstword $(wildcard $(RTE_SDK)/*/.config)))))
+
+include $(RTE_SDK)/mk/rte.vars.mk
+
+CFLAGS += -DALLOW_EXPERIMENTAL_API
+CFLAGS += -I$(SRCDIR)
+CFLAGS += -O3 $(USER_FLAGS)
+CFLAGS += $(WERROR_FLAGS)
+
+include $(RTE_SDK)/mk/rte.extapp.mk
+endif
diff --git a/examples/l3fwd-graph/main.c b/examples/l3fwd-graph/main.c
new file mode 100644
index 000000000..7be41c4dc
--- /dev/null
+++ b/examples/l3fwd-graph/main.c
@@ -0,0 +1,1131 @@
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(C) 2020 Marvell International Ltd.
+ */
+
+#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 <signal.h>
+#include <stdbool.h>
+#include <arpa/inet.h>
+
+#include <rte_common.h>
+#include <rte_vect.h>
+#include <rte_byteorder.h>
+#include <rte_log.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_ip.h>
+#include <rte_tcp.h>
+#include <rte_udp.h>
+#include <rte_string_fns.h>
+#include <rte_cpuflags.h>
+#include <rte_graph_worker.h>
+#include <rte_node_eth_api.h>
+#include <rte_node_ip4_api.h>
+
+#include <unistd.h>
+#include <cmdline_parse.h>
+#include <cmdline_parse_etheraddr.h>
+
+/* Log type */
+#define RTE_LOGTYPE_L3FWD_GRAPH RTE_LOGTYPE_USER1
+
+/*
+ * Configurable number of RX/TX ring descriptors
+ */
+#define RTE_TEST_RX_DESC_DEFAULT 1024
+#define RTE_TEST_TX_DESC_DEFAULT 1024
+
+#define MAX_TX_QUEUE_PER_PORT RTE_MAX_ETHPORTS
+#define MAX_RX_QUEUE_PER_PORT 128
+
+#define MAX_RX_QUEUE_PER_LCORE 16
+
+#define MAX_LCORE_PARAMS 1024
+
+#define NB_SOCKETS 8
+
+/* Static global variables used within this file. */
+static uint16_t nb_rxd = RTE_TEST_RX_DESC_DEFAULT;
+static uint16_t nb_txd = RTE_TEST_TX_DESC_DEFAULT;
+
+/**< Ports set in promiscuous mode off by default. */
+static int promiscuous_on;
+
+static int numa_on = 1; /**< NUMA is enabled by default. */
+static int per_port_pool; /**< Use separate buffer pools per port; disabled */
+			  /**< by default */
+
+static volatile bool force_quit;
+
+/* ethernet addresses of ports */
+static uint64_t dest_eth_addr[RTE_MAX_ETHPORTS];
+static struct rte_ether_addr ports_eth_addr[RTE_MAX_ETHPORTS];
+xmm_t val_eth[RTE_MAX_ETHPORTS];
+
+/* mask of enabled ports */
+static uint32_t enabled_port_mask;
+
+struct lcore_rx_queue {
+	uint16_t port_id;
+	uint8_t queue_id;
+	char node_name[RTE_NODE_NAMESIZE];
+};
+
+/* lcore conf */
+struct lcore_conf {
+	uint16_t n_rx_queue;
+	struct lcore_rx_queue rx_queue_list[MAX_RX_QUEUE_PER_LCORE];
+
+	struct rte_graph *graph;
+	char name[RTE_GRAPH_NAMESIZE];
+	rte_graph_t graph_id;
+} __rte_cache_aligned;
+
+static struct lcore_conf lcore_conf[RTE_MAX_LCORE];
+
+struct lcore_params {
+	uint16_t port_id;
+	uint8_t queue_id;
+	uint8_t lcore_id;
+} __rte_cache_aligned;
+
+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]);
+
+static struct rte_eth_conf port_conf = {
+	.rxmode = {
+		.mq_mode = ETH_MQ_RX_RSS,
+		.max_rx_pkt_len = RTE_ETHER_MAX_LEN,
+		.split_hdr_size = 0,
+	},
+	.rx_adv_conf = {
+		.rss_conf = {
+			.rss_key = NULL,
+			.rss_hf = ETH_RSS_IP,
+		},
+	},
+	.txmode = {
+		.mq_mode = ETH_MQ_TX_NONE,
+	},
+};
+
+static struct rte_mempool *pktmbuf_pool[RTE_MAX_ETHPORTS][NB_SOCKETS];
+
+static struct rte_node_ethdev_config ethdev_conf[RTE_MAX_ETHPORTS];
+
+struct ipv4_l3fwd_lpm_route {
+	uint32_t ip;
+	uint8_t  depth;
+	uint8_t  if_out;
+};
+
+#define IPV4_L3FWD_LPM_NUM_ROUTES \
+	(sizeof(ipv4_l3fwd_lpm_route_array) / sizeof(ipv4_l3fwd_lpm_route_array[0]))
