1// SPDX-License-Identifier: GPL-2.0 2/* Multipath TCP 3 * 4 * Copyright (c) 2020, Red Hat, Inc. 5 */ 6 7#define pr_fmt(fmt) "MPTCP: " fmt 8 9#include <linux/inet.h> 10#include <linux/kernel.h> 11#include <net/tcp.h> 12#include <net/netns/generic.h> 13#include <net/mptcp.h> 14#include <net/genetlink.h> 15#include <uapi/linux/mptcp.h> 16 17#include "protocol.h" 18#include "mib.h" 19 20/* forward declaration */ 21static struct genl_family mptcp_genl_family; 22 23static int pm_nl_pernet_id; 24 25struct mptcp_pm_addr_entry { 26 struct list_head list; 27 struct mptcp_addr_info addr; 28 struct rcu_head rcu; 29}; 30 31struct mptcp_pm_add_entry { 32 struct list_head list; 33 struct mptcp_addr_info addr; 34 struct timer_list add_timer; 35 struct mptcp_sock *sock; 36 u8 retrans_times; 37}; 38 39struct pm_nl_pernet { 40 /* protects pernet updates */ 41 spinlock_t lock; 42 struct list_head local_addr_list; 43 unsigned int addrs; 44 unsigned int add_addr_signal_max; 45 unsigned int add_addr_accept_max; 46 unsigned int local_addr_max; 47 unsigned int subflows_max; 48 unsigned int next_id; 49}; 50 51#define MPTCP_PM_ADDR_MAX 8 52#define ADD_ADDR_RETRANS_MAX 3 53 54static bool addresses_equal(const struct mptcp_addr_info *a, 55 struct mptcp_addr_info *b, bool use_port) 56{ 57 bool addr_equals = false; 58 59 if (a->family != b->family) 60 return false; 61 62 if (a->family == AF_INET) 63 addr_equals = a->addr.s_addr == b->addr.s_addr; 64#if IS_ENABLED(CONFIG_MPTCP_IPV6) 65 else 66 addr_equals = !ipv6_addr_cmp(&a->addr6, &b->addr6); 67#endif 68 69 if (!addr_equals) 70 return false; 71 if (!use_port) 72 return true; 73 74 return a->port == b->port; 75} 76 77static bool address_zero(const struct mptcp_addr_info *addr) 78{ 79 struct mptcp_addr_info zero; 80 81 memset(&zero, 0, sizeof(zero)); 82 zero.family = addr->family; 83 84 return addresses_equal(addr, &zero, false); 85} 86 87static void local_address(const struct sock_common *skc, 88 struct mptcp_addr_info *addr) 89{ 90 addr->port = 0; 91 addr->family = skc->skc_family; 92 if (addr->family == AF_INET) 93 addr->addr.s_addr = skc->skc_rcv_saddr; 94#if IS_ENABLED(CONFIG_MPTCP_IPV6) 95 else if (addr->family == AF_INET6) 96 addr->addr6 = skc->skc_v6_rcv_saddr; 97#endif 98} 99 100static void remote_address(const struct sock_common *skc, 101 struct mptcp_addr_info *addr) 102{ 103 addr->family = skc->skc_family; 104 addr->port = skc->skc_dport; 105 if (addr->family == AF_INET) 106 addr->addr.s_addr = skc->skc_daddr; 107#if IS_ENABLED(CONFIG_MPTCP_IPV6) 108 else if (addr->family == AF_INET6) 109 addr->addr6 = skc->skc_v6_daddr; 110#endif 111} 112 113static bool lookup_subflow_by_saddr(const struct list_head *list, 114 struct mptcp_addr_info *saddr) 115{ 116 struct mptcp_subflow_context *subflow; 117 struct mptcp_addr_info cur; 118 struct sock_common *skc; 119 120 list_for_each_entry(subflow, list, node) { 121 skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow); 122 123 local_address(skc, &cur); 124 if (addresses_equal(&cur, saddr, false)) 125 return true; 126 } 127 128 return false; 129} 130 131static struct mptcp_pm_addr_entry * 132select_local_address(const struct pm_nl_pernet *pernet, 133 struct mptcp_sock *msk) 134{ 135 struct mptcp_pm_addr_entry *entry, *ret = NULL; 136 137 rcu_read_lock(); 138 spin_lock_bh(&msk->join_list_lock); 139 list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { 140 if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)) 141 continue; 142 143 /* avoid any address already in use by subflows and 144 * pending join 145 */ 146 if (entry->addr.family == ((struct sock *)msk)->sk_family && 147 !lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) && 148 !lookup_subflow_by_saddr(&msk->join_list, &entry->addr)) { 149 ret = entry; 150 break; 151 } 152 } 153 spin_unlock_bh(&msk->join_list_lock); 154 rcu_read_unlock(); 155 return ret; 156} 157 158static struct mptcp_pm_addr_entry * 159select_signal_address(struct pm_nl_pernet *pernet, unsigned int pos) 160{ 161 struct mptcp_pm_addr_entry *entry, *ret = NULL; 162 int i = 0; 163 164 rcu_read_lock(); 165 /* do not keep any additional per socket state, just signal 166 * the address list in order. 