1// SPDX-License-Identifier: GPL-2.0-or-later 2/* 3 * INET An implementation of the TCP/IP protocol suite for the LINUX 4 * operating system. INET is implemented using the BSD Socket 5 * interface as the means of communication with the user level. 6 * 7 * "Ping" sockets 8 * 9 * Based on ipv4/udp.c code. 10 * 11 * Authors: Vasiliy Kulikov / Openwall (for Linux 2.6), 12 * Pavel Kankovsky (for Linux 2.4.32) 13 * 14 * Pavel gave all rights to bugs to Vasiliy, 15 * none of the bugs are Pavel's now. 16 */ 17 18#include <linux/uaccess.h> 19#include <linux/types.h> 20#include <linux/fcntl.h> 21#include <linux/socket.h> 22#include <linux/sockios.h> 23#include <linux/in.h> 24#include <linux/errno.h> 25#include <linux/timer.h> 26#include <linux/mm.h> 27#include <linux/inet.h> 28#include <linux/netdevice.h> 29#include <net/snmp.h> 30#include <net/ip.h> 31#include <net/icmp.h> 32#include <net/protocol.h> 33#include <linux/skbuff.h> 34#include <linux/proc_fs.h> 35#include <linux/export.h> 36#include <net/sock.h> 37#include <net/ping.h> 38#include <net/udp.h> 39#include <net/route.h> 40#include <net/inet_common.h> 41#include <net/checksum.h> 42 43#if IS_ENABLED(CONFIG_IPV6) 44#include <linux/in6.h> 45#include <linux/icmpv6.h> 46#include <net/addrconf.h> 47#include <net/ipv6.h> 48#include <net/transp_v6.h> 49#endif 50 51struct ping_table { 52 struct hlist_nulls_head hash[PING_HTABLE_SIZE]; 53 rwlock_t lock; 54}; 55 56static struct ping_table ping_table; 57struct pingv6_ops pingv6_ops; 58EXPORT_SYMBOL_GPL(pingv6_ops); 59 60static u16 ping_port_rover; 61 62static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask) 63{ 64 u32 res = (num + net_hash_mix(net)) & mask; 65 66 pr_debug("hash(%u) = %u\n", num, res); 67 return res; 68} 69EXPORT_SYMBOL_GPL(ping_hash); 70 71static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table, 72 struct net *net, unsigned int num) 73{ 74 return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)]; 75} 76 77int ping_get_port(struct sock *sk, unsigned short ident) 78{ 79 struct hlist_nulls_node *node; 80 struct hlist_nulls_head *hlist; 81 struct inet_sock *isk, *isk2; 82 struct sock *sk2 = NULL; 83 84 isk = inet_sk(sk); 85 write_lock_bh(&ping_table.lock); 86 if (ident == 0) { 87 u32 i; 88 u16 result = ping_port_rover + 1; 89 90 for (i = 0; i < (1L << 16); i++, result++) { 91 if (!result) 92 result++; /* avoid zero */ 93 hlist = ping_hashslot(&ping_table, sock_net(sk), 94 result); 95 ping_portaddr_for_each_entry(sk2, node, hlist) { 96 isk2 = inet_sk(sk2); 97 98 if (isk2->inet_num == result) 99 goto next_port; 100 } 101 102 /* found */ 103 ping_port_rover = ident = result; 104 break; 105next_port: 106 ; 107 } 108 if (i >= (1L << 16)) 109 goto fail; 110 } else { 111 hlist = ping_hashslot(&ping_table, sock_net(sk), ident); 112 ping_portaddr_for_each_entry(sk2, node, hlist) { 113 isk2 = inet_sk(sk2); 114 115 /* BUG? Why is this reuse and not reuseaddr? ping.c 116 * doesn't turn off SO_REUSEADDR, and it doesn't expect 117 * that other ping processes can steal its packets. 118 */ 119 if ((isk2->inet_num == ident) && 120 (sk2 != sk) && 121 (!sk2->sk_reuse || !sk->sk_reuse)) 122 goto fail; 123 } 124 } 125 126 pr_debug("found port/ident = %d\n", ident); 127 isk->inet_num = ident; 128 if (sk_unhashed(sk)) { 129 pr_debug("was not hashed\n"); 130 sock_hold(sk); 131 hlist_nulls_add_head(&sk->sk_nulls_node, hlist); 132 sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); 133 } 134 write_unlock_bh(&ping_table.lock); 135 return 0; 136 137fail: 138 write_unlock_bh(&ping_table.lock); 139 return 1; 140} 141EXPORT_SYMBOL_GPL(ping_get_port); 142 143int ping_hash(struct sock *sk) 144{ 145 pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num); 146 BUG(); /* "Please do not press this button again." */ 147 148 return 0; 149} 150 151void ping_unhash(struct sock *sk) 152{ 153 struct inet_sock *isk = inet_sk(sk); 154 155 pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num); 