| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2003-2013 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the hash:net,port type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/ip.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/random.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/pfxlen.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_getport.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 /* 1 SCTP and UDPLITE support added */ /* 2 Range as input support for IPv4 added */ /* 3 nomatch flag support added */ /* 4 Counters support added */ /* 5 Comments support added */ /* 6 Forceadd support added */ /* 7 skbinfo support added */ #define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("hash:net,port", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:net,port"); /* Type specific function prefix */ #define HTYPE hash_netport #define IP_SET_HASH_WITH_PROTO #define IP_SET_HASH_WITH_NETS /* We squeeze the "nomatch" flag into cidr: we don't support cidr == 0 * However this way we have to store internally cidr - 1, * dancing back and forth. */ #define IP_SET_HASH_WITH_NETS_PACKED /* IPv4 variant */ /* Member elements */ struct hash_netport4_elem { __be32 ip; __be16 port; u8 proto; u8 cidr:7; u8 nomatch:1; }; /* Common functions */ static bool hash_netport4_data_equal(const struct hash_netport4_elem *ip1, const struct hash_netport4_elem *ip2, u32 *multi) { return ip1->ip == ip2->ip && ip1->port == ip2->port && ip1->proto == ip2->proto && ip1->cidr == ip2->cidr; } static int hash_netport4_do_data_match(const struct hash_netport4_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_netport4_data_set_flags(struct hash_netport4_elem *elem, u32 flags) { elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH); } static void hash_netport4_data_reset_flags(struct hash_netport4_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_netport4_data_netmask(struct hash_netport4_elem *elem, u8 cidr) { elem->ip &= ip_set_netmask(cidr); elem->cidr = cidr - 1; } static bool hash_netport4_data_list(struct sk_buff *skb, const struct hash_netport4_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr4(skb, IPSET_ATTR_IP, data->ip) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_netport4_data_next(struct hash_netport4_elem *next, const struct hash_netport4_elem *d) { next->ip = d->ip; next->port = d->port; } #define MTYPE hash_netport4 #define HOST_MASK 32 #include "ip_set_hash_gen.h" static int hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (adt == IPSET_TEST) e.cidr = HOST_MASK - 1; if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); e.ip &= ip_set_netmask(e.cidr + 1); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct hash_netport4 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to, p = 0, ip = 0, ip_to = 0, i = 0; bool with_ports = false; u8 cidr; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; e.cidr = cidr - 1; } e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMP)) e.port = 0; with_ports = with_ports && tb[IPSET_ATTR_PORT_TO]; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) { e.ip = htonl(ip & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } port = port_to = ntohs(e.port); if (tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port_to < port) swap(port, port_to); } if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) return ret; if (ip_to < ip) swap(ip, ip_to); if (ip + UINT_MAX == ip_to) return -IPSET_ERR_HASH_RANGE; } else { ip_set_mask_from_to(ip, ip_to, e.cidr + 1); } if (retried) { ip = ntohl(h->next.ip); p = ntohs(h->next.port); } else { p = port; } do { e.ip = htonl(ip); ip = ip_set_range_to_cidr(ip, ip_to, &cidr); e.cidr = cidr - 1; for (; p <= port_to; p++, i++) { e.port = htons(p); if (i > IPSET_MAX_RANGE) { hash_netport4_data_next(&h->next, &e); return -ERANGE; } ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } p = port; } while (ip++ < ip_to); return ret; } /* IPv6 variant */ struct hash_netport6_elem { union nf_inet_addr ip; __be16 port; u8 proto; u8 cidr:7; u8 nomatch:1; }; /* Common functions */ static bool hash_netport6_data_equal(const struct hash_netport6_elem *ip1, const struct hash_netport6_elem *ip2, u32 *multi) { return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6) && ip1->port == ip2->port && ip1->proto == ip2->proto && ip1->cidr == ip2->cidr; } static int hash_netport6_do_data_match(const struct hash_netport6_elem *elem) { return elem->nomatch ? -ENOTEMPTY : 1; } static void hash_netport6_data_set_flags(struct hash_netport6_elem *elem, u32 flags) { elem->nomatch = !!((flags >> 16) & IPSET_FLAG_NOMATCH); } static void hash_netport6_data_reset_flags(struct hash_netport6_elem *elem, u8 *flags) { swap(*flags, elem->nomatch); } static void hash_netport6_data_netmask(struct hash_netport6_elem *elem, u8 cidr) { ip6_netmask(&elem->ip, cidr); elem->cidr = cidr - 1; } static bool hash_netport6_data_list(struct sk_buff *skb, const struct hash_netport6_elem *data) { u32 flags = data->nomatch ? IPSET_FLAG_NOMATCH : 0; if (nla_put_ipaddr6(skb, IPSET_ATTR_IP, &data->ip.in6) || nla_put_net16(skb, IPSET_ATTR_PORT, data->port) || nla_put_u8(skb, IPSET_ATTR_CIDR, data->cidr + 1) || nla_put_u8(skb, IPSET_ATTR_PROTO, data->proto) || (flags && nla_put_net32(skb, IPSET_ATTR_CADT_FLAGS, htonl(flags)))) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_netport6_data_next(struct hash_netport6_elem *next, const struct hash_netport6_elem *d) { next->port = d->port; } #undef MTYPE #undef HOST_MASK #define MTYPE hash_netport6 #define HOST_MASK 128 #define IP_SET_EMIT_CREATE #include "ip_set_hash_gen.h" static int hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { const struct hash_netport6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem e = { .cidr = INIT_CIDR(h->nets[0].cidr[0], HOST_MASK), }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (adt == IPSET_TEST) e.cidr = HOST_MASK - 1; if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); ip6_netmask(&e.ip, e.cidr + 1); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct hash_netport6 *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem e = { .cidr = HOST_MASK - 1 }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); u32 port, port_to; bool with_ports = false; u8 cidr; int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) || !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) return -IPSET_ERR_PROTOCOL; if (unlikely(tb[IPSET_ATTR_IP_TO])) return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &e.ip); if (ret) return ret; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; if (tb[IPSET_ATTR_CIDR]) { cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); if (!cidr || cidr > HOST_MASK) return -IPSET_ERR_INVALID_CIDR; e.cidr = cidr - 1; } ip6_netmask(&e.ip, e.cidr + 1); e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { e.proto = nla_get_u8(tb[IPSET_ATTR_PROTO]); with_ports = ip_set_proto_with_ports(e.proto); if (e.proto == 0) return -IPSET_ERR_INVALID_PROTO; } else { return -IPSET_ERR_MISSING_PROTO; } if (!(with_ports || e.proto == IPPROTO_ICMPV6)) e.port = 0; if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); if (cadt_flags & IPSET_FLAG_NOMATCH) flags |= (IPSET_FLAG_NOMATCH << 16); } if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } port = ntohs(e.port); port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); if (retried) port = ntohs(h->next.port); for (; port <= port_to; port++) { e.port = htons(port); ret = adtfn(set, &e, &ext, &ext, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; ret = 0; } return ret; } static struct ip_set_type hash_netport_type __read_mostly = { .name = "hash:net,port", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_NOMATCH, .dimension = IPSET_DIM_TWO, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_netport_init(void) { return ip_set_type_register(&hash_netport_type); } static void __exit hash_netport_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_netport_type); } module_init(hash_netport_init); module_exit(hash_netport_fini); |
| 2 2 2 1 1 1 1 1 1 4 1 1 1 1 1 1 1 1 1 1 1 1 1 4 1 1 1 1 2 2 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016 Mellanox Technologies. All rights reserved. * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com> */ #include "devl_internal.h" struct devlink_region { struct devlink *devlink; struct devlink_port *port; struct list_head list; union { const struct devlink_region_ops *ops; const struct devlink_port_region_ops *port_ops; }; struct mutex snapshot_lock; /* protects snapshot_list, * max_snapshots and cur_snapshots * consistency. */ struct list_head snapshot_list; u32 max_snapshots; u32 cur_snapshots; u64 size; }; struct devlink_snapshot { struct list_head list; struct devlink_region *region; u8 *data; u32 id; }; static struct devlink_region * devlink_region_get_by_name(struct devlink *devlink, const char *region_name) { struct devlink_region *region; list_for_each_entry(region, &devlink->region_list, list) if (!strcmp(region->ops->name, region_name)) return region; return NULL; } static struct devlink_region * devlink_port_region_get_by_name(struct devlink_port *port, const char *region_name) { struct devlink_region *region; list_for_each_entry(region, &port->region_list, list) if (!strcmp(region->ops->name, region_name)) return region; return NULL; } static struct devlink_snapshot * devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) { struct devlink_snapshot *snapshot; list_for_each_entry(snapshot, ®ion->snapshot_list, list) if (snapshot->id == id) return snapshot; return NULL; } static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_snapshot *snapshot) { struct nlattr *snap_attr; int err; snap_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOT); if (!snap_attr) return -EINVAL; err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); if (err) goto nla_put_failure; nla_nest_end(msg, snap_attr); return 0; nla_put_failure: nla_nest_cancel(msg, snap_attr); return err; } static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_region *region) { struct devlink_snapshot *snapshot; struct nlattr *snapshots_attr; int err; snapshots_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_SNAPSHOTS); if (!snapshots_attr) return -EINVAL; list_for_each_entry(snapshot, ®ion->snapshot_list, list) { err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot); if (err) goto nla_put_failure; } nla_nest_end(msg, snapshots_attr); return 0; nla_put_failure: nla_nest_cancel(msg, snapshots_attr); return err; } static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags, struct devlink_region *region) { void *hdr; int err; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); if (!hdr) return -EMSGSIZE; err = devlink_nl_put_handle(msg, devlink); if (err) goto nla_put_failure; if (region->port) { err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto nla_put_failure; } err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) goto nla_put_failure; err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE, region->size, DEVLINK_ATTR_PAD); if (err) goto nla_put_failure; err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, region->max_snapshots); if (err) goto nla_put_failure; err = devlink_nl_region_snapshots_id_put(msg, devlink, region); if (err) goto nla_put_failure; genlmsg_end(msg, hdr); return 0; nla_put_failure: genlmsg_cancel(msg, hdr); return err; } static struct sk_buff * devlink_nl_region_notify_build(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd, u32 portid, u32 seq) { struct devlink *devlink = region->devlink; struct sk_buff *msg; void *hdr; int err; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return ERR_PTR(-ENOMEM); hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, 0, cmd); if (!hdr) { err = -EMSGSIZE; goto out_free_msg; } err = devlink_nl_put_handle(msg, devlink); if (err) goto out_cancel_msg; if (region->port) { err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto out_cancel_msg; } err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) goto out_cancel_msg; if (snapshot) { err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id); if (err) goto out_cancel_msg; } else { err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE, region->size, DEVLINK_ATTR_PAD); if (err) goto out_cancel_msg; } genlmsg_end(msg, hdr); return msg; out_cancel_msg: genlmsg_cancel(msg, hdr); out_free_msg: nlmsg_free(msg); return ERR_PTR(err); } static void devlink_nl_region_notify(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd) { struct devlink *devlink = region->devlink; struct sk_buff *msg; WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL); if (!__devl_is_registered(devlink) || !devlink_nl_notify_need(devlink)) return; msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0); if (IS_ERR(msg)) return; devlink_nl_notify_send(devlink, msg); } void devlink_regions_notify_register(struct devlink *devlink) { struct devlink_region *region; list_for_each_entry(region, &devlink->region_list, list) devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); } void devlink_regions_notify_unregister(struct devlink *devlink) { struct devlink_region *region; list_for_each_entry_reverse(region, &devlink->region_list, list) devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); } /** * __devlink_snapshot_id_increment - Increment number of snapshots using an id * @devlink: devlink instance * @id: the snapshot id * * Track when a new snapshot begins using an id. Load the count for the * given id from the snapshot xarray, increment it, and store it back. * * Called when a new snapshot is created with the given id. * * The id *must* have been previously allocated by * devlink_region_snapshot_id_get(). * * Returns 0 on success, or an error on failure. */ static int __devlink_snapshot_id_increment(struct devlink *devlink, u32 id) { unsigned long count; void *p; int err; xa_lock(&devlink->snapshot_ids); p = xa_load(&devlink->snapshot_ids, id); if (WARN_ON(!p)) { err = -EINVAL; goto unlock; } if (WARN_ON(!xa_is_value(p))) { err = -EINVAL; goto unlock; } count = xa_to_value(p); count++; err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), GFP_ATOMIC)); unlock: xa_unlock(&devlink->snapshot_ids); return err; } /** * __devlink_snapshot_id_decrement - Decrease number of snapshots using an id * @devlink: devlink instance * @id: the snapshot id * * Track when a snapshot is deleted and stops using an id. Load the count * for the given id from the snapshot xarray, decrement it, and store it * back. * * If the count reaches zero, erase this id from the xarray, freeing it * up for future re-use by devlink_region_snapshot_id_get(). * * Called when a snapshot using the given id is deleted, and when the * initial allocator of the id is finished using it. */ static void __devlink_snapshot_id_decrement(struct devlink *devlink, u32 id) { unsigned long count; void *p; xa_lock(&devlink->snapshot_ids); p = xa_load(&devlink->snapshot_ids, id); if (WARN_ON(!p)) goto unlock; if (WARN_ON(!xa_is_value(p))) goto unlock; count = xa_to_value(p); if (count > 1) { count--; __xa_store(&devlink->snapshot_ids, id, xa_mk_value(count), GFP_ATOMIC); } else { /* If this was the last user, we can erase this id */ __xa_erase(&devlink->snapshot_ids, id); } unlock: xa_unlock(&devlink->snapshot_ids); } /** * __devlink_snapshot_id_insert - Insert a specific snapshot ID * @devlink: devlink instance * @id: the snapshot id * * Mark the given snapshot id as used by inserting a zero value into the * snapshot xarray. * * This must be called while holding the devlink instance lock. Unlike * devlink_snapshot_id_get, the initial reference count is zero, not one. * It is expected that the id will immediately be used before * releasing the devlink instance lock. * * Returns zero on success, or an error code if the snapshot id could not * be inserted. */ static int __devlink_snapshot_id_insert(struct devlink *devlink, u32 id) { int err; xa_lock(&devlink->snapshot_ids); if (xa_load(&devlink->snapshot_ids, id)) { xa_unlock(&devlink->snapshot_ids); return -EEXIST; } err = xa_err(__xa_store(&devlink->snapshot_ids, id, xa_mk_value(0), GFP_ATOMIC)); xa_unlock(&devlink->snapshot_ids); return err; } /** * __devlink_region_snapshot_id_get - get snapshot ID * @devlink: devlink instance * @id: storage to return snapshot id * * Allocates a new snapshot id. Returns zero on success, or a negative * error on failure. Must be called while holding the devlink instance * lock. * * Snapshot IDs are tracked using an xarray which stores the number of * users of the snapshot id. * * Note that the caller of this function counts as a 'user', in order to * avoid race conditions. The caller must release its hold on the * snapshot by using devlink_region_snapshot_id_put. */ static int __devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) { return xa_alloc(&devlink->snapshot_ids, id, xa_mk_value(1), xa_limit_32b, GFP_KERNEL); } /** * __devlink_region_snapshot_create - create a new snapshot * This will add a new snapshot of a region. The snapshot * will be stored on the region struct and can be accessed * from devlink. This is useful for future analyses of snapshots. * Multiple snapshots can be created on a region. * The @snapshot_id should be obtained using the getter function. * * Must be called only while holding the region snapshot lock. * * @region: devlink region of the snapshot * @data: snapshot data * @snapshot_id: snapshot id to be created */ static int __devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id) { struct devlink *devlink = region->devlink; struct devlink_snapshot *snapshot; int err; lockdep_assert_held(®ion->snapshot_lock); /* check if region can hold one more snapshot */ if (region->cur_snapshots == region->max_snapshots) return -ENOSPC; if (devlink_region_snapshot_get_by_id(region, snapshot_id)) return -EEXIST; snapshot = kzalloc(sizeof(*snapshot), GFP_KERNEL); if (!snapshot) return -ENOMEM; err = __devlink_snapshot_id_increment(devlink, snapshot_id); if (err) goto err_snapshot_id_increment; snapshot->id = snapshot_id; snapshot->region = region; snapshot->data = data; list_add_tail(&snapshot->list, ®ion->snapshot_list); region->cur_snapshots++; devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW); return 0; err_snapshot_id_increment: kfree(snapshot); return err; } static void devlink_region_snapshot_del(struct devlink_region *region, struct devlink_snapshot *snapshot) { struct devlink *devlink = region->devlink; lockdep_assert_held(®ion->snapshot_lock); devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL); region->cur_snapshots--; list_del(&snapshot->list); region->ops->destructor(snapshot->data); __devlink_snapshot_id_decrement(devlink, snapshot->id); kfree(snapshot); } int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; struct sk_buff *msg; unsigned int index; int err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) return -EINVAL; if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, info->snd_portid, info->snd_seq, 0, region); if (err) { nlmsg_free(msg); return err; } return genlmsg_reply(msg, info); } static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg, struct netlink_callback *cb, struct devlink_port *port, int *idx, int start, int flags) { struct devlink_region *region; int err = 0; list_for_each_entry(region, &port->region_list, list) { if (*idx < start) { (*idx)++; continue; } err = devlink_nl_region_fill(msg, port->devlink, DEVLINK_CMD_REGION_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, region); if (err) goto out; (*idx)++; } out: return err; } static int devlink_nl_region_get_dump_one(struct sk_buff *msg, struct devlink *devlink, struct netlink_callback *cb, int flags) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_region *region; struct devlink_port *port; unsigned long port_index; int idx = 0; int err; list_for_each_entry(region, &devlink->region_list, list) { if (idx < state->idx) { idx++; continue; } err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, region); if (err) { state->idx = idx; return err; } idx++; } xa_for_each(&devlink->ports, port_index, port) { err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, &idx, state->idx, flags); if (err) { state->idx = idx; return err; } } return 0; } int devlink_nl_region_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { return devlink_nl_dumpit(skb, cb, devlink_nl_region_get_dump_one); } int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; unsigned int index; u32 snapshot_id; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME) || GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_SNAPSHOT_ID)) return -EINVAL; region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) return -EINVAL; mutex_lock(®ion->snapshot_lock); snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (!snapshot) { mutex_unlock(®ion->snapshot_lock); return -EINVAL; } devlink_region_snapshot_del(region, snapshot); mutex_unlock(®ion->snapshot_lock); return 0; } int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; struct devlink_port *port = NULL; struct nlattr *snapshot_id_attr; struct devlink_region *region; const char *region_name; unsigned int index; u32 snapshot_id; u8 *data; int err; if (GENL_REQ_ATTR_CHECK(info, DEVLINK_ATTR_REGION_NAME)) { NL_SET_ERR_MSG(info->extack, "No region name provided"); return -EINVAL; } region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) return -ENODEV; } if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) { NL_SET_ERR_MSG(info->extack, "The requested region does not exist"); return -EINVAL; } if (!region->ops->snapshot) { NL_SET_ERR_MSG(info->extack, "The requested region does not support taking an immediate snapshot"); return -EOPNOTSUPP; } mutex_lock(®ion->snapshot_lock); if (region->cur_snapshots == region->max_snapshots) { NL_SET_ERR_MSG(info->extack, "The region has reached the maximum number of stored snapshots"); err = -ENOSPC; goto unlock; } snapshot_id_attr = info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; if (snapshot_id_attr) { snapshot_id = nla_get_u32(snapshot_id_attr); if (devlink_region_snapshot_get_by_id(region, snapshot_id)) { NL_SET_ERR_MSG(info->extack, "The requested snapshot id is already in use"); err = -EEXIST; goto unlock; } err = __devlink_snapshot_id_insert(devlink, snapshot_id); if (err) goto unlock; } else { err = __devlink_region_snapshot_id_get(devlink, &snapshot_id); if (err) { NL_SET_ERR_MSG(info->extack, "Failed to allocate a new snapshot id"); goto unlock; } } if (port) err = region->port_ops->snapshot(port, region->port_ops, info->extack, &data); else err = region->ops->snapshot(devlink, region->ops, info->extack, &data); if (err) goto err_snapshot_capture; err = __devlink_region_snapshot_create(region, data, snapshot_id); if (err) goto err_snapshot_create; if (!snapshot_id_attr) { struct sk_buff *msg; snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (WARN_ON(!snapshot)) { err = -EINVAL; goto unlock; } msg = devlink_nl_region_notify_build(region, snapshot, DEVLINK_CMD_REGION_NEW, info->snd_portid, info->snd_seq); err = PTR_ERR_OR_ZERO(msg); if (err) goto err_notify; err = genlmsg_reply(msg, info); if (err) goto err_notify; } mutex_unlock(®ion->snapshot_lock); return 0; err_snapshot_create: region->ops->destructor(data); err_snapshot_capture: __devlink_snapshot_id_decrement(devlink, snapshot_id); mutex_unlock(®ion->snapshot_lock); return err; err_notify: devlink_region_snapshot_del(region, snapshot); unlock: mutex_unlock(®ion->snapshot_lock); return err; } static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg, u8 *chunk, u32 chunk_size, u64 addr) { struct nlattr *chunk_attr; int err; chunk_attr = nla_nest_start_noflag(msg, DEVLINK_ATTR_REGION_CHUNK); if (!chunk_attr) return -EINVAL; err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk); if (err) goto nla_put_failure; err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr, DEVLINK_ATTR_PAD); if (err) goto nla_put_failure; nla_nest_end(msg, chunk_attr); return 0; nla_put_failure: nla_nest_cancel(msg, chunk_attr); return err; } #define DEVLINK_REGION_READ_CHUNK_SIZE 256 typedef int devlink_chunk_fill_t(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack); static int devlink_nl_region_read_fill(struct sk_buff *skb, devlink_chunk_fill_t *cb, void *cb_priv, u64 start_offset, u64 end_offset, u64 *new_offset, struct netlink_ext_ack *extack) { u64 curr_offset = start_offset; int err = 0; u8 *data; /* Allocate and re-use a single buffer */ data = kmalloc(DEVLINK_REGION_READ_CHUNK_SIZE, GFP_KERNEL); if (!data) return -ENOMEM; *new_offset = start_offset; while (curr_offset < end_offset) { u32 data_size; data_size = min_t(u32, end_offset - curr_offset, DEVLINK_REGION_READ_CHUNK_SIZE); err = cb(cb_priv, data, data_size, curr_offset, extack); if (err) break; err = devlink_nl_cmd_region_read_chunk_fill(skb, data, data_size, curr_offset); if (err) break; curr_offset += data_size; } *new_offset = curr_offset; kfree(data); return err; } static int devlink_region_snapshot_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack __always_unused *extack) { struct devlink_snapshot *snapshot = cb_priv; memcpy(chunk, &snapshot->data[curr_offset], chunk_size); return 0; } static int devlink_region_port_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack) { struct devlink_region *region = cb_priv; return region->port_ops->read(region->port, region->port_ops, extack, curr_offset, chunk_size, chunk); } static int devlink_region_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, u64 curr_offset, struct netlink_ext_ack *extack) { struct devlink_region *region = cb_priv; return region->ops->read(region->devlink, region->ops, extack, curr_offset, chunk_size, chunk); } int devlink_nl_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct nlattr *chunks_attr, *region_attr, *snapshot_attr; u64 ret_offset, start_offset, end_offset = U64_MAX; struct nlattr **attrs = info->info.attrs; struct devlink_port *port = NULL; devlink_chunk_fill_t *region_cb; struct devlink_region *region; const char *region_name; struct devlink *devlink; unsigned int index; void *region_cb_priv; void *hdr; int err; start_offset = state->start_offset; devlink = devlink_get_from_attrs_lock(sock_net(cb->skb->sk), attrs, false); if (IS_ERR(devlink)) return PTR_ERR(devlink); if (!attrs[DEVLINK_ATTR_REGION_NAME]) { NL_SET_ERR_MSG(cb->extack, "No region name provided"); err = -EINVAL; goto out_unlock; } if (attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(attrs[DEVLINK_ATTR_PORT_INDEX]); port = devlink_port_get_by_index(devlink, index); if (!port) { err = -ENODEV; goto out_unlock; } } region_attr = attrs[DEVLINK_ATTR_REGION_NAME]; region_name = nla_data(region_attr); if (port) region = devlink_port_region_get_by_name(port, region_name); else region = devlink_region_get_by_name(devlink, region_name); if (!region) { NL_SET_ERR_MSG_ATTR(cb->extack, region_attr, "Requested region does not exist"); err = -EINVAL; goto out_unlock; } snapshot_attr = attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; if (!snapshot_attr) { if (!nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { NL_SET_ERR_MSG(cb->extack, "No snapshot id provided"); err = -EINVAL; goto out_unlock; } if (!region->ops->read) { NL_SET_ERR_MSG(cb->extack, "Requested region does not support direct read"); err = -EOPNOTSUPP; goto out_unlock; } if (port) region_cb = &devlink_region_port_direct_fill; else region_cb = &devlink_region_direct_fill; region_cb_priv = region; } else { struct devlink_snapshot *snapshot; u32 snapshot_id; if (nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Direct region read does not use snapshot"); err = -EINVAL; goto out_unlock; } snapshot_id = nla_get_u32(snapshot_attr); snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); if (!snapshot) { NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Requested snapshot does not exist"); err = -EINVAL; goto out_unlock; } region_cb = &devlink_region_snapshot_fill; region_cb_priv = snapshot; } if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) { if (!start_offset) start_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); } if (end_offset > region->size) end_offset = region->size; /* return 0 if there is no further data to read */ if (start_offset == end_offset) { err = 0; goto out_unlock; } hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, DEVLINK_CMD_REGION_READ); if (!hdr) { err = -EMSGSIZE; goto out_unlock; } err = devlink_nl_put_handle(skb, devlink); if (err) goto nla_put_failure; if (region->port) { err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX, region->port->index); if (err) goto nla_put_failure; } err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name); if (err) goto nla_put_failure; chunks_attr = nla_nest_start_noflag(skb, DEVLINK_ATTR_REGION_CHUNKS); if (!chunks_attr) { err = -EMSGSIZE; goto nla_put_failure; } err = devlink_nl_region_read_fill(skb, region_cb, region_cb_priv, start_offset, end_offset, &ret_offset, cb->extack); if (err && err != -EMSGSIZE) goto nla_put_failure; /* Check if there was any progress done to prevent infinite loop */ if (ret_offset == start_offset) { err = -EINVAL; goto nla_put_failure; } state->start_offset = ret_offset; nla_nest_end(skb, chunks_attr); genlmsg_end(skb, hdr); devl_unlock(devlink); devlink_put(devlink); return skb->len; nla_put_failure: genlmsg_cancel(skb, hdr); out_unlock: devl_unlock(devlink); devlink_put(devlink); return err; } /** * devl_region_create - create a new address region * * @devlink: devlink * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region */ struct devlink_region *devl_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink_region *region; devl_assert_locked(devlink); if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) return ERR_PTR(-EINVAL); if (devlink_region_get_by_name(devlink, ops->name)) return ERR_PTR(-EEXIST); region = kzalloc(sizeof(*region), GFP_KERNEL); if (!region) return ERR_PTR(-ENOMEM); region->devlink = devlink; region->max_snapshots = region_max_snapshots; region->ops = ops; region->size = region_size; INIT_LIST_HEAD(®ion->snapshot_list); mutex_init(®ion->snapshot_lock); list_add_tail(®ion->list, &devlink->region_list); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); return region; } EXPORT_SYMBOL_GPL(devl_region_create); /** * devlink_region_create - create a new address region * * @devlink: devlink * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region * * Context: Takes and release devlink->lock <mutex>. */ struct devlink_region * devlink_region_create(struct devlink *devlink, const struct devlink_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink_region *region; devl_lock(devlink); region = devl_region_create(devlink, ops, region_max_snapshots, region_size); devl_unlock(devlink); return region; } EXPORT_SYMBOL_GPL(devlink_region_create); /** * devlink_port_region_create - create a new address region for a port * * @port: devlink port * @ops: region operations and name * @region_max_snapshots: Maximum supported number of snapshots for region * @region_size: size of region * * Context: Takes and release devlink->lock <mutex>. */ struct devlink_region * devlink_port_region_create(struct devlink_port *port, const struct devlink_port_region_ops *ops, u32 region_max_snapshots, u64 region_size) { struct devlink *devlink = port->devlink; struct devlink_region *region; int err = 0; ASSERT_DEVLINK_PORT_INITIALIZED(port); if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) return ERR_PTR(-EINVAL); devl_lock(devlink); if (devlink_port_region_get_by_name(port, ops->name)) { err = -EEXIST; goto unlock; } region = kzalloc(sizeof(*region), GFP_KERNEL); if (!region) { err = -ENOMEM; goto unlock; } region->devlink = devlink; region->port = port; region->max_snapshots = region_max_snapshots; region->port_ops = ops; region->size = region_size; INIT_LIST_HEAD(®ion->snapshot_list); mutex_init(®ion->snapshot_lock); list_add_tail(®ion->list, &port->region_list); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); devl_unlock(devlink); return region; unlock: devl_unlock(devlink); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(devlink_port_region_create); /** * devl_region_destroy - destroy address region * * @region: devlink region to destroy */ void devl_region_destroy(struct devlink_region *region) { struct devlink *devlink = region->devlink; struct devlink_snapshot *snapshot, *ts; devl_assert_locked(devlink); /* Free all snapshots of region */ mutex_lock(®ion->snapshot_lock); list_for_each_entry_safe(snapshot, ts, ®ion->snapshot_list, list) devlink_region_snapshot_del(region, snapshot); mutex_unlock(®ion->snapshot_lock); list_del(®ion->list); mutex_destroy(®ion->snapshot_lock); devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); kfree(region); } EXPORT_SYMBOL_GPL(devl_region_destroy); /** * devlink_region_destroy - destroy address region * * @region: devlink region to destroy * * Context: Takes and release devlink->lock <mutex>. */ void devlink_region_destroy(struct devlink_region *region) { struct devlink *devlink = region->devlink; devl_lock(devlink); devl_region_destroy(region); devl_unlock(devlink); } EXPORT_SYMBOL_GPL(devlink_region_destroy); /** * devlink_region_snapshot_id_get - get snapshot ID * * This callback should be called when adding a new snapshot, * Driver should use the same id for multiple snapshots taken * on multiple regions at the same time/by the same trigger. * * The caller of this function must use devlink_region_snapshot_id_put * when finished creating regions using this id. * * Returns zero on success, or a negative error code on failure. * * @devlink: devlink * @id: storage to return id */ int devlink_region_snapshot_id_get(struct devlink *devlink, u32 *id) { return __devlink_region_snapshot_id_get(devlink, id); } EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get); /** * devlink_region_snapshot_id_put - put snapshot ID reference * * This should be called by a driver after finishing creating snapshots * with an id. Doing so ensures that the ID can later be released in the * event that all snapshots using it have been destroyed. * * @devlink: devlink * @id: id to release reference on */ void devlink_region_snapshot_id_put(struct devlink *devlink, u32 id) { __devlink_snapshot_id_decrement(devlink, id); } EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_put); /** * devlink_region_snapshot_create - create a new snapshot * This will add a new snapshot of a region. The snapshot * will be stored on the region struct and can be accessed * from devlink. This is useful for future analyses of snapshots. * Multiple snapshots can be created on a region. * The @snapshot_id should be obtained using the getter function. * * @region: devlink region of the snapshot * @data: snapshot data * @snapshot_id: snapshot id to be created */ int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id) { int err; mutex_lock(®ion->snapshot_lock); err = __devlink_region_snapshot_create(region, data, snapshot_id); mutex_unlock(®ion->snapshot_lock); return err; } EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); |
| 6 6 6 6 6 6 6 6 18 5 18 5 17 18 18 5 18 18 5 18 18 6 6 6 6 6 4 6 6 43 41 7 6 6 1 5 37 37 1 1 23 16 18 18 24 23 18 6 6 1 5 5 6 1 5 5 6 4 4 4 15 16 9 7 6 5 4 4 7 7 7 6 1 4 1 1 1 1 1 1 1 2 1 1 2 1 1 14 14 13 6 6 6 6 6 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (c) 2000-2001, 2010, Code Aurora Forum. All rights reserved. Copyright 2023-2024 NXP Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth HCI connection handling. */ #include <linux/export.h> #include <linux/debugfs.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> #include <net/bluetooth/iso.h> #include <net/bluetooth/mgmt.h> #include "smp.h" #include "eir.h" struct sco_param { u16 pkt_type; u16 max_latency; u8 retrans_effort; }; struct conn_handle_t { struct hci_conn *conn; __u16 handle; }; static const struct sco_param esco_param_cvsd[] = { { EDR_ESCO_MASK & ~ESCO_2EV3, 0x000a, 0x01 }, /* S3 */ { EDR_ESCO_MASK & ~ESCO_2EV3, 0x0007, 0x01 }, /* S2 */ { EDR_ESCO_MASK | ESCO_EV3, 0x0007, 0x01 }, /* S1 */ { EDR_ESCO_MASK | ESCO_HV3, 0xffff, 0x01 }, /* D1 */ { EDR_ESCO_MASK | ESCO_HV1, 0xffff, 0x01 }, /* D0 */ }; static const struct sco_param sco_param_cvsd[] = { { EDR_ESCO_MASK | ESCO_HV3, 0xffff, 0xff }, /* D1 */ { EDR_ESCO_MASK | ESCO_HV1, 0xffff, 0xff }, /* D0 */ }; static const struct sco_param esco_param_msbc[] = { { EDR_ESCO_MASK & ~ESCO_2EV3, 0x000d, 0x02 }, /* T2 */ { EDR_ESCO_MASK | ESCO_EV3, 0x0008, 0x02 }, /* T1 */ }; /* This function requires the caller holds hdev->lock */ void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) { struct hci_conn_params *params; struct hci_dev *hdev = conn->hdev; struct smp_irk *irk; bdaddr_t *bdaddr; u8 bdaddr_type; bdaddr = &conn->dst; bdaddr_type = conn->dst_type; /* Check if we need to convert to identity address */ irk = hci_get_irk(hdev, bdaddr, bdaddr_type); if (irk) { bdaddr = &irk->bdaddr; bdaddr_type = irk->addr_type; } params = hci_pend_le_action_lookup(&hdev->pend_le_conns, bdaddr, bdaddr_type); if (!params) return; if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); params->conn = NULL; } if (!params->explicit_connect) return; /* If the status indicates successful cancellation of * the attempt (i.e. Unknown Connection Id) there's no point of * notifying failure since we'll go back to keep trying to * connect. The only exception is explicit connect requests * where a timeout + cancel does indicate an actual failure. */ if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, status); /* The connection attempt was doing scan for new RPA, and is * in scan phase. If params are not associated with any other * autoconnect action, remove them completely. If they are, just unmark * them as waiting for connection, by clearing explicit_connect field. */ params->explicit_connect = false; hci_pend_le_list_del_init(params); switch (params->auto_connect) { case HCI_AUTO_CONN_EXPLICIT: hci_conn_params_del(hdev, bdaddr, bdaddr_type); /* return instead of break to avoid duplicate scan update */ return; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: hci_pend_le_list_add(params, &hdev->pend_le_reports); break; default: break; } hci_update_passive_scan(hdev); } static void hci_conn_cleanup(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; if (test_bit(HCI_CONN_PARAM_REMOVAL_PEND, &conn->flags)) hci_conn_params_del(conn->hdev, &conn->dst, conn->dst_type); if (test_and_clear_bit(HCI_CONN_FLUSH_KEY, &conn->flags)) hci_remove_link_key(hdev, &conn->dst); hci_chan_list_flush(conn); hci_conn_hash_del(hdev, conn); if (HCI_CONN_HANDLE_UNSET(conn->handle)) ida_free(&hdev->unset_handle_ida, conn->handle); if (conn->cleanup) conn->cleanup(conn); if (conn->type == SCO_LINK || conn->type == ESCO_LINK) { switch (conn->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_CVSD: case SCO_AIRMODE_TRANSP: if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_DISABLE_SCO); break; } } else { if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); } debugfs_remove_recursive(conn->debugfs); hci_conn_del_sysfs(conn); hci_dev_put(hdev); } int hci_disconnect(struct hci_conn *conn, __u8 reason) { BT_DBG("hcon %p", conn); /* When we are central of an established connection and it enters * the disconnect timeout, then go ahead and try to read the * current clock offset. Processing of the result is done * within the event handling and hci_clock_offset_evt function. */ if (conn->type == ACL_LINK && conn->role == HCI_ROLE_MASTER && (conn->state == BT_CONNECTED || conn->state == BT_CONFIG)) { struct hci_dev *hdev = conn->hdev; struct hci_cp_read_clock_offset clkoff_cp; clkoff_cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(hdev, HCI_OP_READ_CLOCK_OFFSET, sizeof(clkoff_cp), &clkoff_cp); } return hci_abort_conn(conn, reason); } static void hci_add_sco(struct hci_conn *conn, __u16 handle) { struct hci_dev *hdev = conn->hdev; struct hci_cp_add_sco cp; BT_DBG("hcon %p", conn); conn->state = BT_CONNECT; conn->out = true; conn->attempt++; cp.handle = cpu_to_le16(handle); cp.pkt_type = cpu_to_le16(conn->pkt_type); hci_send_cmd(hdev, HCI_OP_ADD_SCO, sizeof(cp), &cp); } static bool find_next_esco_param(struct hci_conn *conn, const struct sco_param *esco_param, int size) { if (!conn->parent) return false; for (; conn->attempt <= size; conn->attempt++) { if (lmp_esco_2m_capable(conn->parent) || (esco_param[conn->attempt - 1].pkt_type & ESCO_2EV3)) break; BT_DBG("hcon %p skipped attempt %d, eSCO 2M not supported", conn, conn->attempt); } return conn->attempt <= size; } static int configure_datapath_sync(struct hci_dev *hdev, struct bt_codec *codec) { int err; __u8 vnd_len, *vnd_data = NULL; struct hci_op_configure_data_path *cmd = NULL; /* Do not take below 2 checks as error since the 1st means user do not * want to use HFP offload mode and the 2nd means the vendor controller * do not need to send below HCI command for offload mode. */ if (!codec->data_path || !hdev->get_codec_config_data) return 0; err = hdev->get_codec_config_data(hdev, ESCO_LINK, codec, &vnd_len, &vnd_data); if (err < 0) goto error; cmd = kzalloc(sizeof(*cmd) + vnd_len, GFP_KERNEL); if (!cmd) { err = -ENOMEM; goto error; } err = hdev->get_data_path_id(hdev, &cmd->data_path_id); if (err < 0) goto error; cmd->vnd_len = vnd_len; memcpy(cmd->vnd_data, vnd_data, vnd_len); cmd->direction = 0x00; __hci_cmd_sync_status(hdev, HCI_CONFIGURE_DATA_PATH, sizeof(*cmd) + vnd_len, cmd, HCI_CMD_TIMEOUT); cmd->direction = 0x01; err = __hci_cmd_sync_status(hdev, HCI_CONFIGURE_DATA_PATH, sizeof(*cmd) + vnd_len, cmd, HCI_CMD_TIMEOUT); error: kfree(cmd); kfree(vnd_data); return err; } static int hci_enhanced_setup_sync(struct hci_dev *hdev, void *data) { struct conn_handle_t *conn_handle = data; struct hci_conn *conn = conn_handle->conn; __u16 handle = conn_handle->handle; struct hci_cp_enhanced_setup_sync_conn cp; const struct sco_param *param; kfree(conn_handle); bt_dev_dbg(hdev, "hcon %p", conn); configure_datapath_sync(hdev, &conn->codec); conn->state = BT_CONNECT; conn->out = true; conn->attempt++; memset(&cp, 0x00, sizeof(cp)); cp.handle = cpu_to_le16(handle); cp.tx_bandwidth = cpu_to_le32(0x00001f40); cp.rx_bandwidth = cpu_to_le32(0x00001f40); switch (conn->codec.id) { case BT_CODEC_MSBC: if (!find_next_esco_param(conn, esco_param_msbc, ARRAY_SIZE(esco_param_msbc))) return -EINVAL; param = &esco_param_msbc[conn->attempt - 1]; cp.tx_coding_format.id = 0x05; cp.rx_coding_format.id = 0x05; cp.tx_codec_frame_size = __cpu_to_le16(60); cp.rx_codec_frame_size = __cpu_to_le16(60); cp.in_bandwidth = __cpu_to_le32(32000); cp.out_bandwidth = __cpu_to_le32(32000); cp.in_coding_format.id = 0x04; cp.out_coding_format.id = 0x04; cp.in_coded_data_size = __cpu_to_le16(16); cp.out_coded_data_size = __cpu_to_le16(16); cp.in_pcm_data_format = 2; cp.out_pcm_data_format = 2; cp.in_pcm_sample_payload_msb_pos = 0; cp.out_pcm_sample_payload_msb_pos = 0; cp.in_data_path = conn->codec.data_path; cp.out_data_path = conn->codec.data_path; cp.in_transport_unit_size = 1; cp.out_transport_unit_size = 1; break; case BT_CODEC_TRANSPARENT: if (!find_next_esco_param(conn, esco_param_msbc, ARRAY_SIZE(esco_param_msbc))) return false; param = &esco_param_msbc[conn->attempt - 1]; cp.tx_coding_format.id = 0x03; cp.rx_coding_format.id = 0x03; cp.tx_codec_frame_size = __cpu_to_le16(60); cp.rx_codec_frame_size = __cpu_to_le16(60); cp.in_bandwidth = __cpu_to_le32(0x1f40); cp.out_bandwidth = __cpu_to_le32(0x1f40); cp.in_coding_format.id = 0x03; cp.out_coding_format.id = 0x03; cp.in_coded_data_size = __cpu_to_le16(16); cp.out_coded_data_size = __cpu_to_le16(16); cp.in_pcm_data_format = 2; cp.out_pcm_data_format = 2; cp.in_pcm_sample_payload_msb_pos = 0; cp.out_pcm_sample_payload_msb_pos = 0; cp.in_data_path = conn->codec.data_path; cp.out_data_path = conn->codec.data_path; cp.in_transport_unit_size = 1; cp.out_transport_unit_size = 1; break; case BT_CODEC_CVSD: if (conn->parent && lmp_esco_capable(conn->parent)) { if (!find_next_esco_param(conn, esco_param_cvsd, ARRAY_SIZE(esco_param_cvsd))) return -EINVAL; param = &esco_param_cvsd[conn->attempt - 1]; } else { if (conn->attempt > ARRAY_SIZE(sco_param_cvsd)) return -EINVAL; param = &sco_param_cvsd[conn->attempt - 1]; } cp.tx_coding_format.id = 2; cp.rx_coding_format.id = 2; cp.tx_codec_frame_size = __cpu_to_le16(60); cp.rx_codec_frame_size = __cpu_to_le16(60); cp.in_bandwidth = __cpu_to_le32(16000); cp.out_bandwidth = __cpu_to_le32(16000); cp.in_coding_format.id = 4; cp.out_coding_format.id = 4; cp.in_coded_data_size = __cpu_to_le16(16); cp.out_coded_data_size = __cpu_to_le16(16); cp.in_pcm_data_format = 2; cp.out_pcm_data_format = 2; cp.in_pcm_sample_payload_msb_pos = 0; cp.out_pcm_sample_payload_msb_pos = 0; cp.in_data_path = conn->codec.data_path; cp.out_data_path = conn->codec.data_path; cp.in_transport_unit_size = 16; cp.out_transport_unit_size = 16; break; default: return -EINVAL; } cp.retrans_effort = param->retrans_effort; cp.pkt_type = __cpu_to_le16(param->pkt_type); cp.max_latency = __cpu_to_le16(param->max_latency); if (hci_send_cmd(hdev, HCI_OP_ENHANCED_SETUP_SYNC_CONN, sizeof(cp), &cp) < 0) return -EIO; return 0; } static bool hci_setup_sync_conn(struct hci_conn *conn, __u16 handle) { struct hci_dev *hdev = conn->hdev; struct hci_cp_setup_sync_conn cp; const struct sco_param *param; bt_dev_dbg(hdev, "hcon %p", conn); conn->state = BT_CONNECT; conn->out = true; conn->attempt++; cp.handle = cpu_to_le16(handle); cp.tx_bandwidth = cpu_to_le32(0x00001f40); cp.rx_bandwidth = cpu_to_le32(0x00001f40); cp.voice_setting = cpu_to_le16(conn->setting); switch (conn->setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (!find_next_esco_param(conn, esco_param_msbc, ARRAY_SIZE(esco_param_msbc))) return false; param = &esco_param_msbc[conn->attempt - 1]; break; case SCO_AIRMODE_CVSD: if (conn->parent && lmp_esco_capable(conn->parent)) { if (!find_next_esco_param(conn, esco_param_cvsd, ARRAY_SIZE(esco_param_cvsd))) return false; param = &esco_param_cvsd[conn->attempt - 1]; } else { if (conn->attempt > ARRAY_SIZE(sco_param_cvsd)) return false; param = &sco_param_cvsd[conn->attempt - 1]; } break; default: return false; } cp.retrans_effort = param->retrans_effort; cp.pkt_type = __cpu_to_le16(param->pkt_type); cp.max_latency = __cpu_to_le16(param->max_latency); if (hci_send_cmd(hdev, HCI_OP_SETUP_SYNC_CONN, sizeof(cp), &cp) < 0) return false; return true; } bool hci_setup_sync(struct hci_conn *conn, __u16 handle) { int result; struct conn_handle_t *conn_handle; if (enhanced_sync_conn_capable(conn->hdev)) { conn_handle = kzalloc(sizeof(*conn_handle), GFP_KERNEL); if (!conn_handle) return false; conn_handle->conn = conn; conn_handle->handle = handle; result = hci_cmd_sync_queue(conn->hdev, hci_enhanced_setup_sync, conn_handle, NULL); if (result < 0) kfree(conn_handle); return result == 0; } return hci_setup_sync_conn(conn, handle); } u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency, u16 to_multiplier) { struct hci_dev *hdev = conn->hdev; struct hci_conn_params *params; struct hci_cp_le_conn_update cp; hci_dev_lock(hdev); params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type); if (params) { params->conn_min_interval = min; params->conn_max_interval = max; params->conn_latency = latency; params->supervision_timeout = to_multiplier; } hci_dev_unlock(hdev); memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); cp.conn_interval_min = cpu_to_le16(min); cp.conn_interval_max = cpu_to_le16(max); cp.conn_latency = cpu_to_le16(latency); cp.supervision_timeout = cpu_to_le16(to_multiplier); cp.min_ce_len = cpu_to_le16(0x0000); cp.max_ce_len = cpu_to_le16(0x0000); hci_send_cmd(hdev, HCI_OP_LE_CONN_UPDATE, sizeof(cp), &cp); if (params) return 0x01; return 0x00; } void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand, __u8 ltk[16], __u8 key_size) { struct hci_dev *hdev = conn->hdev; struct hci_cp_le_start_enc cp; BT_DBG("hcon %p", conn); memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); cp.rand = rand; cp.ediv = ediv; memcpy(cp.ltk, ltk, key_size); hci_send_cmd(hdev, HCI_OP_LE_START_ENC, sizeof(cp), &cp); } /* Device _must_ be locked */ void hci_sco_setup(struct hci_conn *conn, __u8 status) { struct hci_link *link; link = list_first_entry_or_null(&conn->link_list, struct hci_link, list); if (!link || !link->conn) return; BT_DBG("hcon %p", conn); if (!status) { if (lmp_esco_capable(conn->hdev)) hci_setup_sync(link->conn, conn->handle); else hci_add_sco(link->conn, conn->handle); } else { hci_connect_cfm(link->conn, status); hci_conn_del(link->conn); } } static void hci_conn_timeout(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, disc_work.work); int refcnt = atomic_read(&conn->refcnt); BT_DBG("hcon %p state %s", conn, state_to_string(conn->state)); WARN_ON(refcnt < 0); /* FIXME: It was observed that in pairing failed scenario, refcnt * drops below 0. Probably this is because l2cap_conn_del calls * l2cap_chan_del for each channel, and inside l2cap_chan_del conn is * dropped. After that loop hci_chan_del is called which also drops * conn. For now make sure that ACL is alive if refcnt is higher then 0, * otherwise drop it. */ if (refcnt > 0) return; hci_abort_conn(conn, hci_proto_disconn_ind(conn)); } /* Enter sniff mode */ static void hci_conn_idle(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, idle_work.work); struct hci_dev *hdev = conn->hdev; BT_DBG("hcon %p mode %d", conn, conn->mode); if (!lmp_sniff_capable(hdev) || !lmp_sniff_capable(conn)) return; if (conn->mode != HCI_CM_ACTIVE || !