167 * Note: removal from the local address list during the msk life-cycle 168 * can lead to additional addresses not being announced. 169 */ 170 list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { 171 if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) 172 continue; 173 if (i++ == pos) { 174 ret = entry; 175 break; 176 } 177 } 178 rcu_read_unlock(); 179 return ret; 180} 181 182static void check_work_pending(struct mptcp_sock *msk) 183{ 184 if (msk->pm.add_addr_signaled == msk->pm.add_addr_signal_max && 185 (msk->pm.local_addr_used == msk->pm.local_addr_max || 186 msk->pm.subflows == msk->pm.subflows_max)) 187 WRITE_ONCE(msk->pm.work_pending, false); 188} 189 190static struct mptcp_pm_add_entry * 191lookup_anno_list_by_saddr(struct mptcp_sock *msk, 192 struct mptcp_addr_info *addr) 193{ 194 struct mptcp_pm_add_entry *entry; 195 196 list_for_each_entry(entry, &msk->pm.anno_list, list) { 197 if (addresses_equal(&entry->addr, addr, false)) 198 return entry; 199 } 200 201 return NULL; 202} 203 204static void mptcp_pm_add_timer(struct timer_list *timer) 205{ 206 struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer); 207 struct mptcp_sock *msk = entry->sock; 208 struct sock *sk = (struct sock *)msk; 209 210 pr_debug("msk=%p", msk); 211 212 if (!msk) 213 return; 214 215 if (inet_sk_state_load(sk) == TCP_CLOSE) 216 return; 217 218 if (!entry->addr.id) 219 return; 220 221 if (mptcp_pm_should_add_signal(msk)) { 222 sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8); 223 goto out; 224 } 225 226 spin_lock_bh(&msk->pm.lock); 227 228 if (!mptcp_pm_should_add_signal(msk)) { 229 pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id); 230 mptcp_pm_announce_addr(msk, &entry->addr, false); 231 entry->retrans_times++; 232 } 233 234 if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) 235 sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX); 236 237 spin_unlock_bh(&msk->pm.lock); 238 239out: 240 __sock_put(sk); 241} 242 243struct mptcp_pm_add_entry * 244mptcp_pm_del_add_timer(struct mptcp_sock *msk, 245 struct mptcp_addr_info *addr) 246{ 247 struct mptcp_pm_add_entry *entry; 248 struct sock *sk = (struct sock *)msk; 249 250 spin_lock_bh(&msk->pm.lock); 251 entry = lookup_anno_list_by_saddr(msk, addr); 252 if (entry) 253 entry->retrans_times = ADD_ADDR_RETRANS_MAX; 254 spin_unlock_bh(&msk->pm.lock); 255 256 if (entry) 257 sk_stop_timer_sync(sk, &entry->add_timer); 258 259 return entry; 260} 261 262static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, 263 struct mptcp_pm_addr_entry *entry) 264{ 265 struct mptcp_pm_add_entry *add_entry = NULL; 266 struct sock *sk = (struct sock *)msk; 267 268 if (lookup_anno_list_by_saddr(msk, &entry->addr)) 269 return false; 270 271 add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC); 272 if (!add_entry) 273 return false; 274 275 list_add(&add_entry->list, &msk->pm.anno_list); 276 277 add_entry->addr = entry->addr; 278 add_entry->sock = msk; 279 add_entry->retrans_times = 0; 280 281 timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0); 282 sk_reset_timer(sk, &add_entry->add_timer, jiffies + TCP_RTO_MAX); 283 284 return true; 285} 286 287void mptcp_pm_free_anno_list(struct mptcp_sock *msk) 288{ 289 struct mptcp_pm_add_entry *entry, *tmp; 290 struct sock *sk = (struct sock *)msk; 291 LIST_HEAD(free_list); 292 293 pr_debug("msk=%p", msk); 294 295 spin_lock_bh(&msk->pm.lock); 296 list_splice_init(&msk->pm.anno_list, &free_list); 297 spin_unlock_bh(&msk->pm.lock); 298 299 list_for_each_entry_safe(entry, tmp, &free_list, list) { 300 sk_stop_timer_sync(sk, &entry->add_timer); 