linux/samples/bpf/xdp_tx_iptunnel_user.c
Yafang Shao b25acdafd3 samples/bpf: Use libbpf 1.0 API mode instead of RLIMIT_MEMLOCK
We have switched to memcg-based memory accouting and thus the rlimit is
not needed any more. LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK was introduced in
libbpf for backward compatibility, so we can use it instead now.

This patch also removes the useless header sys/resource.h from many files
in samples/bpf.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20220409125958.92629-2-laoar.shao@gmail.com
2022-04-10 20:17:15 -07:00

311 lines
7.4 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2016 Facebook
*/
#include <linux/bpf.h>
#include <linux/if_link.h>
#include <assert.h>
#include <errno.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <net/if.h>
#include <arpa/inet.h>
#include <netinet/ether.h>
#include <unistd.h>
#include <time.h>
#include <bpf/libbpf.h>
#include <bpf/bpf.h>
#include "bpf_util.h"
#include "xdp_tx_iptunnel_common.h"
#define STATS_INTERVAL_S 2U
static int ifindex = -1;
static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
static int rxcnt_map_fd;
static __u32 prog_id;
static void int_exit(int sig)
{
__u32 curr_prog_id = 0;
if (ifindex > -1) {
if (bpf_xdp_query_id(ifindex, xdp_flags, &curr_prog_id)) {
printf("bpf_xdp_query_id failed\n");
exit(1);
}
if (prog_id == curr_prog_id)
bpf_xdp_detach(ifindex, xdp_flags, NULL);
else if (!curr_prog_id)
printf("couldn't find a prog id on a given iface\n");
else
printf("program on interface changed, not removing\n");
}
exit(0);
}
/* simple per-protocol drop counter
*/
static void poll_stats(unsigned int kill_after_s)
{
const unsigned int nr_protos = 256;
unsigned int nr_cpus = bpf_num_possible_cpus();
time_t started_at = time(NULL);
__u64 values[nr_cpus], prev[nr_protos][nr_cpus];
__u32 proto;
int i;
memset(prev, 0, sizeof(prev));
while (!kill_after_s || time(NULL) - started_at <= kill_after_s) {
sleep(STATS_INTERVAL_S);
for (proto = 0; proto < nr_protos; proto++) {
__u64 sum = 0;
assert(bpf_map_lookup_elem(rxcnt_map_fd, &proto,
values) == 0);
for (i = 0; i < nr_cpus; i++)
sum += (values[i] - prev[proto][i]);
if (sum)
printf("proto %u: sum:%10llu pkts, rate:%10llu pkts/s\n",
proto, sum, sum / STATS_INTERVAL_S);
memcpy(prev[proto], values, sizeof(values));
}
}
}
static void usage(const char *cmd)
{
printf("Start a XDP prog which encapsulates incoming packets\n"
"in an IPv4/v6 header and XDP_TX it out. The dst <VIP:PORT>\n"
"is used to select packets to encapsulate\n\n");
printf("Usage: %s [...]\n", cmd);
printf(" -i <ifname|ifindex> Interface\n");
printf(" -a <vip-service-address> IPv4 or IPv6\n");
printf(" -p <vip-service-port> A port range (e.g. 433-444) is also allowed\n");
printf(" -s <source-ip> Used in the IPTunnel header\n");
printf(" -d <dest-ip> Used in the IPTunnel header\n");
printf(" -m <dest-MAC> Used in sending the IP Tunneled pkt\n");
printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n");
printf(" -P <IP-Protocol> Default is TCP\n");
printf(" -S use skb-mode\n");
printf(" -N enforce native mode\n");
printf(" -F Force loading the XDP prog\n");
printf(" -h Display this help\n");
}
static int parse_ipstr(const char *ipstr, unsigned int *addr)
{
if (inet_pton(AF_INET6, ipstr, addr) == 1) {
return AF_INET6;
} else if (inet_pton(AF_INET, ipstr, addr) == 1) {
addr[1] = addr[2] = addr[3] = 0;
return AF_INET;
}
fprintf(stderr, "%s is an invalid IP\n", ipstr);
return AF_UNSPEC;
}
static int parse_ports(const char *port_str, int *min_port, int *max_port)
{
char *end;
long tmp_min_port;
long tmp_max_port;
tmp_min_port = strtol(optarg, &end, 10);
if (tmp_min_port < 1 || tmp_min_port > 65535) {
fprintf(stderr, "Invalid port(s):%s\n", optarg);
