本篇是之前博客[1]的进阶篇，博客中给出了相关环境安装配置。
功能：本篇通过bpf程序，将icmp数据包重定向到AF_XDP socket。
内核侧程序片断，xdpsock_kern.c
// SPDX-License-Identifier: GPL-2.0
#include <linux/bpf.h>
#include <linux/in.h>
#include <linux/if_ether.h>
#include <linux/ip.h>
#include <linux/types.h>
#include <stddef.h>
#include <memory.h>
#include <sys/types.h>
#define RR_LB 0
#define MAX_SOCKS 4
#define SEC(NAME) __attribute__((section(NAME), used))
#define __uint(name, val) int(*(name))[val]
#define __type(name, val) typeof(val) *(name)
#define __array(name, val) typeof(val) *(name)[]
//https://raw.githubusercontent.com/torvalds/linux/v4.19/tools/testing/selftests/bpf/bpf_helpers.h
static void *(*bpf_map_lookup_elem)(void *map, void *key) =
(void *) BPF_FUNC_map_lookup_elem;
static int (*bpf_redirect_map)(void *map, int key, int flags) =
(void *) BPF_FUNC_redirect_map;
struct {
__uint(type, BPF_MAP_TYPE_ARRAY);
__uint(key_size, sizeof(int));
__uint(value_size, sizeof(int));
__uint(max_entries, 1);
}qidconf_map SEC(".maps");
struct{
__uint(type, BPF_MAP_TYPE_XSKMAP);
__uint(key_size, sizeof(int));
__uint(value_size, sizeof(int));
__uint(max_entries, MAX_SOCKS);
}xsks_map SEC(".maps");
struct{
__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
__uint(key_size, sizeof(int));
__uint(value_size, sizeof(int));
__uint(max_entries, 1);
}rr_map SEC(".maps");
SEC("xdp_sock")
int xdp_sock_prog(struct xdp_md *ctx)
{
int ipsize = 0;
void *data = (void *)(long)ctx->data;
void *data_end = (void *)(long)ctx->data_end;
int *qidconf, key = 0, idx=0;
unsigned int *rr;
struct ethhdr *eth = data;
ipsize = sizeof(*eth);
struct iphdr *ip = data + ipsize;
ipsize += sizeof(struct iphdr);
if (data + ipsize > data_end) {
// not an ip packet, too short. Pass it on
return XDP_PASS;
}
// technically, we should also check if it is an IP packet by
// checking the ethernet header proto field ...
if (ip->protocol == IPPROTO_ICMP) {
/*
qidconf = bpf_map_lookup_elem(&qidconf_map, &key);
if (!qidconf)
return XDP_ABORTED;
if (*qidconf != ctx->rx_queue_index)
return XDP_PASS;
*/
#if RR_LB /* NB! RR_LB is configured in xdpsock.h */
rr = bpf_map_lookup_elem(&rr_map, &key);
if (!rr)
return XDP_ABORTED;
*rr = (*rr + 1) & (MAX_SOCKS - 1);
idx = *rr;
#endif
return bpf_redirect_map(&xsks_map, idx, 0);
}
return XDP_PASS;
}
char _license[] SEC("license") = "GPL";
//clang -g -c -O2 -target bpf -c xdpsock_kern.c -o xdpsock_kern.o
编译命令：
clang -g -c -O2 -target bpf -c xdpsock_kern.c -o xdpsock_kern.o
用户侧程序段，xdpsock_user.c
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2017 - 2018 Intel Corporation. */
//https://android.googlesource.com/kernel/common/+/30bac164aca7/samples/bpf/xdpsock_user.c
#include <assert.h>
#include <errno.h>
#include <getopt.h>
#include <libgen.h>
#include <linux/bpf.h>
#include <linux/if_link.h>
#include <linux/if_xdp.h>
#include <linux/if_ether.h>
#include <net/if.h>