+/* 198.18.0.0/16 are set aside for RFC2544 benchmarking. */
+static struct ipv4_l3fwd_lpm_route ipv4_l3fwd_lpm_route_array[] = {
+	{RTE_IPV4(198, 18, 0, 0), 24, 0},
+	{RTE_IPV4(198, 18, 1, 0), 24, 1},
+	{RTE_IPV4(198, 18, 2, 0), 24, 2},
+	{RTE_IPV4(198, 18, 3, 0), 24, 3},
+	{RTE_IPV4(198, 18, 4, 0), 24, 4},
+	{RTE_IPV4(198, 18, 5, 0), 24, 5},
+	{RTE_IPV4(198, 18, 6, 0), 24, 6},
+	{RTE_IPV4(198, 18, 7, 0), 24, 7},
+};
+
+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;
+		if (!rte_lcore_is_enabled(lcore)) {
+			printf("error: lcore %hhu is not enabled in lcore mask\n", lcore);
+			return -1;
+		}
+
+		if (lcore == rte_get_master_lcore()) {
+			printf("error: lcore %u is master lcore\n", lcore);
+			return -1;
+		}
+		if ((socketid = rte_lcore_to_socket_id(lcore) != 0) &&
+			(numa_on == 0)) {
+			printf("warning: lcore %hhu is on socket %d with numa off \n",
+				lcore, socketid);
+		}
+	}
+	return 0;
+}
+
+static int
+check_port_config(void)
+{
+	uint16_t 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 (!rte_eth_dev_is_valid_port(portid)) {
+			printf("port %u is not present on the board\n", portid);
+			return -1;
+		}
+	}
+	return 0;
+}
+
+static uint8_t
+get_port_n_rx_queues(const uint16_t port)
+{
+	int queue = -1;
+	uint16_t i;
+
+	for (i = 0; i < nb_lcore_params; ++i) {
+		if (lcore_params[i].port_id == port) {
+			if (lcore_params[i].queue_id == queue+1)
+				queue = lcore_params[i].queue_id;
+			else
+				rte_exit(EXIT_FAILURE, "queue ids of the port %d must be"
+						" in sequence and must start with 0\n",
+						lcore_params[i].port_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;
+}
+
+/* display usage */
+static void
+print_usage(const char *prgname)
+{
+	fprintf(stderr, "%s [EAL options] --"
+		" -p PORTMASK"
+		" [-P]"
+		" [-E]"
+		" [-L]"
+		" --config (port,queue,lcore)[,(port,queue,lcore)]"
+		" [--eth-dest=X,MM:MM:MM:MM:MM:MM]"
+		" [--enable-jumbo [--max-pkt-len PKTLEN]]"
+		" [--no-numa]"
+		" [--per-port-pool]\n\n"
+
+		"  -p PORTMASK: Hexadecimal bitmask of ports to configure\n"
+		"  -P : Enable promiscuous mode\n"
+		"  --config (port,queue,lcore): Rx queue configuration\n"
+		"  --eth-dest=X,MM:MM:MM:MM:MM:MM: Ethernet destination for port X\n"
+		"  --enable-jumbo: Enable jumbo frames\n"
+		"  --max-pkt-len: Under the premise of enabling jumbo,\n"
+		"                 maximum packet length in decimal (64-9600)\n"
+		"  --no-numa: Disable numa awareness\n"
+		"  --per-port-pool: Use separate buffer pool per port\n\n",
+		prgname);
+}
+
+static int
+parse_max_pkt_len(const char *pktlen)
+{
+	char *end = NULL;
+	unsigned long len;
+
+	/* parse decimal string */
+	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;
+
+	/* 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 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);
+		if (rte_strsplit(s, sizeof(s), str_fld, _NUM_FLD, ',') != _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 void
+parse_eth_dest(const char *optarg)
+{
+	uint16_t portid;
+	char *port_end;
+	uint8_t c, *dest, peer_addr[6];
+
+	errno = 0;
+	portid = strtoul(optarg, &port_end, 10);
+	if (errno != 0 || port_end == optarg || *port_end++ != ',')
+		rte_exit(EXIT_FAILURE,
+		"Invalid eth-dest: %s", optarg);
+	if (portid >= RTE_MAX_ETHPORTS)
+		rte_exit(EXIT_FAILURE,
+		"eth-dest: port %d >= RTE_MAX_ETHPORTS(%d)\n",
