xdpsock_user.c

// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2017 - 2018 Intel Corporation. */

#include <asm/barrier.h>
#include <errno.h>
#include <getopt.h>
#include <libgen.h>
#include <linux/bpf.h>
#include <linux/compiler.h>
#include <linux/if_link.h>
#include <linux/if_xdp.h>
#include <linux/if_ether.h>
#include <linux/ip.h>
#include <linux/udp.h>
#include <arpa/inet.h>
#include <locale.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <poll.h>
#include <pthread.h>
#include <signal.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/mman.h>
#include <sys/resource.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <time.h>
#include <unistd.h>

#include <bpf/libbpf.h>
#include <bpf/xsk.h>
#include <bpf/bpf.h>
#include "xdpsock.h"

#ifndef SOL_XDP
#define SOL_XDP 283
#endif

#ifndef AF_XDP
#define AF_XDP 44
#endif

#ifndef PF_XDP
#define PF_XDP AF_XDP
#endif

#define NUM_FRAMES (4 * 1024)
#define MIN_PKT_SIZE 64

#define DEBUG_HEXDUMP 0

typedef __u64 u64;
typedef __u32 u32;
typedef __u16 u16;
typedef __u8  u8;

static unsigned long prev_time;

enum benchmark_type {
	BENCH_RXDROP = 0,
	BENCH_TXONLY = 1,
	BENCH_L2FWD = 2,
};

static enum benchmark_type opt_bench = BENCH_RXDROP;
static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
static const char *opt_if = "";
static int opt_ifindex;
static int opt_queue;
static unsigned long opt_duration;
static unsigned long start_time;
static bool benchmark_done;
static u32 opt_batch_size = 64;
static int opt_pkt_count;
static u16 opt_pkt_size = MIN_PKT_SIZE;
static u32 opt_pkt_fill_pattern = 0x12345678;
static bool opt_extra_stats;
static int opt_poll;
static int opt_interval = 1;
static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP;
static u32 opt_umem_flags;
static int opt_unaligned_chunks;
static int opt_mmap_flags;
static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
static int opt_timeout = 1000;
static bool opt_need_wakeup = true;
static u32 opt_num_xsks = 1;
static u32 prog_id;

struct xsk_umem_info {
	struct xsk_ring_prod fq;
	struct xsk_ring_cons cq;
	struct xsk_umem *umem;
	void *buffer;
};

struct xsk_socket_info {
	struct xsk_ring_cons rx;
	struct xsk_ring_prod tx;
	struct xsk_umem_info *umem;
	struct xsk_socket *xsk;
	unsigned long rx_npkts;
	unsigned long tx_npkts;
	unsigned long rx_dropped_npkts;
	unsigned long rx_invalid_npkts;
	unsigned long tx_invalid_npkts;
	unsigned long rx_full_npkts;
	unsigned long rx_fill_empty_npkts;
	unsigned long tx_empty_npkts;
	unsigned long prev_rx_npkts;
	unsigned long prev_tx_npkts;
	unsigned long prev_rx_dropped_npkts;
	unsigned long prev_rx_invalid_npkts;
	unsigned long prev_tx_invalid_npkts;
	unsigned long prev_rx_full_npkts;
	unsigned long prev_rx_fill_empty_npkts;
	unsigned long prev_tx_empty_npkts;
	u32 outstanding_tx;
};

static int num_socks;
struct xsk_socket_info *xsks[MAX_SOCKS];

static unsigned long get_nsecs(void)
{
	struct timespec ts;

	clock_gettime(CLOCK_MONOTONIC, &ts);
	return ts.tv_sec * 1000000000UL + ts.tv_nsec;
}

static void print_benchmark(bool running)
{
	const char *bench_str = "INVALID";

	if (opt_bench == BENCH_RXDROP)
		bench_str = "rxdrop";
	else if (opt_bench == BENCH_TXONLY)
		bench_str = "txonly";
	else if (opt_bench == BENCH_L2FWD)
		bench_str = "l2fwd";

	printf("%s:%d %s ", opt_if, opt_queue, bench_str);
	if (opt_xdp_flags & XDP_FLAGS_SKB_MODE)
		printf("xdp-skb ");
	else if (opt_xdp_flags & XDP_FLAGS_DRV_MODE)
		printf("xdp-drv ");
	else
		printf("	");

	if (opt_poll)
		printf("poll() ");

	if (running) {
		printf("running...");
		fflush(stdout);
	}
}

static int xsk_get_xdp_stats(int fd, struct xsk_socket_info *xsk)
{
	struct xdp_statistics stats;
	socklen_t optlen;
	int err;

	optlen = sizeof(stats);
	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen);
	if (err)
		return err;

