DPDK application to reply ICMP packets received in a Linux server - Advanced Operating Systems DCC/UFMG (Lucas Andrey Caldeira Bleme)

basicfwd.c

/* SPDX-License-Identifier: BSD-3-Clause
 * Copyright(c) 2010-2015 Intel Corporation
 */

#include <stdint.h>
#include <inttypes.h>
#include <rte_eal.h>
#include <rte_ethdev.h>
#include <rte_ether.h>
#include <rte_cycles.h>
#include <rte_lcore.h>
#include <rte_mbuf.h>

#define RX_RING_SIZE 1024
#define TX_RING_SIZE 1024

#define NUM_MBUFS 8191
#define MBUF_CACHE_SIZE 250
#define BURST_SIZE 1024

static const struct rte_eth_conf port_conf_default = {
	.rxmode = {
		.max_rx_pkt_len = RTE_ETHER_MAX_LEN,
	},
};

/* basicfwd.c: Basic DPDK skeleton forwarding example. */

/*
 * Initializes a given port using global settings and with the RX buffers
 * coming from the mbuf_pool passed as a parameter.
 */
static inline int
port_init(uint16_t port, struct rte_mempool *mbuf_pool)
{
	struct rte_eth_conf port_conf = port_conf_default;
	const uint16_t rx_rings = 1, tx_rings = 1;
	uint16_t nb_rxd = RX_RING_SIZE;
	uint16_t nb_txd = TX_RING_SIZE;
	int retval;
	uint16_t q;
	struct rte_eth_dev_info dev_info;
	struct rte_eth_txconf txconf;

	if (!rte_eth_dev_is_valid_port(port))
		return -1;

	retval = rte_eth_dev_info_get(port, &dev_info);
	if (retval != 0) {
		printf("Error during getting device (port %u) info: %s\n",
				port, strerror(-retval));
		return retval;
	}

	if (dev_info.tx_offload_capa & DEV_TX_OFFLOAD_MBUF_FAST_FREE)
		port_conf.txmode.offloads |=
			DEV_TX_OFFLOAD_MBUF_FAST_FREE;

	/* Configure the Ethernet device. */
	retval = rte_eth_dev_configure(port, rx_rings, tx_rings, &port_conf);
	if (retval != 0)
		return retval;

	retval = rte_eth_dev_adjust_nb_rx_tx_desc(port, &nb_rxd, &nb_txd);
	if (retval != 0)
		return retval;

	/* Allocate and set up 1 RX queue per Ethernet port. */
	for (q = 0; q < rx_rings; q++) {
		retval = rte_eth_rx_queue_setup(port, q, nb_rxd,
				rte_eth_dev_socket_id(port), NULL, mbuf_pool);
		if (retval < 0)
			return retval;
	}

	txconf = dev_info.default_txconf;
	txconf.offloads = port_conf.txmode.offloads;
	/* Allocate and set up 1 TX queue per Ethernet port. */
	for (q = 0; q < tx_rings; q++) {
		retval = rte_eth_tx_queue_setup(port, q, nb_txd,
				rte_eth_dev_socket_id(port), &txconf);
		if (retval < 0)
			return retval;
	}

	/* Start the Ethernet port. */
	retval = rte_eth_dev_start(port);
	if (retval < 0)
		return retval;

	/* Display the port MAC address. */
	struct rte_ether_addr addr;
	retval = rte_eth_macaddr_get(port, &addr);
	if (retval != 0)
		return retval;

	printf("Port %u MAC: %02" PRIx8 " %02" PRIx8 " %02" PRIx8
			   " %02" PRIx8 " %02" PRIx8 " %02" PRIx8 "\n",
			port,
			addr.addr_bytes[0], addr.addr_bytes[1],
			addr.addr_bytes[2], addr.addr_bytes[3],
			addr.addr_bytes[4], addr.addr_bytes[5]);

	/* Enable RX in promiscuous mode for the Ethernet device. */
	retval = rte_eth_promiscuous_enable(port);
	if (retval != 0)
		return retval;

	return 0;
}

/*
 * The lcore main. This is the main thread that does the work, reading from
 * an input port and writing to an output port.
 */
static __rte_noreturn void
lcore_main(void)
{
	uint16_t port = 1;
	uint16_t queue = 0;

	struct rte_mbuf *pkt;
	struct rte_mbuf *bufs[BURST_SIZE];

	struct rte_ether_hdr *eth_h;
	struct rte_ether_addr eth_addr;
	struct rte_icmp_hdr *icmp_h;
	struct rte_ipv4_hdr *ip_h;

	uint32_t ip_addr;
	uint32_t cksum;
	uint16_t nb_replies;
	uint16_t nb_tx;

	// Performance
	uint64_t hz;
	uint64_t begin;
	uint64_t elapsed_cycles = 0;
	uint64_t microseconds = 0;

	/*
	 * Check that the port is on the same NUMA node as the polling thread
	 * for best performance.
	 */
		if (rte_eth_dev_socket_id(port) > 0 &&
				rte_eth_dev_socket_id(port) !=
						(int)rte_socket_id())
			printf("WARNING, port %u is on remote NUMA node to "
					"polling thread.\n\tPerformance will "
					"not be optimal.\n", port);

	printf("\nCore %u receiving packages. [Ctrl+C to quit]\n",
			rte_lcore_id());