+		portid, RTE_MAX_ETHPORTS);
+
+	if (cmdline_parse_etheraddr(NULL, port_end,
+		&peer_addr, sizeof(peer_addr)) < 0)
+		rte_exit(EXIT_FAILURE,
+		"Invalid ethernet address: %s\n",
+		port_end);
+	dest = (uint8_t *)&dest_eth_addr[portid];
+	for (c = 0; c < 6; c++)
+		dest[c] = peer_addr[c];
+	*(uint64_t *)(val_eth + portid) = dest_eth_addr[portid];
+}
+
+#define MAX_JUMBO_PKT_LEN  9600
+#define MEMPOOL_CACHE_SIZE 256
+
+static const char short_options[] =
+	"p:"  /* portmask */
+	"P"   /* promiscuous */
+	"L"   /* enable long prefix match */
+	"E"   /* enable exact match */
+	;
+
+#define CMD_LINE_OPT_CONFIG "config"
+#define CMD_LINE_OPT_ETH_DEST "eth-dest"
+#define CMD_LINE_OPT_NO_NUMA "no-numa"
+#define CMD_LINE_OPT_ENABLE_JUMBO "enable-jumbo"
+#define CMD_LINE_OPT_PER_PORT_POOL "per-port-pool"
+enum {
+	/* long options mapped to a short option */
+
+	/* first long only option value must be >= 256, so that we won't
+	 * conflict with short options */
+	CMD_LINE_OPT_MIN_NUM = 256,
+	CMD_LINE_OPT_CONFIG_NUM,
+	CMD_LINE_OPT_ETH_DEST_NUM,
+	CMD_LINE_OPT_NO_NUMA_NUM,
+	CMD_LINE_OPT_ENABLE_JUMBO_NUM,
+	CMD_LINE_OPT_PARSE_PER_PORT_POOL,
+};
+
+static const struct option lgopts[] = {
+	{CMD_LINE_OPT_CONFIG, 1, 0, CMD_LINE_OPT_CONFIG_NUM},
+	{CMD_LINE_OPT_ETH_DEST, 1, 0, CMD_LINE_OPT_ETH_DEST_NUM},
+	{CMD_LINE_OPT_NO_NUMA, 0, 0, CMD_LINE_OPT_NO_NUMA_NUM},
+	{CMD_LINE_OPT_ENABLE_JUMBO, 0, 0, CMD_LINE_OPT_ENABLE_JUMBO_NUM},
+	{CMD_LINE_OPT_PER_PORT_POOL, 0, 0, CMD_LINE_OPT_PARSE_PER_PORT_POOL},
+	{NULL, 0, 0, 0}
+};
+
+/*
+ * This expression is used to calculate the number of mbufs needed
+ * depending on user input, taking  into account memory for rx and
+ * tx hardware rings, cache per lcore and mtable per port per lcore.
+ * RTE_MAX is used to ensure that NB_MBUF never goes below a minimum
+ * value of 8192
+ */
+#define NB_MBUF(nports) RTE_MAX(	\
+	(nports*nb_rx_queue*nb_rxd +		\
+	nports*nb_lcores*RTE_GRAPH_BURST_SIZE +	\
+	nports*n_tx_queue*nb_txd +		\
+	nb_lcores*MEMPOOL_CACHE_SIZE),		\
+	(unsigned)8192)
+
+/* Parse the argument given in the command line of the application */
+static int
+parse_args(int argc, char **argv)
+{
+	int opt, ret;
+	char **argvopt;
+	int option_index;
+	char *prgname = argv[0];
+
+	argvopt = argv;
+
+	/* Error or normal output strings. */
+	while ((opt = getopt_long(argc, argvopt, short_options,
+				lgopts, &option_index)) != EOF) {
+
+		switch (opt) {
+		/* portmask */
+		case 'p':
+			enabled_port_mask = parse_portmask(optarg);
+			if (enabled_port_mask == 0) {
+				fprintf(stderr, "Invalid portmask\n");
+				print_usage(prgname);
+				return -1;
+			}
+			break;
+
+		case 'P':
+			promiscuous_on = 1;
+			break;
+
+		/* long options */
+		case CMD_LINE_OPT_CONFIG_NUM:
+			ret = parse_config(optarg);
+			if (ret) {
+				fprintf(stderr, "Invalid config\n");
+				print_usage(prgname);
+				return -1;
+			}
+			break;
+
+		case CMD_LINE_OPT_ETH_DEST_NUM:
+			parse_eth_dest(optarg);
+			break;
+
+		case CMD_LINE_OPT_NO_NUMA_NUM:
+			numa_on = 0;
+			break;
+
+		case CMD_LINE_OPT_ENABLE_JUMBO_NUM: {
+			const struct option lenopts = {
+				"max-pkt-len", required_argument, 0, 0
+			};
+
+			port_conf.rxmode.offloads |= DEV_RX_OFFLOAD_JUMBO_FRAME;
+			port_conf.txmode.offloads |= DEV_TX_OFFLOAD_MULTI_SEGS;
+
+			/*
+			 * if no max-pkt-len set, use the default
+			 * value RTE_ETHER_MAX_LEN.