#include <signal.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <net/ethernet.h>
#include <sys/resource.h>
#include <sys/socket.h>
#include <sys/mman.h>
#include <time.h>
#include <unistd.h>
#include <pthread.h>
#include <locale.h>
#include <sys/types.h>
#include <poll.h>
#include "bpf/libbpf.h"
//#include "bpf_util.h"
#include <bpf/bpf.h>
/* Power-of-2 number of sockets */
#define MAX_SOCKS 4
/* Round-robin receive */
#define RR_LB 0
#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 131072
#define FRAME_HEADROOM 0
#define FRAME_SHIFT 11
#define FRAME_SIZE 2048
#define NUM_DESCS 1024
#define BATCH_SIZE 16
#define FQ_NUM_DESCS 1024
#define CQ_NUM_DESCS 1024
#define DEBUG_HEXDUMP 0
typedef __u64 u64;
typedef __u32 u32;
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;
static const char *opt_if = "";
static int opt_ifindex;
static int opt_queue;
static int opt_poll;
static int opt_shared_packet_buffer;
static int opt_interval = 1;
static u32 opt_xdp_bind_flags;
struct xdp_umem_uqueue {
u32 cached_prod;
u32 cached_cons;
u32 mask;
u32 size;
u32 *producer;
u32 *consumer;
u64 *ring;
void *map;
};
struct xdp_umem {
char *frames;
struct xdp_umem_uqueue fq;
struct xdp_umem_uqueue cq;
int fd;
};
struct xdp_uqueue {
u32 cached_prod;
u32 cached_cons;
u32 mask;
u32 size;
u32 *producer;
u32 *consumer;
struct xdp_desc *ring;
void *map;
};
struct xdpsock {
struct xdp_uqueue rx;
struct xdp_uqueue tx;
int sfd;
struct xdp_umem *umem;
u32 outstanding_tx;
unsigned long rx_npkts;
unsigned long tx_npkts;
unsigned long prev_rx_npkts;
unsigned long prev_tx_npkts;
};
static int num_socks;
struct xdpsock *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 dump_stats(void);
#define lassert(expr) \
do { \
if (!(expr)) { \
fprintf(stderr, "%s:%s:%i: Assertion failed: " \
#expr ": errno: %d/\"%s\"\n", \
__FILE__, __func__, __LINE__, \
errno, strerror(errno)); \
dump_stats(); \
exit(EXIT_FAILURE); \
} \
} while (0)
#define barrier() __asm__ __volatile__("": : :"memory")
#ifdef __aarch64__
#define u_smp_rmb() __asm__ __volatile__("dmb ishld": : :"memory")
#define u_smp_wmb() __asm__ __volatile__("dmb ishst": : :"memory")
#else
#define u_smp_rmb() barrier()
#define u_smp_wmb() barrier()
#endif
#define likely(x) __builtin_expect(!!(x), 1)
#define unlikely(x) __builtin_expect(!!(x), 0)
static const char pkt_data[] =
"\x3c\xfd\xfe\x9e\x7f\x71\xec\xb1\xd7\x98\x3a\xc0\x08\x00\x45\x00"
"\x00\x2e\x00\x00\x00\x00\x40\x11\x88\x97\x05\x08\x07\x08\xc8\x14"
"\x1e\x04\x10\x92\x10\x92\x00\x1a\x6d\xa3\x34\x33\x1f\x69\x40\x6b"
"\x54\x59\xb6\x14\x2d\x11\x44\xbf\xaf\xd9\xbe\xaa";
static inline u32 umem_nb_free(struct xdp_umem_uqueue *q, u32 nb)
{
u32 free_entries = q->cached_cons - q->cached_prod;
if (free_entries >= nb)
return free_entries;
/* Refresh the local tail pointer */
q->cached_cons = *q->consumer + q->size;
return q->cached_cons - q->cached_prod;