301 kfree(entry); 302 } 303} 304 305static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) 306{ 307 struct mptcp_addr_info remote = { 0 }; 308 struct sock *sk = (struct sock *)msk; 309 struct mptcp_pm_addr_entry *local; 310 struct pm_nl_pernet *pernet; 311 312 pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); 313 314 pr_debug("local %d:%d signal %d:%d subflows %d:%d\n", 315 msk->pm.local_addr_used, msk->pm.local_addr_max, 316 msk->pm.add_addr_signaled, msk->pm.add_addr_signal_max, 317 msk->pm.subflows, msk->pm.subflows_max); 318 319 /* check first for announce */ 320 if (msk->pm.add_addr_signaled < msk->pm.add_addr_signal_max) { 321 local = select_signal_address(pernet, 322 msk->pm.add_addr_signaled); 323 324 if (local) { 325 if (mptcp_pm_alloc_anno_list(msk, local)) { 326 msk->pm.add_addr_signaled++; 327 mptcp_pm_announce_addr(msk, &local->addr, false); 328 } 329 } else { 330 /* pick failed, avoid fourther attempts later */ 331 msk->pm.local_addr_used = msk->pm.add_addr_signal_max; 332 } 333 334 check_work_pending(msk); 335 } 336 337 /* check if should create a new subflow */ 338 if (msk->pm.local_addr_used < msk->pm.local_addr_max && 339 msk->pm.subflows < msk->pm.subflows_max) { 340 remote_address((struct sock_common *)sk, &remote); 341 342 local = select_local_address(pernet, msk); 343 if (local) { 344 msk->pm.local_addr_used++; 345 msk->pm.subflows++; 346 check_work_pending(msk); 347 spin_unlock_bh(&msk->pm.lock); 348 __mptcp_subflow_connect(sk, &local->addr, &remote); 349 spin_lock_bh(&msk->pm.lock); 350 return; 351 } 352 353 /* lookup failed, avoid fourther attempts later */ 354 msk->pm.local_addr_used = msk->pm.local_addr_max; 355 check_work_pending(msk); 356 } 357} 358 359void mptcp_pm_nl_fully_established(struct mptcp_sock *msk) 360{ 361 mptcp_pm_create_subflow_or_signal_addr(msk); 362} 363 364void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk) 365{ 366 mptcp_pm_create_subflow_or_signal_addr(msk); 367} 368 369void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) 370{ 371 struct sock *sk = (struct sock *)msk; 372 struct mptcp_addr_info remote; 373 struct mptcp_addr_info local; 374 375 pr_debug("accepted %d:%d remote family %d", 376 msk->pm.add_addr_accepted, msk->pm.add_addr_accept_max, 377 msk->pm.remote.family); 378 msk->pm.add_addr_accepted++; 379 msk->pm.subflows++; 380 if (msk->pm.add_addr_accepted >= msk->pm.add_addr_accept_max || 381 msk->pm.subflows >= msk->pm.subflows_max) 382 WRITE_ONCE(msk->pm.accept_addr, false); 383 384 /* connect to the specified remote address, using whatever 385 * local address the routing configuration will pick. 386 */ 387 remote = msk->pm.remote; 388 if (!remote.port) 389 remote.port = sk->sk_dport; 390 memset(&local, 0, sizeof(local)); 391 local.family = remote.family; 392 393 spin_unlock_bh(&msk->pm.lock); 394 __mptcp_subflow_connect((struct sock *)msk, &local, &remote); 395 spin_lock_bh(&msk->pm.lock); 396 397 mptcp_pm_announce_addr(msk, &remote, true); 398} 399 400void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk) 401{ 402 struct mptcp_subflow_context *subflow, *tmp; 403 struct sock *sk = (struct sock *)msk; 404 405 pr_debug("address rm_id %d", msk->pm.rm_id); 406 407 if (!msk->pm.rm_id) 408 return; 409 410 if (list_empty(&msk->conn_list)) 411 return; 412 413 list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { 414 struct sock *ssk = mptcp_subflow_tcp_sock(subflow); 415 int how = RCV_SHUTDOWN | SEND_SHUTDOWN; 416 long timeout = 0; 417 418 if (msk->pm.rm_id != subflow->remote_id) 419 continue; 420 421 spin_unlock_bh(&msk->pm.lock); 422 mptcp_subflow_shutdown(sk, ssk, how); 423 __mptcp_close_ssk(sk, ssk, subflow, timeout); 424 spin_lock_bh(&msk->pm.lock); 425 426 msk->pm.add_addr_accepted--; 427 msk->pm.subflows--; 428 WRITE_ONCE(msk->pm.accept_addr, true); 429 430 __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMADDR); 