156 write_lock_bh(&ping_table.lock); 157 if (sk_hashed(sk)) { 158 hlist_nulls_del(&sk->sk_nulls_node); 159 sk_nulls_node_init(&sk->sk_nulls_node); 160 sock_put(sk); 161 isk->inet_num = 0; 162 isk->inet_sport = 0; 163 sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); 164 } 165 write_unlock_bh(&ping_table.lock); 166} 167EXPORT_SYMBOL_GPL(ping_unhash); 168 169static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident) 170{ 171 struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident); 172 struct sock *sk = NULL; 173 struct inet_sock *isk; 174 struct hlist_nulls_node *hnode; 175 int dif, sdif; 176 177 if (skb->protocol == htons(ETH_P_IP)) { 178 dif = inet_iif(skb); 179 sdif = inet_sdif(skb); 180 pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n", 181 (int)ident, &ip_hdr(skb)->daddr, dif); 182#if IS_ENABLED(CONFIG_IPV6) 183 } else if (skb->protocol == htons(ETH_P_IPV6)) { 184 dif = inet6_iif(skb); 185 sdif = inet6_sdif(skb); 186 pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n", 187 (int)ident, &ipv6_hdr(skb)->daddr, dif); 188#endif 189 } else { 190 return NULL; 191 } 192 193 read_lock_bh(&ping_table.lock); 194 195 ping_portaddr_for_each_entry(sk, hnode, hslot) { 196 isk = inet_sk(sk); 197 198 pr_debug("iterate\n"); 199 if (isk->inet_num != ident) 200 continue; 201 202 if (skb->protocol == htons(ETH_P_IP) && 203 sk->sk_family == AF_INET) { 204 pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk, 205 (int) isk->inet_num, &isk->inet_rcv_saddr, 206 sk->sk_bound_dev_if); 207 208 if (isk->inet_rcv_saddr && 209 isk->inet_rcv_saddr != ip_hdr(skb)->daddr) 210 continue; 211#if IS_ENABLED(CONFIG_IPV6) 212 } else if (skb->protocol == htons(ETH_P_IPV6) && 213 sk->sk_family == AF_INET6) { 214 215 pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk, 216 (int) isk->inet_num, 217 &sk->sk_v6_rcv_saddr, 218 sk->sk_bound_dev_if); 219 220 if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && 221 !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, 222 &ipv6_hdr(skb)->daddr)) 223 continue; 224#endif 225 } else { 226 continue; 227 } 228 229 if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif && 230 sk->sk_bound_dev_if != sdif) 231 continue; 232 233 sock_hold(sk); 234 goto exit; 235 } 236 237 sk = NULL; 238exit: 239 read_unlock_bh(&ping_table.lock); 240 241 return sk; 242} 243 244static void inet_get_ping_group_range_net(struct net *net, kgid_t *low, 245 kgid_t *high) 246{ 247 kgid_t *data = net->ipv4.ping_group_range.range; 248 unsigned int seq; 249 250 do { 251 seq = read_seqbegin(&net->ipv4.ping_group_range.lock); 252 253 *low = data[0]; 254 *high = data[1]; 255 } while (read_seqretry(&net->ipv4.ping_group_range.lock, seq)); 256} 257 258 259int ping_init_sock(struct sock *sk) 260{ 261 struct net *net = sock_net(sk); 262 kgid_t group = current_egid(); 263 struct group_info *group_info; 264 int i; 265 kgid_t low, high; 266 int ret = 0; 267 268 if (sk->sk_family == AF_INET6) 269 sk->sk_ipv6only = 1; 270 271 inet_get_ping_group_range_net(net, &low, &high); 272 if (gid_lte(low, group) && gid_lte(group, high)) 273 return 0; 274 275 group_info = get_current_groups(); 276 for (i = 0; i < group_info->ngroups; i++) { 277 kgid_t gid = group_info->gid[i]; 278 279 if (gid_lte(low, gid) && gid_lte(gid, high)) 280 goto out_release_group; 281 } 282 283 ret = -EACCES; 284 285out_release_group: 286 put_group_info(group_info); 287 return ret; 288} 289EXPORT_SYMBOL_GPL(ping_init_sock); 290 291void ping_close(struct sock *sk, long timeout) 292{ 293 pr_debug("ping_close(sk=%p,sk->num=%u)\n", 294 inet_sk(sk), inet_sk(sk)->inet_num); 295 pr_debug("isk->refcnt = %d\n", refcount_read(&sk->sk_refcnt)); 296 297 sk_common_release(sk); 298} 299EXPORT_SYMBOL_GPL(ping_close); 300 301/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ 302static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, 303 struct sockaddr *uaddr, int addr_len) 304{ 305 struct net *net = sock_net(sk); 306 if (sk->sk_family == AF_INET) { 307 struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; 308 u32 tb_id = RT_TABLE_LOCAL; 309 int chk_addr_ret; 310 311 if (addr_len < sizeof(*addr)) 312 return -EINVAL; 313 314 if (addr->sin_family != AF_INET && 315 !