}
static inline u32 xq_nb_free(struct xdp_uqueue *q, u32 ndescs)
{
u32 free_entries = q->cached_cons - q->cached_prod;
if (free_entries >= ndescs)
return free_entries;
/* Refresh the local tail pointer */
q->cached_cons = *q->consumer + q->size;
return q->cached_cons - q->cached_prod;
}
static inline u32 umem_nb_avail(struct xdp_umem_uqueue *q, u32 nb)
{
u32 entries = q->cached_prod - q->cached_cons;
if (entries == 0) {
q->cached_prod = *q->producer;
entries = q->cached_prod - q->cached_cons;
}
return (entries > nb) ? nb : entries;
}
static inline u32 xq_nb_avail(struct xdp_uqueue *q, u32 ndescs)
{
u32 entries = q->cached_prod - q->cached_cons;
if (entries == 0) {
q->cached_prod = *q->producer;
entries = q->cached_prod - q->cached_cons;
}
return (entries > ndescs) ? ndescs : entries;
}
static inline int umem_fill_to_kernel_ex(struct xdp_umem_uqueue *fq,
struct xdp_desc *d,
size_t nb)
{
u32 i;
if (umem_nb_free(fq, nb) < nb)
return -ENOSPC;
for (i = 0; i < nb; i++) {
u32 idx = fq->cached_prod++ & fq->mask;
fq->ring[idx] = d[i].addr;
}
u_smp_wmb();
*fq->producer = fq->cached_prod;
return 0;
}
static inline int umem_fill_to_kernel(struct xdp_umem_uqueue *fq, u64 *d,
size_t nb)
{
u32 i;
if (umem_nb_free(fq, nb) < nb)
return -ENOSPC;
for (i = 0; i < nb; i++) {
u32 idx = fq->cached_prod++ & fq->mask;
fq->ring[idx] = d[i];
}
u_smp_wmb();
*fq->producer = fq->cached_prod;
return 0;
}
static inline size_t umem_complete_from_kernel(struct xdp_umem_uqueue *cq,
u64 *d, size_t nb)
{
u32 idx, i, entries = umem_nb_avail(cq, nb);
u_smp_rmb();
for (i = 0; i < entries; i++) {
idx = cq->cached_cons++ & cq->mask;
d[i] = cq->ring[idx];
}
if (entries > 0) {
u_smp_wmb();
*cq->consumer = cq->cached_cons;
}
return entries;
}
static inline void *xq_get_data(struct xdpsock *xsk, u64 addr)
{
return &xsk->umem->frames[addr];
}
static inline int xq_enq(struct xdp_uqueue *uq,
const struct xdp_desc *descs,
unsigned int ndescs)
{
struct xdp_desc *r = uq->ring;
unsigned int i;
if (xq_nb_free(uq, ndescs) < ndescs)
return -ENOSPC;
for (i = 0; i < ndescs; i++) {
u32 idx = uq->cached_prod++ & uq->mask;
r[idx].addr = descs[i].addr;
r[idx].len = descs[i].len;
}
u_smp_wmb();
*uq->producer = uq->cached_prod;
return 0;
}
static inline int xq_enq_tx_only(struct xdp_uqueue *uq,
unsigned int id, unsigned int ndescs)
{
struct xdp_desc *r = uq->ring;
unsigned int i;
if (xq_nb_free(uq, ndescs) < ndescs)
return -ENOSPC;
for (i = 0; i < ndescs; i++) {
u32 idx = uq->cached_prod++ & uq->mask;
r[idx].addr = (id + i) << FRAME_SHIFT;
r[idx].len = sizeof(pkt_data) - 1;
}
u_smp_wmb();
*uq->producer = uq->cached_prod;
return 0;
}
static inline int xq_deq(struct xdp_uqueue *uq,
struct xdp_desc *descs,
int ndescs)
{
struct xdp_desc *r = uq->ring;
unsigned int idx;
int i, entries;
entries = xq_nb_avail(uq, ndescs);
u_smp_rmb();
for (i = 0; i < entries; i++) {