(conn->link_policy & HCI_LP_SNIFF)) return; if (lmp_sniffsubr_capable(hdev) && lmp_sniffsubr_capable(conn)) { struct hci_cp_sniff_subrate cp; cp.handle = cpu_to_le16(conn->handle); cp.max_latency = cpu_to_le16(0); cp.min_remote_timeout = cpu_to_le16(0); cp.min_local_timeout = cpu_to_le16(0); hci_send_cmd(hdev, HCI_OP_SNIFF_SUBRATE, sizeof(cp), &cp); } if (!test_and_set_bit(HCI_CONN_MODE_CHANGE_PEND, &conn->flags)) { struct hci_cp_sniff_mode cp; cp.handle = cpu_to_le16(conn->handle); cp.max_interval = cpu_to_le16(hdev->sniff_max_interval); cp.min_interval = cpu_to_le16(hdev->sniff_min_interval); cp.attempt = cpu_to_le16(4); cp.timeout = cpu_to_le16(1); hci_send_cmd(hdev, HCI_OP_SNIFF_MODE, sizeof(cp), &cp); } } static void hci_conn_auto_accept(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, auto_accept_work.work); hci_send_cmd(conn->hdev, HCI_OP_USER_CONFIRM_REPLY, sizeof(conn->dst), &conn->dst); } static void le_disable_advertising(struct hci_dev *hdev) { if (ext_adv_capable(hdev)) { struct hci_cp_le_set_ext_adv_enable cp; cp.enable = 0x00; cp.num_of_sets = 0x00; hci_send_cmd(hdev, HCI_OP_LE_SET_EXT_ADV_ENABLE, sizeof(cp), &cp); } else { u8 enable = 0x00; hci_send_cmd(hdev, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable); } } static void le_conn_timeout(struct work_struct *work) { struct hci_conn *conn = container_of(work, struct hci_conn, le_conn_timeout.work); struct hci_dev *hdev = conn->hdev; BT_DBG(""); /* We could end up here due to having done directed advertising, * so clean up the state if necessary. This should however only * happen with broken hardware or if low duty cycle was used * (which doesn't have a timeout of its own). */ if (conn->role == HCI_ROLE_SLAVE) { /* Disable LE Advertising */ le_disable_advertising(hdev); hci_dev_lock(hdev); hci_conn_failed(conn, HCI_ERROR_ADVERTISING_TIMEOUT); hci_dev_unlock(hdev); return; } hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); } struct iso_list_data { union { u8 cig; u8 big; }; union { u8 cis; u8 bis; u16 sync_handle; }; int count; bool big_term; bool pa_sync_term; bool big_sync_term; }; static void bis_list(struct hci_conn *conn, void *data) { struct iso_list_data *d = data; /* Skip if not broadcast/ANY address */ if (bacmp(&conn->dst, BDADDR_ANY)) return; if (d->big != conn->iso_qos.bcast.big || d->bis == BT_ISO_QOS_BIS_UNSET || d->bis != conn->iso_qos.bcast.bis) return; d->count++; } static int terminate_big_sync(struct hci_dev *hdev, void *data) { struct iso_list_data *d = data; bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", d->big, d->bis); hci_disable_per_advertising_sync(hdev, d->bis); hci_remove_ext_adv_instance_sync(hdev, d->bis, NULL); /* Only terminate BIG if it has been created */ if (!d->big_term) return 0; return hci_le_terminate_big_sync(hdev, d->big, HCI_ERROR_LOCAL_HOST_TERM); } static void terminate_big_destroy(struct hci_dev *hdev, void *data, int err) { kfree(data); } static int hci_le_terminate_big(struct hci_dev *hdev, struct hci_conn *conn) { struct iso_list_data *d; int ret; bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", conn->iso_qos.bcast.big, conn->iso_qos.bcast.bis); d = kzalloc(sizeof(*d), GFP_KERNEL); if (!d) return -ENOMEM; d->big = conn->iso_qos.bcast.big; d->bis = conn->iso_qos.bcast.bis; d->big_term = test_and_clear_bit(HCI_CONN_BIG_CREATED, &conn->flags); ret = hci_cmd_sync_queue(hdev, terminate_big_sync, d, terminate_big_destroy); if (ret) kfree(d); return ret; } static int big_terminate_sync(struct hci_dev *hdev, void *data) { struct iso_list_data *d = data; bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", d->big, d->sync_handle); if (d->big_sync_term) hci_le_big_terminate_sync(hdev, d->big); if (d->pa_sync_term) return hci_le_pa_terminate_sync(hdev, d->sync_handle); return 0; } static void find_bis(struct hci_conn *conn, void *data) { struct iso_list_data *d = data; /* Ignore if BIG doesn't match */ if (d->big != conn->iso_qos.bcast.big) return; d->count++; } static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn) { struct iso_list_data *d; int ret; bt_dev_dbg(hdev, "big 0x%2.2x sync_handle 0x%4.4x", big, conn->sync_handle); d = kzalloc(sizeof(*d), GFP_KERNEL); if (!d) return -ENOMEM; memset(d, 0, sizeof(*d)); d->big = big; d->sync_handle = conn->sync_handle; if (test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) { hci_conn_hash_list_flag(hdev, find_bis, ISO_LINK, HCI_CONN_PA_SYNC, d); if (!d->count) d->pa_sync_term = true; d->count = 0; } if (test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags)) { hci_conn_hash_list_flag(hdev, find_bis, ISO_LINK, HCI_CONN_BIG_SYNC, d); if (!d->count) d->big_sync_term = true; } ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, terminate_big_destroy); if (ret) kfree(d); return ret; } /* Cleanup BIS connection * * Detects if there any BIS left connected in a BIG * broadcaster: Remove advertising instance and terminate BIG. * broadcaster receiver: Teminate BIG sync and terminate PA sync. */ static void bis_cleanup(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct hci_conn *bis; bt_dev_dbg(hdev, "conn %p", conn); if (conn->role == HCI_ROLE_MASTER) { if (!test_and_clear_bit(HCI_CONN_PER_ADV, &conn->flags)) return; /* Check if ISO connection is a BIS and terminate advertising * set and BIG if there are no other connections using it. */ bis = hci_conn_hash_lookup_big(hdev, conn->iso_qos.bcast.big); if (bis) return; hci_le_terminate_big(hdev, conn); } else { hci_le_big_terminate(hdev, conn->iso_qos.bcast.big, conn); } } static int remove_cig_sync(struct hci_dev *hdev, void *data) { u8 handle = PTR_UINT(data); return hci_le_remove_cig_sync(hdev, handle); } static int hci_le_remove_cig(struct hci_dev *hdev, u8 handle) { bt_dev_dbg(hdev, "handle 0x%2.2x", handle); return hci_cmd_sync_queue(hdev, remove_cig_sync, UINT_PTR(handle), NULL); } static void find_cis(struct hci_conn *conn, void *data) { struct iso_list_data *d = data; /* Ignore broadcast or if CIG don't match */ if (!bacmp(&conn->dst, BDADDR_ANY) || d->cig != conn->iso_qos.ucast.cig) return; d->count++; } /* Cleanup CIS connection: * * Detects if there any CIS left connected in a CIG and remove it. */ static void cis_cleanup(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct iso_list_data d; if (conn->iso_qos.ucast.cig == BT_ISO_QOS_CIG_UNSET) return; memset(&d, 0, sizeof(d)); d.cig = conn->iso_qos.ucast.cig; /* Check if ISO connection is a CIS and remove CIG if there are * no other connections using it. */ hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_BOUND, &d); hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_CONNECT, &d); hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_CONNECTED, &d); if (d.count) return; hci_le_remove_cig(hdev, conn->iso_qos.ucast.cig); } static int hci_conn_hash_alloc_unset(struct hci_dev *hdev) { return ida_alloc_range(&hdev->unset_handle_ida, HCI_CONN_HANDLE_MAX + 1, U16_MAX, GFP_ATOMIC); } static struct hci_conn *__hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role, u16 handle) { struct hci_conn *conn; switch (type) { case ACL_LINK: if (!hdev->acl_mtu) return ERR_PTR(-ECONNREFUSED); break; case ISO_LINK: if (hdev->iso_mtu) /* Dedicated ISO Buffer exists */ break; fallthrough; case LE_LINK: if (hdev->le_mtu && hdev->le_mtu < HCI_MIN_LE_MTU) return ERR_PTR(-ECONNREFUSED); if (!hdev->le_mtu && hdev->acl_mtu < HCI_MIN_LE_MTU) return ERR_PTR(-ECONNREFUSED); break; case SCO_LINK: case ESCO_LINK: if (!hdev->sco_pkts) /* Controller does not support SCO or eSCO over HCI */ return ERR_PTR(-ECONNREFUSED); break; default: return ERR_PTR(-ECONNREFUSED); } bt_dev_dbg(hdev, "dst %pMR handle 0x%4.4x", dst, handle); conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) return ERR_PTR(-ENOMEM); bacpy(&conn->dst, dst); bacpy(&conn->src, &hdev->bdaddr); conn->handle = handle; conn->hdev = hdev; conn->type = type; conn->role = role; conn->mode = HCI_CM_ACTIVE; conn->state = BT_OPEN; conn->auth_type = HCI_AT_GENERAL_BONDING; conn->io_capability = hdev->io_capability; conn->remote_auth = 0xff; conn->key_type = 0xff; conn->rssi = HCI_RSSI_INVALID; conn->tx_power = HCI_TX_POWER_INVALID; conn->max_tx_power = HCI_TX_POWER_INVALID; conn->sync_handle = HCI_SYNC_HANDLE_INVALID; set_bit(HCI_CONN_POWER_SAVE, &conn->flags); conn->disc_timeout = HCI_DISCONN_TIMEOUT; /* Set Default Authenticated payload timeout to 30s */ conn->auth_payload_timeout = DEFAULT_AUTH_PAYLOAD_TIMEOUT; if (conn->role == HCI_ROLE_MASTER) conn->out = true; switch (type) { case ACL_LINK: conn->pkt_type = hdev->pkt_type & ACL_PTYPE_MASK; conn->mtu = hdev->acl_mtu; break; case LE_LINK: /* conn->src should reflect the local identity address */ hci_copy_identity_address(hdev, &conn->src, &conn->src_type); conn->mtu = hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; break; case ISO_LINK: /* conn->src should reflect the local identity address */ hci_copy_identity_address(hdev, &conn->src, &conn->src_type); /* set proper cleanup function */ if (!bacmp(dst, BDADDR_ANY)) conn->cleanup = bis_cleanup; else if (conn->role == HCI_ROLE_MASTER) conn->cleanup = cis_cleanup; conn->mtu = hdev->iso_mtu ? hdev->iso_mtu : hdev->le_mtu ? hdev->le_mtu : hdev->acl_mtu; break; case SCO_LINK: if (lmp_esco_capable(hdev)) conn->pkt_type = (hdev->esco_type & SCO_ESCO_MASK) | (hdev->esco_type & EDR_ESCO_MASK); else conn->pkt_type = hdev->pkt_type & SCO_PTYPE_MASK; conn->mtu = hdev->sco_mtu; break; case ESCO_LINK: conn->pkt_type = hdev->esco_type & ~EDR_ESCO_MASK; conn->mtu = hdev->sco_mtu; break; } skb_queue_head_init(&conn->data_q); INIT_LIST_HEAD(&conn->chan_list); INIT_LIST_HEAD(&conn->link_list); INIT_DELAYED_WORK(&conn->disc_work, hci_conn_timeout); INIT_DELAYED_WORK(&conn->auto_accept_work, hci_conn_auto_accept); INIT_DELAYED_WORK(&conn->idle_work, hci_conn_idle); INIT_DELAYED_WORK(&conn->le_conn_timeout, le_conn_timeout); atomic_set(&conn->refcnt, 0); hci_dev_hold(hdev); hci_conn_hash_add(hdev, conn); /* The SCO and eSCO connections will only be notified when their * setup has been completed. This is different to ACL links which * can be notified right away. */ if (conn->type != SCO_LINK && conn->type != ESCO_LINK) { if (hdev->notify) hdev->notify(hdev, HCI_NOTIFY_CONN_ADD); } hci_conn_init_sysfs(conn); return conn; } struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role) { int handle; bt_dev_dbg(hdev, "dst %pMR", dst); handle = hci_conn_hash_alloc_unset(hdev); if (unlikely(handle < 0)) return ERR_PTR(-ECONNREFUSED); return __hci_conn_add(hdev, type, dst, role, handle); } struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, u8 role, u16 handle) { if (handle > HCI_CONN_HANDLE_MAX) return ERR_PTR(-EINVAL); return __hci_conn_add(hdev, type, dst, role, handle); } static void hci_conn_cleanup_child(struct hci_conn *conn, u8 reason) { if (!reason) reason = HCI_ERROR_REMOTE_USER_TERM; /* Due to race, SCO/ISO conn might be not established yet at this point, * and nothing else will clean it up. In other cases it is done via HCI * events. */ switch (conn->type) { case SCO_LINK: case ESCO_LINK: if (HCI_CONN_HANDLE_UNSET(conn->handle)) hci_conn_failed(conn, reason); break; case ISO_LINK: if ((conn->state != BT_CONNECTED && !test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) || test_bit(HCI_CONN_BIG_CREATED, &conn->flags)) hci_conn_failed(conn, reason); break; } } static void hci_conn_unlink(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "hcon %p", conn); if (!conn->parent) { struct hci_link *link, *t; list_for_each_entry_safe(link, t, &conn->link_list, list) { struct hci_conn *child = link->conn; hci_conn_unlink(child); /* If hdev is down it means * hci_dev_close_sync/hci_conn_hash_flush is in progress * and links don't need to be cleanup as all connections * would be cleanup. */ if (!test_bit(HCI_UP, &hdev->flags)) continue; hci_conn_cleanup_child(child, conn->abort_reason); } return; } if (!conn->link) return; list_del_rcu(&conn->link->list); synchronize_rcu(); hci_conn_drop(conn->parent); hci_conn_put(conn->parent); conn->parent = NULL; kfree(conn->link); conn->link = NULL; } void hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; BT_DBG("%s hcon %p handle %d", hdev->name, conn, conn->handle); hci_conn_unlink(conn); cancel_delayed_work_sync(&conn->disc_work); cancel_delayed_work_sync(&conn->auto_accept_work); cancel_delayed_work_sync(&conn->idle_work); if (conn->type == ACL_LINK) { /* Unacked frames */ hdev->acl_cnt += conn->sent; } else if (conn->type == LE_LINK) { cancel_delayed_work(&conn->le_conn_timeout); if (hdev->le_pkts) hdev->le_cnt += conn->sent; else hdev->acl_cnt += conn->sent; } else { /* Unacked ISO frames */ if (conn->type == ISO_LINK) { if (hdev->iso_pkts) hdev->iso_cnt += conn->sent; else if (hdev->le_pkts) hdev->le_cnt += conn->sent; else hdev->acl_cnt += conn->sent; } } skb_queue_purge(&conn->data_q); /* Remove the connection from the list and cleanup its remaining * state. This is a separate function since for some cases like * BT_CONNECT_SCAN we *only* want the cleanup part without the * rest of hci_conn_del. */ hci_conn_cleanup(conn); /* Dequeue callbacks using connection pointer as data */ hci_cmd_sync_dequeue(hdev, NULL, conn, NULL); } struct hci_dev *hci_get_route(bdaddr_t *dst, bdaddr_t *src, uint8_t src_type) { int use_src = bacmp(src, BDADDR_ANY); struct hci_dev *hdev = NULL, *d; BT_DBG("%pMR -> %pMR", src, dst); read_lock(&hci_dev_list_lock); list_for_each_entry(d, &hci_dev_list, list) { if (!test_bit(HCI_UP, &d->flags) || hci_dev_test_flag(d, HCI_USER_CHANNEL)) continue; /* Simple routing: * No source address - find interface with bdaddr != dst * Source address - find interface with bdaddr == src */ if (use_src) { bdaddr_t id_addr; u8 id_addr_type; if (src_type == BDADDR_BREDR) { if (!lmp_bredr_capable(d)) continue; bacpy(&id_addr, &d->bdaddr); id_addr_type = BDADDR_BREDR; } else { if (!lmp_le_capable(d)) continue; hci_copy_identity_address(d, &id_addr, &id_addr_type); /* Convert from HCI to three-value type */ if (id_addr_type == ADDR_LE_DEV_PUBLIC) id_addr_type = BDADDR_LE_PUBLIC; else id_addr_type = BDADDR_LE_RANDOM; } if (!bacmp(&id_addr, src) && id_addr_type == src_type) { hdev = d; break; } } else { if (bacmp(&d->bdaddr, dst)) { hdev = d; break; } } } if (hdev) hdev = hci_dev_hold(hdev); read_unlock(&hci_dev_list_lock); return hdev; } EXPORT_SYMBOL(hci_get_route); /* This function requires the caller holds hdev->lock */ static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; hci_connect_le_scan_cleanup(conn, status); /* Enable advertising in case this was a failed connection * attempt as a peripheral. */ hci_enable_advertising(hdev); } /* This function requires the caller holds hdev->lock */ void hci_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "status 0x%2.2x", status); switch (conn->type) { case LE_LINK: hci_le_conn_failed(conn, status); break; case ACL_LINK: mgmt_connect_failed(hdev, &conn->dst, conn->type, conn->dst_type, status); break; } /* In case of BIG/PA sync failed, clear conn flags so that * the conns will be correctly cleaned up by ISO layer */ test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags); test_and_clear_bit(HCI_CONN_PA_SYNC_FAILED, &conn->flags); conn->state = BT_CLOSED; hci_connect_cfm(conn, status); hci_conn_del(conn); } /* This function requires the caller holds hdev->lock */ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) { struct hci_dev *hdev = conn->hdev; bt_dev_dbg(hdev, "hcon %p handle 0x%4.4x", conn, handle); if (conn->handle == handle) return 0; if (handle > HCI_CONN_HANDLE_MAX) { bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", handle, HCI_CONN_HANDLE_MAX); return HCI_ERROR_INVALID_PARAMETERS; } /* If abort_reason has been sent it means the connection is being * aborted and the handle shall not be changed. */ if (conn->abort_reason) return conn->abort_reason; if (HCI_CONN_HANDLE_UNSET(conn->handle)) ida_free(&hdev->unset_handle_ida, conn->handle); conn->handle = handle; return 0; } struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, u16 conn_timeout, u8 role, u8 phy, u8 sec_phy) { struct hci_conn *conn; struct smp_irk *irk; int err; /* Let's make sure that le is enabled.*/ if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { if (lmp_le_capable(hdev)) return ERR_PTR(-ECONNREFUSED); return ERR_PTR(-EOPNOTSUPP); } /* Since the controller supports only one LE connection attempt at a * time, we return -EBUSY if there is any connection attempt running. */ if (hci_lookup_le_connect(hdev)) return ERR_PTR(-EBUSY); /* If there's already a connection object but it's not in * scanning state it means it must already be established, in * which case we can't do anything else except report a failure * to connect. */ conn = hci_conn_hash_lookup_le(hdev, dst, dst_type); if (conn && !test_bit(HCI_CONN_SCANNING, &conn->flags)) { return ERR_PTR(-EBUSY); } /* Check if the destination address has been resolved by the controller * since if it did then the identity address shall be used. */ if (!dst_resolved) { /* When given an identity address with existing identity * resolving key, the connection needs to be established * to a resolvable random address. * * Storing the resolvable random address is required here * to handle connection failures. The address will later * be resolved back into the original identity address * from the connect request. */ irk = hci_find_irk_by_addr(hdev, dst, dst_type); if (irk && bacmp(&irk->rpa, BDADDR_ANY)) { dst = &irk->rpa; dst_type = ADDR_LE_DEV_RANDOM; } } if (conn) { bacpy(&conn->dst, dst); } else { conn = hci_conn_add_unset(hdev, LE_LINK, dst, role); if (IS_ERR(conn)) return conn; hci_conn_hold(conn); conn->pending_sec_level = sec_level; } conn->dst_type = dst_type; conn->sec_level = BT_SECURITY_LOW; conn->conn_timeout = conn_timeout; conn->le_adv_phy = phy; conn->le_adv_sec_phy = sec_phy; err = hci_connect_le_sync(hdev, conn); if (err) { hci_conn_del(conn); return ERR_PTR(err); } return conn; } static bool is_connected(struct hci_dev *hdev, bdaddr_t *addr, u8 type) { struct hci_conn *conn; conn = hci_conn_hash_lookup_le(hdev, addr, type); if (!conn) return false; if (conn->state != BT_CONNECTED) return false; return true; } /* This function requires the caller holds hdev->lock */ static int hci_explicit_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *params; if (is_connected(hdev, addr, addr_type)) return -EISCONN; params = hci_conn_params_lookup(hdev, addr, addr_type); if (!params) { params = hci_conn_params_add(hdev, addr, addr_type); if (!params) return -ENOMEM; /* If we created new params, mark them to be deleted in * hci_connect_le_scan_cleanup. It's different case than * existing disabled params, those will stay after cleanup. */ params->auto_connect = HCI_AUTO_CONN_EXPLICIT; } /* We're trying to connect, so make sure params are at pend_le_conns */ if (params->auto_connect == HCI_AUTO_CONN_DISABLED || params->auto_connect == HCI_AUTO_CONN_REPORT || params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { hci_pend_le_list_del_init(params); hci_pend_le_list_add(params, &hdev->pend_le_conns); } params->explicit_connect = true; BT_DBG("addr %pMR (type %u) auto_connect %u", addr, addr_type, params->auto_connect); return 0; } static int qos_set_big(struct hci_dev *hdev, struct bt_iso_qos *qos) { struct hci_conn *conn; u8 big; /* Allocate a BIG if not set */ if (qos->bcast.big == BT_ISO_QOS_BIG_UNSET) { for (big = 0x00; big < 0xef; big++) { conn = hci_conn_hash_lookup_big(hdev, big); if (!conn) break; } if (big == 0xef) return -EADDRNOTAVAIL; /* Update BIG */ qos->bcast.big = big; } return 0; } static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos) { struct hci_conn *conn; u8 bis; /* Allocate BIS if not set */ if (qos->bcast.bis == BT_ISO_QOS_BIS_UNSET) { if (qos->bcast.big != BT_ISO_QOS_BIG_UNSET) { conn = hci_conn_hash_lookup_big(hdev, qos->bcast.big); if (conn) { /* If the BIG handle is already matched to an advertising * handle, do not allocate a new one. */ qos->bcast.bis = conn->iso_qos.bcast.bis; return 0; } } /* Find an unused adv set to advertise BIS, skip instance 0x00 * since it is reserved as general purpose set. */ for (bis = 0x01; bis < hdev->le_num_of_adv_sets; bis++) { conn = hci_conn_hash_lookup_bis(hdev, BDADDR_ANY, bis); if (!conn) break; } if (bis == hdev->le_num_of_adv_sets) return -EADDRNOTAVAIL; /* Update BIS */ qos->bcast.bis = bis; } return 0; } /* This function requires the caller holds hdev->lock */ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst, struct bt_iso_qos *qos, __u8 base_len, __u8 *base) { struct hci_conn *conn; int err; /* Let's make sure that le is enabled.*/ if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { if (lmp_le_capable(hdev)) return ERR_PTR(-ECONNREFUSED); return ERR_PTR(-EOPNOTSUPP); } err = qos_set_big(hdev, qos); if (err) return ERR_PTR(err); err = qos_set_bis(hdev, qos); if (err) return ERR_PTR(err); /* Check if the LE Create BIG command has already been sent */ conn = hci_conn_hash_lookup_per_adv_bis(hdev, dst, qos->bcast.big, qos->bcast.big); if (conn) return ERR_PTR(-EADDRINUSE); /* Check BIS settings against other bound BISes, since all * BISes in a BIG must have the same value for all parameters */ conn = hci_conn_hash_lookup_big(hdev, qos->bcast.big); if (conn && (memcmp(qos, &conn->iso_qos, sizeof(*qos)) || base_len != conn->le_per_adv_data_len || memcmp(conn->le_per_adv_data, base, base_len))) return ERR_PTR(-EADDRINUSE); conn = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); if (IS_ERR(conn)) return conn; conn->state = BT_CONNECT; hci_conn_hold(conn); return conn; } /* This function requires the caller holds hdev->lock */ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, u8 sec_level, u16 conn_timeout, enum conn_reasons conn_reason) { struct hci_conn *conn; /* Let's make sure that le is enabled.*/ if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED)) { if (lmp_le_capable(hdev)) return ERR_PTR(-ECONNREFUSED); return ERR_PTR(-EOPNOTSUPP); } /* Some devices send ATT messages as soon as the physical link is * established. To be able to handle these ATT messages, the user- * space first establishes the connection and then starts the pairing * process. * * So if a hci_conn object already exists for the following connection * attempt, we simply update pending_sec_level and auth_type fields * and return the object found. */ conn = hci_conn_hash_lookup_le(hdev, dst, dst_type); if (conn) { if (conn->pending_sec_level < sec_level) conn->pending_sec_level = sec_level; goto done; } BT_DBG("requesting refresh of dst_addr"); conn = hci_conn_add_unset(hdev, LE_LINK, dst, HCI_ROLE_MASTER); if (IS_ERR(conn)) return conn; if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0) { hci_conn_del(conn); return ERR_PTR(-EBUSY); } conn->state = BT_CONNECT; set_bit(HCI_CONN_SCANNING, &conn->flags); conn->dst_type = dst_type; conn->sec_level = BT_SECURITY_LOW; conn->pending_sec_level = sec_level; conn->conn_timeout = conn_timeout; conn->conn_reason = conn_reason; hci_update_passive_scan(hdev); done: hci_conn_hold(conn); return conn; } struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, enum conn_reasons conn_reason, u16 timeout) { struct hci_conn *acl; if (!hci_dev_test_flag(hdev, HCI_BREDR_ENABLED)) { if (lmp_bredr_capable(hdev)) return ERR_PTR(-ECONNREFUSED); return ERR_PTR(-EOPNOTSUPP); } /* Reject outgoing connection to device with same BD ADDR against * CVE-2020-26555 */ if (!bacmp(&hdev->bdaddr, dst)) { bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", dst); return ERR_PTR(-ECONNREFUSED); } acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); if (!acl) { acl = hci_conn_add_unset(hdev, ACL_LINK, dst, HCI_ROLE_MASTER); if (IS_ERR(acl)) return acl; } hci_conn_hold(acl); acl->conn_reason = conn_reason; if (acl->state == BT_OPEN || acl->state == BT_CLOSED) { int err; acl->sec_level = BT_SECURITY_LOW; acl->pending_sec_level = sec_level; acl->auth_type = auth_type; acl->conn_timeout = timeout; err = hci_connect_acl_sync(hdev, acl); if (err) { hci_conn_del(acl); return ERR_PTR(err); } } return acl; } static struct hci_link *hci_conn_link(struct hci_conn *parent, struct hci_conn *conn) { struct hci_dev *hdev = parent->hdev; struct hci_link *link; bt_dev_dbg(hdev, "parent %p hcon %p", parent, conn); if (conn->link) return conn->link; if (conn->parent) return NULL; link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) return NULL; link->conn = hci_conn_hold(conn); conn->link = link; conn->parent = hci_conn_get(parent); /* Use list_add_tail_rcu append to the list */ list_add_tail_rcu(&link->list, &parent->link_list); return link; } struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, __u16 setting, struct bt_codec *codec, u16 timeout) { struct hci_conn *acl; struct hci_conn *sco; struct hci_link *link; acl = hci_connect_acl(hdev, dst, BT_SECURITY_LOW, HCI_AT_NO_BONDING, CONN_REASON_SCO_CONNECT, timeout); if (IS_ERR(acl)) return acl; sco = hci_conn_hash_lookup_ba(hdev, type, dst); if (!sco) { sco = hci_conn_add_unset(hdev, type, dst, HCI_ROLE_MASTER); if (IS_ERR(sco)) { hci_conn_drop(acl); return sco; } } link = hci_conn_link(acl, sco); if (!link) { hci_conn_drop(acl); hci_conn_drop(sco); return ERR_PTR(-ENOLINK); } sco->setting = setting; sco->codec = *codec; if (acl->state == BT_CONNECTED && (sco->state == BT_OPEN || sco->state == BT_CLOSED)) { set_bit(HCI_CONN_POWER_SAVE, &acl->flags); hci_conn_enter_active_mode(acl, BT_POWER_FORCE_ACTIVE_ON); if (test_bit(HCI_CONN_MODE_CHANGE_PEND, &acl->flags)) { /* defer SCO setup until mode change completed */ set_bit(HCI_CONN_SCO_SETUP_PEND, &acl->flags); return sco; } hci_sco_setup(acl, 0x00); } return sco; } static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos) { struct hci_dev *hdev = conn->hdev; struct hci_cp_le_create_big cp; struct iso_list_data data; memset(&cp, 0, sizeof(cp)); data.big = qos->bcast.big; data.bis = qos->bcast.bis; data.count = 0; /* Create a BIS for each bound connection */ hci_conn_hash_list_state(hdev, bis_list, ISO_LINK, BT_BOUND, &data); cp.handle = qos->bcast.big; cp.adv_handle = qos->bcast.bis; cp.num_bis = data.count; hci_cpu_to_le24(qos->bcast.out.interval, cp.bis.sdu_interval); cp.bis.sdu = cpu_to_le16(qos->bcast.out.sdu); cp.bis.latency = cpu_to_le16(qos->bcast.out.latency); cp.bis.rtn = qos->bcast.out.rtn; cp.bis.phy = qos->bcast.out.phy; cp.bis.packing = qos->bcast.packing; cp.bis.framing = qos->bcast.framing; cp.bis.encryption = qos->bcast.encryption; memcpy(cp.bis.bcode, qos->bcast.bcode, sizeof(cp.bis.bcode)); return hci_send_cmd(hdev, HCI_OP_LE_CREATE_BIG, sizeof(cp), &cp); } static int set_cig_params_sync(struct hci_dev *hdev, void *data) { DEFINE_FLEX(struct hci_cp_le_set_cig_params, pdu, cis, num_cis, 0x1f); u8 cig_id = PTR_UINT(data); struct hci_conn *conn; struct bt_iso_qos *qos; u8 aux_num_cis = 0; u8 cis_id; conn = hci_conn_hash_lookup_cig(hdev, cig_id); if (!conn) return 0; qos = &conn->iso_qos; pdu->cig_id = cig_id; hci_cpu_to_le24(qos->ucast.out.interval, pdu->c_interval); hci_cpu_to_le24(qos->ucast.in.interval, pdu->p_interval); pdu->sca = qos->ucast.sca; pdu->packing = qos->ucast.packing; pdu->framing = qos->ucast.framing; pdu->c_latency = cpu_to_le16(qos->ucast.out.latency); pdu->p_latency = cpu_to_le16(qos->ucast.in.latency); /* Reprogram all CIS(s) with the same CIG, valid range are: * num_cis: 0x00 to 0x1F * cis_id: 0x00 to 0xEF */ for (cis_id = 0x00; cis_id < 0xf0 && aux_num_cis < pdu->num_cis; cis_id++) { struct hci_cis_params *cis; conn = hci_conn_hash_lookup_cis(hdev, NULL, 0, cig_id, cis_id); if (!conn) continue; qos = &conn->iso_qos; cis = &pdu->cis[aux_num_cis++]; cis->cis_id = cis_id; cis->c_sdu = cpu_to_le16(conn->iso_qos.ucast.out.sdu); cis->p_sdu = cpu_to_le16(conn->iso_qos.ucast.in.sdu); cis->c_phy = qos->ucast.out.phy ? qos->ucast.out.phy : qos->ucast.in.phy; cis->p_phy = qos->ucast.in.phy ? qos->ucast.in.phy : qos->ucast.out.phy; cis->c_rtn = qos->ucast.out.rtn; cis->p_rtn = qos->ucast.in.rtn; } pdu->num_cis = aux_num_cis; if (!pdu->num_cis) return 0; return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_CIG_PARAMS, struct_size(pdu, cis, pdu->num_cis), pdu, HCI_CMD_TIMEOUT); } static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) { struct hci_dev *hdev = conn->hdev; struct iso_list_data data; memset(&data, 0, sizeof(data)); /* Allocate first still reconfigurable CIG if not set */ if (qos->ucast.cig == BT_ISO_QOS_CIG_UNSET) { for (data.cig = 0x00; data.cig < 0xf0; data.cig++) { data.count = 0; hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_CONNECT, &data); if (data.count) continue; hci_conn_hash_list_state(hdev, find_cis, ISO_LINK, BT_CONNECTED, &data); if (!data.count) break; } if (data.cig == 0xf0) return false; /* Update CIG */ qos->ucast.cig = data.cig; } if (qos->ucast.cis != BT_ISO_QOS_CIS_UNSET) { if (hci_conn_hash_lookup_cis(hdev, NULL, 0, qos->ucast.cig, qos->ucast.cis)) return false; goto done; } /* Allocate first available CIS if not set */ for (data.cig = qos->ucast.cig, data.cis = 0x00; data.cis < 0xf0; data.cis++) { if (!hci_conn_hash_lookup_cis(hdev, NULL, 0, data.cig, data.cis)) { /* Update CIS */ qos->ucast.cis = data.cis; break; } } if (qos->ucast.cis == BT_ISO_QOS_CIS_UNSET) return false; done: if (hci_cmd_sync_queue(hdev, set_cig_params_sync, UINT_PTR(qos->ucast.cig), NULL) < 0) return false; return true; } struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos) { struct hci_conn *cis; cis = hci_conn_hash_lookup_cis(hdev, dst, dst_type, qos->ucast.cig, qos->ucast.cis); if (!cis) { cis = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); if (IS_ERR(cis)) return cis; cis->cleanup = cis_cleanup; cis->dst_type = dst_type; cis->iso_qos.ucast.cig = BT_ISO_QOS_CIG_UNSET; cis->iso_qos.ucast.cis = BT_ISO_QOS_CIS_UNSET; } if (cis->state == BT_CONNECTED) return cis; /* Check if CIS has been set and the settings matches */ if (cis->state == BT_BOUND && !memcmp(&cis->iso_qos, qos, sizeof(*qos))) return cis; /* Update LINK PHYs according to QoS preference */ cis->le_tx_phy = qos->ucast.out.phy; cis->le_rx_phy = qos->ucast.in.phy; /* If output interval is not set use the input interval as it cannot be * 0x000000. */ if (!qos->ucast.out.interval) qos->ucast.out.interval = qos->ucast.in.interval; /* If input interval is not set use the output interval as it cannot be * 0x000000. */ if (!qos->ucast.in.interval) qos->ucast.in.interval = qos->ucast.out.interval; /* If output latency is not set use the input latency as it cannot be * 0x0000. */ if (!qos->ucast.out.latency) qos->ucast.out.latency = qos->ucast.in.latency; /* If input latency is not set use the output latency as it cannot be * 0x0000. */ if (!qos->ucast.in.latency) qos->ucast.in.latency = qos->ucast.out.latency; if (!hci_le_set_cig_params(cis, qos)) { hci_conn_drop(cis); return ERR_PTR(-EINVAL); } hci_conn_hold(cis); cis->iso_qos = *qos; cis->state = BT_BOUND; return cis; } bool hci_iso_setup_path(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct hci_cp_le_setup_iso_path cmd; memset(&cmd, 0, sizeof(cmd)); if (conn->iso_qos.ucast.out.sdu) { cmd.handle = cpu_to_le16(conn->handle); cmd.direction = 0x00; /* Input (Host to Controller) */ cmd.path = 0x00; /* HCI path if enabled */ cmd.codec = 0x03; /* Transparent Data */ if (hci_send_cmd(hdev, HCI_OP_LE_SETUP_ISO_PATH, sizeof(cmd), &cmd) < 0) return false; } if (conn->iso_qos.ucast.in.sdu) { cmd.handle = cpu_to_le16(conn->handle); cmd.direction = 0x01; /* Output (Controller to Host) */ cmd.path = 0x00; /* HCI path if enabled */ cmd.codec = 0x03; /* Transparent Data */ if (hci_send_cmd(hdev, HCI_OP_LE_SETUP_ISO_PATH, sizeof(cmd), &cmd) < 0) return false; } return true; } int hci_conn_check_create_cis(struct hci_conn *conn) { if (conn->type != ISO_LINK || !bacmp(&conn->dst, BDADDR_ANY)) return -EINVAL; if (!conn->parent || conn->parent->state != BT_CONNECTED || conn->state != BT_CONNECT || HCI_CONN_HANDLE_UNSET(conn->handle)) return 1; return 0; } static int hci_create_cis_sync(struct hci_dev *hdev, void *data) { return hci_le_create_cis_sync(hdev); } int hci_le_create_cis_pending(struct hci_dev *hdev) { struct hci_conn *conn; bool pending = false; rcu_read_lock(); list_for_each_entry_rcu(conn, &hdev->conn_hash.list, list) { if (test_bit(HCI_CONN_CREATE_CIS, &conn->flags)) { rcu_read_unlock(); return -EBUSY; } if (!hci_conn_check_create_cis(conn)) pending = true; } rcu_read_unlock(); if (!pending) return 0; /* Queue Create CIS */ return hci_cmd_sync_queue(hdev, hci_create_cis_sync, NULL, NULL); } static void hci_iso_qos_setup(struct hci_dev *hdev, struct hci_conn *conn, struct bt_iso_io_qos *qos, __u8 phy) { /* Only set MTU if PHY is enabled */ if (!qos->sdu && qos->phy) qos->sdu = conn->mtu; /* Use the same PHY as ACL if set to any */ if (qos->phy == BT_ISO_PHY_ANY) qos->phy = phy; /* Use LE ACL connection interval if not set */ if (!qos->interval) /* ACL interval unit in 1.25 ms to us */ qos->interval = conn->le_conn_interval * 1250; /* Use LE ACL connection latency if not set */ if (!qos->latency) qos->latency = conn->le_conn_latency; } static int create_big_sync(struct hci_dev *hdev, void *data) { struct hci_conn *conn = data; struct bt_iso_qos *qos = &conn->iso_qos; u16 interval, sync_interval = 0; u32 flags = 0; int err; if (qos->bcast.out.phy == 0x02) flags |= MGMT_ADV_FLAG_SEC_2M; /* Align intervals */ interval = (qos->bcast.out.interval / 1250) * qos->bcast.sync_factor; if (qos->bcast.bis) sync_interval = interval * 4; err = hci_start_per_adv_sync(hdev, qos->bcast.bis, conn->le_per_adv_data_len, conn->le_per_adv_data, flags, interval, interval, sync_interval); if (err) return err; return hci_le_create_big(conn, &conn->iso_qos); } static void create_pa_complete(struct hci_dev *hdev, void *data, int err) { struct hci_cp_le_pa_create_sync *cp = data; bt_dev_dbg(hdev, ""); if (err) bt_dev_err(hdev, "Unable to create PA: %d", err); kfree(cp); } static int create_pa_sync(struct hci_dev *hdev, void *data) { struct hci_cp_le_pa_create_sync *cp = data; int err; err = __hci_cmd_sync_status(hdev, HCI_OP_LE_PA_CREATE_SYNC, sizeof(*cp), cp, HCI_CMD_TIMEOUT); if (err) { hci_dev_clear_flag(hdev, HCI_PA_SYNC); return err; } return hci_update_passive_scan_sync(hdev); } struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, __u8 sid, struct bt_iso_qos *qos) { struct hci_cp_le_pa_create_sync *cp; struct hci_conn *conn; int err; if (hci_dev_test_and_set_flag(hdev, HCI_PA_SYNC)) return ERR_PTR(-EBUSY); conn = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_SLAVE); if (IS_ERR(conn)) return conn; conn->iso_qos = *qos; conn->state = BT_LISTEN; hci_conn_hold(conn); cp = kzalloc(sizeof(*cp), GFP_KERNEL); if (!cp) { hci_dev_clear_flag(hdev, HCI_PA_SYNC); hci_conn_drop(conn); return ERR_PTR(-ENOMEM); } cp->options = qos->bcast.options; cp->sid = sid; cp->addr_type = dst_type; bacpy(&cp->addr, dst); cp->skip = cpu_to_le16(qos->bcast.skip); cp->sync_timeout = cpu_to_le16(qos->bcast.sync_timeout); cp->sync_cte_type = qos->bcast.sync_cte_type; /* Queue start pa_create_sync and scan */ err = hci_cmd_sync_queue(hdev, create_pa_sync, cp, create_pa_complete); if (err < 0) { hci_conn_drop(conn); kfree(cp); return ERR_PTR(err); } return conn; } int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, struct bt_iso_qos *qos, __u16 sync_handle, __u8 num_bis, __u8 bis[]) { DEFINE_FLEX(struct hci_cp_le_big_create_sync, pdu, bis, num_bis, 0x11); int err; if (num_bis < 0x01 || num_bis > pdu->num_bis) return -EINVAL; err = qos_set_big(hdev, qos); if (err) return err; if (hcon) hcon->iso_qos.bcast.big = qos->bcast.big; pdu->handle = qos->bcast.big; pdu->sync_handle = cpu_to_le16(sync_handle); pdu->encryption = qos->bcast.encryption; memcpy(pdu->bcode, qos->bcast.bcode, sizeof(pdu->bcode)); pdu->mse = qos->bcast.mse; pdu->timeout = cpu_to_le16(qos->bcast.timeout); pdu->num_bis = num_bis; memcpy(pdu->bis, bis, num_bis); return hci_send_cmd(hdev, HCI_OP_LE_BIG_CREATE_SYNC, struct_size(pdu, bis, num_bis), pdu); } static void create_big_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; bt_dev_dbg(hdev, "conn %p", conn); if (err) { bt_dev_err(hdev, "Unable to create BIG: %d", err); hci_connect_cfm(conn, err); hci_conn_del(conn); } } struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, struct bt_iso_qos *qos, __u8 base_len, __u8 *base) { struct hci_conn *conn; struct hci_conn *parent; __u8 eir[HCI_MAX_PER_AD_LENGTH]; struct hci_link *link; /* Look for any BIS that is open for rebinding */ conn = hci_conn_hash_lookup_big_state(hdev, qos->bcast.big, BT_OPEN); if (conn) { memcpy(qos, &conn->iso_qos, sizeof(*qos)); conn->state = BT_CONNECTED; return conn; } if (base_len && base) base_len = eir_append_service_data(eir, 0, 0x1851, base, base_len); /* We need hci_conn object using the BDADDR_ANY as dst */ conn = hci_add_bis(hdev, dst, qos, base_len, eir); if (IS_ERR(conn)) return conn; /* Update LINK PHYs according to QoS preference */ conn->le_tx_phy = qos->bcast.out.phy; conn->le_tx_phy = qos->bcast.out.phy; /* Add Basic Announcement into Peridic Adv Data if BASE is set */ if (base_len && base) { memcpy(conn->le_per_adv_data, eir, sizeof(eir)); conn->le_per_adv_data_len = base_len; } hci_iso_qos_setup(hdev, conn, &qos->bcast.out, conn->le_tx_phy ? conn->le_tx_phy : hdev->le_tx_def_phys); conn->iso_qos = *qos; conn->state = BT_BOUND; /* Link BISes together */ parent = hci_conn_hash_lookup_big(hdev, conn->iso_qos.bcast.big); if (parent && parent != conn) { link = hci_conn_link(parent, conn); if (!link) { hci_conn_drop(conn); return ERR_PTR(-ENOLINK); } /* Link takes the refcount */ hci_conn_drop(conn); } return conn; } static void bis_mark_per_adv(struct hci_conn *conn, void *data) { struct iso_list_data *d = data; /* Skip if not broadcast/ANY address */ if (bacmp(&conn->dst, BDADDR_ANY)) return; if (d->big != conn->iso_qos.bcast.big || d->bis == BT_ISO_QOS_BIS_UNSET || d->bis != conn->iso_qos.bcast.bis) return; set_bit(HCI_CONN_PER_ADV, &conn->flags); } struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos, __u8 base_len, __u8 *base) { struct hci_conn *conn; int err; struct iso_list_data data; conn = hci_bind_bis(hdev, dst, qos, base_len, base); if (IS_ERR(conn)) return conn; if (conn->state == BT_CONNECTED) return conn; data.big = qos->bcast.big; data.bis = qos->bcast.bis; /* Set HCI_CONN_PER_ADV for all bound connections, to mark that * the start periodic advertising and create BIG commands have * been queued */ hci_conn_hash_list_state(hdev, bis_mark_per_adv, ISO_LINK, BT_BOUND, &data); /* Queue start periodic advertising and create BIG */ err = hci_cmd_sync_queue(hdev, create_big_sync, conn, create_big_complete); if (err < 0) { hci_conn_drop(conn); return ERR_PTR(err); } return conn; } struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, __u8 dst_type, struct bt_iso_qos *qos) { struct hci_conn *le; struct hci_conn *cis; struct hci_link *link; if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) le = hci_connect_le(hdev, dst, dst_type, false, BT_SECURITY_LOW, HCI_LE_CONN_TIMEOUT, HCI_ROLE_SLAVE, 0, 0); else le = hci_connect_le_scan(hdev, dst, dst_type, BT_SECURITY_LOW, HCI_LE_CONN_TIMEOUT, CONN_REASON_ISO_CONNECT); if (IS_ERR(le)) return le; hci_iso_qos_setup(hdev, le, &qos->ucast.out, le->le_tx_phy ? le->le_tx_phy : hdev->le_tx_def_phys); hci_iso_qos_setup(hdev, le, &qos->ucast.in, le->le_rx_phy ? le->le_rx_phy : hdev->le_rx_def_phys); cis = hci_bind_cis(hdev, dst, dst_type, qos); if (IS_ERR(cis)) { hci_conn_drop(le); return cis; } link = hci_conn_link(le, cis); if (!link) { hci_conn_drop(le); hci_conn_drop(cis); return ERR_PTR(-ENOLINK); } /* Link takes the refcount */ hci_conn_drop(cis); cis->state = BT_CONNECT; hci_le_create_cis_pending(hdev); return cis; } /* Check link security requirement */ int hci_conn_check_link_mode(struct hci_conn *conn) { BT_DBG("hcon %p", conn); /* In Secure Connections Only mode, it is required that Secure * Connections is used and the link is encrypted with AES-CCM * using a P-256 authenticated combination key. */ if (hci_dev_test_flag(conn->hdev, HCI_SC_ONLY)) { if (!hci_conn_sc_enabled(conn) || !test_bit(HCI_CONN_AES_CCM, &conn->flags) || conn->key_type != HCI_LK_AUTH_COMBINATION_P256) return 0; } /* AES encryption is required for Level 4: * * BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 3, Part C * page 1319: * * 128-bit equivalent strength for link and encryption keys * required using FIPS approved algorithms (E0 not allowed, * SAFER+ not allowed, and P-192 not allowed; encryption key * not shortened) */ if (conn->sec_level == BT_SECURITY_FIPS && !test_bit(HCI_CONN_AES_CCM, &conn->flags)) { bt_dev_err(conn->hdev, "Invalid security: Missing AES-CCM usage"); return 0; } if (hci_conn_ssp_enabled(conn) && !test_bit(HCI_CONN_ENCRYPT, &conn->flags)) return 0; return 1; } /* Authenticate remote device */ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) { BT_DBG("hcon %p", conn); if (conn->pending_sec_level > sec_level) sec_level = conn->pending_sec_level; if (sec_level > conn->sec_level) conn->pending_sec_level = sec_level; else if (test_bit(HCI_CONN_AUTH, &conn->flags)) return 1; /* Make sure we preserve an existing MITM requirement*/ auth_type |= (conn->auth_type & 0x01); conn->auth_type = auth_type; if (!test_and_set_bit(HCI_CONN_AUTH_PEND, &conn->flags)) { struct hci_cp_auth_requested cp; cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); /* Set the ENCRYPT_PEND to trigger encryption after * authentication. */ if (!test_bit(HCI_CONN_ENCRYPT, &conn->flags)) set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags); } return 0; } /* Encrypt the link */ static void hci_conn_encrypt(struct hci_conn *conn) { BT_DBG("hcon %p", conn); if (!test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) { struct hci_cp_set_conn_encrypt cp; cp.handle = cpu_to_le16(conn->handle); cp.encrypt = 0x01; hci_send_cmd(conn->hdev, HCI_OP_SET_CONN_ENCRYPT, sizeof(cp), &cp); } } /* Enable security */ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type, bool initiator) { BT_DBG("hcon %p", conn); if (conn->type == LE_LINK) return smp_conn_security(conn, sec_level); /* For sdp we don't need the link key. */ if (sec_level == BT_SECURITY_SDP) return 1; /* For non 2.1 devices and low security level we don't need the link key. */ if (sec_level == BT_SECURITY_LOW && !hci_conn_ssp_enabled(conn)) return 1; /* For other security levels we need the link key. */ if (!test_bit(HCI_CONN_AUTH, &conn->flags)) goto auth; switch (conn->key_type) { case HCI_LK_AUTH_COMBINATION_P256: /* An authenticated FIPS approved combination key has * sufficient security for security level 4 or lower. */ if (sec_level <= BT_SECURITY_FIPS) goto encrypt; break; case HCI_LK_AUTH_COMBINATION_P192: /* An authenticated combination key has sufficient security for * security level 3 or lower. */ if (sec_level <= BT_SECURITY_HIGH) goto encrypt; break; case HCI_LK_UNAUTH_COMBINATION_P192: case HCI_LK_UNAUTH_COMBINATION_P256: /* An unauthenticated combination key has sufficient security * for security level 2 or lower. */ if (sec_level <= BT_SECURITY_MEDIUM) goto encrypt; break; case HCI_LK_COMBINATION: /* A combination key has always sufficient security for the * security levels 2 or lower. High security level requires the * combination key is generated using maximum PIN code length * (16). For pre 2.1 units. */ if (sec_level <= BT_SECURITY_MEDIUM || conn->pin_length == 16) goto encrypt; break; default: break; } auth: if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) return 0; if (initiator) set_bit(HCI_CONN_AUTH_INITIATOR, &conn->flags); if (!hci_conn_auth(conn, sec_level, auth_type)) return 0; encrypt: if (test_bit(HCI_CONN_ENCRYPT, &conn->flags)) { /* Ensure that the encryption key size has been read, * otherwise stall the upper layer responses. */ if (!conn->enc_key_size) return 0; /* Nothing else needed, all requirements are met */ return 1; } hci_conn_encrypt(conn); return 0; } EXPORT_SYMBOL(hci_conn_security); /* Check secure link requirement */ int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level) { BT_DBG("hcon %p", conn); /* Accept if non-secure or higher security level is required */ if (sec_level != BT_SECURITY_HIGH && sec_level != BT_SECURITY_FIPS) return 1; /* Accept if secure or higher security level is already present */ if (conn->sec_level == BT_SECURITY_HIGH || conn->sec_level == BT_SECURITY_FIPS) return 1; /* Reject not secure link */ return 0; } EXPORT_SYMBOL(hci_conn_check_secure); /* Switch role */ int hci_conn_switch_role(struct hci_conn *conn, __u8 role) { BT_DBG("hcon %p", conn); if (role == conn->role) return 1; if (!test_and_set_bit(HCI_CONN_RSWITCH_PEND, &conn->flags)) { struct hci_cp_switch_role cp; bacpy(&cp.bdaddr, &conn->dst); cp.role = role; hci_send_cmd(conn->hdev, HCI_OP_SWITCH_ROLE, sizeof(cp), &cp); } return 0; } EXPORT_SYMBOL(hci_conn_switch_role); /* Enter active mode */ void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active) { struct hci_dev *hdev = conn->hdev; BT_DBG("hcon %p mode %d", conn, conn->mode); if (conn->mode != HCI_CM_SNIFF) goto timer; if (!test_bit(HCI_CONN_POWER_SAVE, &conn->flags) && !force_active) goto timer; if (!test_and_set_bit(HCI_CONN_MODE_CHANGE_PEND, &conn->flags)) { struct hci_cp_exit_sniff_mode cp; cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(hdev, HCI_OP_EXIT_SNIFF_MODE, sizeof(cp), &cp); } timer: if (hdev->idle_timeout > 0) queue_delayed_work(hdev->workqueue, &conn->idle_work, msecs_to_jiffies(hdev->idle_timeout)); } /* Drop all connection on the device */ void hci_conn_hash_flush(struct hci_dev *hdev) { struct list_head *head = &hdev->conn_hash.list; struct hci_conn *conn; BT_DBG("hdev %s", hdev->name); /* We should not traverse the list here, because hci_conn_del * can remove extra links, which may cause the list traversal * to hit items that have already been released. */ while ((conn = list_first_entry_or_null(head, struct hci_conn, list)) != NULL) { conn->state = BT_CLOSED; hci_disconn_cfm(conn, HCI_ERROR_LOCAL_HOST_TERM); hci_conn_del(conn); } } static u32 get_link_mode(struct hci_conn *conn) { u32 link_mode = 0; if (conn->role == HCI_ROLE_MASTER) link_mode |= HCI_LM_MASTER; if (test_bit(HCI_CONN_ENCRYPT, &conn->flags)) link_mode |= HCI_LM_ENCRYPT; if (test_bit(HCI_CONN_AUTH, &conn->flags)) link_mode |= HCI_LM_AUTH; if (test_bit(HCI_CONN_SECURE, &conn->flags)) link_mode |= HCI_LM_SECURE; if (test_bit(HCI_CONN_FIPS, &conn->flags)) link_mode |= HCI_LM_FIPS; return link_mode; } int hci_get_conn_list(void __user *arg) { struct hci_conn *c; struct hci_conn_list_req req, *cl; struct hci_conn_info *ci; struct hci_dev *hdev; int n = 0, size, err; if (copy_from_user(&req, arg, sizeof(req))) return -EFAULT; if (!req.conn_num || req.conn_num > (PAGE_SIZE * 2) / sizeof(*ci)) return -EINVAL; size = sizeof(req) + req.conn_num * sizeof(*ci); cl = kmalloc(size, GFP_KERNEL); if (!cl) return -ENOMEM; hdev = hci_dev_get(req.dev_id); if (!hdev) { kfree(cl); return -ENODEV; } ci = cl->conn_info; hci_dev_lock(hdev); list_for_each_entry(c, &hdev->conn_hash.list, list) { bacpy(&(ci + n)->bdaddr, &c->dst); (ci + n)->handle = c->handle; (ci + n)->type = c->type; (ci + n)->out = c->out; (ci + n)->state = c->state; (ci + n)->link_mode = get_link_mode(c); if (++n >= req.conn_num) break; } hci_dev_unlock(hdev); cl->dev_id = hdev->id; cl->conn_num = n; size = sizeof(req) + n * sizeof(*ci); hci_dev_put(hdev); err = copy_to_user(arg, cl, size); kfree(cl); return err ? -EFAULT : 0; } int hci_get_conn_info(struct hci_dev *hdev, void __user *arg) { struct hci_conn_info_req req; struct hci_conn_info ci; struct hci_conn *conn; char __user *ptr = arg + sizeof(req); if (copy_from_user(&req, arg, sizeof(req))) return -EFAULT; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, req.type, &req.bdaddr); if (conn) { bacpy(&ci.bdaddr, &conn->dst); ci.handle = conn->handle; ci.type = conn->type; ci.out = conn->out; ci.state = conn->state; ci.link_mode = get_link_mode(conn); } hci_dev_unlock(hdev); if (!conn) return -ENOENT; return copy_to_user(ptr, &ci, sizeof(ci)) ? -EFAULT : 0; } int hci_get_auth_info(struct hci_dev *hdev, void __user *arg) { struct hci_auth_info_req req; struct hci_conn *conn; if (copy_from_user(&req, arg, sizeof(req))) return -EFAULT; hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &req.bdaddr); if (conn) req.type = conn->auth_type; hci_dev_unlock(hdev); if (!conn) return -ENOENT; return copy_to_user(arg, &req, sizeof(req)) ? -EFAULT : 0; } struct hci_chan *hci_chan_create(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; struct hci_chan *chan; BT_DBG("%s hcon %p", hdev->name, conn); if (test_bit(HCI_CONN_DROP, &conn->flags)) { BT_DBG("Refusing to create new hci_chan"); return NULL; } chan = kzalloc(sizeof(*chan), GFP_KERNEL); if (!chan) return NULL; chan->conn = hci_conn_get(conn); skb_queue_head_init(&chan->data_q); chan->state = BT_CONNECTED; list_add_rcu(&chan->list, &conn->chan_list); return chan; } void hci_chan_del(struct hci_chan *chan) { struct hci_conn *conn = chan->conn; struct hci_dev *hdev = conn->hdev; BT_DBG("%s hcon %p chan %p", hdev->name, conn, chan); list_del_rcu(&chan->list); synchronize_rcu(); /* Prevent new hci_chan's to be created for this hci_conn */ set_bit(HCI_CONN_DROP, &conn->flags); hci_conn_put(conn); skb_queue_purge(&chan->data_q); kfree(chan); } void hci_chan_list_flush(struct hci_conn *conn) { struct hci_chan *chan, *n; BT_DBG("hcon %p", conn); list_for_each_entry_safe(chan, n, &conn->chan_list, list) hci_chan_del(chan); } static struct hci_chan *__hci_chan_lookup_handle(struct hci_conn *hcon, __u16 handle) { struct hci_chan *hchan; list_for_each_entry(hchan, &hcon->chan_list, list) { if (hchan->handle == handle) return hchan; } return NULL; } struct hci_chan *hci_chan_lookup_handle(struct hci_dev *hdev, __u16 handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *hcon; struct hci_chan *hchan = NULL; rcu_read_lock(); list_for_each_entry_rcu(hcon, &h->list, list) { hchan = __hci_chan_lookup_handle(hcon, handle); if (hchan) break; } rcu_read_unlock(); return hchan; } u32 hci_conn_get_phy(struct hci_conn *conn) { u32 phys = 0; /* BLUETOOTH CORE SPECIFICATION Version 5.2 | Vol 2, Part B page 471: * Table 6.2: Packets defined for synchronous, asynchronous, and * CPB logical transport types. */ switch (conn->type) { case SCO_LINK: /* SCO logical transport (1 Mb/s): * HV1, HV2, HV3 and DV. */ phys |= BT_PHY_BR_1M_1SLOT; break; case ACL_LINK: /* ACL logical transport (1 Mb/s) ptt=0: * DH1, DM3, DH3, DM5 and DH5. */ phys |= BT_PHY_BR_1M_1SLOT; if (conn->pkt_type & (HCI_DM3 | HCI_DH3)) phys |= BT_PHY_BR_1M_3SLOT; if (conn->pkt_type & (HCI_DM5 | HCI_DH5)) phys |= BT_PHY_BR_1M_5SLOT; /* ACL logical transport (2 Mb/s) ptt=1: * 2-DH1, 2-DH3 and 2-DH5. */ if (!(conn->pkt_type & HCI_2DH1)) phys |= BT_PHY_EDR_2M_1SLOT; if (!(conn->pkt_type & HCI_2DH3)) phys |= BT_PHY_EDR_2M_3SLOT; if (!(conn->pkt_type & HCI_2DH5)) phys |= BT_PHY_EDR_2M_5SLOT; /* ACL logical transport (3 Mb/s) ptt=1: * 3-DH1, 3-DH3 and 3-DH5. */ if (!(conn->pkt_type & HCI_3DH1)) phys |= BT_PHY_EDR_3M_1SLOT; if (!(conn->pkt_type & HCI_3DH3)) phys |= BT_PHY_EDR_3M_3SLOT; if (!(conn->pkt_type & HCI_3DH5)) phys |= BT_PHY_EDR_3M_5SLOT; break; case ESCO_LINK: /* eSCO logical transport (1 Mb/s): EV3, EV4 and EV5 */ phys |= BT_PHY_BR_1M_1SLOT; if (!(conn->pkt_type & (ESCO_EV4 | ESCO_EV5))) phys |= BT_PHY_BR_1M_3SLOT; /* eSCO logical transport (2 Mb/s): 2-EV3, 2-EV5 */ if (!(conn->pkt_type & ESCO_2EV3)) phys |= BT_PHY_EDR_2M_1SLOT; if (!(conn->pkt_type & ESCO_2EV5)) phys |= BT_PHY_EDR_2M_3SLOT; /* eSCO logical transport (3 Mb/s): 3-EV3, 3-EV5 */ if (!(conn->pkt_type & ESCO_3EV3)) phys |= BT_PHY_EDR_3M_1SLOT; if (!(conn->pkt_type & ESCO_3EV5)) phys |= BT_PHY_EDR_3M_3SLOT; break; case LE_LINK: if (conn->le_tx_phy & HCI_LE_SET_PHY_1M) phys |= BT_PHY_LE_1M_TX; if (conn->le_rx_phy & HCI_LE_SET_PHY_1M) phys |= BT_PHY_LE_1M_RX; if (conn->le_tx_phy & HCI_LE_SET_PHY_2M) phys |= BT_PHY_LE_2M_TX; if (conn->le_rx_phy & HCI_LE_SET_PHY_2M) phys |= BT_PHY_LE_2M_RX; if (conn->le_tx_phy & HCI_LE_SET_PHY_CODED) phys |= BT_PHY_LE_CODED_TX; if (conn->le_rx_phy & HCI_LE_SET_PHY_CODED) phys |= BT_PHY_LE_CODED_RX; break; } return phys; } static int abort_conn_sync(struct hci_dev *hdev, void *data) { struct hci_conn *conn = data; if (!hci_conn_valid(hdev, conn)) return -ECANCELED; return hci_abort_conn_sync(hdev, conn, conn->abort_reason); } int hci_abort_conn(struct hci_conn *conn, u8 reason) { struct hci_dev *hdev = conn->hdev; /* If abort_reason has already been set it means the connection is * already being aborted so don't attempt to overwrite it. */ if (conn->abort_reason) return 0; bt_dev_dbg(hdev, "handle 0x%2.2x reason 0x%2.2x", conn->handle, reason); conn->abort_reason = reason; /* If the connection is pending check the command opcode since that * might be blocking on hci_cmd_sync_work while waiting its respective * event so we need to hci_cmd_sync_cancel to cancel it. * * hci_connect_le serializes the connection attempts so only one * connection can be in BT_CONNECT at time. */ if (conn->state == BT_CONNECT && hdev->req_status == HCI_REQ_PEND) { switch (hci_skb_event(hdev->sent_cmd)) { case HCI_EV_CONN_COMPLETE: case HCI_EV_LE_CONN_COMPLETE: case HCI_EV_LE_ENHANCED_CONN_COMPLETE: case HCI_EVT_LE_CIS_ESTABLISHED: hci_cmd_sync_cancel(hdev, ECANCELED); break; } /* Cancel connect attempt if still queued/pending */ } else if (!hci_cancel_connect_sync(hdev, conn)) { return 0; } /* Run immediately if on cmd_sync_work since this may be called * as a result to MGMT_OP_DISCONNECT/MGMT_OP_UNPAIR which does * already queue its callback on cmd_sync_work. */ return hci_cmd_sync_run_once(hdev, abort_conn_sync, conn, NULL); } |