431 432 break; 433 } 434} 435 436void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id) 437{ 438 struct mptcp_subflow_context *subflow, *tmp; 439 struct sock *sk = (struct sock *)msk; 440 441 pr_debug("subflow rm_id %d", rm_id); 442 443 if (!rm_id) 444 return; 445 446 if (list_empty(&msk->conn_list)) 447 return; 448 449 list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { 450 struct sock *ssk = mptcp_subflow_tcp_sock(subflow); 451 int how = RCV_SHUTDOWN | SEND_SHUTDOWN; 452 long timeout = 0; 453 454 if (rm_id != subflow->local_id) 455 continue; 456 457 spin_unlock_bh(&msk->pm.lock); 458 mptcp_subflow_shutdown(sk, ssk, how); 459 __mptcp_close_ssk(sk, ssk, subflow, timeout); 460 spin_lock_bh(&msk->pm.lock); 461 462 msk->pm.local_addr_used--; 463 msk->pm.subflows--; 464 465 __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); 466 467 break; 468 } 469} 470 471static bool address_use_port(struct mptcp_pm_addr_entry *entry) 472{ 473 return (entry->addr.flags & 474 (MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_SUBFLOW)) == 475 MPTCP_PM_ADDR_FLAG_SIGNAL; 476} 477 478static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, 479 struct mptcp_pm_addr_entry *entry) 480{ 481 struct mptcp_pm_addr_entry *cur; 482 int ret = -EINVAL; 483 484 spin_lock_bh(&pernet->lock); 485 /* to keep the code simple, don't do IDR-like allocation for address ID, 486 * just bail when we exceed limits 487 */ 488 if (pernet->next_id > 255) 489 goto out; 490 if (pernet->addrs >= MPTCP_PM_ADDR_MAX) 491 goto out; 492 493 /* do not insert duplicate address, differentiate on port only 494 * singled addresses 495 */ 496 list_for_each_entry(cur, &pernet->local_addr_list, list) { 497 if (addresses_equal(&cur->addr, &entry->addr, 498 address_use_port(entry) && 499 address_use_port(cur))) 500 goto out; 501 } 502 503 if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) 504 pernet->add_addr_signal_max++; 505 if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) 506 pernet->local_addr_max++; 507 508 entry->addr.id = pernet->next_id++; 509 pernet->addrs++; 510 list_add_tail_rcu(&entry->list, &pernet->local_addr_list); 511 ret = entry->addr.id; 512 513out: 514 spin_unlock_bh(&pernet->lock); 515 return ret; 516} 517 518int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) 519{ 520 struct mptcp_pm_addr_entry *entry; 521 struct mptcp_addr_info skc_local; 522 struct mptcp_addr_info msk_local; 523 struct pm_nl_pernet *pernet; 524 int ret = -1; 525 526 if (WARN_ON_ONCE(!msk)) 527 return -1; 528 529 /* The 0 ID mapping is defined by the first subflow, copied into the msk 530 * addr 531 */ 532 local_address((struct sock_common *)msk, &msk_local); 533 local_address((struct sock_common *)skc, &skc_local); 534 if (addresses_equal(&msk_local, &skc_local, false)) 535 return 0; 536 537 if (address_zero(&skc_local)) 538 return 0; 539 540 pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); 541 542 rcu_read_lock(); 543 list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { 544 if (addresses_equal(&entry->addr, &skc_local, false)) { 545 ret = entry->addr.id; 546 break; 547 } 548 } 549 rcu_read_unlock(); 550 if (ret >= 0) 551 return ret; 552 553 /* address not found, add to local list */ 554 entry = kmalloc(sizeof(*entry), GFP_ATOMIC); 555 if (!entry) 556 return -ENOMEM; 557 558 entry->addr = skc_local; 559 entry->addr.ifindex = 0; 560 entry->addr.flags = 0; 561 ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); 562 if (ret < 0) 563 kfree(entry); 564 565 return ret; 566} 567 568void mptcp_pm_nl_data_init(struct mptcp_sock *msk) 569{ 570 struct mptcp_pm_data *pm = &msk->pm; 571 struct pm_nl_pernet *pernet; 572 bool subflows; 573 574 pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id); 575 576 pm->add_addr_signal_max = READ_ONCE(pernet->add_addr_signal_max); 577 pm->add_addr_accept_max = READ_ONCE(pernet->add_addr_accept_max); 578 pm->local_addr_max = READ_ONCE(pernet->local_addr_max); 579 pm->subflows_max = READ_ONCE(pernet->subflows_max); 580 subflows = !!pm->subflows_max; 581 WRITE_ONCE(pm->work_pending, (!!pm->local_addr_max && subflows) || 582 !!pm->add_addr_signal_max); 583 WRITE_ONCE(pm->accept_addr, !!pm->add_addr_accept_max && subflows); 584 WRITE_ONCE(pm->accept_subflow, subflows); 585} 586 587#define MPTCP_PM_CMD_GRP_OFFSET 0 588 589static const struct genl_multicast_group mptcp_pm_mcgrps[] = { 590 [MPTCP_PM_CMD_GRP_OFFSET] = { .name = MPTCP_PM_CMD_GRP_NAME, }, 591}; 592 593static const struct nla_policy 594mptcp_pm_addr_policy[MPTCP_PM_ADDR_ATTR_MAX + 1] = { 595 [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, 596 [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, 597 [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, 598 [MPTCP_PM_ADDR_ATTR_ADDR6] = 599 NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), 600 [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16 }, 601 [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32 }, 602 [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32 }, 603}; 604 605static const struct nla_policy mptcp_pm_policy[MPTCP_PM_ATTR_MAX + 1] = { 606 [MPTCP_PM_ATTR_ADDR] = 607 NLA_POLICY_NESTED(mptcp_pm_addr_policy), 608 [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, 609 [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, 610}; 611 612static int mptcp_pm_family_to_addr(int family) 613{ 614#if IS_ENABLED(CONFIG_MPTCP_IPV6) 615 if (family == AF_INET6) 616 return MPTCP_PM_ADDR_ATTR_ADDR6; 617#endif 618 return MPTCP_PM_ADDR_ATTR_ADDR4; 619} 620 621static int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info, 622 bool require_family, 623 struct mptcp_pm_addr_entry *entry) 624{ 625 struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; 626 int err, addr_addr; 627 628 if (!attr) { 629 GENL_SET_ERR_MSG(info, "missing address info"); 630 return -EINVAL; 631 } 632 633 /* no validation needed - was already done via nested policy */ 634 err = nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, 635 mptcp_pm_addr_policy, info->extack); 636 if (err) 637 return err; 638 639 memset(entry, 0, sizeof(*entry)); 640 if (!tb[MPTCP_PM_ADDR_ATTR_FAMILY]) { 641 if (!require_family) 642 goto skip_family; 643 644 NL_SET_ERR_MSG_ATTR(info->extack, attr, 645 "missing family"); 646 return -EINVAL; 647 } 648 649 entry->addr.family = nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_FAMILY]); 650 if (entry->addr.family != AF_INET 651#if IS_ENABLED(CONFIG_MPTCP_IPV6) 652 && entry->addr.family != AF_INET6 653#endif 654 ) { 655 NL_SET_ERR_MSG_ATTR(info->extack, attr, 656 "unknown address family"); 657 return -EINVAL; 658 } 659 addr_addr = mptcp_pm_family_to_addr(entry->addr.family); 660 if (!tb[addr_addr]) { 661 NL_SET_ERR_MSG_ATTR(info->extack, attr, 662 "missing address data"); 663 return -EINVAL; 664 } 665 666#if IS_ENABLED(CONFIG_MPTCP_IPV6) 667 if (entry->addr.family == AF_INET6) 668 entry->addr.addr6 = nla_get_in6_addr(tb[addr_addr]); 669 else 670#endif 671 entry->addr.addr.s_addr = nla_get_in_addr(tb[addr_addr]); 672 673skip_family: 674 if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) { 675 u32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]); 676 677 entry->addr.ifindex = val; 678 } 679 680 if (tb[MPTCP_PM_ADDR_ATTR_ID]) 681 entry->addr.id = nla_get_u8(tb[MPTCP_PM_ADDR_ATTR_ID]); 682 683 if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) 684 entry->addr.flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]); 685 686 return 0; 687} 688 689static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info) 690{ 691 return net_generic(genl_info_net(info), pm_nl_pernet_id); 692} 693 694static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) 695{ 696 struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; 697 