1// SPDX-License-Identifier: GPL-2.0-only 2/* 3 * Copyright 2013 Google Inc. 4 * Author: Willem de Bruijn (willemb@google.com) 5 * 6 * A basic test of packet socket fanout behavior. 7 * 8 * Control: 9 * - create fanout fails as expected with illegal flag combinations 10 * - join fanout fails as expected with diverging types or flags 11 * 12 * Datapath: 13 * Open a pair of packet sockets and a pair of INET sockets, send a known 14 * number of packets across the two INET sockets and count the number of 15 * packets enqueued onto the two packet sockets. 16 * 17 * The test currently runs for 18 * - PACKET_FANOUT_HASH 19 * - PACKET_FANOUT_HASH with PACKET_FANOUT_FLAG_ROLLOVER 20 * - PACKET_FANOUT_LB 21 * - PACKET_FANOUT_CPU 22 * - PACKET_FANOUT_ROLLOVER 23 * - PACKET_FANOUT_CBPF 24 * - PACKET_FANOUT_EBPF 25 * 26 * Todo: 27 * - functionality: PACKET_FANOUT_FLAG_DEFRAG 28 */ 29 30#define _GNU_SOURCE /* for sched_setaffinity */ 31 32#include <arpa/inet.h> 33#include <errno.h> 34#include <fcntl.h> 35#include <linux/unistd.h> /* for __NR_bpf */ 36#include <linux/filter.h> 37#include <linux/bpf.h> 38#include <linux/if_packet.h> 39#include <net/if.h> 40#include <net/ethernet.h> 41#include <netinet/ip.h> 42#include <netinet/udp.h> 43#include <poll.h> 44#include <sched.h> 45#include <stdint.h> 46#include <stdio.h> 47#include <stdlib.h> 48#include <string.h> 49#include <sys/mman.h> 50#include <sys/socket.h> 51#include <sys/stat.h> 52#include <sys/types.h> 53#include <unistd.h> 54 55#include "psock_lib.h" 56 57#define RING_NUM_FRAMES 20 58 59/* Open a socket in a given fanout mode. 60 * @return -1 if mode is bad, a valid socket otherwise */ 61static int sock_fanout_open(uint16_t typeflags, uint16_t group_id) 62{ 63 struct sockaddr_ll addr = {0}; 64 int fd, val; 65 66 fd = socket(PF_PACKET, SOCK_RAW, 0); 67 if (fd < 0) { 68 perror("socket packet"); 69 exit(1); 70 } 71 72 pair_udp_setfilter(fd); 73 74 addr.sll_family = AF_PACKET; 75 addr.sll_protocol = htons(ETH_P_IP); 76 addr.sll_ifindex = if_nametoindex("lo"); 77 if (addr.sll_ifindex == 0) { 78 perror("if_nametoindex"); 79 exit(1); 80 } 81 if (bind(fd, (void *) &addr, sizeof(addr))) { 82 perror("bind packet"); 83 exit(1); 84 } 85 86 val = (((int) typeflags) << 16) | group_id; 87 if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val))) { 88 if (close(fd)) { 89 perror("close packet"); 90 exit(1); 91 } 92 return -1; 93 } 94 95 return fd; 96} 97 98static void sock_fanout_set_cbpf(int fd) 99{ 100 struct sock_filter bpf_filter[] = { 101 BPF_STMT(BPF_LD+BPF_B+BPF_ABS, 80), /* ldb [80] */ 102 BPF_STMT(BPF_RET+BPF_A, 0), /* ret A */ 103 }; 104 struct sock_fprog bpf_prog; 105 106 bpf_prog.filter = bpf_filter; 107 bpf_prog.len = sizeof(bpf_filter) / sizeof(struct sock_filter); 108 109 if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &bpf_prog, 110 sizeof(bpf_prog))) { 111 perror("fanout data cbpf"); 112 exit(1); 113 } 114} 115 116static void sock_fanout_getopts(int fd, uint16_t *typeflags, uint16_t *group_id) 117{ 118 int sockopt; 119 socklen_t sockopt_len = sizeof(sockopt); 120 121 if (getsockopt(fd, SOL_PACKET, PACKET_FANOUT, 122 &sockopt, &sockopt_len)) { 123 perror("failed to getsockopt"); 124 exit(1); 125 } 126 *typeflags = sockopt >> 16; 127 *group_id = sockopt & 0xfffff; 128} 129 130static void sock_fanout_set_ebpf(int fd) 131{ 132 static char log_buf[65536]; 133 134 const int len_off = __builtin_offsetof(struct __sk_buff, len); 135 struct bpf_insn prog[] = { 136 { BPF_ALU64 | BPF_MOV | BPF_X, 6, 1, 0, 0 }, 137 { BPF_LDX | BPF_W | BPF_MEM, 0, 6, len_off, 0 }, 138 { BPF_JMP | BPF_JGE | BPF_K, 0, 0, 1, DATA_LEN }, 139 { BPF_JMP | BPF_JA | BPF_K, 0, 0, 4, 0 }, 140 { BPF_LD | BPF_B | BPF_ABS, 0, 0, 0, 0x50 }, 141 { BPF_JMP | BPF_JEQ | BPF_K, 0, 0, 2, DATA_CHAR }, 142 { BPF_JMP | BPF_JEQ | BPF_K, 0, 0, 1, DATA_CHAR_1 }, 143 { BPF_ALU | BPF_MOV | BPF_K, 0, 0, 0, 0 }, 144 { BPF_JMP | BPF_EXIT, 0, 0, 0, 0 } 145 }; 146 union bpf_attr attr; 147 int pfd; 148 149 memset(&attr, 0, sizeof(attr)); 150 attr.prog_type = BPF_PROG_TYPE_SOCKET_FILTER; 151 attr.insns = (unsigned long) prog; 152 attr.insn_cnt = sizeof(prog) / sizeof(prog[0]); 153 attr.license = (unsigned long) "GPL"; 154 attr.log_buf = (unsigned long) log_buf, 155 attr.log_size = sizeof(log_buf), 156 attr.log_level = 1, 157 158 pfd = syscall(__NR_bpf, BPF_PROG_LOAD, &attr, sizeof(attr)); 159 if (pfd < 0) { 160 perror("bpf"); 161 fprintf(stderr, "bpf verifier:\n%s\n", log_buf); 162 exit(1); 163 } 164 165 if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT_DATA, &pfd, sizeof(pfd))) { 166 perror("fanout data ebpf"); 167 exit(1); 168 } 169 170 if (close(pfd)) { 171 perror("close ebpf"); 172 exit(1); 173 } 174} 175 176static char *sock_fanout_open_ring(int fd) 177{ 178 struct tpacket_req req = { 179 .tp_block_size = getpagesize(), 180 .tp_frame_size = getpagesize(), 181 .tp_block_nr = RING_NUM_FRAMES, 182 .tp_frame_nr = RING_NUM_FRAMES, 183 }; 184 char *ring; 185 int val = TPACKET_V2; 186 187 if (setsockopt(fd, SOL_PACKET, PACKET_VERSION, (void *) &val, 188 sizeof(val))) { 189 perror("packetsock ring setsockopt version"); 190 exit(1); 191 } 192 if (setsockopt(fd, SOL_PACKET, PACKET_RX_RING, (void *) &req, 193 sizeof(req))) { 194 perror("packetsock ring setsockopt"); 195 exit(1); 196 } 197 198 ring = mmap(0, req.tp_block_size * req.tp_block_nr, 199 PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); 200 if (ring == MAP_FAILED) { 201 perror("packetsock ring mmap"); 202 exit(1); 203 } 204 205 return ring; 206} 207 208static int sock_fanout_read_ring(int fd, void *ring) 209{ 210 struct tpacket2_hdr *header = ring; 211 int count = 0; 212 213 while (count < RING_NUM_FRAMES && header->tp_status & TP_STATUS_USER) { 214 count++; 215 header = ring + (count * getpagesize()); 216 } 217 218 return count; 219} 220 221static int sock_fanout_read(int fds[], char *rings[], const int expect[]) 222{ 223 int ret[2]; 224 225 ret[0] = sock_fanout_read_ring(fds[0], rings[0]); 226 ret[1] = sock_fanout_read_ring(fds[1], rings[1]); 227 228 fprintf(stderr, "info: count=%d,%d, expect=%d,%d\n", 229 ret[0], ret[1], expect[0], expect[1]); 230 231 if ((!(ret[0] == expect[0] && ret[1] == expect[1])) && 232 (!(ret[0] == expect[1] && ret[1] == expect[0]))) { 233 fprintf(stderr, "warning: incorrect queue lengths\n"); 234 return 1; 235 } 236 237 return 0; 238} 239 240/* Test illegal mode + flag combination */ 241static void test_control_single(void) 242{ 243 fprintf(stderr, "test: control single socket\n"); 244 245 if (sock_fanout_open(PACKET_FANOUT_ROLLOVER | 246 PACKET_FANOUT_FLAG_ROLLOVER, 0) != -1) { 247 fprintf(stderr, "ERROR: opened socket with dual rollover\n"); 248 exit(1); 249 } 250} 251 252/* Test illegal group with different modes or flags */ 253static void test_control_group(void) 254{ 255 int fds[2]; 256 