+			 */
+			if (getopt_long(argc, argvopt, "",
+					&lenopts, &option_index) == 0) {
+				ret = parse_max_pkt_len(optarg);
+				if (ret < 64 || ret > MAX_JUMBO_PKT_LEN) {
+					fprintf(stderr,
+						"invalid maximum packet length\n");
+					print_usage(prgname);
+					return -1;
+				}
+				port_conf.rxmode.max_rx_pkt_len = ret;
+			}
+			break;
+		}
+
+		case CMD_LINE_OPT_PARSE_PER_PORT_POOL:
+			printf("per port buffer pool is enabled\n");
+			per_port_pool = 1;
+			break;
+
+		default:
+			print_usage(prgname);
+			return -1;
+		}
+	}
+
+	if (optind >= 0)
+		argv[optind-1] = prgname;
+
+	ret = optind-1;
+	optind = 1; /* reset getopt lib */
+	return ret;
+}
+
+static void
+print_ethaddr(const char *name, const struct rte_ether_addr *eth_addr)
+{
+	char buf[RTE_ETHER_ADDR_FMT_SIZE];
+	rte_ether_format_addr(buf, RTE_ETHER_ADDR_FMT_SIZE, eth_addr);
+	printf("%s%s", name, buf);
+}
+
+static int
+init_mem(uint16_t portid, unsigned int nb_mbuf)
+{
+	int socketid;
+	unsigned lcore_id;
+	char s[64];
+
+	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+		if (rte_lcore_is_enabled(lcore_id) == 0)
+			continue;
+
+		if (numa_on)
+			socketid = rte_lcore_to_socket_id(lcore_id);
+		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[portid][socketid] == NULL) {
+			snprintf(s, sizeof(s), "mbuf_pool_%d:%d",
+				 portid, socketid);
+			/* Create a pool with priv size of a cacheline */
+			pktmbuf_pool[portid][socketid] =
+				rte_pktmbuf_pool_create(s, nb_mbuf,
+					MEMPOOL_CACHE_SIZE, RTE_CACHE_LINE_SIZE,
+					RTE_MBUF_DEFAULT_BUF_SIZE, socketid);
+			if (pktmbuf_pool[portid][socketid] == NULL)
+				rte_exit(EXIT_FAILURE,
+					"Cannot init mbuf pool on socket %d\n",
+					socketid);
+			else
+				printf("Allocated mbuf pool on socket %d\n",
+					socketid);
+
+		}
+	}
+	return 0;
+}
+
+/* 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++) {
+		if (force_quit)
+			return;
+		all_ports_up = 1;
+		RTE_ETH_FOREACH_DEV(portid) {
+			if (force_quit)
+				return;
+			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
+signal_handler(int signum)
+{
+	if (signum == SIGINT || signum == SIGTERM) {
+		printf("\n\nSignal %d received, preparing to exit...\n",
+				signum);
+		force_quit = true;
+	}
+}
+
+static void
+print_stats(void)
+{
+	const char topLeft[] = { 27, '[', '1', ';', '1', 'H','\0' };
+	const char clr[] = { 27, '[', '2', 'J', '\0' };
+	struct rte_graph_cluster_stats_param s_param;
+	struct rte_graph_cluster_stats *stats;
+	const char *pattern = "worker_*";
+
+	/* Prepare stats object */
+	memset(&s_param, 0, sizeof(s_param));
+	s_param.f = stdout;
+	s_param.socket_id = SOCKET_ID_ANY;
+	s_param.graph_patterns = &pattern;
+	s_param.nb_graph_patterns =  1;
+
+	stats = rte_graph_cluster_stats_create(&s_param);
+	if (stats == NULL)
+		rte_exit(EXIT_FAILURE,
+			 "Unable to create stats object\n");
+
+	while (!force_quit) {
+		/* Clear screen and move to top left */
+		printf("%s%s", clr, topLeft);
+		rte_graph_cluster_stats_get(stats, 0);
+		rte_delay_ms(1E3);
+	}
+
+	rte_graph_cluster_stats_destroy(stats);
+}
+
+/* main processing loop */
+static int
+graph_main_loop(void *conf)
+{
+	struct lcore_conf *qconf;
+	struct rte_graph *graph;
+	unsigned lcore_id;
+
+	RTE_SET_USED(conf);
+
+	lcore_id = rte_lcore_id();
+	qconf = &lcore_conf[lcore_id];
+	graph = qconf->graph;
+
+	if (!graph) {
+		RTE_LOG(INFO, L3FWD_GRAPH,