(addr->sin_family == AF_UNSPEC && 316 addr->sin_addr.s_addr == htonl(INADDR_ANY))) 317 return -EAFNOSUPPORT; 318 319 pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", 320 sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); 321 322 if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) 323 chk_addr_ret = RTN_LOCAL; 324 else { 325 tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; 326 chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); 327 } 328 329 if ((!inet_can_nonlocal_bind(net, isk) && 330 chk_addr_ret != RTN_LOCAL) || 331 chk_addr_ret == RTN_MULTICAST || 332 chk_addr_ret == RTN_BROADCAST) 333 return -EADDRNOTAVAIL; 334 335#if IS_ENABLED(CONFIG_IPV6) 336 } else if (sk->sk_family == AF_INET6) { 337 struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; 338 int addr_type, scoped, has_addr; 339 struct net_device *dev = NULL; 340 341 if (addr_len < sizeof(*addr)) 342 return -EINVAL; 343 344 if (addr->sin6_family != AF_INET6) 345 return -EAFNOSUPPORT; 346 347 pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n", 348 sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port)); 349 350 addr_type = ipv6_addr_type(&addr->sin6_addr); 351 scoped = __ipv6_addr_needs_scope_id(addr_type); 352 if ((addr_type != IPV6_ADDR_ANY && 353 !(addr_type & IPV6_ADDR_UNICAST)) || 354 (scoped && !addr->sin6_scope_id)) 355 return -EINVAL; 356 357 rcu_read_lock(); 358 if (addr->sin6_scope_id) { 359 dev = dev_get_by_index_rcu(net, addr->sin6_scope_id); 360 if (!dev) { 361 rcu_read_unlock(); 362 return -ENODEV; 363 } 364 } 365 366 if (!dev && sk->sk_bound_dev_if) { 367 dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); 368 if (!dev) { 369 rcu_read_unlock(); 370 return -ENODEV; 371 } 372 } 373 has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev, 374 scoped); 375 rcu_read_unlock(); 376 377 if (!(ipv6_can_nonlocal_bind(net, isk) || has_addr || 378 addr_type == IPV6_ADDR_ANY)) 379 return -EADDRNOTAVAIL; 380 381 if (scoped) 382 sk->sk_bound_dev_if = addr->sin6_scope_id; 383#endif 384 } else { 385 return -EAFNOSUPPORT; 386 } 387 return 0; 388} 389 390static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) 391{ 392 if (saddr->sa_family == AF_INET) { 393 struct inet_sock *isk = inet_sk(sk); 394 struct sockaddr_in *addr = (struct sockaddr_in *) saddr; 395 isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr; 396#if IS_ENABLED(CONFIG_IPV6) 397 } else if (saddr->sa_family == AF_INET6) { 398 struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr; 399 struct ipv6_pinfo *np = inet6_sk(sk); 400 sk->sk_v6_rcv_saddr = np->saddr = addr->sin6_addr; 401#endif 402 } 403} 404 405/* 406 * We need our own bind because there are no privileged id's == local ports. 407 * Moreover, we don't allow binding to multi- and broadcast addresses. 408 */ 409 410int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) 411{ 412 struct inet_sock *isk = inet_sk(sk); 413 unsigned short snum; 414 int err; 415 int dif = sk->sk_bound_dev_if; 416 417 err = ping_check_bind_addr(sk, isk, uaddr, addr_len); 418 if (err) 419 return err; 420 421 lock_sock(sk); 422 423 err = -EINVAL; 424 if (isk->inet_num != 0) 425 goto out; 426 427 err = -EADDRINUSE; 428 snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port); 429 if (ping_get_port(sk, snum) != 0) { 430 /* Restore possibly modified sk->sk_bound_dev_if by ping_check_bind_addr(). */ 431 sk->sk_bound_dev_if = dif; 432 goto out; 433 } 434 ping_set_saddr(sk, uaddr); 435 436 pr_debug("after bind(): num = %hu, dif = %d\n", 437 isk->inet_num, 438 sk->sk_bound_dev_if); 439 440 err = 0; 441 if (sk->sk_family == AF_INET && isk->inet_rcv_saddr) 442 sk->sk_userlocks |= SOCK_BINDADDR_LOCK; 443#if IS_ENABLED(CONFIG_IPV6) 444 if (sk->sk_family == AF_INET6 && !ipv6_addr_any(&sk->sk_v6_rcv_saddr)) 445 sk->sk_userlocks |= SOCK_BINDADDR_LOCK; 446#endif 447 448 if (snum) 449 sk->sk_userlocks |= SOCK_BINDPORT_LOCK; 450 isk->inet_sport = htons(isk->inet_num); 451 isk->inet_daddr = 0; 452 isk->inet_dport = 0; 453 454#if IS_ENABLED(CONFIG_IPV6) 455 if (sk->sk_family == AF_INET6) 456 memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr)); 457#endif 458 459 sk_dst_reset(sk); 460out: 461 release_sock(sk); 462 pr_debug("ping_v4_bind -> %d\n", err); 463 return err; 464} 465EXPORT_SYMBOL_GPL(ping_bind); 466 467/* 468 * Is this a supported type of ICMP message? 469 */ 470 471static inline int ping_supported(int family, int type, int code) 472{ 473 return (family == AF_INET && type == ICMP_ECHO && code == 0) || 474 (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0); 475} 476 477/* 478 * This routine is called by the ICMP module when it gets some 479 * sort of error condition. 480 */ 481 482void ping_err(struct sk_buff *skb, int offset, u32 info) 483{ 484 int family; 485 struct icmphdr *icmph; 486 struct inet_sock *inet_sock; 487 int type; 488 int code; 489 struct net *net = dev_net(skb->dev); 490 struct sock *sk; 491 int harderr; 492 int err; 493 494 if (skb->protocol == htons(ETH_P_IP)) { 495 family = AF_INET; 496 type = icmp_hdr(skb)->type; 497 code = icmp_hdr(skb)->code; 498 icmph = (struct icmphdr *)(skb->data + offset); 499 } else if (skb->protocol == htons(ETH_P_IPV6)) { 500 family = AF_INET6; 501 type = icmp6_hdr(skb)->icmp6_type; 502 code = icmp6_hdr(skb)->icmp6_code; 503 icmph = (struct icmphdr *) (skb->data + offset); 504 } else { 505 BUG(); 506 } 507 508 /* We assume the packet has already been checked by icmp_unreach */ 509 510 if (!ping_supported(family, icmph->type, icmph->code)) 511 return; 512 513 pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n", 514 skb->protocol, type, code, ntohs(icmph->un.echo.id), 515 ntohs(icmph->un.echo.sequence)); 516 517 sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); 518 if (!sk) { 519 pr_debug("no socket, dropping\n"); 520 return; /* No socket for error */ 521 } 522 pr_debug("err on socket %p\n", sk); 523 524 err = 0; 525 harderr = 0; 526 inet_sock = inet_sk(sk); 527 528 if (skb->protocol == htons(ETH_P_IP)) { 529 switch (type) { 530 default: 531 case ICMP_TIME_EXCEEDED: 532 err = EHOSTUNREACH; 533 break; 534 case ICMP_SOURCE_QUENCH: 535 /* This is not a real error but ping wants to see it. 536 * Report it with some fake errno. 537 */ 538 err = EREMOTEIO; 539 break; 540 case ICMP_PARAMETERPROB: 541 err = EPROTO; 542 harderr = 1; 543 break; 544 case ICMP_DEST_UNREACH: 545 if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ 546 ipv4_sk_update_pmtu(skb, sk, info); 547 if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) { 548 err = EMSGSIZE; 549 harderr = 1; 550 break; 551 } 552 goto out; 553 } 554 err = EHOSTUNREACH; 555 if (code <= NR_ICMP_UNREACH) { 556 harderr = icmp_err_convert[code].fatal; 557 err = icmp_err_convert[code].errno; 558 } 559 break; 560 case ICMP_REDIRECT: 561 /* See ICMP_SOURCE_QUENCH */ 562 ipv4_sk_redirect(skb, sk); 563 err = EREMOTEIO; 564 break; 565 } 566#if IS_ENABLED(CONFIG_IPV6) 567 } else if (skb->protocol == htons(ETH_P_IPV6)) { 568 harderr = pingv6_ops.icmpv6_err_convert(type, code, &err); 569#endif 570 } 571 572 /* 573 * RFC1122: OK. Passes ICMP errors back to application, as per 574 * 4.1.3.3. 575 */ 576 if ((family == AF_INET && !inet_sock->recverr) || 577 (family == AF_INET6 && !inet6_sk(sk)->recverr)) { 578 if (!harderr || sk->sk_state != TCP_ESTABLISHED) 579 goto out; 580 } else { 581 if (family == AF_INET) { 582 ip_icmp_error(sk, skb, err, 0 /* no remote port */, 583 info, (u8 *)icmph); 584#if IS_ENABLED(CONFIG_IPV6) 585 } else if (family == AF_INET6) { 586 pingv6_ops.ipv6_icmp_error(sk, skb, err, 0, 587 info, (u8 *)icmph); 588#endif 589 } 590 } 591 sk->sk_err = err; 592 sk->sk_error_report(sk); 593out: 594 sock_put(sk); 595} 596EXPORT_SYMBOL_GPL(ping_err); 597 598/* 599 * Copy and checksum an ICMP Echo packet from user space into a buffer 600 * starting from the payload. 