	if (optlen == sizeof(struct xdp_statistics)) {
		xsk->rx_dropped_npkts = stats.rx_dropped;
		xsk->rx_invalid_npkts = stats.rx_invalid_descs;
		xsk->tx_invalid_npkts = stats.tx_invalid_descs;
		xsk->rx_full_npkts = stats.rx_ring_full;
		xsk->rx_fill_empty_npkts = stats.rx_fill_ring_empty_descs;
		xsk->tx_empty_npkts = stats.tx_ring_empty_descs;
		return 0;
	}

	return -EINVAL;
}

static void dump_stats(void)
{
	unsigned long now = get_nsecs();
	long dt = now - prev_time;
	int i;

	prev_time = now;

	for (i = 0; i < num_socks && xsks[i]; i++) {
		char *fmt = "%-15s %'-11.0f %'-11lu\n";
		double rx_pps, tx_pps, dropped_pps, rx_invalid_pps, full_pps, fill_empty_pps,
			tx_invalid_pps, tx_empty_pps;

		rx_pps = (xsks[i]->rx_npkts - xsks[i]->prev_rx_npkts) *
			 1000000000. / dt;
		tx_pps = (xsks[i]->tx_npkts - xsks[i]->prev_tx_npkts) *
			 1000000000. / dt;

		printf("\n sock%d@", i);
		print_benchmark(false);
		printf("\n");

		printf("%-15s %-11s %-11s %-11.2f\n", "", "pps", "pkts",
		       dt / 1000000000.);
		printf(fmt, "rx", rx_pps, xsks[i]->rx_npkts);
		printf(fmt, "tx", tx_pps, xsks[i]->tx_npkts);

		xsks[i]->prev_rx_npkts = xsks[i]->rx_npkts;
		xsks[i]->prev_tx_npkts = xsks[i]->tx_npkts;

		if (opt_extra_stats) {
			if (!xsk_get_xdp_stats(xsk_socket__fd(xsks[i]->xsk), xsks[i])) {
				dropped_pps = (xsks[i]->rx_dropped_npkts -
						xsks[i]->prev_rx_dropped_npkts) * 1000000000. / dt;
				rx_invalid_pps = (xsks[i]->rx_invalid_npkts -
						xsks[i]->prev_rx_invalid_npkts) * 1000000000. / dt;
				tx_invalid_pps = (xsks[i]->tx_invalid_npkts -
						xsks[i]->prev_tx_invalid_npkts) * 1000000000. / dt;
				full_pps = (xsks[i]->rx_full_npkts -
						xsks[i]->prev_rx_full_npkts) * 1000000000. / dt;
				fill_empty_pps = (xsks[i]->rx_fill_empty_npkts -
						xsks[i]->prev_rx_fill_empty_npkts)
						* 1000000000. / dt;
				tx_empty_pps = (xsks[i]->tx_empty_npkts -
						xsks[i]->prev_tx_empty_npkts) * 1000000000. / dt;

				printf(fmt, "rx dropped", dropped_pps,
				       xsks[i]->rx_dropped_npkts);
				printf(fmt, "rx invalid", rx_invalid_pps,
				       xsks[i]->rx_invalid_npkts);
				printf(fmt, "tx invalid", tx_invalid_pps,
				       xsks[i]->tx_invalid_npkts);
				printf(fmt, "rx queue full", full_pps,
				       xsks[i]->rx_full_npkts);
				printf(fmt, "fill ring empty", fill_empty_pps,
				       xsks[i]->rx_fill_empty_npkts);
				printf(fmt, "tx ring empty", tx_empty_pps,
				       xsks[i]->tx_empty_npkts);

				xsks[i]->prev_rx_dropped_npkts = xsks[i]->rx_dropped_npkts;
				xsks[i]->prev_rx_invalid_npkts = xsks[i]->rx_invalid_npkts;
				xsks[i]->prev_tx_invalid_npkts = xsks[i]->tx_invalid_npkts;
				xsks[i]->prev_rx_full_npkts = xsks[i]->rx_full_npkts;
				xsks[i]->prev_rx_fill_empty_npkts = xsks[i]->rx_fill_empty_npkts;
				xsks[i]->prev_tx_empty_npkts = xsks[i]->tx_empty_npkts;
			} else {
				printf("%-15s\n", "Error retrieving extra stats");
			}
		}
	}
}

static bool is_benchmark_done(void)
{
	if (opt_duration > 0) {
		unsigned long dt = (get_nsecs() - start_time);

		if (dt >= opt_duration)
			benchmark_done = true;
	}
	return benchmark_done;
}

static void *poller(void *arg)
{
	(void)arg;
	while (!is_benchmark_done()) {
		sleep(opt_interval);
		dump_stats();
	}

	return NULL;
}

static void remove_xdp_program(void)
{
	u32 curr_prog_id = 0;

	if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) {
		printf("bpf_get_link_xdp_id failed\n");
		exit(EXIT_FAILURE);
	}
	if (prog_id == curr_prog_id)
		bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags);
	else if (!curr_prog_id)
		printf("couldn't find a prog id on a given interface\n");
	else
		printf("program on interface changed, not removing\n");
}

static void int_exit(int sig)
{
	benchmark_done = true;
}

static void xdpsock_cleanup(void)
{
	struct xsk_umem *umem = xsks[0]->umem->umem;
	int i;

	dump_stats();
	for (i = 0; i < num_socks; i++)
		xsk_socket__delete(xsks[i]->xsk);
	(void)xsk_umem__delete(umem);
	remove_xdp_program();
}

static void __exit_with_error(int error, const char *file, const char *func,
			      int line)
{
	fprintf(stderr, "%s:%s:%i: errno: %d/\"%s\"\n", file, func,
		line, error, strerror(error));
	dump_stats();
	remove_xdp_program();
	exit(EXIT_FAILURE);
}