257 fprintf(stderr, "test: control multiple sockets\n"); 258 259 fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 0); 260 if (fds[0] == -1) { 261 fprintf(stderr, "ERROR: failed to open HASH socket\n"); 262 exit(1); 263 } 264 if (sock_fanout_open(PACKET_FANOUT_HASH | 265 PACKET_FANOUT_FLAG_DEFRAG, 0) != -1) { 266 fprintf(stderr, "ERROR: joined group with wrong flag defrag\n"); 267 exit(1); 268 } 269 if (sock_fanout_open(PACKET_FANOUT_HASH | 270 PACKET_FANOUT_FLAG_ROLLOVER, 0) != -1) { 271 fprintf(stderr, "ERROR: joined group with wrong flag ro\n"); 272 exit(1); 273 } 274 if (sock_fanout_open(PACKET_FANOUT_CPU, 0) != -1) { 275 fprintf(stderr, "ERROR: joined group with wrong mode\n"); 276 exit(1); 277 } 278 fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, 0); 279 if (fds[1] == -1) { 280 fprintf(stderr, "ERROR: failed to join group\n"); 281 exit(1); 282 } 283 if (close(fds[1]) || close(fds[0])) { 284 fprintf(stderr, "ERROR: closing sockets\n"); 285 exit(1); 286 } 287} 288 289/* Test creating a unique fanout group ids */ 290static void test_unique_fanout_group_ids(void) 291{ 292 int fds[3]; 293 uint16_t typeflags, first_group_id, second_group_id; 294 295 fprintf(stderr, "test: unique ids\n"); 296 297 fds[0] = sock_fanout_open(PACKET_FANOUT_HASH | 298 PACKET_FANOUT_FLAG_UNIQUEID, 0); 299 if (fds[0] == -1) { 300 fprintf(stderr, "ERROR: failed to create a unique id group.\n"); 301 exit(1); 302 } 303 304 sock_fanout_getopts(fds[0], &typeflags, &first_group_id); 305 if (typeflags != PACKET_FANOUT_HASH) { 306 fprintf(stderr, "ERROR: unexpected typeflags %x\n", typeflags); 307 exit(1); 308 } 309 310 if (sock_fanout_open(PACKET_FANOUT_CPU, first_group_id) != -1) { 311 fprintf(stderr, "ERROR: joined group with wrong type.\n"); 312 exit(1); 313 } 314 315 fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, first_group_id); 316 if (fds[1] == -1) { 317 fprintf(stderr, 318 "ERROR: failed to join previously created group.\n"); 319 exit(1); 320 } 321 322 fds[2] = sock_fanout_open(PACKET_FANOUT_HASH | 323 PACKET_FANOUT_FLAG_UNIQUEID, 0); 324 if (fds[2] == -1) { 325 fprintf(stderr, 326 "ERROR: failed to create a second unique id group.\n"); 327 exit(1); 328 } 329 330 sock_fanout_getopts(fds[2], &typeflags, &second_group_id); 331 if (sock_fanout_open(PACKET_FANOUT_HASH | PACKET_FANOUT_FLAG_UNIQUEID, 332 second_group_id) != -1) { 333 fprintf(stderr, 334 "ERROR: specified a group id when requesting unique id\n"); 335 exit(1); 336 } 337 338 if (close(fds[0]) || close(fds[1]) || close(fds[2])) { 339 fprintf(stderr, "ERROR: closing sockets\n"); 340 exit(1); 341 } 342} 343 344static int test_datapath(uint16_t typeflags, int port_off, 345 const int expect1[], const int expect2[]) 346{ 347 const int expect0[] = { 0, 0 }; 348 char *rings[2]; 349 uint8_t type = typeflags & 0xFF; 350 int fds[2], fds_udp[2][2], ret; 351 352 fprintf(stderr, "\ntest: datapath 0x%hx ports %hu,%hu\n", 353 typeflags, (uint16_t)PORT_BASE, 354 (uint16_t)(PORT_BASE + port_off)); 355 356 fds[0] = sock_fanout_open(typeflags, 0); 357 fds[1] = sock_fanout_open(typeflags, 0); 358 if (fds[0] == -1 || fds[1] == -1) { 359 fprintf(stderr, "ERROR: failed open\n"); 360 exit(1); 361 } 362 if (type == PACKET_FANOUT_CBPF) 363 sock_fanout_set_cbpf(fds[0]); 364 else if (type == PACKET_FANOUT_EBPF) 365 sock_fanout_set_ebpf(fds[0]); 366 367 rings[0] = sock_fanout_open_ring(fds[0]); 368 