601 */ 602 603int ping_getfrag(void *from, char *to, 604 int offset, int fraglen, int odd, struct sk_buff *skb) 605{ 606 struct pingfakehdr *pfh = (struct pingfakehdr *)from; 607 608 if (offset == 0) { 609 fraglen -= sizeof(struct icmphdr); 610 if (fraglen < 0) 611 BUG(); 612 if (!csum_and_copy_from_iter_full(to + sizeof(struct icmphdr), 613 fraglen, &pfh->wcheck, 614 &pfh->msg->msg_iter)) 615 return -EFAULT; 616 } else if (offset < sizeof(struct icmphdr)) { 617 BUG(); 618 } else { 619 if (!csum_and_copy_from_iter_full(to, fraglen, &pfh->wcheck, 620 &pfh->msg->msg_iter)) 621 return -EFAULT; 622 } 623 624#if IS_ENABLED(CONFIG_IPV6) 625 /* For IPv6, checksum each skb as we go along, as expected by 626 * icmpv6_push_pending_frames. For IPv4, accumulate the checksum in 627 * wcheck, it will be finalized in ping_v4_push_pending_frames. 628 */ 629 if (pfh->family == AF_INET6) { 630 skb->csum = pfh->wcheck; 631 skb->ip_summed = CHECKSUM_NONE; 632 pfh->wcheck = 0; 633 } 634#endif 635 636 return 0; 637} 638EXPORT_SYMBOL_GPL(ping_getfrag); 639 640static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh, 641 struct flowi4 *fl4) 642{ 643 struct sk_buff *skb = skb_peek(&sk->sk_write_queue); 644 645 if (!skb) 646 return 0; 647 pfh->wcheck = csum_partial((char *)&pfh->icmph, 648 sizeof(struct icmphdr), pfh->wcheck); 649 pfh->icmph.checksum = csum_fold(pfh->wcheck); 650 memcpy(icmp_hdr(skb), &pfh->icmph, sizeof(struct icmphdr)); 651 skb->ip_summed = CHECKSUM_NONE; 652 return ip_push_pending_frames(sk, fl4); 653} 654 655int ping_common_sendmsg(int family, struct msghdr *msg, size_t len, 656 void *user_icmph, size_t icmph_len) 657{ 658 u8 type, code; 659 660 if (len > 0xFFFF) 661 return -EMSGSIZE; 662 663 /* Must have at least a full ICMP header. */ 664 if (len < icmph_len) 665 return -EINVAL; 666 667 /* 668 * Check the flags. 669 */ 670 671 /* Mirror BSD error message compatibility */ 672 if (msg->msg_flags & MSG_OOB) 673 return -EOPNOTSUPP; 674 675 /* 676 * Fetch the ICMP header provided by the userland. 677 * iovec is modified! The ICMP header is consumed. 678 */ 679 if (memcpy_from_msg(user_icmph, msg, icmph_len)) 680 return -EFAULT; 681 682 if (family == AF_INET) { 683 type = ((struct icmphdr *) user_icmph)->type; 684 code = ((struct icmphdr *) user_icmph)->code; 685#if IS_ENABLED(CONFIG_IPV6) 686 } else if (family == AF_INET6) { 687 type = ((struct icmp6hdr *) user_icmph)->icmp6_type; 688 code = ((struct icmp6hdr *) user_icmph)->icmp6_code; 689#endif 690 } else { 691 BUG(); 692 } 693 694 if (!ping_supported(family, type, code)) 695 return -EINVAL; 696 697 return 0; 698} 699EXPORT_SYMBOL_GPL(ping_common_sendmsg); 700 701static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) 702{ 703 struct net *net = sock_net(sk); 704 struct flowi4 fl4; 705 struct inet_sock *inet = inet_sk(sk); 706 struct ipcm_cookie ipc; 707 struct icmphdr user_icmph; 708 struct pingfakehdr pfh; 709 struct rtable *rt = NULL; 710 struct ip_options_data opt_copy; 711 int free = 0; 712 __be32 saddr, daddr, faddr; 713 u8 tos; 714 int err; 715 716 pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num); 717 718 err = ping_common_sendmsg(AF_INET, msg, len, &user_icmph, 719 sizeof(user_icmph)); 720 if (err) 721 return err; 722 723 /* 724 * Get and verify the address. 