#define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, \
						 __LINE__)
static void swap_mac_addresses(void *data)
{
	struct ether_header *eth = (struct ether_header *)data;
	struct ether_addr *src_addr = (struct ether_addr *)&eth->ether_shost;
	struct ether_addr *dst_addr = (struct ether_addr *)&eth->ether_dhost;
	struct ether_addr tmp;

	tmp = *src_addr;
	*src_addr = *dst_addr;
	*dst_addr = tmp;
}

static void hex_dump(void *pkt, size_t length, u64 addr)
{
	const unsigned char *address = (unsigned char *)pkt;
	const unsigned char *line = address;
	size_t line_size = 32;
	unsigned char c;
	char buf[32];
	int i = 0;

	if (!DEBUG_HEXDUMP)
		return;

	sprintf(buf, "addr=%llu", addr);
	printf("length = %zu\n", length);
	printf("%s | ", buf);
	while (length-- > 0) {
		printf("%02X ", *address++);
		if (!(++i % line_size) || (length == 0 && i % line_size)) {
			if (length == 0) {
				while (i++ % line_size)
					printf("__ ");
			}
			printf(" | ");	/* right close */
			while (line < address) {
				c = *line++;
				printf("%c", (c < 33 || c == 255) ? 0x2E : c);
			}
			printf("\n");
			if (length > 0)
				printf("%s | ", buf);
		}
	}
	printf("\n");
}

static void *memset32_htonl(void *dest, u32 val, u32 size)
{
	u32 *ptr = (u32 *)dest;
	int i;

	val = htonl(val);

	for (i = 0; i < (size & (~0x3)); i += 4)
		ptr[i >> 2] = val;

	for (; i < size; i++)
		((char *)dest)[i] = ((char *)&val)[i & 3];

	return dest;
}

/*
 * This function code has been taken from
 * Linux kernel lib/checksum.c
 */
static inline unsigned short from32to16(unsigned int x)
{
	/* add up 16-bit and 16-bit for 16+c bit */
	x = (x & 0xffff) + (x >> 16);
	/* add up carry.. */
	x = (x & 0xffff) + (x >> 16);
	return x;
}

/*
 * This function code has been taken from
 * Linux kernel lib/checksum.c
 */
static unsigned int do_csum(const unsigned char *buff, int len)
{
	unsigned int result = 0;
	int odd;

	if (len <= 0)
		goto out;
	odd = 1 & (unsigned long)buff;
	if (odd) {
#ifdef __LITTLE_ENDIAN
		result += (*buff << 8);
#else
		result = *buff;
#endif
		len--;
		buff++;
	}
	if (len >= 2) {
		if (2 & (unsigned long)buff) {
			result += *(unsigned short *)buff;
			len -= 2;
			buff += 2;
		}
		if (len >= 4) {
			const unsigned char *end = buff +
						   ((unsigned int)len & ~3);
			unsigned int carry = 0;

			do {
				unsigned int w = *(unsigned int *)buff;

				buff += 4;
				result += carry;
				result += w;
				carry = (w > result);
			} while (buff < end);
			result += carry;
			result = (result & 0xffff) + (result >> 16);
		}
		if (len & 2) {
			result += *(unsigned short *)buff;
			buff += 2;
		}
	}
	if (len & 1)
#ifdef __LITTLE_ENDIAN
		result += *buff;
#else
		result += (*buff << 8);
#endif
	result = from32to16(result);
	if (odd)
		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
out:
	return result;
}

__sum16 ip_fast_csum(const void *iph, unsigned int ihl);

/*
 *	This is a version of ip_compute_csum() optimized for IP headers,
 *	which always checksum on 4 octet boundaries.
 *	This function code has been taken from
 *	Linux kernel lib/checksum.c
 */
__sum16 ip_fast_csum(const void *iph, unsigned int ihl)
{
	return (__force __sum16)~do_csum(iph, ihl * 4);
}

/*
 * Fold a partial checksum
 * This function code has been taken from
 * Linux kernel include/asm-generic/checksum.h
 */
static inline __sum16 csum_fold(__wsum csum)
{
	u32 sum = (__force u32)csum;

	sum = (sum & 0xffff) + (sum >> 16);
	sum = (sum & 0xffff) + (sum >> 16);
	return (__force __sum16)~sum;
}

