Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 | // 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_prog_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; } |