725 */ 726 727 if (msg->msg_name) { 728 DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); 729 if (msg->msg_namelen < sizeof(*usin)) 730 return -EINVAL; 731 if (usin->sin_family != AF_INET) 732 return -EAFNOSUPPORT; 733 daddr = usin->sin_addr.s_addr; 734 /* no remote port */ 735 } else { 736 if (sk->sk_state != TCP_ESTABLISHED) 737 return -EDESTADDRREQ; 738 daddr = inet->inet_daddr; 739 /* no remote port */ 740 } 741 742 ipcm_init_sk(&ipc, inet); 743 744 if (msg->msg_controllen) { 745 err = ip_cmsg_send(sk, msg, &ipc, false); 746 if (unlikely(err)) { 747 kfree(ipc.opt); 748 return err; 749 } 750 if (ipc.opt) 751 free = 1; 752 } 753 if (!ipc.opt) { 754 struct ip_options_rcu *inet_opt; 755 756 rcu_read_lock(); 757 inet_opt = rcu_dereference(inet->inet_opt); 758 if (inet_opt) { 759 memcpy(&opt_copy, inet_opt, 760 sizeof(*inet_opt) + inet_opt->opt.optlen); 761 ipc.opt = &opt_copy.opt; 762 } 763 rcu_read_unlock(); 764 } 765 766 saddr = ipc.addr; 767 ipc.addr = faddr = daddr; 768 769 if (ipc.opt && ipc.opt->opt.srr) { 770 if (!daddr) { 771 err = -EINVAL; 772 goto out_free; 773 } 774 faddr = ipc.opt->opt.faddr; 775 } 776 tos = get_rttos(&ipc, inet); 777 if (sock_flag(sk, SOCK_LOCALROUTE) || 778 (msg->msg_flags & MSG_DONTROUTE) || 779 (ipc.opt && ipc.opt->opt.is_strictroute)) { 780 tos |= RTO_ONLINK; 781 } 782 783 if (ipv4_is_multicast(daddr)) { 784 if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) 785 ipc.oif = inet->mc_index; 786 if (!saddr) 787 saddr = inet->mc_addr; 788 } else if (!ipc.oif) 789 ipc.oif = inet->uc_index; 790 791 flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, 792 RT_SCOPE_UNIVERSE, sk->sk_protocol, 793 inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, 794 sk->sk_uid); 795 796 fl4.fl4_icmp_type = user_icmph.type; 797 fl4.fl4_icmp_code = user_icmph.code; 798 799 security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4)); 800 rt = ip_route_output_flow(net, &fl4, sk); 801 if (IS_ERR(rt)) { 802 err = PTR_ERR(rt); 803 rt = NULL; 804 if (err == -ENETUNREACH) 805 IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); 806 goto out; 807 } 808 809 err = -EACCES; 810 if ((rt->rt_flags & RTCF_BROADCAST) && 811 !sock_flag(sk, SOCK_BROADCAST)) 812 goto out; 813 814 if (msg->msg_flags & MSG_CONFIRM) 815 goto do_confirm; 816back_from_confirm: 817 818 if (!ipc.addr) 819 ipc.addr = fl4.daddr; 820 821 lock_sock(sk); 822 823 pfh.icmph.type = user_icmph.type; /* already checked */ 824 pfh.icmph.code = user_icmph.code; /* ditto */ 825 pfh.icmph.checksum = 0; 826 pfh.icmph.un.echo.id = inet->inet_sport; 827 pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence; 828 pfh.msg = msg; 829 pfh.wcheck = 0; 830 pfh.family = AF_INET; 831 832 err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len, 833 0, &ipc, &rt, msg->msg_flags); 834 if (err) 835 ip_flush_pending_frames(sk); 836 else 837 err = ping_v4_push_pending_frames(sk, &pfh, &fl4); 838 release_sock(sk); 839 840out: 841 ip_rt_put(rt); 842out_free: 843 if (free) 844 kfree(ipc.opt); 845 if (!err) { 846 icmp_out_count(sock_net(sk), user_icmph.type); 847 return len; 848 } 849 return err; 850 851do_confirm: 852 if (msg->msg_flags & MSG_PROBE) 853 dst_confirm_neigh(&rt->dst, &fl4.daddr); 854 if (!(msg->msg_flags & MSG_PROBE) || len) 855 goto back_from_confirm; 856 err = 0; 857 goto out; 858} 859 860int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, 861 int flags, int *addr_len) 862{ 863 struct inet_sock *isk = inet_sk(sk); 864 int family = sk->sk_family; 865 struct sk_buff *skb; 866 int copied, err; 867 868 pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num); 869 870 err = -EOPNOTSUPP; 871 if (flags & MSG_OOB) 872 goto out; 873 874 if (flags & MSG_ERRQUEUE) 875 return inet_recv_error(sk, msg, len, addr_len); 876 877 skb = skb_recv_datagram(sk, flags, noblock, &err); 878 if (!skb) 879 goto out; 880 881 copied = skb->len; 882 if (copied > len) { 883 msg->msg_flags |= MSG_TRUNC; 884 copied = len; 885 } 886 887 /* Don't bother checking the checksum */ 888 err = skb_copy_datagram_msg(skb, 0, msg, copied); 889 if (err) 890 goto done; 891 892 sock_recv_timestamp(msg, sk, skb); 893 894 /* Copy the address and add cmsg data. */ 895 if (family == AF_INET) { 896 DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); 