+			"lcore %u has nothing to do\n", lcore_id);
+		return 0;
+	}
+
+	RTE_LOG(INFO, L3FWD_GRAPH,
+		"entering main loop on lcore %u, graph %s(%p)\n",
+		lcore_id, qconf->name, graph);
+
+	while (likely(!force_quit)) {
+		rte_graph_walk(graph);
+	}
+
+	return 0;
+}
+
+int
+main(int argc, char **argv)
+{
+	const char *node_patterns[64] = {"ip4*", "ethdev_tx-*", "pkt_drop", };
+	uint8_t rewrite_data[2 * sizeof(struct rte_ether_addr)];
+	uint8_t nb_rx_queue, queue, socketid;
+	struct rte_ether_addr *ether_addr;
+	struct rte_graph_param graph_conf;
+	struct rte_eth_dev_info dev_info;
+	unsigned nb_ports, nb_conf = 0;
+	uint32_t n_tx_queue, nb_lcores;
+	struct rte_eth_txconf *txconf;
+	uint16_t queueid, portid, i;
+	struct lcore_conf *qconf;
+	uint16_t nb_patterns = 3;
+	uint16_t nb_graphs = 0;
+	uint8_t rewrite_len;
+	unsigned lcore_id;
+	int ret;
+
+	/* init EAL */
+	ret = rte_eal_init(argc, argv);
+	if (ret < 0)
+		rte_exit(EXIT_FAILURE, "Invalid EAL parameters\n");
+	argc -= ret;
+	argv += ret;
+
+	force_quit = false;
+	signal(SIGINT, signal_handler);
+	signal(SIGTERM, signal_handler);
+
+	/* pre-init dst MACs for all ports to 02:00:00:00:00:xx */
+	for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++) {
+		dest_eth_addr[portid] =
+			RTE_ETHER_LOCAL_ADMIN_ADDR + ((uint64_t)portid << 40);
+		*(uint64_t *)(val_eth + portid) = dest_eth_addr[portid];
+	}
+
+	/* parse application arguments (after the EAL ones) */
+	ret = parse_args(argc, argv);
+	if (ret < 0)
+		rte_exit(EXIT_FAILURE, "Invalid L3FWD_GRAPH 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");
+
+	nb_ports = rte_eth_dev_count_avail();
+
+	if (check_port_config() < 0)
+		rte_exit(EXIT_FAILURE, "check_port_config failed\n");
+
+	nb_lcores = rte_lcore_count();
+
+	/* initialize all ports */
+	RTE_ETH_FOREACH_DEV(portid) {
+		struct rte_eth_conf local_port_conf = port_conf;
+
+		/* skip ports that are not enabled */
+		if ((enabled_port_mask & (1 << portid)) == 0) {
+			printf("\nSkipping disabled port %d\n", portid);
+			continue;
+		}
+
+		/* init port */
+		printf("Initializing port %d ... ", portid );
+		fflush(stdout);
+
+		nb_rx_queue = get_port_n_rx_queues(portid);
+		n_tx_queue = nb_lcores;
+		if (n_tx_queue > MAX_TX_QUEUE_PER_PORT)
+			n_tx_queue = MAX_TX_QUEUE_PER_PORT;
+		printf("Creating queues: nb_rxq=%d nb_txq=%u... ",
+			nb_rx_queue, (unsigned)n_tx_queue );
+
+		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;
+
+		local_port_conf.rx_adv_conf.rss_conf.rss_hf &=
+			dev_info.flow_type_rss_offloads;
+		if (local_port_conf.rx_adv_conf.rss_conf.rss_hf !=
+				port_conf.rx_adv_conf.rss_conf.rss_hf) {
+			printf("Port %u modified RSS hash function based on hardware support,"
+				"requested:%#"PRIx64" configured:%#"PRIx64"\n",
+				portid,
+				port_conf.rx_adv_conf.rss_conf.rss_hf,
+				local_port_conf.rx_adv_conf.rss_conf.rss_hf);
+		}
+
+		ret = rte_eth_dev_configure(portid, nb_rx_queue,
+					(uint16_t)n_tx_queue, &local_port_conf);
+		if (ret < 0)
+			rte_exit(EXIT_FAILURE,
+				"Cannot configure device: err=%d, port=%d\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=%d\n", ret, portid);
+
+		rte_eth_macaddr_get(portid, &ports_eth_addr[portid]);
+		print_ethaddr(" Address:", &ports_eth_addr[portid]);
+		printf(", ");
+		print_ethaddr("Destination:",
+			(const struct rte_ether_addr *)&dest_eth_addr[portid]);
+		printf(", ");
+
+		/*
+		 * prepare src MACs for each port.