idx = uq->cached_cons++ & uq->mask;
descs[i] = r[idx];
}
if (entries > 0) {
u_smp_wmb();
*uq->consumer = uq->cached_cons;
}
return entries;
}
static void swap_mac_addresses(void *data)
{
struct ether_header *eth = (struct ether_header *)data;
struct ether_addr *src_addr = (struct ether_addr *)ð->ether_shost;
struct ether_addr *dst_addr = (struct ether_addr *)ð->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 size_t gen_eth_frame(char *frame)
{
memcpy(frame, pkt_data, sizeof(pkt_data) - 1);
return sizeof(pkt_data) - 1;
}
static struct xdp_umem *xdp_umem_configure(int sfd)
{
int fq_size = FQ_NUM_DESCS, cq_size = CQ_NUM_DESCS;
struct xdp_mmap_offsets off;
struct xdp_umem_reg mr;
struct xdp_umem *umem;
socklen_t optlen;
void *bufs;
umem = calloc(1, sizeof(*umem));
lassert(umem);
lassert(posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */
NUM_FRAMES * FRAME_SIZE) == 0);
mr.addr = (__u64)bufs;
mr.len = NUM_FRAMES * FRAME_SIZE;
mr.chunk_size = FRAME_SIZE;
mr.headroom = FRAME_HEADROOM;
lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr)) == 0);
lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_FILL_RING, &fq_size,
sizeof(int)) == 0);
lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_COMPLETION_RING, &cq_size,
sizeof(int)) == 0);
optlen = sizeof(off);
lassert(getsockopt(sfd, SOL_XDP, XDP_MMAP_OFFSETS, &off,
&optlen) == 0);
umem->fq.map = mmap(0, off.fr.desc +
FQ_NUM_DESCS * sizeof(u64),
PROT_READ | PROT_WRITE,
MAP_SHARED | MAP_POPULATE, sfd,
XDP_UMEM_PGOFF_FILL_RING);
lassert(umem->fq.map != MAP_FAILED);
umem->fq.mask = FQ_NUM_DESCS - 1;
umem->fq.size = FQ_NUM_DESCS;
umem->fq.producer = umem->fq.map + off.fr.producer;
umem->fq.consumer = umem->fq.map + off.fr.consumer;
umem->fq.ring = umem->fq.map + off.fr.desc;
umem->fq.cached_cons = FQ_NUM_DESCS;
umem->cq.map = mmap(0, off.cr.desc +
CQ_NUM_DESCS * sizeof(u64),
PROT_READ | PROT_WRITE,
MAP_SHARED | MAP_POPULATE, sfd,
XDP_UMEM_PGOFF_COMPLETION_RING);
lassert(umem->cq.map != MAP_FAILED);
umem->cq.mask = CQ_NUM_DESCS - 1;
umem->cq.size = CQ_NUM_DESCS;
umem->cq.producer = umem->cq.map + off.cr.producer;
umem->cq.consumer = umem->cq.map + off.cr.consumer;
umem->cq.ring = umem->cq.map + off.cr.desc;
umem->frames = bufs;
umem->fd = sfd;
if (opt_bench == BENCH_TXONLY) {
int i;
for (i = 0; i < NUM_FRAMES * FRAME_SIZE; i += FRAME_SIZE)
(void)gen_eth_frame(&umem->frames[i]);
}
return umem;
}
static struct xdpsock *xsk_configure(struct xdp_umem *umem)
{
struct sockaddr_xdp sxdp = {};
struct xdp_mmap_offsets off;
int sfd, ndescs = NUM_DESCS;
struct xdpsock *xsk;
bool shared = true;
socklen_t optlen;
u64 i;
sfd = socket(PF_XDP, SOCK_RAW, 0);
lassert(sfd >= 0);
xsk = calloc(1, sizeof(*xsk));
lassert(xsk);
xsk->sfd = sfd;
xsk->outstanding_tx = 0;
if (!umem) {
shared = false;
xsk->umem = xdp_umem_configure(sfd);
} else {
xsk->umem = umem;
}