| 8 8 8 1010 1007 1007 931 931 7 7 7 651 293 1 295 295 295 294 79 78 24 23 24 24 24 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1995 Linus Torvalds * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs. * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar */ #include <linux/sched.h> /* test_thread_flag(), ... */ #include <linux/sched/task_stack.h> /* task_stack_*(), ... */ #include <linux/kdebug.h> /* oops_begin/end, ... */ #include <linux/extable.h> /* search_exception_tables */ #include <linux/memblock.h> /* max_low_pfn */ #include <linux/kfence.h> /* kfence_handle_page_fault */ #include <linux/kprobes.h> /* NOKPROBE_SYMBOL, ... */ #include <linux/mmiotrace.h> /* kmmio_handler, ... */ #include <linux/perf_event.h> /* perf_sw_event */ #include <linux/hugetlb.h> /* hstate_index_to_shift */ #include <linux/prefetch.h> /* prefetchw */ #include <linux/context_tracking.h> /* exception_enter(), ... */ #include <linux/uaccess.h> /* faulthandler_disabled() */ #include <linux/efi.h> /* efi_crash_gracefully_on_page_fault()*/ #include <linux/mm_types.h> #include <linux/mm.h> /* find_and_lock_vma() */ #include <linux/vmalloc.h> #include <asm/cpufeature.h> /* boot_cpu_has, ... */ #include <asm/traps.h> /* dotraplinkage, ... */ #include <asm/fixmap.h> /* VSYSCALL_ADDR */ #include <asm/vsyscall.h> /* emulate_vsyscall */ #include <asm/vm86.h> /* struct vm86 */ #include <asm/mmu_context.h> /* vma_pkey() */ #include <asm/efi.h> /* efi_crash_gracefully_on_page_fault()*/ #include <asm/desc.h> /* store_idt(), ... */ #include <asm/cpu_entry_area.h> /* exception stack */ #include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ #include <asm/kvm_para.h> /* kvm_handle_async_pf */ #include <asm/vdso.h> /* fixup_vdso_exception() */ #include <asm/irq_stack.h> #include <asm/fred.h> #include <asm/sev.h> /* snp_dump_hva_rmpentry() */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> /* * Returns 0 if mmiotrace is disabled, or if the fault is not * handled by mmiotrace: */ static nokprobe_inline int kmmio_fault(struct pt_regs *regs, unsigned long addr) { if (unlikely(is_kmmio_active())) if (kmmio_handler(regs, addr) == 1) return -1; return 0; } /* * Prefetch quirks: * * 32-bit mode: * * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch. * Check that here and ignore it. This is AMD erratum #91. * * 64-bit mode: * * Sometimes the CPU reports invalid exceptions on prefetch. * Check that here and ignore it. * * Opcode checker based on code by Richard Brunner. */ static inline int check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr, unsigned char opcode, int *prefetch) { unsigned char instr_hi = opcode & 0xf0; unsigned char instr_lo = opcode & 0x0f; switch (instr_hi) { case 0x20: case 0x30: /* * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes. * In X86_64 long mode, the CPU will signal invalid * opcode if some of these prefixes are present so * X86_64 will never get here anyway */ return ((instr_lo & 7) == 0x6); #ifdef CONFIG_X86_64 case 0x40: /* * In 64-bit mode 0x40..0x4F are valid REX prefixes */ return (!user_mode(regs) || user_64bit_mode(regs)); #endif case 0x60: /* 0x64 thru 0x67 are valid prefixes in all modes. */ return (instr_lo & 0xC) == 0x4; case 0xF0: /* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */ return !instr_lo || (instr_lo>>1) == 1; case 0x00: /* Prefetch instruction is 0x0F0D or 0x0F18 */ if (get_kernel_nofault(opcode, instr)) return 0; *prefetch = (instr_lo == 0xF) && (opcode == 0x0D || opcode == 0x18); return 0; default: return 0; } } static bool is_amd_k8_pre_npt(void) { struct cpuinfo_x86 *c = &boot_cpu_data; return unlikely(IS_ENABLED(CONFIG_CPU_SUP_AMD) && c->x86_vendor == X86_VENDOR_AMD && c->x86 == 0xf && c->x86_model < 0x40); } static int is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) { unsigned char *max_instr; unsigned char *instr; int prefetch = 0; /* Erratum #91 affects AMD K8, pre-NPT CPUs */ if (!is_amd_k8_pre_npt()) return 0; /* * If it was a exec (instruction fetch) fault on NX page, then * do not ignore the fault: */ if (error_code & X86_PF_INSTR) return 0; instr = (void *)convert_ip_to_linear(current, regs); max_instr = instr + 15; /* * This code has historically always bailed out if IP points to a * not-present page (e.g. due to a race). No one has ever * complained about this. */ pagefault_disable(); while (instr < max_instr) { unsigned char opcode; if (user_mode(regs)) { if (get_user(opcode, (unsigned char __user *) instr)) break; } else { if (get_kernel_nofault(opcode, instr)) break; } instr++; if (!check_prefetch_opcode(regs, instr, opcode, &prefetch)) break; } pagefault_enable(); return prefetch; } DEFINE_SPINLOCK(pgd_lock); LIST_HEAD(pgd_list); #ifdef CONFIG_X86_32 static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) { unsigned index = pgd_index(address); pgd_t *pgd_k; p4d_t *p4d, *p4d_k; pud_t *pud, *pud_k; pmd_t *pmd, *pmd_k; pgd += index; pgd_k = init_mm.pgd + index; if (!pgd_present(*pgd_k)) return NULL; /* * set_pgd(pgd, *pgd_k); here would be useless on PAE * and redundant with the set_pmd() on non-PAE. As would * set_p4d/set_pud. */ p4d = p4d_offset(pgd, address); p4d_k = p4d_offset(pgd_k, address); if (!p4d_present(*p4d_k)) return NULL; pud = pud_offset(p4d, address); pud_k = pud_offset(p4d_k, address); if (!pud_present(*pud_k)) return NULL; pmd = pmd_offset(pud, address); pmd_k = pmd_offset(pud_k, address); if (pmd_present(*pmd) != pmd_present(*pmd_k)) set_pmd(pmd, *pmd_k); if (!pmd_present(*pmd_k)) return NULL; else BUG_ON(pmd_pfn(*pmd) != pmd_pfn(*pmd_k)); return pmd_k; } /* * Handle a fault on the vmalloc or module mapping area * * This is needed because there is a race condition between the time * when the vmalloc mapping code updates the PMD to the point in time * where it synchronizes this update with the other page-tables in the * system. * * In this race window another thread/CPU can map an area on the same * PMD, finds it already present and does not synchronize it with the * rest of the system yet. As a result v[mz]alloc might return areas * which are not mapped in every page-table in the system, causing an * unhandled page-fault when they are accessed. */ static noinline int vmalloc_fault(unsigned long address) { unsigned long pgd_paddr; pmd_t *pmd_k; pte_t *pte_k; /* Make sure we are in vmalloc area: */ if (!(address >= VMALLOC_START && address < VMALLOC_END)) return -1; /* * Synchronize this task's top level page-table * with the 'reference' page table. * * Do _not_ use "current" here. We might be inside * an interrupt in the middle of a task switch.. */ pgd_paddr = read_cr3_pa(); pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); if (!pmd_k) return -1; if (pmd_leaf(*pmd_k)) return 0; pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; return 0; } NOKPROBE_SYMBOL(vmalloc_fault); void arch_sync_kernel_mappings(unsigned long start, unsigned long end) { unsigned long addr; for (addr = start & PMD_MASK; addr >= TASK_SIZE_MAX && addr < VMALLOC_END; addr += PMD_SIZE) { struct page *page; spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { spinlock_t *pgt_lock; /* the pgt_lock only for Xen */ pgt_lock = &pgd_page_get_mm(page)->page_table_lock; spin_lock(pgt_lock); vmalloc_sync_one(page_address(page), addr); spin_unlock(pgt_lock); } spin_unlock(&pgd_lock); } } static bool low_pfn(unsigned long pfn) { return pfn < max_low_pfn; } static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = &base[pgd_index(address)]; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; #ifdef CONFIG_X86_PAE pr_info("*pdpt = %016Lx ", pgd_val(*pgd)); if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd)) goto out; #define pr_pde pr_cont #else #define pr_pde pr_info #endif p4d = p4d_offset(pgd, address); pud = pud_offset(p4d, address); pmd = pmd_offset(pud, address); pr_pde("*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd)); #undef pr_pde /* * We must not directly access the pte in the highpte * case if the page table is located in highmem. * And let's rather not kmap-atomic the pte, just in case * it's allocated already: */ if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_leaf(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); pr_cont("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte)); out: pr_cont("\n"); } #else /* CONFIG_X86_64: */ #ifdef CONFIG_CPU_SUP_AMD static const char errata93_warning[] = KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n" "******* Working around it, but it may cause SEGVs or burn power.\n" "******* Please consider a BIOS update.\n" "******* Disabling USB legacy in the BIOS may also help.\n"; #endif static int bad_address(void *p) { unsigned long dummy; return get_kernel_nofault(dummy, (unsigned long *)p); } static void dump_pagetable(unsigned long address) { pgd_t *base = __va(read_cr3_pa()); pgd_t *pgd = base + pgd_index(address); p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; if (bad_address(pgd)) goto bad; pr_info("PGD %lx ", pgd_val(*pgd)); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (bad_address(p4d)) goto bad; pr_cont("P4D %lx ", p4d_val(*p4d)); if (!p4d_present(*p4d) || p4d_leaf(*p4d)) goto out; pud = pud_offset(p4d, address); if (bad_address(pud)) goto bad; pr_cont("PUD %lx ", pud_val(*pud)); if (!pud_present(*pud) || pud_leaf(*pud)) goto out; pmd = pmd_offset(pud, address); if (bad_address(pmd)) goto bad; pr_cont("PMD %lx ", pmd_val(*pmd)); if (!pmd_present(*pmd) || pmd_leaf(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); if (bad_address(pte)) goto bad; pr_cont("PTE %lx", pte_val(*pte)); out: pr_cont("\n"); return; bad: pr_info("BAD\n"); } #endif /* CONFIG_X86_64 */ /* * Workaround for K8 erratum #93 & buggy BIOS. * * BIOS SMM functions are required to use a specific workaround * to avoid corruption of the 64bit RIP register on C stepping K8. * * A lot of BIOS that didn't get tested properly miss this. * * The OS sees this as a page fault with the upper 32bits of RIP cleared. * Try to work around it here. * * Note we only handle faults in kernel here. * Does nothing on 32-bit. */ static int is_errata93(struct pt_regs *regs, unsigned long address) { #if defined(CONFIG_X86_64) && defined(CONFIG_CPU_SUP_AMD) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD || boot_cpu_data.x86 != 0xf) return 0; if (user_mode(regs)) return 0; if (address != regs->ip) return 0; if ((address >> 32) != 0) return 0; address |= 0xffffffffUL << 32; if ((address >= (u64)_stext && address <= (u64)_etext) || (address >= MODULES_VADDR && address <= MODULES_END)) { printk_once(errata93_warning); regs->ip = address; return 1; } #endif return 0; } /* * Work around K8 erratum #100 K8 in compat mode occasionally jumps * to illegal addresses >4GB. * * We catch this in the page fault handler because these addresses * are not reachable. Just detect this case and return. Any code * segment in LDT is compatibility mode. */ static int is_errata100(struct pt_regs *regs, unsigned long address) { #ifdef CONFIG_X86_64 if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32)) return 1; #endif return 0; } /* Pentium F0 0F C7 C8 bug workaround: */ static int is_f00f_bug(struct pt_regs *regs, unsigned long error_code, unsigned long address) { #ifdef CONFIG_X86_F00F_BUG if (boot_cpu_has_bug(X86_BUG_F00F) && !(error_code & X86_PF_USER) && idt_is_f00f_address(address)) { handle_invalid_op(regs); return 1; } #endif return 0; } static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index) { u32 offset = (index >> 3) * sizeof(struct desc_struct); unsigned long addr; struct ldttss_desc desc; if (index == 0) { pr_alert("%s: NULL\n", name); return; } if (offset + sizeof(struct ldttss_desc) >= gdt->size) { pr_alert("%s: 0x%hx -- out of bounds\n", name, index); return; } if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset), sizeof(struct ldttss_desc))) { pr_alert("%s: 0x%hx -- GDT entry is not readable\n", name, index); return; } addr = desc.base0 | (desc.base1 << 16) | ((unsigned long)desc.base2 << 24); #ifdef CONFIG_X86_64 addr |= ((u64)desc.base3 << 32); #endif pr_alert("%s: 0x%hx -- base=0x%lx limit=0x%x\n", name, index, addr, (desc.limit0 | (desc.limit1 << 16))); } static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address) { if (!oops_may_print()) return; if (error_code & X86_PF_INSTR) { unsigned int level; bool nx, rw; pgd_t *pgd; pte_t *pte; pgd = __va(read_cr3_pa()); pgd += pgd_index(address); pte = lookup_address_in_pgd_attr(pgd, address, &level, &nx, &rw); if (pte && pte_present(*pte) && (!pte_exec(*pte) || nx)) pr_crit("kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", from_kuid(&init_user_ns, current_uid())); if (pte && pte_present(*pte) && pte_exec(*pte) && !nx && (pgd_flags(*pgd) & _PAGE_USER) && (__read_cr4() & X86_CR4_SMEP)) pr_crit("unable to execute userspace code (SMEP?) (uid: %d)\n", from_kuid(&init_user_ns, current_uid())); } if (address < PAGE_SIZE && !user_mode(regs)) pr_alert("BUG: kernel NULL pointer dereference, address: %px\n", (void *)address); else pr_alert("BUG: unable to handle page fault for address: %px\n", (void *)address); pr_alert("#PF: %s %s in %s mode\n", (error_code & X86_PF_USER) ? "user" : "supervisor", (error_code & X86_PF_INSTR) ? "instruction fetch" : (error_code & X86_PF_WRITE) ? "write access" : "read access", user_mode(regs) ? "user" : "kernel"); pr_alert("#PF: error_code(0x%04lx) - %s\n", error_code, !(error_code & X86_PF_PROT) ? "not-present page" : (error_code & X86_PF_RSVD) ? "reserved bit violation" : (error_code & X86_PF_PK) ? "protection keys violation" : (error_code & X86_PF_RMP) ? "RMP violation" : "permissions violation"); if (!(error_code & X86_PF_USER) && user_mode(regs)) { struct desc_ptr idt, gdt; u16 ldtr, tr; /* * This can happen for quite a few reasons. The more obvious * ones are faults accessing the GDT, or LDT. Perhaps * surprisingly, if the CPU tries to deliver a benign or * contributory exception from user code and gets a page fault * during delivery, the page fault can be delivered as though * it originated directly from user code. This could happen * due to wrong permissions on the IDT, GDT, LDT, TSS, or * kernel or IST stack. */ store_idt(&idt); /* Usable even on Xen PV -- it's just slow. */ native_store_gdt(&gdt); pr_alert("IDT: 0x%lx (limit=0x%hx) GDT: 0x%lx (limit=0x%hx)\n", idt.address, idt.size, gdt.address, gdt.size); store_ldt(ldtr); show_ldttss(&gdt, "LDTR", ldtr); store_tr(tr); show_ldttss(&gdt, "TR", tr); } dump_pagetable(address); if (error_code & X86_PF_RMP) snp_dump_hva_rmpentry(address); } static noinline void pgtable_bad(struct pt_regs *regs, unsigned long error_code, unsigned long address) { struct task_struct *tsk; unsigned long flags; int sig; flags = oops_begin(); tsk = current; sig = SIGKILL; printk(KERN_ALERT "%s: Corrupted page table at address %lx\n", tsk->comm, address); dump_pagetable(address); if (__die("Bad pagetable", regs, error_code)) sig = 0; oops_end(flags, regs, sig); } static void sanitize_error_code(unsigned long address, unsigned long *error_code) { /* * To avoid leaking information about the kernel page * table layout, pretend that user-mode accesses to * kernel addresses are always protection faults. * * NB: This means that failed vsyscalls with vsyscall=none * will have the PROT bit. This doesn't leak any * information and does not appear to cause any problems. */ if (address >= TASK_SIZE_MAX) *error_code |= X86_PF_PROT; } static void set_signal_archinfo(unsigned long address, unsigned long error_code) { struct task_struct *tsk = current; tsk->thread.trap_nr = X86_TRAP_PF; tsk->thread.error_code = error_code | X86_PF_USER; tsk->thread.cr2 = address; } static noinline void page_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address) { #ifdef CONFIG_VMAP_STACK struct stack_info info; #endif unsigned long flags; int sig; if (user_mode(regs)) { /* * Implicit kernel access from user mode? Skip the stack * overflow and EFI special cases. */ goto oops; } #ifdef CONFIG_VMAP_STACK /* * Stack overflow? During boot, we can fault near the initial * stack in the direct map, but that's not an overflow -- check * that we're in vmalloc space to avoid this. */ if (is_vmalloc_addr((void *)address) && get_stack_guard_info((void *)address, &info)) { /* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but * double-fault even before we get this far, in which case * we're fine: the double-fault handler will deal with it. * * We don't want to make it all the way into the oops code * and then double-fault, though, because we're likely to * break the console driver and lose most of the stack dump. */ call_on_stack(__this_cpu_ist_top_va(DF) - sizeof(void*), handle_stack_overflow, ASM_CALL_ARG3, , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info)); unreachable(); } #endif /* * Buggy firmware could access regions which might page fault. If * this happens, EFI has a special OOPS path that will try to * avoid hanging the system. */ if (IS_ENABLED(CONFIG_EFI)) efi_crash_gracefully_on_page_fault(address); /* Only not-present faults should be handled by KFENCE. */ if (!(error_code & X86_PF_PROT) && kfence_handle_page_fault(address, error_code & X86_PF_WRITE, regs)) return; oops: /* * Oops. The kernel tried to access some bad page. We'll have to * terminate things with extreme prejudice: */ flags = oops_begin(); show_fault_oops(regs, error_code, address); if (task_stack_end_corrupted(current)) printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); sig = SIGKILL; if (__die("Oops", regs, error_code)) sig = 0; /* Executive summary in case the body of the oops scrolled away */ printk(KERN_DEFAULT "CR2: %016lx\n", address); oops_end(flags, regs, sig); } static noinline void kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address, int signal, int si_code, u32 pkey) { WARN_ON_ONCE(user_mode(regs)); /* Are we prepared to handle this kernel fault? */ if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) return; /* * AMD erratum #91 manifests as a spurious page fault on a PREFETCH * instruction. */ if (is_prefetch(regs, error_code, address)) return; page_fault_oops(regs, error_code, address); } /* * Print out info about fatal segfaults, if the show_unhandled_signals * sysctl is set: */ static inline void show_signal_msg(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct task_struct *tsk) { const char *loglvl = task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG; /* This is a racy snapshot, but it's better than nothing. */ int cpu = raw_smp_processor_id(); if (!unhandled_signal(tsk, SIGSEGV)) return; if (!printk_ratelimit()) return; printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx", loglvl, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); print_vma_addr(KERN_CONT " in ", regs->ip); /* * Dump the likely CPU where the fatal segfault happened. * This can help identify faulty hardware. */ printk(KERN_CONT " likely on CPU %d (core %d, socket %d)", cpu, topology_core_id(cpu), topology_physical_package_id(cpu)); printk(KERN_CONT "\n"); show_opcodes(regs, loglvl); } static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) { struct task_struct *tsk = current; if (!user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, SIGSEGV, si_code, pkey); return; } if (!(error_code & X86_PF_USER)) { /* Implicit user access to kernel memory -- just oops */ page_fault_oops(regs, error_code, address); return; } /* * User mode accesses just cause a SIGSEGV. * It's possible to have interrupts off here: */ local_irq_enable(); /* * Valid to do another page fault here because this one came * from user space: */ if (is_prefetch(regs, error_code, address)) return; if (is_errata100(regs, address)) return; sanitize_error_code(address, &error_code); if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address)) return; if (likely(show_unhandled_signals)) show_signal_msg(regs, error_code, address, tsk); set_signal_archinfo(address, error_code); if (si_code == SEGV_PKUERR) force_sig_pkuerr((void __user *)address, pkey); else force_sig_fault(SIGSEGV, si_code, (void __user *)address); local_irq_disable(); } static noinline void bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address) { __bad_area_nosemaphore(regs, error_code, address, 0, SEGV_MAPERR); } static void __bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct mm_struct *mm, struct vm_area_struct *vma, u32 pkey, int si_code) { /* * Something tried to access memory that isn't in our memory map.. * Fix it, but check if it's kernel or user first.. */ if (mm) mmap_read_unlock(mm); else vma_end_read(vma); __bad_area_nosemaphore(regs, error_code, address, pkey, si_code); } static inline bool bad_area_access_from_pkeys(unsigned long error_code, struct vm_area_struct *vma) { /* This code is always called on the current mm */ bool foreign = false; if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) return false; if (error_code & X86_PF_PK) return true; /* this checks permission keys on the VMA: */ if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), (error_code & X86_PF_INSTR), foreign)) return true; return false; } static noinline void bad_area_access_error(struct pt_regs *regs, unsigned long error_code, unsigned long address, struct mm_struct *mm, struct vm_area_struct *vma) { /* * This OSPKE check is not strictly necessary at runtime. * But, doing it this way allows compiler optimizations * if pkeys are compiled out. */ if (bad_area_access_from_pkeys(error_code, vma)) { /* * A protection key fault means that the PKRU value did not allow * access to some PTE. Userspace can figure out what PKRU was * from the XSAVE state. This function captures the pkey from * the vma and passes it to userspace so userspace can discover * which protection key was set on the PTE. * * If we get here, we know that the hardware signaled a X86_PF_PK * fault and that there was a VMA once we got in the fault * handler. It does *not* guarantee that the VMA we find here * was the one that we faulted on. * * 1. T1 : mprotect_key(foo, PAGE_SIZE, pkey=4); * 2. T1 : set PKRU to deny access to pkey=4, touches page * 3. T1 : faults... * 4. T2: mprotect_key(foo, PAGE_SIZE, pkey=5); * 5. T1 : enters fault handler, takes mmap_lock, etc... * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ u32 pkey = vma_pkey(vma); __bad_area(regs, error_code, address, mm, vma, pkey, SEGV_PKUERR); } else { __bad_area(regs, error_code, address, mm, vma, 0, SEGV_ACCERR); } } static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, vm_fault_t fault) { /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY); return; } /* User-space => ok to do another page fault: */ if (is_prefetch(regs, error_code, address)) return; sanitize_error_code(address, &error_code); if (fixup_vdso_exception(regs, X86_TRAP_PF, error_code, address)) return; set_signal_archinfo(address, error_code); #ifdef CONFIG_MEMORY_FAILURE if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) { struct task_struct *tsk = current; unsigned lsb = 0; pr_err( "MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n", tsk->comm, tsk->pid, address); if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); if (fault & VM_FAULT_HWPOISON) lsb = PAGE_SHIFT; force_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, lsb); return; } #endif force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address); } static int spurious_kernel_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & X86_PF_WRITE) && !pte_write(*pte)) return 0; if ((error_code & X86_PF_INSTR) && !pte_exec(*pte)) return 0; return 1; } /* * Handle a spurious fault caused by a stale TLB entry. * * This allows us to lazily refresh the TLB when increasing the * permissions of a kernel page (RO -> RW or NX -> X). Doing it * eagerly is very expensive since that implies doing a full * cross-processor TLB flush, even if no stale TLB entries exist * on other processors. * * Spurious faults may only occur if the TLB contains an entry with * fewer permission than the page table entry. Non-present (P = 0) * and reserved bit (R = 1) faults are never spurious. * * There are no security implications to leaving a stale TLB when * increasing the permissions on a page. * * Returns non-zero if a spurious fault was handled, zero otherwise. * * See Intel Developer's Manual Vol 3 Section 4.10.4.3, bullet 3 * (Optional Invalidation). */ static noinline int spurious_kernel_fault(unsigned long error_code, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; int ret; /* * Only writes to RO or instruction fetches from NX may cause * spurious faults. * * These could be from user or supervisor accesses but the TLB * is only lazily flushed after a kernel mapping protection * change, so user accesses are not expected to cause spurious * faults. */ if (error_code != (X86_PF_WRITE | X86_PF_PROT) && error_code != (X86_PF_INSTR | X86_PF_PROT)) return 0; pgd = init_mm.pgd + pgd_index(address); if (!pgd_present(*pgd)) return 0; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) return 0; if (p4d_leaf(*p4d)) return spurious_kernel_fault_check(error_code, (pte_t *) p4d); pud = pud_offset(p4d, address); if (!pud_present(*pud)) return 0; if (pud_leaf(*pud)) return spurious_kernel_fault_check(error_code, (pte_t *) pud); pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return 0; if (pmd_leaf(*pmd)) return spurious_kernel_fault_check(error_code, (pte_t *) pmd); pte = pte_offset_kernel(pmd, address); if (!pte_present(*pte)) return 0; ret = spurious_kernel_fault_check(error_code, pte); if (!ret) return 0; /* * Make sure we have permissions in PMD. * If not, then there's a bug in the page tables: */ ret = spurious_kernel_fault_check(error_code, (pte_t *) pmd); WARN_ONCE(!ret, "PMD has incorrect permission bits\n"); return ret; } NOKPROBE_SYMBOL(spurious_kernel_fault); int show_unhandled_signals = 1; static inline int access_error(unsigned long error_code, struct vm_area_struct *vma) { /* This is only called for the current mm, so: */ bool foreign = false; /* * Read or write was blocked by protection keys. This is * always an unconditional error and can never result in * a follow-up action to resolve the fault, like a COW. */ if (error_code & X86_PF_PK) return 1; /* * SGX hardware blocked the access. This usually happens * when the enclave memory contents have been destroyed, like * after a suspend/resume cycle. In any case, the kernel can't * fix the cause of the fault. Handle the fault as an access * error even in cases where no actual access violation * occurred. This allows userspace to rebuild the enclave in * response to the signal. */ if (unlikely(error_code & X86_PF_SGX)) return 1; /* * Make sure to check the VMA so that we do not perform * faults just to hit a X86_PF_PK as soon as we fill in a * page. */ if (!arch_vma_access_permitted(vma, (error_code & X86_PF_WRITE), (error_code & X86_PF_INSTR), foreign)) return 1; /* * Shadow stack accesses (PF_SHSTK=1) are only permitted to * shadow stack VMAs. All other accesses result in an error. */ if (error_code & X86_PF_SHSTK) { if (unlikely(!