+		 */
+		rte_ether_addr_copy(&ports_eth_addr[portid],
+			(struct rte_ether_addr *)(val_eth + portid) + 1);
+
+		/* init memory */
+		if (!per_port_pool) {
+			/* portid = 0; this is *not* signifying the first port,
+			 * rather, it signifies that portid is ignored.
+			 */
+			ret = init_mem(0, NB_MBUF(nb_ports));
+		} else {
+			ret = init_mem(portid, NB_MBUF(1));
+		}
+		if (ret < 0)
+			rte_exit(EXIT_FAILURE, "init_mem failed\n");
+
+		/* init one TX queue per couple (lcore,port) */
+		queueid = 0;
+		for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+			if (rte_lcore_is_enabled(lcore_id) == 0)
+				continue;
+
+			qconf = &lcore_conf[lcore_id];
+
+			if (numa_on)
+				socketid =
+				(uint8_t)rte_lcore_to_socket_id(lcore_id);
+			else
+				socketid = 0;
+
+			printf("txq=%u,%d,%d ", lcore_id, queueid, socketid);
+			fflush(stdout);
+
+			txconf = &dev_info.default_txconf;
+			txconf->offloads = local_port_conf.txmode.offloads;
+			ret = rte_eth_tx_queue_setup(portid, queueid, nb_txd,
+						     socketid, txconf);
+			if (ret < 0)
+				rte_exit(EXIT_FAILURE,
+					"rte_eth_tx_queue_setup: err=%d, "
+					"port=%d\n", ret, portid);
+			queueid++;
+		}
+
+		/* Setup ethdev node config */
+		ethdev_conf[nb_conf].port_id = portid;
+		ethdev_conf[nb_conf].num_rx_queues = nb_rx_queue;
+		ethdev_conf[nb_conf].num_tx_queues = n_tx_queue;
+		if (!per_port_pool)
+			ethdev_conf[nb_conf].mp =
+				pktmbuf_pool[0];
+
+		else
+			ethdev_conf[nb_conf].mp =
+				pktmbuf_pool[portid];
+		ethdev_conf[nb_conf].mp_count = NB_SOCKETS;
+
+		nb_conf++;
+		printf("\n");
+	}
+
+	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+		if (rte_lcore_is_enabled(lcore_id) == 0)
+			continue;
+		qconf = &lcore_conf[lcore_id];
+		printf("\nInitializing rx queues on lcore %u ... ", lcore_id );
+		fflush(stdout);
+		/* init RX queues */
+		for(queue = 0; queue < qconf->n_rx_queue; ++queue) {
+			struct rte_eth_rxconf rxq_conf;
+
+			portid = qconf->rx_queue_list[queue].port_id;
+			queueid = qconf->rx_queue_list[queue].queue_id;
+
+			if (numa_on)
+				socketid =
+				(uint8_t)rte_lcore_to_socket_id(lcore_id);
+			else
+				socketid = 0;
+
+			printf("rxq=%d,%d,%d ", portid, queueid, socketid);
+			fflush(stdout);
+
+			rte_eth_dev_info_get(portid, &dev_info);
+			rxq_conf = dev_info.default_rxconf;
+			rxq_conf.offloads = port_conf.rxmode.offloads;
+			if (!per_port_pool)
+				ret = rte_eth_rx_queue_setup(portid, queueid,
+						nb_rxd, socketid,
+						&rxq_conf,
+						pktmbuf_pool[0][socketid]);
+			else
+				ret = rte_eth_rx_queue_setup(portid, queueid,
+						nb_rxd, socketid,
+						&rxq_conf,
+						pktmbuf_pool[portid][socketid]);
+			if (ret < 0)
+				rte_exit(EXIT_FAILURE,
+				"rte_eth_rx_queue_setup: err=%d, port=%d\n",
+				ret, portid);
+
+			/* Add this queue node to its graph */
+			snprintf(qconf->rx_queue_list[queue].node_name,
+				 RTE_NODE_NAMESIZE, "ethdev_rx-%u-%u",
+				 portid, queueid);
+		}
+
+		/* Alloc a graph to this lcore only if source exists  */