struct pm_nl_pernet *pernet = genl_info_pm_nl(info); 698 struct mptcp_pm_addr_entry addr, *entry; 699 int ret; 700 701 ret = mptcp_pm_parse_addr(attr, info, true, &addr); 702 if (ret < 0) 703 return ret; 704 705 entry = kmalloc(sizeof(*entry), GFP_KERNEL); 706 if (!entry) { 707 GENL_SET_ERR_MSG(info, "can't allocate addr"); 708 return -ENOMEM; 709 } 710 711 *entry = addr; 712 ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); 713 if (ret < 0) { 714 GENL_SET_ERR_MSG(info, "too many addresses or duplicate one"); 715 kfree(entry); 716 return ret; 717 } 718 719 return 0; 720} 721 722static struct mptcp_pm_addr_entry * 723__lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id) 724{ 725 struct mptcp_pm_addr_entry *entry; 726 727 list_for_each_entry(entry, &pernet->local_addr_list, list) { 728 if (entry->addr.id == id) 729 return entry; 730 } 731 return NULL; 732} 733 734static bool remove_anno_list_by_saddr(struct mptcp_sock *msk, 735 struct mptcp_addr_info *addr) 736{ 737 struct mptcp_pm_add_entry *entry; 738 739 entry = mptcp_pm_del_add_timer(msk, addr); 740 if (entry) { 741 list_del(&entry->list); 742 kfree(entry); 743 return true; 744 } 745 746 return false; 747} 748 749static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk, 750 struct mptcp_addr_info *addr, 751 bool force) 752{ 753 bool ret; 754 755 ret = remove_anno_list_by_saddr(msk, addr); 756 if (ret || force) { 757 spin_lock_bh(&msk->pm.lock); 758 mptcp_pm_remove_addr(msk, addr->id); 759 spin_unlock_bh(&msk->pm.lock); 760 } 761 return ret; 762} 763 764static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, 765 struct mptcp_addr_info *addr) 766{ 767 struct mptcp_sock *msk; 768 long s_slot = 0, s_num = 0; 769 770 pr_debug("remove_id=%d", addr->id); 771 772 while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { 773 struct sock *sk = (struct sock *)msk; 774 bool remove_subflow; 775 776 if (list_empty(&msk->conn_list)) { 777 mptcp_pm_remove_anno_addr(msk, addr, false); 778 goto next; 779 } 780 781 lock_sock(sk); 782 remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr); 783 mptcp_pm_remove_anno_addr(msk, addr, remove_subflow); 784 if (remove_subflow) 785 mptcp_pm_remove_subflow(msk, addr->id); 786 release_sock(sk); 787 788next: 789 sock_put(sk); 790 cond_resched(); 791 } 792 793 return 0; 794} 795 796static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) 797{ 798 struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; 799 struct pm_nl_pernet *pernet = genl_info_pm_nl(info); 800 struct mptcp_pm_addr_entry addr, *entry; 801 int ret; 802 803 ret = mptcp_pm_parse_addr(attr, info, false, &addr); 804 if (ret < 0) 805 return ret; 806 807 spin_lock_bh(&pernet->lock); 808 entry = __lookup_addr_by_id(pernet, addr.addr.id); 809 if (!entry) { 810 GENL_SET_ERR_MSG(info, "address not found"); 811 spin_unlock_bh(&pernet->lock); 812 return -EINVAL; 813 } 814 if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) 815 pernet->add_addr_signal_max--; 816 if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) 817 pernet->local_addr_max--; 818 819 pernet->addrs--; 820 list_del_rcu(&entry->list); 821 spin_unlock_bh(&pernet->lock); 822 823 mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr); 824 kfree_rcu(entry, rcu); 825 826 return ret; 827} 828 829static void __flush_addrs(struct pm_nl_pernet *pernet) 830{ 831 while (!list_empty(&pernet->local_addr_list)) { 832 struct mptcp_pm_addr_entry *cur; 833 834 cur = list_entry(pernet->local_addr_list.next, 835 struct mptcp_pm_addr_entry, list); 836 list_del_rcu(&cur->list); 837 kfree_rcu(cur, rcu); 838 } 839} 840 841static void __reset_counters(struct pm_nl_pernet *pernet) 842{ 843 pernet->add_addr_signal_max = 0; 844 pernet->add_addr_accept_max = 0; 845 pernet->local_addr_max = 0; 846 pernet->addrs = 0; 847} 848 849static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info) 850{ 851 struct