897 898 if (sin) { 899 sin->sin_family = AF_INET; 900 sin->sin_port = 0 /* skb->h.uh->source */; 901 sin->sin_addr.s_addr = ip_hdr(skb)->saddr; 902 memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); 903 *addr_len = sizeof(*sin); 904 } 905 906 if (isk->cmsg_flags) 907 ip_cmsg_recv(msg, skb); 908 909#if IS_ENABLED(CONFIG_IPV6) 910 } else if (family == AF_INET6) { 911 struct ipv6_pinfo *np = inet6_sk(sk); 912 struct ipv6hdr *ip6 = ipv6_hdr(skb); 913 DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); 914 915 if (sin6) { 916 sin6->sin6_family = AF_INET6; 917 sin6->sin6_port = 0; 918 sin6->sin6_addr = ip6->saddr; 919 sin6->sin6_flowinfo = 0; 920 if (np->sndflow) 921 sin6->sin6_flowinfo = ip6_flowinfo(ip6); 922 sin6->sin6_scope_id = 923 ipv6_iface_scope_id(&sin6->sin6_addr, 924 inet6_iif(skb)); 925 *addr_len = sizeof(*sin6); 926 } 927 928 if (inet6_sk(sk)->rxopt.all) 929 pingv6_ops.ip6_datagram_recv_common_ctl(sk, msg, skb); 930 if (skb->protocol == htons(ETH_P_IPV6) && 931 inet6_sk(sk)->rxopt.all) 932 pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb); 933 else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags) 934 ip_cmsg_recv(msg, skb); 935#endif 936 } else { 937 BUG(); 938 } 939 940 err = copied; 941 942done: 943 skb_free_datagram(sk, skb); 944out: 945 pr_debug("ping_recvmsg -> %d\n", err); 946 return err; 947} 948EXPORT_SYMBOL_GPL(ping_recvmsg); 949 950int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) 951{ 952 pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", 953 inet_sk(sk), inet_sk(sk)->inet_num, skb); 954 if (sock_queue_rcv_skb(sk, skb) < 0) { 955 kfree_skb(skb); 956 pr_debug("ping_queue_rcv_skb -> failed\n"); 957 return -1; 958 } 959 return 0; 960} 961EXPORT_SYMBOL_GPL(ping_queue_rcv_skb); 962 963 964/* 965 * All we need to do is get the socket. 966 */ 967 968bool ping_rcv(struct sk_buff *skb) 969{ 970 struct sock *sk; 971 struct net *net = dev_net(skb->dev); 972 struct icmphdr *icmph = icmp_hdr(skb); 973 bool rc = false; 974 975 /* We assume the packet has already been checked by icmp_rcv */ 976 977 pr_debug("ping_rcv(skb=%p,id=%04x,seq=%04x)\n", 978 skb, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence)); 979 980 /* Push ICMP header back */ 981 skb_push(skb, skb->data - (u8 *)icmph); 982 983 sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id)); 984 if (sk) { 985 struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); 986 987 pr_debug("rcv on socket %p\n", sk); 988 if (skb2 && !ping_queue_rcv_skb(sk, skb2)) 989 rc = true; 990 sock_put(sk); 991 } 992 993 if (!rc) 994 pr_debug("no socket, dropping\n"); 995 996 return rc; 997} 998EXPORT_SYMBOL_GPL(ping_rcv); 999 1000struct proto ping_prot = { 1001 .name = "PING", 1002 .owner = THIS_MODULE, 1003 .init = ping_init_sock, 1004 .close = ping_close, 1005 .connect = ip4_datagram_connect, 1006 .disconnect = __udp_disconnect, 1007 .setsockopt = ip_setsockopt, 1008 .getsockopt = ip_getsockopt, 1009 .sendmsg = ping_v4_sendmsg, 1010 .recvmsg = ping_recvmsg, 1011 .bind = ping_bind, 1012 .backlog_rcv = ping_queue_rcv_skb, 1013 .release_cb = ip4_datagram_release_cb, 1014 .hash = ping_hash, 1015 .unhash = ping_unhash, 1016 .get_port = ping_get_port, 1017 .obj_size = sizeof(struct inet_sock), 1018}; 1019EXPORT_SYMBOL(ping_prot); 1020 1021#ifdef CONFIG_PROC_FS 1022 1023static struct sock *ping_get_first(struct seq_file *seq, int start) 1024{ 1025 struct sock *sk; 1026 struct ping_iter_state *state = seq->private; 1027 struct net *net = seq_file_net(seq); 1028 1029 for (state->bucket = start; state->bucket < PING_HTABLE_SIZE; 1030 ++state->bucket) { 1031 struct hlist_nulls_node *node; 1032 struct hlist_nulls_head *hslot; 1033 1034 hslot = &ping_table.hash[state->bucket]; 1035 1036 if (hlist_nulls_empty(hslot)) 1037 continue; 1038 1039 sk_nulls_for_each(sk, node, hslot) { 1040 if (net_eq(sock_net(sk), net) && 1041 sk->sk_family == state->family) 1042 goto found; 1043 } 1044 } 1045 sk = NULL; 1046found: 1047 return sk; 1048} 1049 1050static struct sock *ping_get_next(struct seq_file *seq, struct sock *sk) 1051{ 1052 struct ping_iter_state *state = seq->private; 1053 struct net *net = seq_file_net(seq); 1054 1055 do { 1056 sk = sk_nulls_next(sk); 1057 } while (sk && (!net_eq(sock_net(sk), net))); 1058 1059 if (!sk) 1060 return ping_get_first(seq, state->bucket + 1); 1061 return sk; 1062} 1063 1064static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos) 1065{ 1066 struct sock *sk = ping_get_first(seq, 0); 1067 1068 if (sk) 1069 while (pos && (sk = ping_get_next(seq, sk)) != NULL) 1070 --pos; 1071 return pos ? NULL : sk; 1072} 1073 1074void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family) 1075 __acquires(ping_table.lock) 1076{ 1077 struct ping_iter_state *state = seq->private; 1078 state->bucket = 0; 1079 state->family = family; 1080 1081 read_lock_bh(&ping_table.lock); 1082 1083 return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN; 1084} 1085EXPORT_SYMBOL_GPL(ping_seq_start); 1086 1087static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos) 1088{ 1089 return ping_seq_start(seq, pos, AF_INET); 1090} 1091 1092void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos) 1093{ 1094 struct sock *sk; 1095 1096 if (v == SEQ_START_TOKEN) 1097 sk = ping_get_idx(seq, 0); 1098 else 1099 sk = ping_get_next(seq, v); 1100 1101 ++*pos; 1102 return sk; 1103} 1104EXPORT_SYMBOL_GPL(ping_seq_next); 1105 1106void ping_seq_stop(struct seq_file *seq, void *v) 1107 __releases(ping_table.lock) 1108{ 1109 read_unlock_bh(&ping_table.lock); 1110} 1111EXPORT_SYMBOL_GPL(ping_seq_stop); 1112 1113static void ping_v4_format_sock(struct sock *sp, struct seq_file *f, 1114 int bucket) 1115{ 1116 struct inet_sock *inet = inet_sk(sp); 1117 __be32 dest = inet->inet_daddr; 1118 __be32 src = inet->inet_rcv_saddr; 1119 __u16 destp = ntohs(inet->inet_dport); 1120 __u16 srcp = ntohs(inet->inet_sport); 1121 1122 seq_printf(f, "%5d: %08X:%04X %08X:%04X" 1123 " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u", 1124 bucket, src, srcp, dest, destp, sp->sk_state, 1125 sk_wmem_alloc_get(sp), 1126 sk_rmem_alloc_get(sp), 1127 0, 0L, 0, 1128 from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), 1129 0, sock_i_ino(sp), 1130 refcount_read(&sp->sk_refcnt), sp, 1131 atomic_read(&sp->sk_drops)); 1132} 1133 1134static int ping_v4_seq_show(struct seq_file *seq, void *v) 1135{ 1136 seq_setwidth(seq, 127); 1137 if (v == SEQ_START_TOKEN) 1138 seq_puts(seq, " sl local_address rem_address st tx_queue " 1139 "rx_queue tr tm->when retrnsmt uid timeout " 1140 "inode ref pointer drops"); 1141 else { 1142 struct ping_iter_state *state = seq->private; 1143 1144 ping_v4_format_sock(v, seq, state->bucket); 1145 } 1146 seq_pad(seq, '\n'); 1147 return 0; 1148} 1149 1150static const struct seq_operations ping_v4_seq_ops = { 1151 .start = ping_v4_seq_start, 1152 .show = ping_v4_seq_show, 1153 .next = ping_seq_next, 1154 .stop = ping_seq_stop, 1155}; 1156 1157static int __net_init ping_v4_proc_init_net(struct net *net) 1158{ 1159 if (!proc_create_net("icmp", 0444, net->proc_net, &ping_v4_seq_ops, 1160 sizeof(struct ping_iter_state))) 1161 return -ENOMEM; 1162 return 0; 1163} 1164 1165static void __net_exit ping_v4_proc_exit_net(struct net *net) 1166{ 1167 remove_proc_entry("icmp", net->proc_net); 1168} 1169 1170static struct pernet_operations ping_v4_net_ops = { 1171 .init = ping_v4_proc_init_net, 1172 .exit = ping_v4_proc_exit_net, 1173}; 1174 1175int __init ping_proc_init(void) 1176{ 1177 return register_pernet_subsys(&ping_v4_net_ops); 1178} 1179 1180void ping_proc_exit(void) 1181{ 1182 unregister_pernet_subsys(&ping_v4_net_ops); 1183} 1184 1185#endif 1186 1187void __init ping_init(void) 1188{ 1189 int i; 1190 1191 for (i = 0; i < PING_HTABLE_SIZE; i++) 1192 INIT_HLIST_NULLS_HEAD(&ping_table.hash[i], i); 1193 rwlock_init(&ping_table.lock); 1194} 1195