/*
 * This function code has been taken from
 * Linux kernel lib/checksum.c
 */
static inline u32 from64to32(u64 x)
{
	/* add up 32-bit and 32-bit for 32+c bit */
	x = (x & 0xffffffff) + (x >> 32);
	/* add up carry.. */
	x = (x & 0xffffffff) + (x >> 32);
	return (u32)x;
}

__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
			  __u32 len, __u8 proto, __wsum sum);

/*
 * This function code has been taken from
 * Linux kernel lib/checksum.c
 */
__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
			  __u32 len, __u8 proto, __wsum sum)
{
	unsigned long long s = (__force u32)sum;

	s += (__force u32)saddr;
	s += (__force u32)daddr;
#ifdef __BIG_ENDIAN__
	s += proto + len;
#else
	s += (proto + len) << 8;
#endif
	return (__force __wsum)from64to32(s);
}

/*
 * This function has been taken from
 * Linux kernel include/asm-generic/checksum.h
 */
static inline __sum16
csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
		  __u8 proto, __wsum sum)
{
	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
}

static inline u16 udp_csum(u32 saddr, u32 daddr, u32 len,
			   u8 proto, u16 *udp_pkt)
{
	u32 csum = 0;
	u32 cnt = 0;

	/* udp hdr and data */
	for (; cnt < len; cnt += 2)
		csum += udp_pkt[cnt >> 1];

	return csum_tcpudp_magic(saddr, daddr, len, proto, csum);
}

#define ETH_FCS_SIZE 4

#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
		      sizeof(struct udphdr))

#define PKT_SIZE		(opt_pkt_size - ETH_FCS_SIZE)
#define IP_PKT_SIZE		(PKT_SIZE - sizeof(struct ethhdr))
#define UDP_PKT_SIZE		(IP_PKT_SIZE - sizeof(struct iphdr))
#define UDP_PKT_DATA_SIZE	(UDP_PKT_SIZE - sizeof(struct udphdr))

static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE];

static void gen_eth_hdr_data(void)
{
	struct udphdr *udp_hdr = (struct udphdr *)(pkt_data +
						   sizeof(struct ethhdr) +
						   sizeof(struct iphdr));
	struct iphdr *ip_hdr = (struct iphdr *)(pkt_data +
						sizeof(struct ethhdr));
	struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;

	/* ethernet header */
	memcpy(eth_hdr->h_dest, "\x3c\xfd\xfe\x9e\x7f\x71", ETH_ALEN);
	memcpy(eth_hdr->h_source, "\xec\xb1\xd7\x98\x3a\xc0", ETH_ALEN);
	eth_hdr->h_proto = htons(ETH_P_IP);

	/* IP header */
	ip_hdr->version = IPVERSION;
	ip_hdr->ihl = 0x5; /* 20 byte header */
	ip_hdr->tos = 0x0;
	ip_hdr->tot_len = htons(IP_PKT_SIZE);
	ip_hdr->id = 0;
	ip_hdr->frag_off = 0;
	ip_hdr->ttl = IPDEFTTL;
	ip_hdr->protocol = IPPROTO_UDP;
	ip_hdr->saddr = htonl(0x0a0a0a10);
	ip_hdr->daddr = htonl(0x0a0a0a20);

	/* IP header checksum */
	ip_hdr->check = 0;
	ip_hdr->check = ip_fast_csum((const void *)ip_hdr, ip_hdr->ihl);

	/* UDP header */
	udp_hdr->source = htons(0x1000);
	udp_hdr->dest = htons(0x1000);
	udp_hdr->len = htons(UDP_PKT_SIZE);

	/* UDP data */
	memset32_htonl(pkt_data + PKT_HDR_SIZE, opt_pkt_fill_pattern,
		       UDP_PKT_DATA_SIZE);

	/* UDP header checksum */
	udp_hdr->check = 0;
	udp_hdr->check = udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE,
				  IPPROTO_UDP, (u16 *)udp_hdr);
}

static void gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
{
	memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data,
	       PKT_SIZE);
}

static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size)
{
	struct xsk_umem_info *umem;
	struct xsk_umem_config cfg = {
		/* We recommend that you set the fill ring size >= HW RX ring size +
		 * AF_XDP RX ring size. Make sure you fill up the fill ring
		 * with buffers at regular intervals, and you will with this setting
		 * avoid allocation failures in the driver. These are usually quite
		 * expensive since drivers have not been written to assume that
		 * allocation failures are common. For regular sockets, kernel
		 * allocated memory is used that only runs out in OOM situations
		 * that should be rare.
		 */
		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS * 2,
		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
		.frame_size = opt_xsk_frame_size,
		.frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM,
		.flags = opt_umem_flags
	};
	int ret;

	umem = calloc(1, sizeof(*umem));
	if (!umem)
		exit_with_error(errno);

	ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq,
			       &cfg);
	if (ret)
		exit_with_error(-ret);

	umem->buffer = buffer;
	return umem;
}

static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
{
	int ret, i;
	u32 idx;

	ret = xsk_ring_prod__reserve(&umem->fq,
				     XSK_RING_PROD__DEFAULT_NUM_DESCS * 2, &idx);
	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS * 2)
		exit_with_error(-ret);
	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS * 2; i++)
		*xsk_ring_prod__fill_addr(&umem->fq, idx++) =
			i * opt_xsk_frame_size;
	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS * 2);
}

static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem,
						    bool rx, bool tx)
{
	struct xsk_socket_config cfg;
	struct xsk_socket_info *xsk;
	struct xsk_ring_cons *rxr;
	struct xsk_ring_prod *txr;
	int ret;

	xsk = calloc(1, sizeof(*xsk));
	if (!xsk)
		exit_with_error(errno);

	xsk->umem = umem;
	cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
	if (opt_num_xsks > 1)
		cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD;
	else
		cfg.libbpf_flags = 0;
	cfg.xdp_flags = opt_xdp_flags;
	cfg.bind_flags = opt_xdp_bind_flags;

	rxr = rx ? &xsk->rx : NULL;
	txr = tx ? &xsk->tx : NULL;
	ret = xsk_socket__create(&xsk->xsk, opt_if, opt_queue, umem->umem,
				 rxr, txr, &cfg);
	if (ret)
		exit_with_error(-ret);

	ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags);
	if (ret)
		exit_with_error(-ret);

	return xsk;
}

static struct option long_options[] = {
	{"rxdrop", no_argument, 0, 'r'},
	{"txonly", no_argument, 0, 't'},
	{"l2fwd", no_argument, 0, 'l'},
	{"interface", required_argument, 0, 'i'},
	{"queue", required_argument, 0, 'q'},
	{"poll", no_argument, 0, 'p'},
	{"xdp-skb", no_argument, 0, 'S'},
	{"xdp-native", no_argument, 0, 'N'},
	{"interval", required_argument, 0, 'n'},
	{"zero-copy", no_argument, 0, 'z'},
	{"copy", no_argument, 0, 'c'},
	{"frame-size", required_argument, 0, 'f'},
	{"no-need-wakeup", no_argument, 0, 'm'},
	{"unaligned", no_argument, 0, 'u'},
	{"shared-umem", no_argument, 0, 'M'},
	{"force", no_argument, 0, 'F'},
	{"duration", required_argument, 0, 'd'},
	{"batch-size", required_argument, 0, 'b'},
	{"tx-pkt-count", required_argument, 0, 'C'},
	{"tx-pkt-size", required_argument, 0, 's'},
	{"tx-pkt-pattern", required_argument, 0, 'P'},
	{"extra-stats", no_argument, 0, 'x'},
	{0, 0, 0, 0}
};

static void usage(const char *prog)
{
	const char *str =
		"  Usage: %s [OPTIONS]\n"
		"  Options:\n"
		"  -r, --rxdrop		Discard all incoming packets (default)\n"
		"  -t, --txonly		Only send packets\n"
		"  -l, --l2fwd		MAC swap L2 forwarding\n"
		"  -i, --interface=n	Run on interface n\n"
		"  -q, --queue=n	Use queue n (default 0)\n"
		"  -p, --poll		Use poll syscall\n"
		"  -S, --xdp-skb=n	Use XDP skb-mod\n"
		"  -N, --xdp-native=n	Enforce XDP native mode\n"
		"  -n, --interval=n	Specify statistics update interval (default 1 sec).\n"
		"  -z, --zero-copy      Force zero-copy mode.\n"
		"  -c, --copy           Force copy mode.\n"
		"  -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n"
		"  -f, --frame-size=n   Set the frame size (must be a power of two in aligned mode, default is %d).\n"
		"  -u, --unaligned	Enable unaligned chunk placement\n"
		"  -M, --shared-umem	Enable XDP_SHARED_UMEM\n"
		"  -F, --force		Force loading the XDP prog\n"
		"  -d, --duration=n	Duration in secs to run command.\n"
		"			Default: forever.\n"
		"  -b, --batch-size=n	Batch size for sending or receiving\n"
		"			packets. Default: %d\n"
		"  -C, --tx-pkt-count=n	Number of packets to send.\n"
		"			Default: Continuous packets.\n"
		"  -s, --tx-pkt-size=n	Transmit packet size.\n"
		"			(Default: %d bytes)\n"
		"			Min size: %d, Max size %d.\n"
		"  -P, --tx-pkt-pattern=nPacket fill pattern. Default: 0x%x\n"
		"  -x, --extra-stats	Display extra statistics.\n"
		"\n";
	fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE,
		opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE,
		XSK_UMEM__DEFAULT_FRAME_SIZE, opt_pkt_fill_pattern);