pm_nl_pernet *pernet = genl_info_pm_nl(info); 852 853 spin_lock_bh(&pernet->lock); 854 __flush_addrs(pernet); 855 __reset_counters(pernet); 856 spin_unlock_bh(&pernet->lock); 857 return 0; 858} 859 860static int mptcp_nl_fill_addr(struct sk_buff *skb, 861 struct mptcp_pm_addr_entry *entry) 862{ 863 struct mptcp_addr_info *addr = &entry->addr; 864 struct nlattr *attr; 865 866 attr = nla_nest_start(skb, MPTCP_PM_ATTR_ADDR); 867 if (!attr) 868 return -EMSGSIZE; 869 870 if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_FAMILY, addr->family)) 871 goto nla_put_failure; 872 if (nla_put_u8(skb, MPTCP_PM_ADDR_ATTR_ID, addr->id)) 873 goto nla_put_failure; 874 if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->addr.flags)) 875 goto nla_put_failure; 876 if (entry->addr.ifindex && 877 nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->addr.ifindex)) 878 goto nla_put_failure; 879 880 if (addr->family == AF_INET && 881 nla_put_in_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR4, 882 addr->addr.s_addr)) 883 goto nla_put_failure; 884#if IS_ENABLED(CONFIG_MPTCP_IPV6) 885 else if (addr->family == AF_INET6 && 886 nla_put_in6_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR6, &addr->addr6)) 887 goto nla_put_failure; 888#endif 889 nla_nest_end(skb, attr); 890 return 0; 891 892nla_put_failure: 893 nla_nest_cancel(skb, attr); 894 return -EMSGSIZE; 895} 896 897static int mptcp_nl_cmd_get_addr(struct sk_buff *skb, struct genl_info *info) 898{ 899 struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; 900 struct pm_nl_pernet *pernet = genl_info_pm_nl(info); 901 struct mptcp_pm_addr_entry addr, *entry; 902 struct sk_buff *msg; 903 void *reply; 904 int ret; 905 906 ret = mptcp_pm_parse_addr(attr, info, false, &addr); 907 if (ret < 0) 908 return ret; 909 910 msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); 911 if (!msg) 912 return -ENOMEM; 913 914 reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0, 915 info->genlhdr->cmd); 916 if (!reply) { 917 GENL_SET_ERR_MSG(info, "not enough space in Netlink message"); 918 ret = -EMSGSIZE; 919 goto fail; 920 } 921 922 spin_lock_bh(&pernet->lock); 923 entry = __lookup_addr_by_id(pernet, addr.addr.id); 924 if (!entry) { 925 GENL_SET_ERR_MSG(info, "address not found"); 926 ret = -EINVAL; 927 goto unlock_fail; 928 } 929 930 ret = mptcp_nl_fill_addr(msg, entry); 931 if (ret) 932 goto unlock_fail; 933 934 genlmsg_end(msg, reply); 935 ret = genlmsg_reply(msg, info); 936 spin_unlock_bh(&pernet->lock); 937 return ret; 938 939unlock_fail: 940 spin_unlock_bh(&pernet->lock); 941 942fail: 943 nlmsg_free(msg); 944 return ret; 945} 946 947static int mptcp_nl_cmd_dump_addrs(struct sk_buff *msg, 948 struct netlink_callback *cb) 949{ 950 struct net *net = sock_net(msg->sk); 951 struct mptcp_pm_addr_entry *entry; 952 struct pm_nl_pernet *pernet; 953 int id = cb->args[0]; 954 void *hdr; 955 956 pernet = net_generic(net, pm_nl_pernet_id); 957 958 spin_lock_bh(&pernet->lock); 959 list_for_each_entry(entry, &pernet->local_addr_list, list) { 960 if (entry->addr.id <= id) 961 continue; 962 963 hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, 964 cb->nlh->nlmsg_seq, &mptcp_genl_family, 965 NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); 966 if (!hdr) 967 break; 968 969 if (mptcp_nl_fill_addr(msg, entry) < 0) { 970 genlmsg_cancel(msg, hdr); 971 break; 972 } 973 974 id = entry->addr.id; 975 genlmsg_end(msg, hdr); 976 } 977 spin_unlock_bh(&pernet->lock); 978 979 cb->args[0] = id; 980 return msg->len; 981} 982 983static int parse_limit(struct genl_info *info, int id, unsigned int *limit) 984{ 985 struct nlattr *attr = info->attrs[id]; 986 987 if (!attr) 988 return 0; 989 990 *limit = nla_get_u32(attr); 991 if (*limit > MPTCP_PM_ADDR_MAX) { 992 GENL_SET_ERR_MSG(info, "limit greater than maximum"); 993 return -EINVAL; 994 } 995 return 0; 996} 997 998static int 