	// Init performance counters
	hz = rte_get_timer_hz(); 
	begin = rte_rdtsc_precise();

	// Run until the application is quit or killed.
	for (;;) {
		// Get burst of RX packets
		const uint16_t nb_rx = rte_eth_rx_burst(port, queue, bufs, BURST_SIZE);

		for (uint8_t i = 0; i < nb_rx; i++) {
			if (likely(i < nb_rx - 1))
				rte_prefetch0(rte_pktmbuf_mtod(bufs[i + 1], void *));
			pkt = bufs[i];

			eth_h = rte_pktmbuf_mtod(pkt, struct rte_ether_hdr *);
			int l2_len = sizeof(struct rte_ether_hdr);
			ip_h = (struct rte_ipv4_hdr *) ((char *)eth_h + l2_len);

			// Check if packet is a ICMP echo
			icmp_h = (struct rte_icmp_hdr *) ((char *)ip_h + sizeof(struct rte_ipv4_hdr));
			if (! ((ip_h->next_proto_id == IPPROTO_ICMP) &&
				(icmp_h->icmp_type == RTE_IP_ICMP_ECHO_REQUEST) &&
				(icmp_h->icmp_code == 0))) {
				rte_pktmbuf_free(pkt);
				continue;
			}
			printf("ICMP packet received here id=%d\n", rte_be_to_cpu_16(icmp_h->icmp_seq_nb));

			// Send back the ICMP echo reply, keeping the IP header and setting the RTE_IP_ICMP_ECHO_REPLY
			rte_ether_addr_copy(&eth_h->s_addr, &eth_addr);
			rte_ether_addr_copy(&eth_h->d_addr, &eth_h->s_addr);
			rte_ether_addr_copy(&eth_addr, &eth_h->d_addr);

			ip_addr = ip_h->src_addr;
			ip_h->src_addr = ip_h->dst_addr;
			ip_h->dst_addr = ip_addr;

			icmp_h->icmp_type = RTE_IP_ICMP_ECHO_REPLY;
			cksum = ~icmp_h->icmp_cksum & 0xffff;
			cksum += ~htons(RTE_IP_ICMP_ECHO_REQUEST << 8) & 0xffff;
			cksum += htons(RTE_IP_ICMP_ECHO_REPLY << 8);
			cksum = (cksum & 0xffff) + (cksum >> 16);
			cksum = (cksum & 0xffff) + (cksum >> 16);
			icmp_h->icmp_cksum = ~cksum;

			bufs[nb_replies++] = pkt;
		}

		// Send back the existing ICMP echo replies
		if (nb_replies > 0) {
			nb_tx = rte_eth_tx_burst(port, queue, bufs, nb_replies);
			// Retry
			if (unlikely(nb_tx < nb_replies)) {
				uint32_t retry = 0;
				while (nb_tx < nb_replies && retry++ < 64) {
					rte_delay_us(1);
					nb_tx += rte_eth_tx_burst(port, queue, &bufs[nb_tx], nb_replies - nb_tx);
				}
			}
			if (unlikely(nb_tx < nb_replies)) {
				do {
					rte_pktmbuf_free(bufs[nb_tx]);
				} while (++nb_tx < nb_replies);
			}
			printf("ICMP packet replied id=%d\n", rte_be_to_cpu_16(icmp_h->icmp_seq_nb));

			// Terminate performance counters
			elapsed_cycles = rte_rdtsc_precise() - begin; 
			microseconds = elapsed_cycles * 1000000 / hz;
			printf("\nICMP packet replied time: %u", microseconds);
			continue;
		}
	}
}

/*
 * The main function, which does initialization and calls the per-lcore
 * functions.
 */
int
main(int argc, char *argv[])
{
	struct rte_mempool *mbuf_pool;
	unsigned nb_ports;
	uint16_t portid = 1;

	/* Initialize the Environment Abstraction Layer (EAL). */
	int ret = rte_eal_init(argc, argv);
	if (ret < 0)
		rte_exit(EXIT_FAILURE, "Error with EAL initialization\n");

	argc -= ret;
	argv += ret;

	/* Check that there is an even number of ports to send/receive on. */
	nb_ports = rte_eth_dev_count_avail();
	if (nb_ports < 2 || (nb_ports & 1))
		rte_exit(EXIT_FAILURE, "Error: number of ports must be even\n");

	/* Creates a new mempool in memory to hold the mbufs. */
	mbuf_pool = rte_pktmbuf_pool_create("MBUF_POOL", NUM_MBUFS * nb_ports,
		MBUF_CACHE_SIZE, 0, RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id());

	if (mbuf_pool == NULL)
		rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n");

	/* Initialize only port 1. */
		if (port_init(portid, mbuf_pool) != 0)
			rte_exit(EXIT_FAILURE, "Cannot init port %"PRIu16 "\n", portid);

	if (rte_lcore_count() > 1)
		printf("\nWARNING: Too many lcores enabled. Only 1 used.\n");

	/* Call lcore_main on the main core only. */
	lcore_main();

	return 0;
}