+		if (qconf->n_rx_queue) {
+			qconf->graph_id = nb_graphs;
+			nb_graphs++;
+		}
+	}
+
+	printf("\n");
+
+	/* Ethdev node config, skip rx queue mapping */
+	ret = rte_node_eth_config(ethdev_conf, nb_conf, nb_graphs);
+	if (ret)
+		rte_exit(EXIT_FAILURE,
+			 "rte_node_eth_config: err=%d\n", ret);
+
+	/* start ports */
+	RTE_ETH_FOREACH_DEV(portid) {
+		if ((enabled_port_mask & (1 << portid)) == 0) {
+			continue;
+		}
+		/* Start device */
+		ret = rte_eth_dev_start(portid);
+		if (ret < 0)
+			rte_exit(EXIT_FAILURE,
+				"rte_eth_dev_start: err=%d, port=%d\n",
+				ret, portid);
+
+		/*
+		 * If enabled, put device in promiscuous mode.
+		 * This allows IO forwarding mode to forward packets
+		 * to itself through 2 cross-connected  ports of the
+		 * target machine.
+		 */
+		if (promiscuous_on)
+			rte_eth_promiscuous_enable(portid);
+	}
+
+	printf("\n");
+
+	check_all_ports_link_status(enabled_port_mask);
+
+	/* Graph Initialization */
+	memset(&graph_conf, 0, sizeof(graph_conf));
+	graph_conf.node_patterns = node_patterns;
+
+	for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
+		rte_graph_t graph_id;
+		rte_edge_t i;
+
+		if (rte_lcore_is_enabled(lcore_id) == 0)
+			continue;
+
+		qconf = &lcore_conf[lcore_id];
+
+		/* Skip graph creation if no source exists */
+		if (!qconf->n_rx_queue)
+			continue;
+
+		/* Add rx node patterns of this lcore */
+		for (i = 0; i < qconf->n_rx_queue; i++) {
+			graph_conf.node_patterns[nb_patterns + i]
+				 = qconf->rx_queue_list[i].node_name;
+		}
+
+		graph_conf.nb_node_patterns = nb_patterns + i;
+		graph_conf.socket_id = rte_lcore_to_socket_id(lcore_id);
+
+		snprintf(qconf->name, sizeof(qconf->name),
+			 "worker_%u", lcore_id);
+
+		graph_id = rte_graph_create(qconf->name, &graph_conf);
+		if (graph_id != qconf->graph_id)
+			rte_exit(EXIT_FAILURE,
+				 "rte_graph_create(): graph_id=%d not "
+				 " as expected for lcore %u(%u\n",
+				 graph_id, lcore_id, qconf->graph_id);
+
+		qconf->graph = rte_graph_lookup(qconf->name);
+		if (!qconf->graph)
+			rte_exit(EXIT_FAILURE,
+				 "rte_graph_lookup(): graph %s not found\n",
+				 qconf->name);
+
+	}
+
+	/* Update mac header rewrite data */
+	memset(&rewrite_data, 0, sizeof(rewrite_data));
+	rewrite_len = sizeof(rewrite_data);
+	ether_addr = (struct rte_ether_addr *)rewrite_data;
+	ether_addr[0].addr_bytes[0] = RTE_ETHER_LOCAL_ADMIN_ADDR;
+	ether_addr[1].addr_bytes[0] = RTE_ETHER_LOCAL_ADMIN_ADDR;
+
+	/* Add route to ip4 graph infra */
+	for (i = 0; i < IPV4_L3FWD_LPM_NUM_ROUTES; i++) {
+		char route_str[INET6_ADDRSTRLEN * 4];
+		char abuf[INET6_ADDRSTRLEN];
+		struct in_addr in;
+		uint32_t dst_port;
+		uint16_t next_hop;
+
+		/* skip unused ports */
+		if ((1 << ipv4_l3fwd_lpm_route_array[i].if_out &
+				enabled_port_mask) == 0)
+			continue;
+
+		dst_port = ipv4_l3fwd_lpm_route_array[i].if_out;
+		next_hop = i;
+
+		in.s_addr = htonl(ipv4_l3fwd_lpm_route_array[i].ip);
+		snprintf(route_str, sizeof(route_str), "%s / %d (%d)",
+			 inet_ntop(AF_INET, &in, abuf, sizeof(abuf)),