return 1;
}
if (*end == '-') {
end++;
tmp_max_port = strtol(end, NULL, 10);
if (tmp_max_port < 1 || tmp_max_port > 65535) {
fprintf(stderr, "Invalid port(s):%s\n", optarg);
return 1;
}
} else {
tmp_max_port = tmp_min_port;
}
if (tmp_min_port > tmp_max_port) {
fprintf(stderr, "Invalid port(s):%s\n", optarg);
return 1;
}
if (tmp_max_port - tmp_min_port + 1 > MAX_IPTNL_ENTRIES) {
fprintf(stderr, "Port range (%s) is larger than %u\n",
port_str, MAX_IPTNL_ENTRIES);
return 1;
}
*min_port = tmp_min_port;
*max_port = tmp_max_port;
return 0;
}
int main(int argc, char **argv)
{
int min_port = 0, max_port = 0, vip2tnl_map_fd;
const char *optstr = "i:a:p:s:d:m:T:P:FSNh";
unsigned char opt_flags[256] = {};
struct bpf_prog_info info = {};
__u32 info_len = sizeof(info);
unsigned int kill_after_s = 0;
struct iptnl_info tnl = {};
struct bpf_program *prog;
struct bpf_object *obj;
struct vip vip = {};
char filename[256];
int opt, prog_fd;
int i, err;
tnl.family = AF_UNSPEC;
vip.protocol = IPPROTO_TCP;
for (i = 0; i < strlen(optstr); i++)
if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z')
opt_flags[(unsigned char)optstr[i]] = 1;
while ((opt = getopt(argc, argv, optstr)) != -1) {
unsigned short family;
unsigned int *v6;
switch (opt) {
case 'i':
ifindex = if_nametoindex(optarg);
if (!ifindex)
ifindex = atoi(optarg);
break;
case 'a':
vip.family = parse_ipstr(optarg, vip.daddr.v6);
if (vip.family == AF_UNSPEC)
return 1;
break;
case 'p':
if (parse_ports(optarg, &min_port, &max_port))
return 1;
break;
case 'P':
vip.protocol = atoi(optarg);
break;
case 's':
case 'd':
if (opt == 's')
v6 = tnl.saddr.v6;
else
v6 = tnl.daddr.v6;
family = parse_ipstr(optarg, v6);
if (family == AF_UNSPEC)
return 1;
if (tnl.family == AF_UNSPEC) {
tnl.family = family;
} else if (tnl.family != family) {
fprintf(stderr,
"The IP version of the src and dst addresses used in the IP encapsulation does not match\n");
return 1;
}
break;
case 'm':
if (!ether_aton_r(optarg,
(struct ether_addr *)tnl.dmac)) {
fprintf(stderr, "Invalid mac address:%s\n",
optarg);
return 1;
}
break;
case 'T':
kill_after_s = atoi(optarg);
break;
case 'S':
xdp_flags |= XDP_FLAGS_SKB_MODE;
break;
case 'N':
/* default, set below */
break;
case 'F':
xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST;
break;
default:
usage(argv[0]);
return 1;
}
opt_flags[opt] = 0;
}
if (!(xdp_flags & XDP_FLAGS_SKB_MODE))
xdp_flags |= XDP_FLAGS_DRV_MODE;
for (i = 0; i < strlen(optstr); i++) {
if (opt_flags[(unsigned int)optstr[i]]) {
fprintf(stderr, "Missing argument -%c\n", optstr[i]);
usage(argv[0]);
return 1;
}
}
if (!ifindex) {
fprintf(stderr, "Invalid ifname\n");
return 1;
}
snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
obj = bpf_object__open_file(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);
err = bpf_object__load(obj);
if (err) {
printf("bpf_object__load(): %s\n", strerror(errno));
return 1;
}
prog_fd = bpf_program__fd(prog);
rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt");
vip2tnl_map_fd = bpf_object__find_map_fd_by_name(obj, "vip2tnl");
if (vip2tnl_map_fd < 0 || rxcnt_map_fd < 0) {
printf("bpf_object__find_map_fd_by_name failed\n");
return 1;
}
signal(SIGINT, int_exit);
signal(SIGTERM, int_exit);
while (min_port <= max_port) {
vip.dport = htons(min_port++);
if (bpf_map_update_elem(vip2tnl_map_fd, &vip, &tnl,
BPF_NOEXIST)) {
perror("bpf_map_update_elem(&vip2tnl)");
return 1;
}
}
if (bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL) < 0) {
printf("link set xdp fd failed\n");
return 1;
}
err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
if (err) {
printf("can't get prog info - %s\n", strerror(errno));
return err;
}
prog_id = info.id;
poll_stats(kill_after_s);
bpf_xdp_detach(ifindex, xdp_flags, NULL);
return 0;
}