999mptcp_nl_cmd_set_limits(struct sk_buff *skb, struct genl_info *info) 1000{ 1001 struct pm_nl_pernet *pernet = genl_info_pm_nl(info); 1002 unsigned int rcv_addrs, subflows; 1003 int ret; 1004 1005 spin_lock_bh(&pernet->lock); 1006 rcv_addrs = pernet->add_addr_accept_max; 1007 ret = parse_limit(info, MPTCP_PM_ATTR_RCV_ADD_ADDRS, &rcv_addrs); 1008 if (ret) 1009 goto unlock; 1010 1011 subflows = pernet->subflows_max; 1012 ret = parse_limit(info, MPTCP_PM_ATTR_SUBFLOWS, &subflows); 1013 if (ret) 1014 goto unlock; 1015 1016 WRITE_ONCE(pernet->add_addr_accept_max, rcv_addrs); 1017 WRITE_ONCE(pernet->subflows_max, subflows); 1018 1019unlock: 1020 spin_unlock_bh(&pernet->lock); 1021 return ret; 1022} 1023 1024static int 1025mptcp_nl_cmd_get_limits(struct sk_buff *skb, struct genl_info *info) 1026{ 1027 struct pm_nl_pernet *pernet = genl_info_pm_nl(info); 1028 struct sk_buff *msg; 1029 void *reply; 1030 1031 msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); 1032 if (!msg) 1033 return -ENOMEM; 1034 1035 reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0, 1036 MPTCP_PM_CMD_GET_LIMITS); 1037 if (!reply) 1038 goto fail; 1039 1040 if (nla_put_u32(msg, MPTCP_PM_ATTR_RCV_ADD_ADDRS, 1041 READ_ONCE(pernet->add_addr_accept_max))) 1042 goto fail; 1043 1044 if (nla_put_u32(msg, MPTCP_PM_ATTR_SUBFLOWS, 1045 READ_ONCE(pernet->subflows_max))) 1046 goto fail; 1047 1048 genlmsg_end(msg, reply); 1049 return genlmsg_reply(msg, info); 1050 1051fail: 1052 GENL_SET_ERR_MSG(info, "not enough space in Netlink message"); 1053 nlmsg_free(msg); 1054 return -EMSGSIZE; 1055} 1056 1057static const struct genl_small_ops mptcp_pm_ops[] = { 1058 { 1059 .cmd = MPTCP_PM_CMD_ADD_ADDR, 1060 .doit = mptcp_nl_cmd_add_addr, 1061 .flags = GENL_ADMIN_PERM, 1062 }, 1063 { 1064 .cmd = MPTCP_PM_CMD_DEL_ADDR, 1065 .doit = mptcp_nl_cmd_del_addr, 1066 .flags = GENL_ADMIN_PERM, 1067 }, 1068 { 1069 .cmd = MPTCP_PM_CMD_FLUSH_ADDRS, 1070 .doit = mptcp_nl_cmd_flush_addrs, 1071 .flags = GENL_ADMIN_PERM, 1072 }, 1073 { 1074 .cmd = MPTCP_PM_CMD_GET_ADDR, 1075 .doit = mptcp_nl_cmd_get_addr, 1076 .dumpit = mptcp_nl_cmd_dump_addrs, 1077 }, 1078 { 1079 .cmd = MPTCP_PM_CMD_SET_LIMITS, 1080 .doit = mptcp_nl_cmd_set_limits, 1081 .flags = GENL_ADMIN_PERM, 1082 }, 1083 { 1084 .cmd = MPTCP_PM_CMD_GET_LIMITS, 1085 .doit = mptcp_nl_cmd_get_limits, 1086 }, 1087}; 1088 1089static struct genl_family mptcp_genl_family __ro_after_init = { 1090 .name = MPTCP_PM_NAME, 1091 .version = MPTCP_PM_VER, 1092 .maxattr = MPTCP_PM_ATTR_MAX, 1093 .policy = mptcp_pm_policy, 1094 .netnsok = true, 1095 .module = THIS_MODULE, 1096 .small_ops = mptcp_pm_ops, 1097 .n_small_ops = ARRAY_SIZE(mptcp_pm_ops), 1098 .mcgrps = mptcp_pm_mcgrps, 1099 .n_mcgrps = ARRAY_SIZE(mptcp_pm_mcgrps), 1100}; 1101 1102static int __net_init pm_nl_init_net(struct net *net) 1103{ 1104 struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id); 1105 1106 INIT_LIST_HEAD_RCU(&pernet->local_addr_list); 1107 __reset_counters(pernet); 1108 pernet->next_id = 1; 1109 spin_lock_init(&pernet->lock); 1110 return 0; 1111} 1112 1113static void __net_exit pm_nl_exit_net(struct list_head *net_list) 1114{ 1115 struct net *net; 1116 1117 list_for_each_entry(net, net_list, exit_list) { 1118 /* net is removed from namespace list, can't race with 1119 * other modifiers 1120 */ 1121 __flush_addrs(net_generic(net, pm_nl_pernet_id)); 1122 } 1123} 1124 1125static struct pernet_operations mptcp_pm_pernet_ops = { 1126 .init = pm_nl_init_net, 1127 .exit_batch = pm_nl_exit_net, 1128 .id = &pm_nl_pernet_id, 1129 .size = sizeof(struct pm_nl_pernet), 1130}; 1131 1132void __init mptcp_pm_nl_init(void) 1133{ 1134 if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0) 1135 panic("Failed to register MPTCP PM pernet subsystem.\n"); 1136 1137 if (genl_register_family(&mptcp_genl_family)) 1138 panic("Failed to register MPTCP PM netlink family\n"); 1139} 1140