(vma->vm_flags & VM_SHADOW_STACK))) return 1; if (unlikely(!(vma->vm_flags & VM_WRITE))) return 1; return 0; } if (error_code & X86_PF_WRITE) { /* write, present and write, not present: */ if (unlikely(vma->vm_flags & VM_SHADOW_STACK)) return 1; if (unlikely(!(vma->vm_flags & VM_WRITE))) return 1; return 0; } /* read, present: */ if (unlikely(error_code & X86_PF_PROT)) return 1; /* read, not present: */ if (unlikely(!vma_is_accessible(vma))) return 1; return 0; } bool fault_in_kernel_space(unsigned long address) { /* * On 64-bit systems, the vsyscall page is at an address above * TASK_SIZE_MAX, but is not considered part of the kernel * address space. */ if (IS_ENABLED(CONFIG_X86_64) && is_vsyscall_vaddr(address)) return false; return address >= TASK_SIZE_MAX; } /* * Called for all faults where 'address' is part of the kernel address * space. Might get called for faults that originate from *code* that * ran in userspace or the kernel. */ static void do_kern_addr_fault(struct pt_regs *regs, unsigned long hw_error_code, unsigned long address) { /* * Protection keys exceptions only happen on user pages. We * have no user pages in the kernel portion of the address * space, so do not expect them here. */ WARN_ON_ONCE(hw_error_code & X86_PF_PK); #ifdef CONFIG_X86_32 /* * We can fault-in kernel-space virtual memory on-demand. The * 'reference' page table is init_mm.pgd. * * NOTE! We MUST NOT take any locks for this case. We may * be in an interrupt or a critical region, and should * only copy the information from the master page table, * nothing more. * * Before doing this on-demand faulting, ensure that the * fault is not any of the following: * 1. A fault on a PTE with a reserved bit set. * 2. A fault caused by a user-mode access. (Do not demand- * fault kernel memory due to user-mode accesses). * 3. A fault caused by a page-level protection violation. * (A demand fault would be on a non-present page which * would have X86_PF_PROT==0). * * This is only needed to close a race condition on x86-32 in * the vmalloc mapping/unmapping code. See the comment above * vmalloc_fault() for details. On x86-64 the race does not * exist as the vmalloc mappings don't need to be synchronized * there. */ if (!(hw_error_code & (X86_PF_RSVD | X86_PF_USER | X86_PF_PROT))) { if (vmalloc_fault(address) >= 0) return; } #endif if (is_f00f_bug(regs, hw_error_code, address)) return; /* Was the fault spurious, caused by lazy TLB invalidation? */ if (spurious_kernel_fault(hw_error_code, address)) return; /* kprobes don't want to hook the spurious faults: */ if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF))) return; /* * Note, despite being a "bad area", there are quite a few * acceptable reasons to get here, such as erratum fixups * and handling kernel code that can fault, like get_user(). * * Don't take the mm semaphore here. If we fixup a prefetch * fault we could otherwise deadlock: */ bad_area_nosemaphore(regs, hw_error_code, address); } NOKPROBE_SYMBOL(do_kern_addr_fault); /* * Handle faults in the user portion of the address space. Nothing in here * should check X86_PF_USER without a specific justification: for almost * all purposes, we should treat a normal kernel access to user memory * (e.g. get_user(), put_user(), etc.) the same as the WRUSS instruction. * The one exception is AC flag handling, which is, per the x86 * architecture, special for WRUSS. */ static inline void do_user_addr_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { struct vm_area_struct *vma; struct task_struct *tsk; struct mm_struct *mm; vm_fault_t fault; unsigned int flags = FAULT_FLAG_DEFAULT; tsk = current; mm = tsk->mm; if (unlikely((error_code & (X86_PF_USER | X86_PF_INSTR)) == X86_PF_INSTR)) { /* * Whoops, this is kernel mode code trying to execute from * user memory. Unless this is AMD erratum #93, which * corrupts RIP such that it looks like a user address, * this is unrecoverable. Don't even try to look up the * VMA or look for extable entries. */ if (is_errata93(regs, address)) return; page_fault_oops(regs, error_code, address); return; } /* kprobes don't want to hook the spurious faults: */ if (WARN_ON_ONCE(kprobe_page_fault(regs, X86_TRAP_PF))) return; /* * Reserved bits are never expected to be set on * entries in the user portion of the page tables. */ if (unlikely(error_code & X86_PF_RSVD)) pgtable_bad(regs, error_code, address); /* * If SMAP is on, check for invalid kernel (supervisor) access to user * pages in the user address space. The odd case here is WRUSS, * which, according to the preliminary documentation, does not respect * SMAP and will have the USER bit set so, in all cases, SMAP * enforcement appears to be consistent with the USER bit. */ if (unlikely(cpu_feature_enabled(X86_FEATURE_SMAP) && !(error_code & X86_PF_USER) && !(regs->flags & X86_EFLAGS_AC))) { /* * No extable entry here. This was a kernel access to an * invalid pointer. get_kernel_nofault() will not get here. */ page_fault_oops(regs, error_code, address); return; } /* * If we're in an interrupt, have no user context or are running * in a region with pagefaults disabled then we must not take the fault */ if (unlikely(faulthandler_disabled() || !mm)) { bad_area_nosemaphore(regs, error_code, address); return; } /* Legacy check - remove this after verifying that it doesn't trigger */ if (WARN_ON_ONCE(!(regs->flags & X86_EFLAGS_IF))) { bad_area_nosemaphore(regs, error_code, address); return; } local_irq_enable(); perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); /* * Read-only permissions can not be expressed in shadow stack PTEs. * Treat all shadow stack accesses as WRITE faults. This ensures * that the MM will prepare everything (e.g., break COW) such that * maybe_mkwrite() can create a proper shadow stack PTE. */ if (error_code & X86_PF_SHSTK) flags |= FAULT_FLAG_WRITE; if (error_code & X86_PF_WRITE) flags |= FAULT_FLAG_WRITE; if (error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; /* * We set FAULT_FLAG_USER based on the register state, not * based on X86_PF_USER. User space accesses that cause * system page faults are still user accesses. */ if (user_mode(regs)) flags |= FAULT_FLAG_USER; #ifdef CONFIG_X86_64 /* * Faults in the vsyscall page might need emulation. The * vsyscall page is at a high address (>PAGE_OFFSET), but is * considered to be part of the user address space. * * The vsyscall page does not have a "real" VMA, so do this * emulation before we go searching for VMAs. * * PKRU never rejects instruction fetches, so we don't need * to consider the PF_PK bit. */ if (is_vsyscall_vaddr(address)) { if (emulate_vsyscall(error_code, regs, address)) return; } #endif if (!(flags & FAULT_FLAG_USER)) goto lock_mmap; vma = lock_vma_under_rcu(mm, address); if (!vma) goto lock_mmap; if (unlikely(access_error(error_code, vma))) { bad_area_access_error(regs, error_code, address, NULL, vma); count_vm_vma_lock_event(VMA_LOCK_SUCCESS); return; } fault = handle_mm_fault(vma, address, flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); if (fault & VM_FAULT_MAJOR) flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY); return; } lock_mmap: retry: vma = lock_mm_and_find_vma(mm, address, regs); if (unlikely(!vma)) { bad_area_nosemaphore(regs, error_code, address); return; } /* * Ok, we have a good vm_area for this memory access, so * we can handle it.. */ if (unlikely(access_error(error_code, vma))) { bad_area_access_error(regs, error_code, address, mm, vma); return; } /* * If for any reason at all we couldn't handle the fault, * make sure we exit gracefully rather than endlessly redo * the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if * we get VM_FAULT_RETRY back, the mmap_lock has been unlocked. * * Note that handle_userfault() may also release and reacquire mmap_lock * (and not return with VM_FAULT_RETRY), when returning to userland to * repeat the page fault later with a VM_FAULT_NOPAGE retval * (potentially after handling any pending signal during the return to * userland). The return to userland is identified whenever * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags. */ fault = handle_mm_fault(vma, address, flags, regs); if (fault_signal_pending(fault, regs)) { /* * Quick path to respond to signals. The core mm code * has unlocked the mm for us if we get here. */ if (!user_mode(regs)) kernelmode_fixup_or_oops(regs, error_code, address, SIGBUS, BUS_ADRERR, ARCH_DEFAULT_PKEY); return; } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) return; /* * If we need to retry the mmap_lock has already been released, * and if there is a fatal signal pending there is no guarantee * that we made any progress. Handle this case first. */ if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); done: if (likely(!(fault & VM_FAULT_ERROR))) return; if (fatal_signal_pending(current) && !user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, 0, 0, ARCH_DEFAULT_PKEY); return; } if (fault & VM_FAULT_OOM) { /* Kernel mode? Handle exceptions or die: */ if (!user_mode(regs)) { kernelmode_fixup_or_oops(regs, error_code, address, SIGSEGV, SEGV_MAPERR, ARCH_DEFAULT_PKEY); return; } /* * We ran out of memory, call the OOM killer, and return the * userspace (which will retry the fault, or kill us if we got * oom-killed): */ pagefault_out_of_memory(); } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) do_sigbus(regs, error_code, address, fault); else if (fault & VM_FAULT_SIGSEGV) bad_area_nosemaphore(regs, error_code, address); else BUG(); } } NOKPROBE_SYMBOL(do_user_addr_fault); static __always_inline void trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code, unsigned long address) { if (!trace_pagefault_enabled()) return; if (user_mode(regs)) trace_page_fault_user(address, regs, error_code); else trace_page_fault_kernel(address, regs, error_code); } static __always_inline void handle_page_fault(struct pt_regs *regs, unsigned long error_code, unsigned long address) { trace_page_fault_entries(regs, error_code, address); if (unlikely(kmmio_fault(regs, address))) return; /* Was the fault on kernel-controlled part of the address space? */ if (unlikely(fault_in_kernel_space(address))) { do_kern_addr_fault(regs, error_code, address); } else { do_user_addr_fault(regs, error_code, address); /* * User address page fault handling might have reenabled * interrupts. Fixing up all potential exit points of * do_user_addr_fault() and its leaf functions is just not * doable w/o creating an unholy mess or turning the code * upside down. */ local_irq_disable(); } } DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) { irqentry_state_t state; unsigned long address; address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2(); prefetchw(¤t->mm->mmap_lock); /* * KVM uses #PF vector to deliver 'page not present' events to guests * (asynchronous page fault mechanism). The event happens when a * userspace task is trying to access some valid (from guest's point of * view) memory which is not currently mapped by the host (e.g. the * memory is swapped out). Note, the corresponding "page ready" event * which is injected when the memory becomes available, is delivered via * an interrupt mechanism and not a #PF exception * (see arch/x86/kernel/kvm.c: sysvec_kvm_asyncpf_interrupt()). * * We are relying on the interrupted context being sane (valid RSP, * relevant locks not held, etc.), which is fine as long as the * interrupted context had IF=1. We are also relying on the KVM * async pf type field and CR2 being read consistently instead of * getting values from real and async page faults mixed up. * * Fingers crossed. * * The async #PF handling code takes care of idtentry handling * itself. */ if (kvm_handle_async_pf(regs, (u32)address)) return; /* * Entry handling for valid #PF from kernel mode is slightly * different: RCU is already watching and ct_irq_enter() must not * be invoked because a kernel fault on a user space address might * sleep. * * In case the fault hit a RCU idle region the conditional entry * code reenabled RCU to avoid subsequent wreckage which helps * debuggability. */ state = irqentry_enter(regs); instrumentation_begin(); handle_page_fault(regs, error_code, address); instrumentation_end(); irqentry_exit(regs, state); } |
| 10569 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM x86_fpu #if !defined(_TRACE_FPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FPU_H #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(x86_fpu, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu), TP_STRUCT__entry( __field(struct fpu *, fpu) __field(bool, load_fpu) __field(u64, xfeatures) __field(u64, xcomp_bv) ), TP_fast_assign( __entry->fpu = fpu; __entry->load_fpu = test_thread_flag(TIF_NEED_FPU_LOAD); if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { __entry->xfeatures = fpu->fpstate->regs.xsave.header.xfeatures; __entry->xcomp_bv = fpu->fpstate->regs.xsave.header.xcomp_bv; } ), TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx", __entry->fpu, __entry->load_fpu, __entry->xfeatures, __entry->xcomp_bv ) ); DEFINE_EVENT(x86_fpu, x86_fpu_before_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_after_save, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_before_restore, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_after_restore, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_init_state, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_dropped, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_copy_src, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); DEFINE_EVENT(x86_fpu, x86_fpu_xstate_check_failed, TP_PROTO(struct fpu *fpu), TP_ARGS(fpu) ); #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH asm/trace/ #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE fpu #endif /* _TRACE_FPU_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 39 1 1 4 33 1 2 1 18 3 3 8 1 26 1 22 3 1 2 2 2 1 6 14 2 2 4 2 3 1 18 18 4 22 20 2 18 4 22 22 22 10 1 16 10 1 15 15 12 3 13 2 12 3 15 15 15 15 20 19 1 1 1 1 21 20 20 19 20 20 20 20 20 20 1 17 2 6 6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_police.c Input police filter * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * J Hadi Salim (action changes) */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <net/act_api.h> #include <net/gso.h> #include <net/netlink.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_police.h> #include <net/tc_wrapper.h> /* Each policer is serialized by its individual spinlock */ static struct tc_action_ops act_police_ops; static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { [TCA_POLICE_RATE] = { .len = TC_RTAB_SIZE }, [TCA_POLICE_PEAKRATE] = { .len = TC_RTAB_SIZE }, [TCA_POLICE_AVRATE] = { .type = NLA_U32 }, [TCA_POLICE_RESULT] = { .type = NLA_U32 }, [TCA_POLICE_RATE64] = { .type = NLA_U64 }, [TCA_POLICE_PEAKRATE64] = { .type = NLA_U64 }, [TCA_POLICE_PKTRATE64] = { .type = NLA_U64, .min = 1 }, [TCA_POLICE_PKTBURST64] = { .type = NLA_U64, .min = 1 }, }; static int tcf_police_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 flags, struct netlink_ext_ack *extack) { int ret = 0, tcfp_result = TC_ACT_OK, err, size; bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_POLICE_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_police *parm; struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, act_police_ops.net_id); struct tcf_police_params *new; bool exists = false; u32 index; u64 rate64, prate64; u64 pps, ppsburst; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_POLICE_MAX, nla, police_policy, NULL); if (err < 0) return err; if (tb[TCA_POLICE_TBF] == NULL) return -EINVAL; size = nla_len(tb[TCA_POLICE_TBF]); if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat)) return -EINVAL; parm = nla_data(tb[TCA_POLICE_TBF]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (!exists) { ret = tcf_idr_create(tn, index, NULL, a, &act_police_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; spin_lock_init(&(to_police(*a)->tcfp_lock)); } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; police = to_police(*a); if (parm->rate.rate) { err = -ENOMEM; R_tab = qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE], NULL); if (R_tab == NULL) goto failure; if (parm->peakrate.rate) { P_tab = qdisc_get_rtab(&parm->peakrate, tb[TCA_POLICE_PEAKRATE], NULL); if (P_tab == NULL) goto failure; } } if (est) { err = gen_replace_estimator(&police->tcf_bstats, police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, false, est); if (err) goto failure; } else if (tb[TCA_POLICE_AVRATE] && (ret == ACT_P_CREATED || !gen_estimator_active(&police->tcf_rate_est))) { err = -EINVAL; goto failure; } if (tb[TCA_POLICE_RESULT]) { tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) { NL_SET_ERR_MSG(extack, "goto chain not allowed on fallback"); err = -EINVAL; goto failure; } } if ((tb[TCA_POLICE_PKTRATE64] && !tb[TCA_POLICE_PKTBURST64]) || (!tb[TCA_POLICE_PKTRATE64] && tb[TCA_POLICE_PKTBURST64])) { NL_SET_ERR_MSG(extack, "Both or neither packet-per-second burst and rate must be provided"); err = -EINVAL; goto failure; } if (tb[TCA_POLICE_PKTRATE64] && R_tab) { NL_SET_ERR_MSG(extack, "packet-per-second and byte-per-second rate limits not allowed in same action"); err = -EINVAL; goto failure; } new = kzalloc(sizeof(*new), GFP_KERNEL); if (unlikely(!new)) { err = -ENOMEM; goto failure; } /* No failure allowed after this point */ new->tcfp_result = tcfp_result; new->tcfp_mtu = parm->mtu; if (!new->tcfp_mtu) { new->tcfp_mtu = ~0; if (R_tab) new->tcfp_mtu = 255 << R_tab->rate.cell_log; } if (R_tab) { new->rate_present = true; rate64 = tb[TCA_POLICE_RATE64] ? nla_get_u64(tb[TCA_POLICE_RATE64]) : 0; psched_ratecfg_precompute(&new->rate, &R_tab->rate, rate64); qdisc_put_rtab(R_tab); } else { new->rate_present = false; } if (P_tab) { new->peak_present = true; prate64 = tb[TCA_POLICE_PEAKRATE64] ? nla_get_u64(tb[TCA_POLICE_PEAKRATE64]) : 0; psched_ratecfg_precompute(&new->peak, &P_tab->rate, prate64); qdisc_put_rtab(P_tab); } else { new->peak_present = false; } new->tcfp_burst = PSCHED_TICKS2NS(parm->burst); if (new->peak_present) new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak, new->tcfp_mtu); if (tb[TCA_POLICE_AVRATE]) new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); if (tb[TCA_POLICE_PKTRATE64]) { pps = nla_get_u64(tb[TCA_POLICE_PKTRATE64]); ppsburst = nla_get_u64(tb[TCA_POLICE_PKTBURST64]); new->pps_present = true; new->tcfp_pkt_burst = PSCHED_TICKS2NS(ppsburst); psched_ppscfg_precompute(&new->ppsrate, pps); } spin_lock_bh(&police->tcf_lock); spin_lock_bh(&police->tcfp_lock); police->tcfp_t_c = ktime_get_ns(); police->tcfp_toks = new->tcfp_burst; if (new->peak_present) police->tcfp_ptoks = new->tcfp_mtu_ptoks; spin_unlock_bh(&police->tcfp_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); new = rcu_replace_pointer(police->params, new, lockdep_is_held(&police->tcf_lock)); spin_unlock_bh(&police->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (new) kfree_rcu(new, rcu); return ret; failure: qdisc_put_rtab(P_tab); qdisc_put_rtab(R_tab); if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static bool tcf_police_mtu_check(struct sk_buff *skb, u32 limit) { u32 len; if (skb_is_gso(skb)) return skb_gso_validate_mac_len(skb, limit); len = qdisc_pkt_len(skb); if (skb_at_tc_ingress(skb)) len += skb->mac_len; return len <= limit; } TC_INDIRECT_SCOPE int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_police *police = to_police(a); s64 now, toks, ppstoks = 0, ptoks = 0; struct tcf_police_params *p; int ret; tcf_lastuse_update(&police->tcf_tm); bstats_update(this_cpu_ptr(police->common.cpu_bstats), skb); ret = READ_ONCE(police->tcf_action); p = rcu_dereference_bh(police->params); if (p->tcfp_ewma_rate) { struct gnet_stats_rate_est64 sample; if (!gen_estimator_read(&police->tcf_rate_est, &sample) || sample.bps >= p->tcfp_ewma_rate) goto inc_overlimits; } if (tcf_police_mtu_check(skb, p->tcfp_mtu)) { if (!p->rate_present && !p->pps_present) { ret = p->tcfp_result; goto end; } now = ktime_get_ns(); spin_lock_bh(&police->tcfp_lock); toks = min_t(s64, now - police->tcfp_t_c, p->tcfp_burst); if (p->peak_present) { ptoks = toks + police->tcfp_ptoks; if (ptoks > p->tcfp_mtu_ptoks) ptoks = p->tcfp_mtu_ptoks; ptoks -= (s64)psched_l2t_ns(&p->peak, qdisc_pkt_len(skb)); } if (p->rate_present) { toks += police->tcfp_toks; if (toks > p->tcfp_burst) toks = p->tcfp_burst; toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); } else if (p->pps_present) { ppstoks = min_t(s64, now - police->tcfp_t_c, p->tcfp_pkt_burst); ppstoks += police->tcfp_pkttoks; if (ppstoks > p->tcfp_pkt_burst) ppstoks = p->tcfp_pkt_burst; ppstoks -= (s64)psched_pkt2t_ns(&p->ppsrate, 1); } if ((toks | ptoks | ppstoks) >= 0) { police->tcfp_t_c = now; police->tcfp_toks = toks; police->tcfp_ptoks = ptoks; police->tcfp_pkttoks = ppstoks; spin_unlock_bh(&police->tcfp_lock); ret = p->tcfp_result; goto inc_drops; } spin_unlock_bh(&police->tcfp_lock); } inc_overlimits: qstats_overlimit_inc(this_cpu_ptr(police->common.cpu_qstats)); inc_drops: if (ret == TC_ACT_SHOT) qstats_drop_inc(this_cpu_ptr(police->common.cpu_qstats)); end: return ret; } static void tcf_police_cleanup(struct tc_action *a) { struct tcf_police *police = to_police(a); struct tcf_police_params *p; p = rcu_dereference_protected(police->params, 1); if (p) kfree_rcu(p, rcu); } static void tcf_police_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_police *police = to_police(a); struct tcf_t *tm = &police->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_police *police = to_police(a); struct tcf_police_params *p; struct tc_police opt = { .index = police->tcf_index, .refcnt = refcount_read(&police->tcf_refcnt) - ref, .bindcnt = atomic_read(&police->tcf_bindcnt) - bind, }; struct tcf_t t; spin_lock_bh(&police->tcf_lock); opt.action = police->tcf_action; p = rcu_dereference_protected(police->params, lockdep_is_held(&police->tcf_lock)); opt.mtu = p->tcfp_mtu; opt.burst = PSCHED_NS2TICKS(p->tcfp_burst); if (p->rate_present) { psched_ratecfg_getrate(&opt.rate, &p->rate); if ((p->rate.rate_bytes_ps >= (1ULL << 32)) && nla_put_u64_64bit(skb, TCA_POLICE_RATE64, p->rate.rate_bytes_ps, TCA_POLICE_PAD)) goto nla_put_failure; } if (p->peak_present) { psched_ratecfg_getrate(&opt.peakrate, &p->peak); if ((p->peak.rate_bytes_ps >= (1ULL << 32)) && nla_put_u64_64bit(skb, TCA_POLICE_PEAKRATE64, p->peak.rate_bytes_ps, TCA_POLICE_PAD)) goto nla_put_failure; } if (p->pps_present) { if (nla_put_u64_64bit(skb, TCA_POLICE_PKTRATE64, p->ppsrate.rate_pkts_ps, TCA_POLICE_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(skb, TCA_POLICE_PKTBURST64, PSCHED_NS2TICKS(p->tcfp_pkt_burst), TCA_POLICE_PAD)) goto nla_put_failure; } if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; if (p->tcfp_result && nla_put_u32(skb, TCA_POLICE_RESULT, p->tcfp_result)) goto nla_put_failure; if (p->tcfp_ewma_rate && nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate)) goto nla_put_failure; tcf_tm_dump(&t, &police->tcf_tm); if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD)) goto nla_put_failure; spin_unlock_bh(&police->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&police->tcf_lock); nlmsg_trim(skb, b); return -1; } static int tcf_police_act_to_flow_act(int tc_act, u32 *extval, struct netlink_ext_ack *extack) { int act_id = -EOPNOTSUPP; if (!TC_ACT_EXT_OPCODE(tc_act)) { if (tc_act == TC_ACT_OK) act_id = FLOW_ACTION_ACCEPT; else if (tc_act == TC_ACT_SHOT) act_id = FLOW_ACTION_DROP; else if (tc_act == TC_ACT_PIPE) act_id = FLOW_ACTION_PIPE; else if (tc_act == TC_ACT_RECLASSIFY) NL_SET_ERR_MSG_MOD(extack, "Offload not supported when conform/exceed action is \"reclassify\""); else NL_SET_ERR_MSG_MOD(extack, "Unsupported conform/exceed action offload"); } else if (TC_ACT_EXT_CMP(tc_act, TC_ACT_GOTO_CHAIN)) { act_id = FLOW_ACTION_GOTO; *extval = tc_act & TC_ACT_EXT_VAL_MASK; } else if (TC_ACT_EXT_CMP(tc_act, TC_ACT_JUMP)) { act_id = FLOW_ACTION_JUMP; *extval = tc_act & TC_ACT_EXT_VAL_MASK; } else if (tc_act == TC_ACT_UNSPEC) { act_id = FLOW_ACTION_CONTINUE; } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported conform/exceed action offload"); } return act_id; } static int tcf_police_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; struct tcf_police *police = to_police(act); struct tcf_police_params *p; int act_id; p = rcu_dereference_protected(police->params, lockdep_is_held(&police->tcf_lock)); entry->id = FLOW_ACTION_POLICE; entry->police.burst = tcf_police_burst(act); entry->police.rate_bytes_ps = tcf_police_rate_bytes_ps(act); entry->police.peakrate_bytes_ps = tcf_police_peakrate_bytes_ps(act); entry->police.avrate = tcf_police_tcfp_ewma_rate(act); entry->police.overhead = tcf_police_rate_overhead(act); entry->police.burst_pkt = tcf_police_burst_pkt(act); entry->police.rate_pkt_ps = tcf_police_rate_pkt_ps(act); entry->police.mtu = tcf_police_tcfp_mtu(act); act_id = tcf_police_act_to_flow_act(police->tcf_action, &entry->police.exceed.extval, extack); if (act_id < 0) return act_id; entry->police.exceed.act_id = act_id; act_id = tcf_police_act_to_flow_act(p->tcfp_result, &entry->police.notexceed.extval, extack); if (act_id < 0) return act_id; entry->police.notexceed.act_id = act_id; *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; fl_action->id = FLOW_ACTION_POLICE; } return 0; } MODULE_AUTHOR("Alexey Kuznetsov"); MODULE_DESCRIPTION("Policing actions"); MODULE_LICENSE("GPL"); static struct tc_action_ops act_police_ops = { .kind = "police", .id = TCA_ID_POLICE, .owner = THIS_MODULE, .stats_update = tcf_police_stats_update, .act = tcf_police_act, .dump = tcf_police_dump, .init = tcf_police_init, .cleanup = tcf_police_cleanup, .offload_act_setup = tcf_police_offload_act_setup, .size = sizeof(struct tcf_police), }; MODULE_ALIAS_NET_ACT("police"); static __net_init int police_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_police_ops.net_id); return tc_action_net_init(net, tn, &act_police_ops); } static void __net_exit police_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_police_ops.net_id); } static struct pernet_operations police_net_ops = { .init = police_init_net, .exit_batch = police_exit_net, .id = &act_police_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init police_init_module(void) { return tcf_register_action(&act_police_ops, &police_net_ops); } static void __exit police_cleanup_module(void) { tcf_unregister_action(&act_police_ops, &police_net_ops); } module_init(police_init_module); module_exit(police_cleanup_module); |