	exit(EXIT_FAILURE);
}

static void parse_command_line(int argc, char **argv)
{
	int option_index, c;

	opterr = 0;

	for (;;) {
		c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:x",
				long_options, &option_index);
		if (c == -1)
			break;

		switch (c) {
		case 'r':
			opt_bench = BENCH_RXDROP;
			break;
		case 't':
			opt_bench = BENCH_TXONLY;
			break;
		case 'l':
			opt_bench = BENCH_L2FWD;
			break;
		case 'i':
			opt_if = optarg;
			break;
		case 'q':
			opt_queue = atoi(optarg);
			break;
		case 'p':
			opt_poll = 1;
			break;
		case 'S':
			opt_xdp_flags |= XDP_FLAGS_SKB_MODE;
			opt_xdp_bind_flags |= XDP_COPY;
			break;
		case 'N':
			/* default, set below */
			break;
		case 'n':
			opt_interval = atoi(optarg);
			break;
		case 'z':
			opt_xdp_bind_flags |= XDP_ZEROCOPY;
			break;
		case 'c':
			opt_xdp_bind_flags |= XDP_COPY;
			break;
		case 'u':
			opt_umem_flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG;
			opt_unaligned_chunks = 1;
			opt_mmap_flags = MAP_HUGETLB;
			break;
		case 'F':
			opt_xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
			break;
		case 'f':
			opt_xsk_frame_size = atoi(optarg);
			break;
		case 'm':
			opt_need_wakeup = false;
			opt_xdp_bind_flags &= ~XDP_USE_NEED_WAKEUP;
			break;
		case 'M':
			opt_num_xsks = MAX_SOCKS;
			break;
		case 'd':
			opt_duration = atoi(optarg);
			opt_duration *= 1000000000;
			break;
		case 'b':
			opt_batch_size = atoi(optarg);
			break;
		case 'C':
			opt_pkt_count = atoi(optarg);
			break;
		case 's':
			opt_pkt_size = atoi(optarg);
			if (opt_pkt_size > (XSK_UMEM__DEFAULT_FRAME_SIZE) ||
			    opt_pkt_size < MIN_PKT_SIZE) {
				fprintf(stderr,
					"ERROR: Invalid frame size %d\n",
					opt_pkt_size);
				usage(basename(argv[0]));
			}
			break;
		case 'P':
			opt_pkt_fill_pattern = strtol(optarg, NULL, 16);
			break;
		case 'x':
			opt_extra_stats = 1;
			break;
		default:
			usage(basename(argv[0]));
		}
	}

	if (!(opt_xdp_flags & XDP_FLAGS_SKB_MODE))
		opt_xdp_flags |= XDP_FLAGS_DRV_MODE;

	opt_ifindex = if_nametoindex(opt_if);
	if (!opt_ifindex) {
		fprintf(stderr, "ERROR: interface \"%s\" does not exist\n",
			opt_if);
		usage(basename(argv[0]));
	}

	if ((opt_xsk_frame_size & (opt_xsk_frame_size - 1)) &&
	    !opt_unaligned_chunks) {
		fprintf(stderr, "--frame-size=%d is not a power of two\n",
			opt_xsk_frame_size);
		usage(basename(argv[0]));
	}
}

static void kick_tx(struct xsk_socket_info *xsk)
{
	int ret;

	ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0);
	if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN ||
	    errno == EBUSY || errno == ENETDOWN)
		return;
	exit_with_error(errno);
}

static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk,
				     struct pollfd *fds)
{
	struct xsk_umem_info *umem = xsk->umem;
	u32 idx_cq = 0, idx_fq = 0;
	unsigned int rcvd;
	size_t ndescs;

	if (!xsk->outstanding_tx)
		return;

	ndescs = (xsk->outstanding_tx > opt_batch_size) ? opt_batch_size :
		xsk->outstanding_tx;

	/* re-add completed Tx buffers */
	rcvd = xsk_ring_cons__peek(&umem->cq, ndescs, &idx_cq);
	if (rcvd > 0) {
		unsigned int i;
		int ret;

		ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
		while (ret != rcvd) {
			if (ret < 0)
				exit_with_error(-ret);
			if (xsk_ring_prod__needs_wakeup(&umem->fq))
				ret = poll(fds, num_socks, opt_timeout);
			ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
		}

		for (i = 0; i < rcvd; i++)
			*xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) =
				*xsk_ring_cons__comp_addr(&umem->cq, idx_cq++);

		xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
		xsk->outstanding_tx -= rcvd;
		xsk->tx_npkts += rcvd;
	}
}

static inline void complete_tx_only(struct xsk_socket_info *xsk,
				    int batch_size)
{
	unsigned int rcvd;
	u32 idx;

	if (!xsk->outstanding_tx)
		return;

	if (!opt_need_wakeup || xsk_ring_prod__needs_wakeup(&xsk->tx))
		kick_tx(xsk);