lassert(setsockopt(sfd, SOL_XDP, XDP_RX_RING,
&ndescs, sizeof(int)) == 0);
lassert(setsockopt(sfd, SOL_XDP, XDP_TX_RING,
&ndescs, sizeof(int)) == 0);
optlen = sizeof(off);
lassert(getsockopt(sfd, SOL_XDP, XDP_MMAP_OFFSETS, &off,
&optlen) == 0);
/* Rx */
xsk->rx.map = mmap(NULL,
off.rx.desc +
NUM_DESCS * sizeof(struct xdp_desc),
PROT_READ | PROT_WRITE,
MAP_SHARED | MAP_POPULATE, sfd,
XDP_PGOFF_RX_RING);
lassert(xsk->rx.map != MAP_FAILED);
if (!shared) {
for (i = 0; i < NUM_DESCS * FRAME_SIZE; i += FRAME_SIZE)
lassert(umem_fill_to_kernel(&xsk->umem->fq, &i, 1)
== 0);
}
/* Tx */
xsk->tx.map = mmap(NULL,
off.tx.desc +
NUM_DESCS * sizeof(struct xdp_desc),
PROT_READ | PROT_WRITE,
MAP_SHARED | MAP_POPULATE, sfd,
XDP_PGOFF_TX_RING);
lassert(xsk->tx.map != MAP_FAILED);
xsk->rx.mask = NUM_DESCS - 1;
xsk->rx.size = NUM_DESCS;
xsk->rx.producer = xsk->rx.map + off.rx.producer;
xsk->rx.consumer = xsk->rx.map + off.rx.consumer;
xsk->rx.ring = xsk->rx.map + off.rx.desc;
xsk->tx.mask = NUM_DESCS - 1;
xsk->tx.size = NUM_DESCS;
xsk->tx.producer = xsk->tx.map + off.tx.producer;
xsk->tx.consumer = xsk->tx.map + off.tx.consumer;
xsk->tx.ring = xsk->tx.map + off.tx.desc;
xsk->tx.cached_cons = NUM_DESCS;
sxdp.sxdp_family = PF_XDP;
sxdp.sxdp_ifindex = opt_ifindex;
sxdp.sxdp_queue_id = opt_queue;
if (shared) {
sxdp.sxdp_flags = XDP_SHARED_UMEM;
sxdp.sxdp_shared_umem_fd = umem->fd;
} else {
sxdp.sxdp_flags = opt_xdp_bind_flags;
}
lassert(bind(sfd, (struct sockaddr *)&sxdp, sizeof(sxdp)) == 0);
return xsk;
}
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 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;
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;
}
}
static volatile bool g_running=true;
static void *poller(void *arg)
{
(void)arg;
while(g_running) {
sleep(opt_interval);
dump_stats();
}
return NULL;
}
static void sig_handler(int signo)
{
(void)signo;
g_running=false;
dump_stats();
}
static int do_attach(int fd,u32 xdp_flags,int if_index){
struct bpf_prog_info info = {};
uint32_t info_len = sizeof(info);
int prog_id=-1,err = 0;
err = bpf_xdp_attach(if_index, fd, xdp_flags, NULL);
if (err < 0) {
printf("ERROR: failed to attach program to nic\n");
return prog_id;
}
err = bpf_obj_get_info_by_fd(fd, &info, &info_len);
if (err) {
printf("can't get prog info - %s\n", strerror(errno));
return prog_id;
}
prog_id = info.id;
return prog_id;
}
static int do_detach(int prog_id,u32 xdp_flags,int if_index)
{
u32 curr_prog_id = 0;
int err = 0;
err = bpf_xdp_query_id(if_index, xdp_flags, &curr_prog_id);
if (err) {
printf("bpf_xdp_query_id failed\n");
return err;
}
if (prog_id == curr_prog_id) {
err = bpf_xdp_detach(if_index, xdp_flags, NULL);
if (err < 0)
printf("ERROR: failed to detach prog from nic\n");
} else if (!curr_prog_id) {
printf("couldn't find a prog id on nic\n");
} else {
printf("program on interface changed, not removing\n");
}