| 10 2 1 1 5 1 1 1 1 1 1 1 6 2 1 3 1 1 2 2 2 2 2 1 1 1 18 9 7 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2016 Laura Garcia <nevola@gmail.com> */ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <linux/jhash.h> struct nft_jhash { u8 sreg; u8 dreg; u8 len; bool autogen_seed:1; u32 modulus; u32 seed; u32 offset; }; static void nft_jhash_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_jhash *priv = nft_expr_priv(expr); const void *data = ®s->data[priv->sreg]; u32 h; h = reciprocal_scale(jhash(data, priv->len, priv->seed), priv->modulus); regs->data[priv->dreg] = h + priv->offset; } struct nft_symhash { u8 dreg; u32 modulus; u32 offset; }; static void nft_symhash_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct nft_symhash *priv = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; u32 h; h = reciprocal_scale(__skb_get_hash_symmetric_net(nft_net(pkt), skb), priv->modulus); regs->data[priv->dreg] = h + priv->offset; } static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_SREG] = { .type = NLA_U32 }, [NFTA_HASH_DREG] = { .type = NLA_U32 }, [NFTA_HASH_LEN] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_HASH_MODULUS] = { .type = NLA_U32 }, [NFTA_HASH_SEED] = { .type = NLA_U32 }, [NFTA_HASH_OFFSET] = { .type = NLA_U32 }, [NFTA_HASH_TYPE] = { .type = NLA_U32 }, }; static int nft_jhash_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_jhash *priv = nft_expr_priv(expr); u32 len; int err; if (!tb[NFTA_HASH_SREG] || !tb[NFTA_HASH_DREG] || !tb[NFTA_HASH_LEN] || !tb[NFTA_HASH_MODULUS]) return -EINVAL; if (tb[NFTA_HASH_OFFSET]) priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); err = nft_parse_u32_check(tb[NFTA_HASH_LEN], U8_MAX, &len); if (err < 0) return err; if (len == 0) return -ERANGE; priv->len = len; err = nft_parse_register_load(tb[NFTA_HASH_SREG], &priv->sreg, len); if (err < 0) return err; priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); if (priv->modulus < 1) return -ERANGE; if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; if (tb[NFTA_HASH_SEED]) { priv->seed = ntohl(nla_get_be32(tb[NFTA_HASH_SEED])); } else { priv->autogen_seed = true; get_random_bytes(&priv->seed, sizeof(priv->seed)); } return nft_parse_register_store(ctx, tb[NFTA_HASH_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, sizeof(u32)); } static int nft_symhash_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_symhash *priv = nft_expr_priv(expr); if (!tb[NFTA_HASH_DREG] || !tb[NFTA_HASH_MODULUS]) return -EINVAL; if (tb[NFTA_HASH_OFFSET]) priv->offset = ntohl(nla_get_be32(tb[NFTA_HASH_OFFSET])); priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); if (priv->modulus < 1) return -ERANGE; if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; return nft_parse_register_store(ctx, tb[NFTA_HASH_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, sizeof(u32)); } static int nft_jhash_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_jhash *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_HASH_SREG, priv->sreg)) goto nla_put_failure; if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_LEN, htonl(priv->len))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus))) goto nla_put_failure; if (!priv->autogen_seed && nla_put_be32(skb, NFTA_HASH_SEED, htonl(priv->seed))) goto nla_put_failure; if (priv->offset != 0) if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_JENKINS))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static bool nft_jhash_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { const struct nft_jhash *priv = nft_expr_priv(expr); nft_reg_track_cancel(track, priv->dreg, sizeof(u32)); return false; } static int nft_symhash_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_symhash *priv = nft_expr_priv(expr); if (nft_dump_register(skb, NFTA_HASH_DREG, priv->dreg)) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_MODULUS, htonl(priv->modulus))) goto nla_put_failure; if (priv->offset != 0) if (nla_put_be32(skb, NFTA_HASH_OFFSET, htonl(priv->offset))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_HASH_TYPE, htonl(NFT_HASH_SYM))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static bool nft_symhash_reduce(struct nft_regs_track *track, const struct nft_expr *expr) { struct nft_symhash *priv = nft_expr_priv(expr); struct nft_symhash *symhash; if (!nft_reg_track_cmp(track, expr, priv->dreg)) { nft_reg_track_update(track, expr, priv->dreg, sizeof(u32)); return false; } symhash = nft_expr_priv(track->regs[priv->dreg].selector); if (priv->offset != symhash->offset || priv->modulus != symhash->modulus) { nft_reg_track_update(track, expr, priv->dreg, sizeof(u32)); return false; } if (!track->regs[priv->dreg].bitwise) return true; return false; } static struct nft_expr_type nft_hash_type; static const struct nft_expr_ops nft_jhash_ops = { .type = &nft_hash_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_jhash)), .eval = nft_jhash_eval, .init = nft_jhash_init, .dump = nft_jhash_dump, .reduce = nft_jhash_reduce, }; static const struct nft_expr_ops nft_symhash_ops = { .type = &nft_hash_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)), .eval = nft_symhash_eval, .init = nft_symhash_init, .dump = nft_symhash_dump, .reduce = nft_symhash_reduce, }; static const struct nft_expr_ops * nft_hash_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { u32 type; if (!tb[NFTA_HASH_TYPE]) return &nft_jhash_ops; type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE])); switch (type) { case NFT_HASH_SYM: return &nft_symhash_ops; case NFT_HASH_JENKINS: return &nft_jhash_ops; default: break; } return ERR_PTR(-EOPNOTSUPP); } static struct nft_expr_type nft_hash_type __read_mostly = { .name = "hash", .select_ops = nft_hash_select_ops, .policy = nft_hash_policy, .maxattr = NFTA_HASH_MAX, .owner = THIS_MODULE, }; static int __init nft_hash_module_init(void) { return nft_register_expr(&nft_hash_type); } static void __exit nft_hash_module_exit(void) { nft_unregister_expr(&nft_hash_type); } module_init(nft_hash_module_init); module_exit(nft_hash_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Laura Garcia <nevola@gmail.com>"); MODULE_ALIAS_NFT_EXPR("hash"); MODULE_DESCRIPTION("Netfilter nftables hash module"); |
| 8 21 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/dccp/timer.c * * An implementation of the DCCP protocol * Arnaldo Carvalho de Melo <acme@conectiva.com.br> */ #include <linux/dccp.h> #include <linux/skbuff.h> #include <linux/export.h> #include "dccp.h" /* sysctl variables governing numbers of retransmission attempts */ int sysctl_dccp_request_retries __read_mostly = TCP_SYN_RETRIES; int sysctl_dccp_retries1 __read_mostly = TCP_RETR1; int sysctl_dccp_retries2 __read_mostly = TCP_RETR2; static void dccp_write_err(struct sock *sk) { sk->sk_err = READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT; sk_error_report(sk); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_done(sk); __DCCP_INC_STATS(DCCP_MIB_ABORTONTIMEOUT); } /* A write timeout has occurred. Process the after effects. */ static int dccp_write_timeout(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); int retry_until; if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) { if (icsk->icsk_retransmits != 0) dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : sysctl_dccp_request_retries; } else { if (icsk->icsk_retransmits >= sysctl_dccp_retries1) { /* NOTE. draft-ietf-tcpimpl-pmtud-01.txt requires pmtu black hole detection. :-( It is place to make it. It is not made. I do not want to make it. It is disguisting. It does not work in any case. Let me to cite the same draft, which requires for us to implement this: "The one security concern raised by this memo is that ICMP black holes are often caused by over-zealous security administrators who block all ICMP messages. It is vitally important that those who design and deploy security systems understand the impact of strict filtering on upper-layer protocols. The safest web site in the world is worthless if most TCP implementations cannot transfer data from it. It would be far nicer to have all of the black holes fixed rather than fixing all of the TCP implementations." Golden words :-). */ dst_negative_advice(sk); } retry_until = sysctl_dccp_retries2; /* * FIXME: see tcp_write_timout and tcp_out_of_resources */ } if (icsk->icsk_retransmits >= retry_until) { /* Has it gone just too far? */ dccp_write_err(sk); return 1; } return 0; } /* * The DCCP retransmit timer. */ static void dccp_retransmit_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); /* * More than 4MSL (8 minutes) has passed, a RESET(aborted) was * sent, no need to retransmit, this sock is dead. */ if (dccp_write_timeout(sk)) return; /* * We want to know the number of packets retransmitted, not the * total number of retransmissions of clones of original packets. */ if (icsk->icsk_retransmits == 0) __DCCP_INC_STATS(DCCP_MIB_TIMEOUTS); if (dccp_retransmit_skb(sk) != 0) { /* * Retransmission failed because of local congestion, * do not backoff. */ if (--icsk->icsk_retransmits == 0) icsk->icsk_retransmits = 1; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL), DCCP_RTO_MAX); return; } icsk->icsk_backoff++; icsk->icsk_rto = min(icsk->icsk_rto << 1, DCCP_RTO_MAX); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, DCCP_RTO_MAX); if (icsk->icsk_retransmits > sysctl_dccp_retries1) __sk_dst_reset(sk); } static void dccp_write_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_retransmit_timer); struct sock *sk = &icsk->icsk_inet.sk; int event = 0; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later */ sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + (HZ / 20)); goto out; } if (sk->sk_state == DCCP_CLOSED || !icsk->icsk_pending) goto out; if (time_after(icsk->icsk_timeout, jiffies)) { sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); goto out; } event = icsk->icsk_pending; icsk->icsk_pending = 0; switch (event) { case ICSK_TIME_RETRANS: dccp_retransmit_timer(sk); break; } out: bh_unlock_sock(sk); sock_put(sk); } static void dccp_keepalive_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); pr_err("dccp should not use a keepalive timer !\n"); sock_put(sk); } /* This is the same as tcp_delack_timer, sans prequeue & mem_reclaim stuff */ static void dccp_delack_timer(struct timer_list *t) { struct inet_connection_sock *icsk = from_timer(icsk, t, icsk_delack_timer); struct sock *sk = &icsk->icsk_inet.sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later. */ __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN); goto out; } if (sk->sk_state == DCCP_CLOSED || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) goto out; if (time_after(icsk->icsk_ack.timeout, jiffies)) { sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); goto out; } icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ icsk->icsk_ack.ato = min_t(u32, icsk->icsk_ack.ato << 1, icsk->icsk_rto); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } dccp_send_ack(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } out: bh_unlock_sock(sk); sock_put(sk); } /** * dccp_write_xmitlet - Workhorse for CCID packet dequeueing interface * @t: pointer to the tasklet associated with this handler * * See the comments above %ccid_dequeueing_decision for supported modes. */ static void dccp_write_xmitlet(struct tasklet_struct *t) { struct dccp_sock *dp = from_tasklet(dp, t, dccps_xmitlet); struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk; bh_lock_sock(sk); if (sock_owned_by_user(sk)) sk_reset_timer(sk, &dccp_sk(sk)->dccps_xmit_timer, jiffies + 1); else dccp_write_xmit(sk); bh_unlock_sock(sk); sock_put(sk); } static void dccp_write_xmit_timer(struct timer_list *t) { struct dccp_sock *dp = from_timer(dp, t, dccps_xmit_timer); dccp_write_xmitlet(&dp->dccps_xmitlet); } void dccp_init_xmit_timers(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); tasklet_setup(&dp->dccps_xmitlet, dccp_write_xmitlet); timer_setup(&dp->dccps_xmit_timer, dccp_write_xmit_timer, 0); inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer, &dccp_keepalive_timer); } static ktime_t dccp_timestamp_seed; /** * dccp_timestamp - 10s of microseconds time source * Returns the number of 10s of microseconds since loading DCCP. This is native * DCCP time difference format (RFC 4340, sec. 13). * Please note: This will wrap around about circa every 11.9 hours. */ u32 dccp_timestamp(void) { u64 delta = (u64)ktime_us_delta(ktime_get_real(), dccp_timestamp_seed); do_div(delta, 10); return delta; } EXPORT_SYMBOL_GPL(dccp_timestamp); void __init dccp_timestamping_init(void) { dccp_timestamp_seed = ktime_get_real(); } |
| 10 9 10 3 3 3 1 3 3 1 1 1 2 3 2 2 2 7 7 5 1 1 3 3 1 2 1 2 4 3 1 14 3 3 4 1 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 | // SPDX-License-Identifier: GPL-2.0-or-later /* * taskstats.c - Export per-task statistics to userland * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 * (C) Balbir Singh, IBM Corp. 2006 */ #include <linux/kernel.h> #include <linux/taskstats_kern.h> #include <linux/tsacct_kern.h> #include <linux/acct.h> #include <linux/delayacct.h> #include <linux/cpumask.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/cgroupstats.h> #include <linux/cgroup.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/pid_namespace.h> #include <net/genetlink.h> #include <linux/atomic.h> #include <linux/sched/cputime.h> /* * Maximum length of a cpumask that can be specified in * the TASKSTATS_CMD_ATTR_REGISTER/DEREGISTER_CPUMASK attribute */ #define TASKSTATS_CPUMASK_MAXLEN (100+6*NR_CPUS) static DEFINE_PER_CPU(__u32, taskstats_seqnum); static int family_registered; struct kmem_cache *taskstats_cache; static struct genl_family family; static const struct nla_policy taskstats_cmd_get_policy[] = { [TASKSTATS_CMD_ATTR_PID] = { .type = NLA_U32 }, [TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 }, [TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING }, [TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },}; static const struct nla_policy cgroupstats_cmd_get_policy[] = { [CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 }, }; struct listener { struct list_head list; pid_t pid; char valid; }; struct listener_list { struct rw_semaphore sem; struct list_head list; }; static DEFINE_PER_CPU(struct listener_list, listener_array); enum actions { REGISTER, DEREGISTER, CPU_DONT_CARE }; static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, size_t size) { struct sk_buff *skb; void *reply; /* * If new attributes are added, please revisit this allocation */ skb = genlmsg_new(size, GFP_KERNEL); if (!skb) return -ENOMEM; if (!info) { int seq = this_cpu_inc_return(taskstats_seqnum) - 1; reply = genlmsg_put(skb, 0, seq, &family, 0, cmd); } else reply = genlmsg_put_reply(skb, info, &family, 0, cmd); if (reply == NULL) { nlmsg_free(skb); return -EINVAL; } *skbp = skb; return 0; } /* * Send taskstats data in @skb to listener with nl_pid @pid */ static int send_reply(struct sk_buff *skb, struct genl_info *info) { struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); void *reply = genlmsg_data(genlhdr); genlmsg_end(skb, reply); return genlmsg_reply(skb, info); } /* * Send taskstats data in @skb to listeners registered for @cpu's exit data */ static void send_cpu_listeners(struct sk_buff *skb, struct listener_list *listeners) { struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); struct listener *s, *tmp; struct sk_buff *skb_next, *skb_cur = skb; void *reply = genlmsg_data(genlhdr); int delcount = 0; genlmsg_end(skb, reply); down_read(&listeners->sem); list_for_each_entry(s, &listeners->list, list) { int rc; skb_next = NULL; if (!list_is_last(&s->list, &listeners->list)) { skb_next = skb_clone(skb_cur, GFP_KERNEL); if (!skb_next) break; } rc = genlmsg_unicast(&init_net, skb_cur, s->pid); if (rc == -ECONNREFUSED) { s->valid = 0; delcount++; } skb_cur = skb_next; } up_read(&listeners->sem); if (skb_cur) nlmsg_free(skb_cur); if (!delcount) return; /* Delete invalidated entries */ down_write(&listeners->sem); list_for_each_entry_safe(s, tmp, &listeners->list, list) { if (!s->valid) { list_del(&s->list); kfree(s); } } up_write(&listeners->sem); } static void exe_add_tsk(struct taskstats *stats, struct task_struct *tsk) { /* No idea if I'm allowed to access that here, now. */ struct file *exe_file = get_task_exe_file(tsk); if (exe_file) { /* Following cp_new_stat64() in stat.c . */ stats->ac_exe_dev = huge_encode_dev(exe_file->f_inode->i_sb->s_dev); stats->ac_exe_inode = exe_file->f_inode->i_ino; fput(exe_file); } else { stats->ac_exe_dev = 0; stats->ac_exe_inode = 0; } } static void fill_stats(struct user_namespace *user_ns, struct pid_namespace *pid_ns, struct task_struct *tsk, struct taskstats *stats) { memset(stats, 0, sizeof(*stats)); /* * Each accounting subsystem adds calls to its functions to * fill in relevant parts of struct taskstsats as follows * * per-task-foo(stats, tsk); */ delayacct_add_tsk(stats, tsk); /* fill in basic acct fields */ stats->version = TASKSTATS_VERSION; stats->nvcsw = tsk->nvcsw; stats->nivcsw = tsk->nivcsw; bacct_add_tsk(user_ns, pid_ns, stats, tsk); /* fill in extended acct fields */ xacct_add_tsk(stats, tsk); /* add executable info */ exe_add_tsk(stats, tsk); } static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) { struct task_struct *tsk; tsk = find_get_task_by_vpid(pid); if (!tsk) return -ESRCH; fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats); put_task_struct(tsk); return 0; } static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) { struct task_struct *tsk, *first; unsigned long flags; int rc = -ESRCH; u64 delta, utime, stime; u64 start_time; /* * Add additional stats from live tasks except zombie thread group * leaders who are already counted with the dead tasks */ rcu_read_lock(); first = find_task_by_vpid(tgid); if (!first || !lock_task_sighand(first, &flags)) goto out; if (first->signal->stats) memcpy(stats, first->signal->stats, sizeof(*stats)); else memset(stats, 0, sizeof(*stats)); start_time = ktime_get_ns(); for_each_thread(first, tsk) { if (tsk->exit_state) continue; /* * Accounting subsystem can call its functions here to * fill in relevant parts of struct taskstsats as follows * * per-task-foo(stats, tsk); */ delayacct_add_tsk(stats, tsk); /* calculate task elapsed time in nsec */ delta = start_time - tsk->start_time; /* Convert to micro seconds */ do_div(delta, NSEC_PER_USEC); stats->ac_etime += delta; task_cputime(tsk, &utime, &stime); stats->ac_utime += div_u64(utime, NSEC_PER_USEC); stats->ac_stime += div_u64(stime, NSEC_PER_USEC); stats->nvcsw += tsk->nvcsw; stats->nivcsw += tsk->nivcsw; } unlock_task_sighand(first, &flags); rc = 0; out: rcu_read_unlock(); stats->version = TASKSTATS_VERSION; /* * Accounting subsystems can also add calls here to modify * fields of taskstats. */ return rc; } static void fill_tgid_exit(struct task_struct *tsk) { unsigned long flags; spin_lock_irqsave(&tsk->sighand->siglock, flags); if (!tsk->signal->stats) goto ret; /* * Each accounting subsystem calls its functions here to * accumalate its per-task stats for tsk, into the per-tgid structure * * per-task-foo(tsk->signal->stats, tsk); */ delayacct_add_tsk(tsk->signal->stats, tsk); ret: spin_unlock_irqrestore(&tsk->sighand->siglock, flags); return; } static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) { struct listener_list *listeners; struct listener *s, *tmp, *s2; unsigned int cpu; int ret = 0; if (!cpumask_subset(mask, cpu_possible_mask)) return -EINVAL; if (current_user_ns() != &init_user_ns) return -EINVAL; if (task_active_pid_ns(current) != &init_pid_ns) return -EINVAL; if (isadd == REGISTER) { for_each_cpu(cpu, mask) { s = kmalloc_node(sizeof(struct listener), GFP_KERNEL, cpu_to_node(cpu)); if (!s) { ret = -ENOMEM; goto cleanup; } s->pid = pid; s->valid = 1; listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); list_for_each_entry(s2, &listeners->list, list) { if (s2->pid == pid && s2->valid) goto exists; } list_add(&s->list, &listeners->list); s = NULL; exists: up_write(&listeners->sem); kfree(s); /* nop if NULL */ } return 0; } /* Deregister or cleanup */ cleanup: for_each_cpu(cpu, mask) { listeners = &per_cpu(listener_array, cpu); down_write(&listeners->sem); list_for_each_entry_safe(s, tmp, &listeners->list, list) { if (s->pid == pid) { list_del(&s->list); kfree(s); break; } } up_write(&listeners->sem); } return ret; } static int parse(struct nlattr *na, struct cpumask *mask) { char *data; int len; int ret; if (na == NULL) return 1; len = nla_len(na); if (len > TASKSTATS_CPUMASK_MAXLEN) return -E2BIG; if (len < 1) return -EINVAL; data = kmalloc(len, GFP_KERNEL); if (!data) return -ENOMEM; nla_strscpy(data, na, len); ret = cpulist_parse(data, mask); kfree(data); return ret; } static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) { struct nlattr *na, *ret; int aggr; aggr = (type == TASKSTATS_TYPE_PID) ? TASKSTATS_TYPE_AGGR_PID : TASKSTATS_TYPE_AGGR_TGID; na = nla_nest_start_noflag(skb, aggr); if (!na) goto err; if (nla_put(skb, type, sizeof(pid), &pid) < 0) { nla_nest_cancel(skb, na); goto err; } ret = nla_reserve_64bit(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats), TASKSTATS_TYPE_NULL); if (!ret) { nla_nest_cancel(skb, na); goto err; } nla_nest_end(skb, na); return nla_data(ret); err: return NULL; } static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) { int rc = 0; struct sk_buff *rep_skb; struct cgroupstats *stats; struct nlattr *na; size_t size; u32 fd; struct fd f; na = info->attrs[CGROUPSTATS_CMD_ATTR_FD]; if (!na) return -EINVAL; fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]); f = fdget(fd); if (!f.file) return 0; size = nla_total_size(sizeof(struct cgroupstats)); rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) goto err; na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS, sizeof(struct cgroupstats)); if (na == NULL) { nlmsg_free(rep_skb); rc = -EMSGSIZE; goto err; } stats = nla_data(na); memset(stats, 0, sizeof(*stats)); rc = cgroupstats_build(stats, f.file->f_path.dentry); if (rc < 0) { nlmsg_free(rep_skb); goto err; } rc = send_reply(rep_skb, info); err: fdput(f); return rc; } static int cmd_attr_register_cpumask(struct genl_info *info) { cpumask_var_t mask; int rc; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask); if (rc < 0) goto out; rc = add_del_listener(info->snd_portid, mask, REGISTER); out: free_cpumask_var(mask); return rc; } static int cmd_attr_deregister_cpumask(struct genl_info *info) { cpumask_var_t mask; int rc; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) return -ENOMEM; rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask); if (rc < 0) goto out; rc = add_del_listener(info->snd_portid, mask, DEREGISTER); out: free_cpumask_var(mask); return rc; } static size_t taskstats_packet_size(void) { size_t size; size = nla_total_size(sizeof(u32)) + nla_total_size_64bit(sizeof(struct taskstats)) + nla_total_size(0); return size; } static int cmd_attr_pid(struct genl_info *info) { struct taskstats *stats; struct sk_buff *rep_skb; size_t size; u32 pid; int rc; size = taskstats_packet_size(); rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return rc; rc = -EINVAL; pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]); stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid); if (!stats) goto err; rc = fill_stats_for_pid(pid, stats); if (rc < 0) goto err; return send_reply(rep_skb, info); err: nlmsg_free(rep_skb); return rc; } static int cmd_attr_tgid(struct genl_info *info) { struct taskstats *stats; struct sk_buff *rep_skb; size_t size; u32 tgid; int rc; size = taskstats_packet_size(); rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return rc; rc = -EINVAL; tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]); stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid); if (!stats) goto err; rc = fill_stats_for_tgid(tgid, stats); if (rc < 0) goto err; return send_reply(rep_skb, info); err: nlmsg_free(rep_skb); return rc; } static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) { if (info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK]) return cmd_attr_register_cpumask(info); else if (info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK]) return cmd_attr_deregister_cpumask(info); else if (info->attrs[TASKSTATS_CMD_ATTR_PID]) return cmd_attr_pid(info); else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) return cmd_attr_tgid(info); else return -EINVAL; } static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct taskstats *stats_new, *stats; /* Pairs with smp_store_release() below. */ stats = smp_load_acquire(&sig->stats); if (stats || thread_group_empty(tsk)) return stats; /* No problem if kmem_cache_zalloc() fails */ stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); spin_lock_irq(&tsk->sighand->siglock); stats = sig->stats; if (!stats) { /* * Pairs with smp_store_release() above and order the * kmem_cache_zalloc(). */ smp_store_release(&sig->stats, stats_new); stats = stats_new; stats_new = NULL; } spin_unlock_irq(&tsk->sighand->siglock); if (stats_new) kmem_cache_free(taskstats_cache, stats_new); return stats; } /* Send pid data out on exit */ void taskstats_exit(struct task_struct *tsk, int group_dead) { int rc; struct listener_list *listeners; struct taskstats *stats; struct sk_buff *rep_skb; size_t size; int is_thread_group; if (!family_registered) return; /* * Size includes space for nested attributes */ size = taskstats_packet_size(); is_thread_group = !!taskstats_tgid_alloc(tsk); if (is_thread_group) { /* PID + STATS + TGID + STATS */ size = 2 * size; /* fill the tsk->signal->stats structure */ fill_tgid_exit(tsk); } listeners = raw_cpu_ptr(&listener_array); if (list_empty(&listeners->list)) return; rc = prepare_reply(NULL, TASKSTATS_CMD_NEW, &rep_skb, size); if (rc < 0) return; stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, task_pid_nr_ns(tsk, &init_pid_ns)); if (!stats) goto err; fill_stats(&init_user_ns, &init_pid_ns, tsk, stats); if (group_dead) stats->ac_flag |= AGROUP; /* * Doesn't matter if tsk is the leader or the last group member leaving */ if (!is_thread_group || !group_dead) goto send; stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, task_tgid_nr_ns(tsk, &init_pid_ns)); if (!stats) goto err; memcpy(stats, tsk->signal->stats, sizeof(*stats)); send: send_cpu_listeners(rep_skb, listeners); return; err: nlmsg_free(rep_skb); } static const struct genl_ops taskstats_ops[] = { { .cmd = TASKSTATS_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = taskstats_user_cmd, .policy = taskstats_cmd_get_policy, .maxattr = ARRAY_SIZE(taskstats_cmd_get_policy) - 1, .flags = GENL_ADMIN_PERM, }, { .cmd = CGROUPSTATS_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = cgroupstats_user_cmd, .policy = cgroupstats_cmd_get_policy, .maxattr = ARRAY_SIZE(cgroupstats_cmd_get_policy) - 1, }, }; static struct genl_family family __ro_after_init = { .name = TASKSTATS_GENL_NAME, .version = TASKSTATS_GENL_VERSION, .module = THIS_MODULE, .ops = taskstats_ops, .n_ops = ARRAY_SIZE(taskstats_ops), .resv_start_op = CGROUPSTATS_CMD_GET + 1, .netnsok = true, }; /* Needed early in initialization */ void __init taskstats_init_early(void) { unsigned int i; taskstats_cache = KMEM_CACHE(taskstats, SLAB_PANIC); for_each_possible_cpu(i) { INIT_LIST_HEAD(&(per_cpu(listener_array, i).list)); init_rwsem(&(per_cpu(listener_array, i).sem)); } } static int __init taskstats_init(void) { int rc; rc = genl_register_family(&family); if (rc) return rc; family_registered = 1; pr_info("registered taskstats version %d\n", TASKSTATS_GENL_VERSION); return 0; } /* * late initcall ensures initialization of statistics collection * mechanisms precedes initialization of the taskstats interface */ late_initcall(taskstats_init); |