	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
	if (rcvd > 0) {
		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
		xsk->outstanding_tx -= rcvd;
		xsk->tx_npkts += rcvd;
	}
}

static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds)
{
	unsigned int rcvd, i;
	u32 idx_rx = 0, idx_fq = 0;
	int ret;

	rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx);
	if (!rcvd) {
		if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
			ret = poll(fds, num_socks, opt_timeout);
		return;
	}

	ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
	while (ret != rcvd) {
		if (ret < 0)
			exit_with_error(-ret);
		if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
			ret = poll(fds, num_socks, opt_timeout);
		ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
	}

	for (i = 0; i < rcvd; i++) {
		u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr;
		u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len;
		u64 orig = xsk_umem__extract_addr(addr);

		addr = xsk_umem__add_offset_to_addr(addr);
		char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr);

		hex_dump(pkt, len, addr);
		*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig;
	}

	xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
	xsk_ring_cons__release(&xsk->rx, rcvd);
	xsk->rx_npkts += rcvd;
}

static void rx_drop_all(void)
{
	struct pollfd fds[MAX_SOCKS] = {};
	int i, ret;

	for (i = 0; i < num_socks; i++) {
		fds[i].fd = xsk_socket__fd(xsks[i]->xsk);
		fds[i].events = POLLIN;
	}

	for (;;) {
		if (opt_poll) {
			ret = poll(fds, num_socks, opt_timeout);
			if (ret <= 0)
				continue;
		}

		for (i = 0; i < num_socks; i++)
			rx_drop(xsks[i], fds);

		if (benchmark_done)
			break;
	}
}

static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size)
{
	u32 idx;
	unsigned int i;

	while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) <
				      batch_size) {
		complete_tx_only(xsk, batch_size);
	}

	for (i = 0; i < batch_size; i++) {
		struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx,
								  idx + i);
		tx_desc->addr = (*frame_nb + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT;
		tx_desc->len = PKT_SIZE;
	}

	xsk_ring_prod__submit(&xsk->tx, batch_size);
	xsk->outstanding_tx += batch_size;
	*frame_nb += batch_size;
	*frame_nb %= NUM_FRAMES;
	complete_tx_only(xsk, batch_size);
}

static inline int get_batch_size(int pkt_cnt)
{
	if (!opt_pkt_count)
		return opt_batch_size;

	if (pkt_cnt + opt_batch_size <= opt_pkt_count)
		return opt_batch_size;

	return opt_pkt_count - pkt_cnt;
}

static void complete_tx_only_all(void)
{
	bool pending;
	int i;

	do {
		pending = false;
		for (i = 0; i < num_socks; i++) {
			if (xsks[i]->outstanding_tx) {
				complete_tx_only(xsks[i], opt_batch_size);
				pending = !!xsks[i]->outstanding_tx;
			}
		}
	} while (pending);
}

static void tx_only_all(void)
{
	struct pollfd fds[MAX_SOCKS] = {};
	u32 frame_nb[MAX_SOCKS] = {};
	int pkt_cnt = 0;
	int i, ret;

	for (i = 0; i < num_socks; i++) {
		fds[0].fd = xsk_socket__fd(xsks[i]->xsk);
		fds[0].events = POLLOUT;
	}

	while ((opt_pkt_count && pkt_cnt < opt_pkt_count) || !opt_pkt_count) {
		int batch_size = get_batch_size(pkt_cnt);

		if (opt_poll) {
			ret = poll(fds, num_socks, opt_timeout);
			if (ret <= 0)
				continue;

			if (!(fds[0].revents & POLLOUT))
				continue;
		}

		for (i = 0; i < num_socks; i++)
			tx_only(xsks[i], &frame_nb[i], batch_size);

		pkt_cnt += batch_size;

		if (benchmark_done)
			break;
	}

	if (opt_pkt_count)
		complete_tx_only_all();
}

static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds)
{
	unsigned int rcvd, i;
	u32 idx_rx = 0, idx_tx = 0;
	int ret;

	complete_tx_l2fwd(xsk, fds);

	rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx);
	if (!rcvd) {
		if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq))
			ret = poll(fds, num_socks, opt_timeout);
		return;
	}

	ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx);
	while (ret != rcvd) {
		if (ret < 0)
			exit_with_error(-ret);
		if (xsk_ring_prod__needs_wakeup(&xsk->tx))
			kick_tx(xsk);
		ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx);
	}

	for (i = 0; i < rcvd; i++) {
		u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr;
		u32 len = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len;
		u64 orig = addr;

		addr = xsk_umem__add_offset_to_addr(addr);
		char *pkt = xsk_umem__get_data(xsk->umem->buffer, addr);

		swap_mac_addresses(pkt);

		hex_dump(pkt, len, addr);
		xsk_ring_prod__tx_desc(&xsk->tx, idx_tx)->addr = orig;
		xsk_ring_prod__tx_desc(&xsk->tx, idx_tx++)->len = len;
	}