rings[1] = sock_fanout_open_ring(fds[1]); 369 pair_udp_open(fds_udp[0], PORT_BASE); 370 pair_udp_open(fds_udp[1], PORT_BASE + port_off); 371 sock_fanout_read(fds, rings, expect0); 372 373 /* Send data, but not enough to overflow a queue */ 374 pair_udp_send(fds_udp[0], 15); 375 pair_udp_send_char(fds_udp[1], 5, DATA_CHAR_1); 376 ret = sock_fanout_read(fds, rings, expect1); 377 378 /* Send more data, overflow the queue */ 379 pair_udp_send_char(fds_udp[0], 15, DATA_CHAR_1); 380 /* TODO: ensure consistent order between expect1 and expect2 */ 381 ret |= sock_fanout_read(fds, rings, expect2); 382 383 if (munmap(rings[1], RING_NUM_FRAMES * getpagesize()) || 384 munmap(rings[0], RING_NUM_FRAMES * getpagesize())) { 385 fprintf(stderr, "close rings\n"); 386 exit(1); 387 } 388 if (close(fds_udp[1][1]) || close(fds_udp[1][0]) || 389 close(fds_udp[0][1]) || close(fds_udp[0][0]) || 390 close(fds[1]) || close(fds[0])) { 391 fprintf(stderr, "close datapath\n"); 392 exit(1); 393 } 394 395 return ret; 396} 397 398static int set_cpuaffinity(int cpuid) 399{ 400 cpu_set_t mask; 401 402 CPU_ZERO(&mask); 403 CPU_SET(cpuid, &mask); 404 if (sched_setaffinity(0, sizeof(mask), &mask)) { 405 if (errno != EINVAL) { 406 fprintf(stderr, "setaffinity %d\n", cpuid); 407 exit(1); 408 } 409 return 1; 410 } 411 412 return 0; 413} 414 415int main(int argc, char **argv) 416{ 417 const int expect_hash[2][2] = { { 15, 5 }, { 20, 5 } }; 418 const int expect_hash_rb[2][2] = { { 15, 5 }, { 20, 15 } }; 419 const int expect_lb[2][2] = { { 10, 10 }, { 18, 17 } }; 420 const int expect_rb[2][2] = { { 15, 5 }, { 20, 15 } }; 421 const int expect_cpu0[2][2] = { { 20, 0 }, { 20, 0 } }; 422 const int expect_cpu1[2][2] = { { 0, 20 }, { 0, 20 } }; 423 const int expect_bpf[2][2] = { { 15, 5 }, { 15, 20 } }; 424 const int expect_uniqueid[2][2] = { { 20, 20}, { 20, 20 } }; 425 int port_off = 2, tries = 20, ret; 426 427 test_control_single(); 428 test_control_group(); 429 test_unique_fanout_group_ids(); 430 431 /* find a set of ports that do not collide onto the same socket */ 432 ret = test_datapath(PACKET_FANOUT_HASH, port_off, 433 expect_hash[0], expect_hash[1]); 434 while (ret) { 435 fprintf(stderr, "info: trying alternate ports (%d)\n", tries); 436 ret = test_datapath(PACKET_FANOUT_HASH, ++port_off, 437 expect_hash[0], expect_hash[1]); 438 if (!--tries) { 439 fprintf(stderr, "too many collisions\n"); 440 return 1; 441 } 442 } 443 444 ret |= test_datapath(PACKET_FANOUT_HASH | PACKET_FANOUT_FLAG_ROLLOVER, 445 port_off, expect_hash_rb[0], expect_hash_rb[1]); 446 ret |= test_datapath(PACKET_FANOUT_LB, 447 port_off, expect_lb[0], expect_lb[1]); 448 ret |= test_datapath(PACKET_FANOUT_ROLLOVER, 449 port_off, expect_rb[0], expect_rb[1]); 450 451 ret |= test_datapath(PACKET_FANOUT_CBPF, 452 port_off, expect_bpf[0], expect_bpf[1]); 453 ret |= test_datapath(PACKET_FANOUT_EBPF, 454 port_off, expect_bpf[0], expect_bpf[1]); 455 456 set_cpuaffinity(0); 457 ret |= test_datapath(PACKET_FANOUT_CPU, port_off, 458 expect_cpu0[0], expect_cpu0[1]); 459 if (!set_cpuaffinity(1)) 460 /* TODO: test that choice alternates with previous */ 461 ret |= test_datapath(PACKET_FANOUT_CPU, port_off, 462 expect_cpu1[0], expect_cpu1[1]); 463 464 ret |= test_datapath(PACKET_FANOUT_FLAG_UNIQUEID, port_off, 465 expect_uniqueid[0], expect_uniqueid[1]); 466 467 if (ret) 468 return 1; 469 470 printf("OK. All tests passed\n"); 471 return 0; 472} 473