return err;
}
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'},
{"shared-buffer", no_argument, 0, 's'},
{"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'},
{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, --shared-buffer Use shared packet buffer\n"
" -S, --xdp-skb=n Use XDP skb-mod\n"
" -N, --xdp-native=n Enfore 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"
"\n";
fprintf(stderr, str, prog);
exit(EXIT_FAILURE);
}
static void parse_command_line(int argc, char **argv)
{
int option_index, c;
opterr = 0;
for (;;) {
c = getopt_long(argc, argv, "rtli:q:psSNn:cz", 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 's':
opt_shared_packet_buffer = 1;
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':
opt_xdp_flags |= XDP_FLAGS_DRV_MODE;
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;
default:
usage(basename(argv[0]));
}
}
opt_ifindex = if_nametoindex(opt_if);
if (!opt_ifindex) {
fprintf(stderr, "ERROR: interface \"%s\" does not exist\n",
opt_if);
usage(basename(argv[0]));
}
}
static void kick_tx(int fd)
{
int ret;
ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0);
if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY)
return;
lassert(0);
}
static inline void complete_tx_l2fwd(struct xdpsock *xsk)
{
u64 descs[BATCH_SIZE];
unsigned int rcvd;
size_t ndescs;
if (!xsk->outstanding_tx)
return;
kick_tx(xsk->sfd);
ndescs = (xsk->outstanding_tx > BATCH_SIZE) ? BATCH_SIZE :
xsk->outstanding_tx;
/* re-add completed Tx buffers */
rcvd = umem_complete_from_kernel(&xsk->umem->cq, descs, ndescs);
if (rcvd > 0) {
umem_fill_to_kernel(&xsk->umem->fq, descs, rcvd);
xsk->outstanding_tx -= rcvd;
xsk->tx_npkts += rcvd;
}
}
static inline void complete_tx_only(struct xdpsock *xsk)
{
u64 descs[BATCH_SIZE];
unsigned int rcvd;
if (!xsk->outstanding_tx)
return;
kick_tx(xsk->sfd);
rcvd = umem_complete_from_kernel(&xsk->umem->cq, descs, BATCH_SIZE);
if (rcvd > 0) {
xsk->outstanding_tx -= rcvd;
xsk->tx_npkts += rcvd;
}
}
//http://blog.chinaunix.net/uid-30012596-id-4729018.html
#include <net/ethernet.h>
#include <netinet/ether.h>//ether_ntoa
#include <netinet/ip.h>
#include<sys/socket.h>
static void print_pkt_info(const char *pkt, size_t sz){
const struct ethhdr * eth_hdr=(const struct ethhdr*)pkt;
int offset = sizeof(*eth_hdr);
printf("recv packet length %d\n",sz);
/*for (int i = 0; i <ETH_ALEN; ++i)
printf(" %02x", (unsigned char)eth_hdr->h_source[i]);
printf("\n");
for (int i = 0; i <ETH_ALEN; ++i)
printf(" %02x", (unsigned char)eth_hdr->h_dest[i]);
printf("\n");
*/
printf("src mac:%s,",ether_ntoa((struct ether_addr*)&(eth_hdr->h_source)));
if(0==memcmp(eth_hdr->h_source,eth_hdr->h_dest,ETH_ALEN)){
printf("dst mac=src mac");
}
if(sz>offset){
const struct iphdr *ip_hdr = (const struct iphdr*)(pkt + offset);
printf("ip version %d,proto %d\n",ip_hdr->version,ip_hdr->protocol);
}
}