+			 ipv4_l3fwd_lpm_route_array[i].depth,
+			 ipv4_l3fwd_lpm_route_array[i].if_out);
+
+		ret = rte_node_ip4_route_add(ipv4_l3fwd_lpm_route_array[i].ip,
+			ipv4_l3fwd_lpm_route_array[i].depth, next_hop,
+			IP4_LOOKUP_NEXT_REWRITE);
+
+		if (ret < 0)
+			rte_exit(EXIT_FAILURE,
+				"Unable to add ip4 route %s to graph\n",
+				route_str);
+
+		ether_addr[0].addr_bytes[5] = dst_port + 1;
+
+		/* Add next hop for a given destination */
+		ret = rte_node_ip4_rewrite_add(next_hop, rewrite_data,
+					       rewrite_len, dst_port);
+		if (ret < 0)
+			rte_exit(EXIT_FAILURE,
+				"Unable to add next hop %u for "
+				"route %s\n", next_hop, route_str);
+
+		RTE_LOG(INFO, L3FWD_GRAPH,
+			"Added route %s, next_hop %u\n",
+			route_str, next_hop);
+	}
+
+	/* launch per-lcore init on every slave lcore */
+	rte_eal_mp_remote_launch(graph_main_loop, NULL, SKIP_MASTER);
+
+	/* Accumulate and print stats on master until exit */
+	if (rte_graph_has_stats_feature())
+		print_stats();
+
+	/* Wait for slave cores to exit */
+	ret = 0;
+	RTE_LCORE_FOREACH_SLAVE(lcore_id) {
+		ret = rte_eal_wait_lcore(lcore_id);
+		/* Destroy graph */
+		rte_graph_destroy(lcore_conf[lcore_id].name);
+		if (ret < 0) {
+			ret = -1;
+			break;
+		}
+	}
+
+	/* stop ports */
+	RTE_ETH_FOREACH_DEV(portid) {
+		if ((enabled_port_mask & (1 << portid)) == 0)
+			continue;
+		printf("Closing port %d...", portid);
+		rte_eth_dev_stop(portid);
+		rte_eth_dev_close(portid);
+		printf(" Done\n");
+	}
+	printf("Bye...\n");
+
+	return ret;
+}
diff --git a/examples/l3fwd-graph/meson.build b/examples/l3fwd-graph/meson.build
new file mode 100644
index 000000000..a816bd890
--- /dev/null
+++ b/examples/l3fwd-graph/meson.build
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: BSD-3-Clause
+# Copyright(C) 2020 Marvell International Ltd.
+
+# 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'
+
+deps += ['graph', 'eal', 'lpm', 'ethdev', 'node' ]
+sources = files(
+	'main.c'
+)
+allow_experimental_apis = true
diff --git a/examples/meson.build b/examples/meson.build
index 1f2b6f516..3b540012f 100644
--- a/examples/meson.build
+++ b/examples/meson.build
@@ -2,8 +2,10 @@
 # Copyright(c) 2017-2019 Intel Corporation
 
 driver_libs = []
+node_libs = []
 if get_option('default_library') == 'static'
 	driver_libs = dpdk_drivers
+	node_libs = dpdk_graph_nodes
 endif
 
 execinfo = cc.find_library('execinfo', required: false)
@@ -23,7 +25,7 @@ all_examples = [
 	'l2fwd', 'l2fwd-cat', 'l2fwd-event',
 	'l2fwd-crypto', 'l2fwd-jobstats',
 	'l2fwd-keepalive', 'l3fwd',
-	'l3fwd-acl', 'l3fwd-power',
+	'l3fwd-acl', 'l3fwd-power', 'l3fwd-graph',
 	'link_status_interrupt',
 	'multi_process/client_server_mp/mp_client',
 	'multi_process/client_server_mp/mp_server',
@@ -99,7 +101,7 @@ foreach example: examples
 		endif
 		executable('dpdk-' + name, sources,
 			include_directories: includes,
-			link_whole: driver_libs,
+			link_whole: driver_libs + node_libs,
 			link_args: dpdk_extra_ldflags,
 			c_args: cflags,
 			dependencies: dep_objs)
-- 
2.24.1