	xsk_ring_prod__submit(&xsk->tx, rcvd);
	xsk_ring_cons__release(&xsk->rx, rcvd);

	xsk->rx_npkts += rcvd;
	xsk->outstanding_tx += rcvd;
}

static void l2fwd_all(void)
{
	struct pollfd fds[MAX_SOCKS] = {};
	int i, ret;

	for (i = 0; i < num_socks; i++) {
		fds[i].fd = xsk_socket__fd(xsks[i]->xsk);
		fds[i].events = POLLOUT | POLLIN;
	}

	for (;;) {
		if (opt_poll) {
			ret = poll(fds, num_socks, opt_timeout);
			if (ret <= 0)
				continue;
		}

		for (i = 0; i < num_socks; i++)
			l2fwd(xsks[i], fds);

		if (benchmark_done)
			break;
	}
}

static void load_xdp_program(char **argv, struct bpf_object **obj)
{
	struct bpf_prog_load_attr prog_load_attr = {
		.prog_type      = BPF_PROG_TYPE_XDP,
	};
	char xdp_filename[256];
	int prog_fd;

	snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]);
	prog_load_attr.file = xdp_filename;

	if (bpf_prog_load_xattr(&prog_load_attr, obj, &prog_fd))
		exit(EXIT_FAILURE);
	if (prog_fd < 0) {
		fprintf(stderr, "ERROR: no program found: %s\n",
			strerror(prog_fd));
		exit(EXIT_FAILURE);
	}

	if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd, opt_xdp_flags) < 0) {
		fprintf(stderr, "ERROR: link set xdp fd failed\n");
		exit(EXIT_FAILURE);
	}
}

static void enter_xsks_into_map(struct bpf_object *obj)
{
	struct bpf_map *map;
	int i, xsks_map;

	map = bpf_object__find_map_by_name(obj, "xsks_map");
	xsks_map = bpf_map__fd(map);
	if (xsks_map < 0) {
		fprintf(stderr, "ERROR: no xsks map found: %s\n",
			strerror(xsks_map));
			exit(EXIT_FAILURE);
	}

	for (i = 0; i < num_socks; i++) {
		int fd = xsk_socket__fd(xsks[i]->xsk);
		int key, ret;

		key = i;
		ret = bpf_map_update_elem(xsks_map, &key, &fd, 0);
		if (ret) {
			fprintf(stderr, "ERROR: bpf_map_update_elem %d\n", i);
			exit(EXIT_FAILURE);
		}
	}
}

int main(int argc, char **argv)
{
	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
	bool rx = false, tx = false;
	struct xsk_umem_info *umem;
	struct bpf_object *obj;
	pthread_t pt;
	int i, ret;
	void *bufs;

	parse_command_line(argc, argv);

	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
		fprintf(stderr, "ERROR: setrlimit(RLIMIT_MEMLOCK) \"%s\"\n",
			strerror(errno));
		exit(EXIT_FAILURE);
	}

	if (opt_num_xsks > 1)
		load_xdp_program(argv, &obj);

	/* Reserve memory for the umem. Use hugepages if unaligned chunk mode */
	bufs = mmap(NULL, NUM_FRAMES * opt_xsk_frame_size,
		    PROT_READ | PROT_WRITE,
		    MAP_PRIVATE | MAP_ANONYMOUS | opt_mmap_flags, -1, 0);
	if (bufs == MAP_FAILED) {
		printf("ERROR: mmap failed\n");
		exit(EXIT_FAILURE);
	}

	/* Create sockets... */
	umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size);
	if (opt_bench == BENCH_RXDROP || opt_bench == BENCH_L2FWD) {
		rx = true;
		xsk_populate_fill_ring(umem);
	}
	if (opt_bench == BENCH_L2FWD || opt_bench == BENCH_TXONLY)
		tx = true;
	for (i = 0; i < opt_num_xsks; i++)
		xsks[num_socks++] = xsk_configure_socket(umem, rx, tx);

	if (opt_bench == BENCH_TXONLY) {
		gen_eth_hdr_data();

		for (i = 0; i < NUM_FRAMES; i++)
			gen_eth_frame(umem, i * opt_xsk_frame_size);
	}

	if (opt_num_xsks > 1 && opt_bench != BENCH_TXONLY)
		enter_xsks_into_map(obj);

	signal(SIGINT, int_exit);
	signal(SIGTERM, int_exit);
	signal(SIGABRT, int_exit);

	setlocale(LC_ALL, "");

	ret = pthread_create(&pt, NULL, poller, NULL);
	if (ret)
		exit_with_error(ret);

	prev_time = get_nsecs();
	start_time = prev_time;

	if (opt_bench == BENCH_RXDROP)
		rx_drop_all();
	else if (opt_bench == BENCH_TXONLY)
		tx_only_all();
	else
		l2fwd_all();

	benchmark_done = true;

	pthread_join(pt, NULL);

	xdpsock_cleanup();

	return 0;
}