static void rx_drop(struct xdpsock *xsk)
{
struct xdp_desc descs[BATCH_SIZE];
unsigned int rcvd, i;
rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE);
if (!rcvd)
return;
for (i = 0; i < rcvd; i++) {
char *pkt = xq_get_data(xsk, descs[i].addr);
//hex_dump(pkt, descs[i].len, descs[i].addr);
print_pkt_info(pkt,descs[i].len);
}
xsk->rx_npkts += rcvd;
umem_fill_to_kernel_ex(&xsk->umem->fq, descs, rcvd);
}
static void rx_drop_all(void)
{
struct pollfd fds[MAX_SOCKS + 1];
int i, ret, timeout, nfds = 1;
memset(fds, 0, sizeof(fds));
printf("run %s\n",__FUNCTION__);
for (i = 0; i < num_socks; i++) {
fds[i].fd = xsks[i]->sfd;
fds[i].events = POLLIN;
timeout = 1000; /* 1sn */
}
while(g_running) {
if (opt_poll) {
ret = poll(fds, nfds, timeout);
if (ret <= 0)
continue;
}
for (i = 0; i < num_socks; i++)
rx_drop(xsks[i]);
}
}
static void tx_only(struct xdpsock *xsk)
{
int timeout, ret, nfds = 1;
struct pollfd fds[nfds + 1];
unsigned int idx = 0;
memset(fds, 0, sizeof(fds));
fds[0].fd = xsk->sfd;
fds[0].events = POLLOUT;
timeout = 1000; /* 1sn */
while(g_running) {
if (opt_poll) {
ret = poll(fds, nfds, timeout);
if (ret <= 0)
continue;
if (fds[0].fd != xsk->sfd ||
!(fds[0].revents & POLLOUT))
continue;
}
if (xq_nb_free(&xsk->tx, BATCH_SIZE) >= BATCH_SIZE) {
lassert(xq_enq_tx_only(&xsk->tx, idx, BATCH_SIZE) == 0);
xsk->outstanding_tx += BATCH_SIZE;
idx += BATCH_SIZE;
idx %= NUM_FRAMES;
}
complete_tx_only(xsk);
}
}
static void l2fwd(struct xdpsock *xsk)
{
while(g_running){
struct xdp_desc descs[BATCH_SIZE];
unsigned int rcvd, i;
int ret;
for (;;) {
complete_tx_l2fwd(xsk);
rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE);
if (rcvd > 0)
break;
}
for (i = 0; i < rcvd; i++) {
char *pkt = xq_get_data(xsk, descs[i].addr);
swap_mac_addresses(pkt);
hex_dump(pkt, descs[i].len, descs[i].addr);
}
xsk->rx_npkts += rcvd;
ret = xq_enq(&xsk->tx, descs, rcvd);
lassert(ret == 0);
xsk->outstanding_tx += rcvd;
}
}
// ./xdpsock -r -i wlxe0e1a997ab49 -q 0 -n 5 -S
int main(int argc, char **argv)
{
struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
int prog_fd, qidconf_map, xsks_map;
struct bpf_object *obj=NULL;
char xdp_filename[256];
struct bpf_map *map;
int i, ret, key = 0;
pthread_t pt;
if (signal(SIGINT, sig_handler) ||
signal(SIGHUP, sig_handler) ||
signal(SIGTERM, sig_handler)||
signal(SIGTSTP,sig_handler)){
perror("signal");
return 1;
}
parse_command_line(argc, argv);
if (setrlimit(RLIMIT_MEMLOCK, &r)) {
fprintf(stderr, "ERROR: setrlimit(RLIMIT_MEMLOCK) \"%s\"\n",
strerror(errno));
exit(EXIT_FAILURE);
}
snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]);
if(opt_ifindex){
struct bpf_program *prog;
const char *qidconf_map_name="qidconf_map";
const char *xsks_map_name="xsks_map";
obj = bpf_object__open_file(xdp_filename, NULL);
if (libbpf_get_error(obj)){
return 1;
}
prog = bpf_object__next_program(obj, NULL);
bpf_program__set_type(prog, BPF_PROG_TYPE_XDP);
if(prog){
const char *sec_name = bpf_program__section_name(prog);
printf("sec:%s\n",sec_name);
}
int err = bpf_object__load(obj);
if (err){
bpf_object__close(obj);
return 1;
}
prog_fd = bpf_program__fd(prog);
map =bpf_object__find_map_by_name(obj,qidconf_map_name);
if(map){
printf("finding %s \n",qidconf_map_name);
}else{
printf("finding %s failed\n",qidconf_map_name);
bpf_object__close(obj);
return 1;
}
qidconf_map = bpf_map__fd(map);
if(qidconf_map < 0){
fprintf(stderr, "ERROR: no qidconf map found: %s\n",
strerror(qidconf_map));
bpf_object__close(obj);
return 1;
}
map = bpf_object__find_map_by_name(obj,xsks_map_name);
xsks_map = bpf_map__fd(map);
if (xsks_map < 0) {
fprintf(stderr, "ERROR: no xsks map found: %s\n",
strerror(xsks_map));
bpf_object__close(obj);
return 1;
}
}else{
printf("nic does not exist\n");
bpf_object__close(obj);
return 1;
}
int prog_id=-1;
printf("%s,%d\n",opt_if,opt_ifindex);
prog_id=do_attach(prog_fd,opt_xdp_flags,opt_ifindex);
ret = bpf_map_update_elem(qidconf_map, &key, &opt_queue, 0);
if (ret) {
fprintf(stderr, "ERROR: bpf_map_update_elem qidconf\n");
bpf_object__close(obj);
exit(EXIT_FAILURE);
}
xsks[num_socks++] = xsk_configure(NULL);
#if RR_LB
for (i = 0; i < MAX_SOCKS - 1; i++)
xsks[num_socks++] = xsk_configure(xsks[0]->umem);
#endif
// ...and insert them into the map.
for (i = 0; i < num_socks; i++) {
key = i;
ret = bpf_map_update_elem(xsks_map, &key, &xsks[i]->sfd, 0);
if (ret) {
fprintf(stderr, "ERROR: bpf_map_update_elem %d\n", i);
bpf_object__close(obj);
exit(EXIT_FAILURE);
}
}
setlocale(LC_ALL, "");
ret = pthread_create(&pt, NULL, poller, NULL);
lassert(ret == 0);
prev_time = get_nsecs();
if (opt_bench == BENCH_RXDROP)
rx_drop_all();
else if (opt_bench == BENCH_TXONLY)
tx_only(xsks[0]);
else
l2fwd(xsks[0]);
do_detach(prog_id,opt_xdp_flags,opt_ifindex);
bpf_object__close(obj);
return 0;
}
CMakeLists.txt
PROJECT(project)
cmake_minimum_required(VERSION 2.6)
SET(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -g -Wall -O2")
SET(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -g -Wall -O2")
SET(CMAKE_CXX_FLAGS "-fPIC")
#for libbpf
set(LIBBPF_DIR /build/root/usr)
include_directories(${LIBBPF_DIR}/include)
LINK_DIRECTORIES(${LIBBPF_DIR}/lib64)
set(EXECUTABLE_NAME "xdpsock")
add_executable(${EXECUTABLE_NAME} ${CMAKE_SOURCE_DIR}/xdpsock_user.c)
target_link_libraries(${EXECUTABLE_NAME} bpf pthread)
#cmake .. -DCMAKE_C_COMPILER=/usr/bin/clang -DCMAKE_CXX_COMPILER=/usr/bin/clang++
xdpsock_user.c的编译步骤：
mkdir build && cd build
cmake .. -DCMAKE_C_COMPILER=/usr/bin/clang -DCMAKE_CXX_COMPILER=/usr/bin/clang++
make
运行步骤，wlxe0e1a997ab49是我的网卡名字，请替换：
sudo su
./xdpsock -r -i wlxe0e1a997ab49 -q 0 -n 5 -S
Referenec
[1]xdp测试例子
[2]xdpsock_user.c in linux
[3]AF_XDP技术详解
[4]借助libbpf/libxdp使用AF_XDP，我们都需要做什么
3933
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