| 9 9 9 9 9 8 8 27 22 33 17 17 17 31 31 31 25 16 9 2 23 47 47 47 5 1 9 34 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 10 10 9 1 1 9 9 1 2 2 1 2 9 9 9 5 5 3 2 4 5 1 1 1 1 1 1 1 1 1 1 1 3 3 3 1 2 81 81 1 1 80 81 1 1 79 78 1 72 5 72 8 78 2 6 5 1 3 1 1 1 3 2 1 1 3 3 7 105 105 1 21 81 1 24 10 20 4 9 9 14 3 11 4 4 3 4 3 1 1 1 2 1 26 18 5 7 4 1 8 10 2 4 1 1 1 1 22 1 8 10 4 38 33 3 5 2 4 9 30 23 23 23 36 28 8 1 31 1 23 20 8 27 24 3 26 5 1 20 1 21 2 6 10 1 6 3 8 8 5 1 6 39 88 2 1 1 3 1 1 2 1 1 1 81 2 2 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 over IPv4 tunnel device - Simple Internet Transition (SIT) * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * * Changes: * Roger Venning <r.venning@telstra.com>: 6to4 support * Nate Thompson <nate@thebog.net>: 6to4 support * Fred Templin <fred.l.templin@boeing.com>: isatap support */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmp.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/transp_v6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/ip.h> #include <net/udp.h> #include <net/icmp.h> #include <net/ip_tunnels.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/dsfield.h> #include <net/net_namespace.h> #include <net/netns/generic.h> /* This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c For comments look at net/ipv4/ip_gre.c --ANK */ #define IP6_SIT_HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static int ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); static void ipip6_dev_free(struct net_device *dev); static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, __be32 *v4dst); static struct rtnl_link_ops sit_link_ops __read_mostly; static unsigned int sit_net_id __read_mostly; struct sit_net { struct ip_tunnel __rcu *tunnels_r_l[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_r[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_l[IP6_SIT_HASH_SIZE]; struct ip_tunnel __rcu *tunnels_wc[1]; struct ip_tunnel __rcu **tunnels[4]; struct net_device *fb_tunnel_dev; }; static inline struct sit_net *dev_to_sit_net(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); return net_generic(t->net, sit_net_id); } /* * Must be invoked with rcu_read_lock */ static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net, struct net_device *dev, __be32 remote, __be32 local, int sifindex) { unsigned int h0 = HASH(remote); unsigned int h1 = HASH(local); struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); int ifindex = dev ? dev->ifindex : 0; for_each_ip_tunnel_rcu(t, sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } for_each_ip_tunnel_rcu(t, sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && (!dev || !t->parms.link || ifindex == t->parms.link || sifindex == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } t = rcu_dereference(sitn->tunnels_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } static struct ip_tunnel __rcu ** __ipip6_bucket(struct sit_net *sitn, struct ip_tunnel_parm_kern *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; unsigned int h = 0; int prio = 0; if (remote) { prio |= 2; h ^= HASH(remote); } if (local) { prio |= 1; h ^= HASH(local); } return &sitn->tunnels[prio][h]; } static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn, struct ip_tunnel *t) { return __ipip6_bucket(sitn, &t->parms); } static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp; struct ip_tunnel *iter; for (tp = ipip6_bucket(sitn, t); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t); rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) { #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel *t = netdev_priv(dev); if (dev == sitn->fb_tunnel_dev || !sitn->fb_tunnel_dev) { ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0); t->ip6rd.relay_prefix = 0; t->ip6rd.prefixlen = 16; t->ip6rd.relay_prefixlen = 0; } else { struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev); memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd)); } #endif } static int ipip6_tunnel_create(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); int err; __dev_addr_set(dev, &t->parms.iph.saddr, 4); memcpy(dev->broadcast, &t->parms.iph.daddr, 4); if (test_bit(IP_TUNNEL_SIT_ISATAP_BIT, t->parms.i_flags)) dev->priv_flags |= IFF_ISATAP; dev->rtnl_link_ops = &sit_link_ops; err = register_netdevice(dev); if (err < 0) goto out; ipip6_tunnel_clone_6rd(dev, sitn); ipip6_tunnel_link(sitn, t); return 0; out: return err; } static struct ip_tunnel *ipip6_tunnel_locate(struct net *net, struct ip_tunnel_parm_kern *parms, int create) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; struct ip_tunnel *t, *nt; struct ip_tunnel __rcu **tp; struct net_device *dev; char name[IFNAMSIZ]; struct sit_net *sitn = net_generic(net, sit_net_id); for (tp = __ipip6_bucket(sitn, parms); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && parms->link == t->parms.link) { if (create) return NULL; else return t; } } if (!create) goto failed; if (parms->name[0]) { if (!dev_valid_name(parms->name)) goto failed; strscpy(name, parms->name, IFNAMSIZ); } else { strcpy(name, "sit%d"); } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!dev) return NULL; dev_net_set(dev, net); nt = netdev_priv(dev); nt->parms = *parms; if (ipip6_tunnel_create(dev) < 0) goto failed_free; if (!parms->name[0]) strcpy(parms->name, dev->name); return nt; failed_free: free_netdev(dev); failed: return NULL; } #define for_each_prl_rcu(start) \ for (prl = rcu_dereference(start); \ prl; \ prl = rcu_dereference(prl->next)) static struct ip_tunnel_prl_entry * __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { struct ip_tunnel_prl_entry *prl; for_each_prl_rcu(t->prl) if (prl->addr == addr) break; return prl; } static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __user *a) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_prl kprl, *kp; struct ip_tunnel_prl_entry *prl; unsigned int cmax, c = 0, ca, len; int ret = 0; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) return -EINVAL; if (copy_from_user(&kprl, a, sizeof(kprl))) return -EFAULT; cmax = kprl.datalen / sizeof(kprl); if (cmax > 1 && kprl.addr != htonl(INADDR_ANY)) cmax = 1; /* For simple GET or for root users, * we try harder to allocate. */ kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ? kcalloc(cmax, sizeof(*kp), GFP_KERNEL_ACCOUNT | __GFP_NOWARN) : NULL; ca = min(t->prl_count, cmax); if (!kp) { /* We don't try hard to allocate much memory for * non-root users. * For root users, retry allocating enough memory for * the answer. */ kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC | __GFP_ACCOUNT | __GFP_NOWARN); if (!kp) { ret = -ENOMEM; goto out; } } rcu_read_lock(); for_each_prl_rcu(t->prl) { if (c >= cmax) break; if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) continue; kp[c].addr = prl->addr; kp[c].flags = prl->flags; c++; if (kprl.addr != htonl(INADDR_ANY)) break; } rcu_read_unlock(); len = sizeof(*kp) * c; ret = 0; if ((len && copy_to_user(a + 1, kp, len)) || put_user(len, &a->datalen)) ret = -EFAULT; kfree(kp); out: return ret; } static int ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) { struct ip_tunnel_prl_entry *p; int err = 0; if (a->addr == htonl(INADDR_ANY)) return -EINVAL; ASSERT_RTNL(); for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) { if (p->addr == a->addr) { if (chg) { p->flags = a->flags; goto out; } err = -EEXIST; goto out; } } if (chg) { err = -ENXIO; goto out; } p = kzalloc(sizeof(struct ip_tunnel_prl_entry), GFP_KERNEL); if (!p) { err = -ENOBUFS; goto out; } p->next = t->prl; p->addr = a->addr; p->flags = a->flags; t->prl_count++; rcu_assign_pointer(t->prl, p); out: return err; } static void prl_list_destroy_rcu(struct rcu_head *head) { struct ip_tunnel_prl_entry *p, *n; p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); do { n = rcu_dereference_protected(p->next, 1); kfree(p); p = n; } while (p); } static int ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) { struct ip_tunnel_prl_entry *x; struct ip_tunnel_prl_entry __rcu **p; int err = 0; ASSERT_RTNL(); if (a && a->addr != htonl(INADDR_ANY)) { for (p = &t->prl; (x = rtnl_dereference(*p)) != NULL; p = &x->next) { if (x->addr == a->addr) { *p = x->next; kfree_rcu(x, rcu_head); t->prl_count--; goto out; } } err = -ENXIO; } else { x = rtnl_dereference(t->prl); if (x) { t->prl_count = 0; call_rcu(&x->rcu_head, prl_list_destroy_rcu); t->prl = NULL; } } out: return err; } static int ipip6_tunnel_prl_ctl(struct net_device *dev, struct ip_tunnel_prl __user *data, int cmd) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_prl prl; int err; if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) return -EINVAL; if (copy_from_user(&prl, data, sizeof(prl))) return -EFAULT; switch (cmd) { case SIOCDELPRL: err = ipip6_tunnel_del_prl(t, &prl); break; case SIOCADDPRL: case SIOCCHGPRL: err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } dst_cache_reset(&t->dst_cache); netdev_state_change(dev); return err; } static int isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t) { struct ip_tunnel_prl_entry *p; int ok = 1; rcu_read_lock(); p = __ipip6_tunnel_locate_prl(t, iph->saddr); if (p) { if (p->flags & PRL_DEFAULT) skb->ndisc_nodetype = NDISC_NODETYPE_DEFAULT; else skb->ndisc_nodetype = NDISC_NODETYPE_NODEFAULT; } else { const struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr; if (ipv6_addr_is_isatap(addr6) && (addr6->s6_addr32[3] == iph->saddr) && ipv6_chk_prefix(addr6, t->dev)) skb->ndisc_nodetype = NDISC_NODETYPE_HOST; else ok = 0; } rcu_read_unlock(); return ok; } static void ipip6_tunnel_uninit(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct sit_net *sitn = net_generic(tunnel->net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL); } else { ipip6_tunnel_unlink(sitn, tunnel); ipip6_tunnel_del_prl(tunnel, NULL); } dst_cache_reset(&tunnel->dst_cache); netdev_put(dev, &tunnel->dev_tracker); } static int ipip6_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; int sifindex; int err; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: /* Impossible event. */ return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: break; } err = -ENOENT; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->daddr, iph->saddr, sifindex); if (!t) goto out; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, t->parms.link, iph->protocol); err = 0; goto out; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, iph->protocol); err = 0; goto out; } err = 0; if (__in6_dev_get(skb->dev) && !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) goto out; if (t->parms.iph.daddr == 0) goto out; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; out: return err; } static inline bool is_spoofed_6rd(struct ip_tunnel *tunnel, const __be32 v4addr, const struct in6_addr *v6addr) { __be32 v4embed = 0; if (check_6rd(tunnel, v6addr, &v4embed) && v4addr != v4embed) return true; return false; } /* Checks if an address matches an address on the tunnel interface. * Used to detect the NAT of proto 41 packets and let them pass spoofing test. * Long story: * This function is called after we considered the packet as spoofed * in is_spoofed_6rd. * We may have a router that is doing NAT for proto 41 packets * for an internal station. Destination a.a.a.a/PREFIX:bbbb:bbbb * will be translated to n.n.n.n/PREFIX:bbbb:bbbb. And is_spoofed_6rd * function will return true, dropping the packet. * But, we can still check if is spoofed against the IP * addresses associated with the interface. */ static bool only_dnatted(const struct ip_tunnel *tunnel, const struct in6_addr *v6dst) { int prefix_len; #ifdef CONFIG_IPV6_SIT_6RD prefix_len = tunnel->ip6rd.prefixlen + 32 - tunnel->ip6rd.relay_prefixlen; #else prefix_len = 48; #endif return ipv6_chk_custom_prefix(v6dst, prefix_len, tunnel->dev); } /* Returns true if a packet is spoofed */ static bool packet_is_spoofed(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *tunnel) { const struct ipv6hdr *ipv6h; if (tunnel->dev->priv_flags & IFF_ISATAP) { if (!isatap_chksrc(skb, iph, tunnel)) return true; return false; } if (tunnel->dev->flags & IFF_POINTOPOINT) return false; ipv6h = ipv6_hdr(skb); if (unlikely(is_spoofed_6rd(tunnel, iph->saddr, &ipv6h->saddr))) { net_warn_ratelimited("Src spoofed %pI4/%pI6c -> %pI4/%pI6c\n", &iph->saddr, &ipv6h->saddr, &iph->daddr, &ipv6h->daddr); return true; } if (likely(!is_spoofed_6rd(tunnel, iph->daddr, &ipv6h->daddr))) return false; if (only_dnatted(tunnel, &ipv6h->daddr)) return false; net_warn_ratelimited("Dst spoofed %pI4/%pI6c -> %pI4/%pI6c\n", &iph->saddr, &ipv6h->saddr, &iph->daddr, &ipv6h->daddr); return true; } static int ipip6_rcv(struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct ip_tunnel *tunnel; int sifindex; int err; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr, sifindex); if (tunnel) { if (tunnel->parms.iph.protocol != IPPROTO_IPV6 && tunnel->parms.iph.protocol != 0) goto out; skb->mac_header = skb->network_header; skb_reset_network_header(skb); IPCB(skb)->flags = 0; skb->dev = tunnel->dev; if (packet_is_spoofed(skb, iph, tunnel)) { DEV_STATS_INC(tunnel->dev, rx_errors); goto out; } if (iptunnel_pull_header(skb, 0, htons(ETH_P_IPV6), !net_eq(tunnel->net, dev_net(tunnel->dev)))) goto out; /* skb can be uncloned in iptunnel_pull_header, so * old iph is no longer valid */ iph = (const struct iphdr *)skb_mac_header(skb); skb_reset_mac_header(skb); err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", &iph->saddr, iph->tos); if (err > 1) { DEV_STATS_INC(tunnel->dev, rx_frame_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto out; } } dev_sw_netstats_rx_add(tunnel->dev, skb->len); netif_rx(skb); return 0; } /* no tunnel matched, let upstream know, ipsec may handle it */ return 1; out: kfree_skb(skb); return 0; } static const struct tnl_ptk_info ipip_tpi = { /* no tunnel info required for ipip. */ .proto = htons(ETH_P_IP), }; #if IS_ENABLED(CONFIG_MPLS) static const struct tnl_ptk_info mplsip_tpi = { /* no tunnel info required for mplsip. */ .proto = htons(ETH_P_MPLS_UC), }; #endif static int sit_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { const struct iphdr *iph; struct ip_tunnel *tunnel; int sifindex; sifindex = netif_is_l3_master(skb->dev) ? IPCB(skb)->iif : 0; iph = ip_hdr(skb); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr, sifindex); if (tunnel) { const struct tnl_ptk_info *tpi; if (tunnel->parms.iph.protocol != ipproto && tunnel->parms.iph.protocol != 0) goto drop; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; #if IS_ENABLED(CONFIG_MPLS) if (ipproto == IPPROTO_MPLS) tpi = &mplsip_tpi; else #endif tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; skb_reset_mac_header(skb); return ip_tunnel_rcv(tunnel, skb, tpi, NULL, log_ecn_error); } return 1; drop: kfree_skb(skb); return 0; } static int ipip_rcv(struct sk_buff *skb) { return sit_tunnel_rcv(skb, IPPROTO_IPIP); } #if IS_ENABLED(CONFIG_MPLS) static int mplsip_rcv(struct sk_buff *skb) { return sit_tunnel_rcv(skb, IPPROTO_MPLS); } #endif /* * If the IPv6 address comes from 6rd / 6to4 (RFC 3056) addr space this function * stores the embedded IPv4 address in v4dst and returns true. */ static bool check_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst, __be32 *v4dst) { #ifdef CONFIG_IPV6_SIT_6RD if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, tunnel->ip6rd.prefixlen)) { unsigned int pbw0, pbi0; int pbi1; u32 d; pbw0 = tunnel->ip6rd.prefixlen >> 5; pbi0 = tunnel->ip6rd.prefixlen & 0x1f; d = tunnel->ip6rd.relay_prefixlen < 32 ? (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> tunnel->ip6rd.relay_prefixlen : 0; pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; if (pbi1 > 0) d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >> (32 - pbi1); *v4dst = tunnel->ip6rd.relay_prefix | htonl(d); return true; } #else if (v6dst->s6_addr16[0] == htons(0x2002)) { /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ memcpy(v4dst, &v6dst->s6_addr16[1], 4); return true; } #endif return false; } static inline __be32 try_6rd(struct ip_tunnel *tunnel, const struct in6_addr *v6dst) { __be32 dst = 0; check_6rd(tunnel, v6dst, &dst); return dst; } /* * This function assumes it is being called from dev_queue_xmit() * and that skb is filled properly by that function. */ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; const struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ unsigned int max_headroom; /* The extra header space needed */ __be32 dst = tiph->daddr; struct flowi4 fl4; int mtu; const struct in6_addr *addr6; int addr_type; u8 ttl; u8 protocol = IPPROTO_IPV6; int t_hlen = tunnel->hlen + sizeof(struct iphdr); if (tos == 1) tos = ipv6_get_dsfield(iph6); /* ISATAP (RFC4214) - must come before 6to4 */ if (dev->priv_flags & IFF_ISATAP) { struct neighbour *neigh = NULL; bool do_tx_error = false; if (skb_dst(skb)) neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (!neigh) { net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if ((addr_type & IPV6_ADDR_UNICAST) && ipv6_addr_is_isatap(addr6)) dst = addr6->s6_addr32[3]; else do_tx_error = true; neigh_release(neigh); if (do_tx_error) goto tx_error; } if (!dst) dst = try_6rd(tunnel, &iph6->daddr); if (!dst) { struct neighbour *neigh = NULL; bool do_tx_error = false; if (skb_dst(skb)) neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr); if (!neigh) { net_dbg_ratelimited("nexthop == NULL\n"); goto tx_error; } addr6 = (const struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { addr6 = &ipv6_hdr(skb)->daddr; addr_type = ipv6_addr_type(addr6); } if ((addr_type & IPV6_ADDR_COMPATv4) != 0) dst = addr6->s6_addr32[3]; else do_tx_error = true; neigh_release(neigh); if (do_tx_error) goto tx_error; } flowi4_init_output(&fl4, tunnel->parms.link, tunnel->fwmark, RT_TOS(tos), RT_SCOPE_UNIVERSE, IPPROTO_IPV6, 0, dst, tiph->saddr, 0, 0, sock_net_uid(tunnel->net, NULL)); rt = dst_cache_get_ip4(&tunnel->dst_cache, &fl4.saddr); if (!rt) { rt = ip_route_output_flow(tunnel->net, &fl4, NULL); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } dst_cache_set_ip4(&tunnel->dst_cache, &rt->dst, fl4.saddr); } if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } tdev = rt->dst.dev; if (tdev == dev) { ip_rt_put(rt); DEV_STATS_INC(dev, collisions); goto tx_error; } if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) { ip_rt_put(rt); goto tx_error; } if (df) { mtu = dst_mtu(&rt->dst) - t_hlen; if (mtu < IPV4_MIN_MTU) { DEV_STATS_INC(dev, collisions); ip_rt_put(rt); goto tx_error; } if (mtu < IPV6_MIN_MTU) { mtu = IPV6_MIN_MTU; df = 0; } if (tunnel->parms.iph.daddr) skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; } } if (tunnel->err_count > 0) { if (time_before(jiffies, tunnel->err_time + IPTUNNEL_ERR_TIMEO)) { tunnel->err_count--; dst_link_failure(skb); } else tunnel->err_count = 0; } /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom = LL_RESERVED_SPACE(tdev) + t_hlen; if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } if (skb->sk) skb_set_owner_w(new_skb, skb->sk); dev_kfree_skb(skb); skb = new_skb; iph6 = ipv6_hdr(skb); } ttl = tiph->ttl; if (ttl == 0) ttl = iph6->hop_limit; tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); if (ip_tunnel_encap(skb, &tunnel->encap, &protocol, &fl4) < 0) { ip_rt_put(rt); goto tx_error; } skb_set_inner_ipproto(skb, IPPROTO_IPV6); iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: kfree_skb(skb); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static netdev_tx_t sit_tunnel_xmit__(struct sk_buff *skb, struct net_device *dev, u8 ipproto) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) goto tx_error; skb_set_inner_ipproto(skb, ipproto); ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; tx_error: kfree_skb(skb); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static netdev_tx_t sit_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { if (!pskb_inet_may_pull(skb)) goto tx_err; switch (skb->protocol) { case htons(ETH_P_IP): sit_tunnel_xmit__(skb, dev, IPPROTO_IPIP); break; case htons(ETH_P_IPV6): ipip6_tunnel_xmit(skb, dev); break; #if IS_ENABLED(CONFIG_MPLS) case htons(ETH_P_MPLS_UC): sit_tunnel_xmit__(skb, dev, IPPROTO_MPLS); break; #endif default: goto tx_err; } return NETDEV_TX_OK; tx_err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } static void ipip6_tunnel_bind_dev(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); struct net_device *tdev = NULL; int hlen = LL_MAX_HEADER; const struct iphdr *iph; struct flowi4 fl4; iph = &tunnel->parms.iph; if (iph->daddr) { struct rtable *rt = ip_route_output_ports(tunnel->net, &fl4, NULL, iph->daddr, iph->saddr, 0, 0, IPPROTO_IPV6, RT_TOS(iph->tos), tunnel->parms.link); if (!IS_ERR(rt)) { tdev = rt->dst.dev; ip_rt_put(rt); } dev->flags |= IFF_POINTOPOINT; } if (!tdev && tunnel->parms.link) tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link); if (tdev && !netif_is_l3_master(tdev)) { int mtu; mtu = tdev->mtu - t_hlen; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; WRITE_ONCE(dev->mtu, mtu); hlen = tdev->hard_header_len + tdev->needed_headroom; } dev->needed_headroom = t_hlen + hlen; } static void ipip6_tunnel_update(struct ip_tunnel *t, struct ip_tunnel_parm_kern *p, __u32 fwmark) { struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); ipip6_tunnel_unlink(sitn, t); synchronize_net(); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; __dev_addr_set(t->dev, &p->iph.saddr, 4); memcpy(t->dev->broadcast, &p->iph.daddr, 4); ipip6_tunnel_link(sitn, t); t->parms.iph.ttl = p->iph.ttl; t->parms.iph.tos = p->iph.tos; t->parms.iph.frag_off = p->iph.frag_off; if (t->parms.link != p->link || t->fwmark != fwmark) { t->parms.link = p->link; t->fwmark = fwmark; ipip6_tunnel_bind_dev(t->dev); } dst_cache_reset(&t->dst_cache); netdev_state_change(t->dev); } #ifdef CONFIG_IPV6_SIT_6RD static int ipip6_tunnel_update_6rd(struct ip_tunnel *t, struct ip_tunnel_6rd *ip6rd) { struct in6_addr prefix; __be32 relay_prefix; if (ip6rd->relay_prefixlen > 32 || ip6rd->prefixlen + (32 - ip6rd->relay_prefixlen) > 64) return -EINVAL; ipv6_addr_prefix(&prefix, &ip6rd->prefix, ip6rd->prefixlen); if (!ipv6_addr_equal(&prefix, &ip6rd->prefix)) return -EINVAL; if (ip6rd->relay_prefixlen) relay_prefix = ip6rd->relay_prefix & htonl(0xffffffffUL << (32 - ip6rd->relay_prefixlen)); else relay_prefix = 0; if (relay_prefix != ip6rd->relay_prefix) return -EINVAL; t->ip6rd.prefix = prefix; t->ip6rd.relay_prefix = relay_prefix; t->ip6rd.prefixlen = ip6rd->prefixlen; t->ip6rd.relay_prefixlen = ip6rd->relay_prefixlen; dst_cache_reset(&t->dst_cache); netdev_state_change(t->dev); return 0; } static int ipip6_tunnel_get6rd(struct net_device *dev, struct ip_tunnel_parm __user *data) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; struct ip_tunnel_6rd ip6rd; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { if (!ip_tunnel_parm_from_user(&p, data)) return -EFAULT; t = ipip6_tunnel_locate(t->net, &p, 0); } if (!t) t = netdev_priv(dev); ip6rd.prefix = t->ip6rd.prefix; ip6rd.relay_prefix = t->ip6rd.relay_prefix; ip6rd.prefixlen = t->ip6rd.prefixlen; ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; if (copy_to_user(data, &ip6rd, sizeof(ip6rd))) return -EFAULT; return 0; } static int ipip6_tunnel_6rdctl(struct net_device *dev, struct ip_tunnel_6rd __user *data, int cmd) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_6rd ip6rd; int err; if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (copy_from_user(&ip6rd, data, sizeof(ip6rd))) return -EFAULT; if (cmd != SIOCDEL6RD) { err = ipip6_tunnel_update_6rd(t, &ip6rd); if (err < 0) return err; } else ipip6_tunnel_clone_6rd(dev, dev_to_sit_net(dev)); return 0; } #endif /* CONFIG_IPV6_SIT_6RD */ static bool ipip6_valid_ip_proto(u8 ipproto) { return ipproto == IPPROTO_IPV6 || ipproto == IPPROTO_IPIP || #if IS_ENABLED(CONFIG_MPLS) ipproto == IPPROTO_MPLS || #endif ipproto == 0; } static int __ipip6_tunnel_ioctl_validate(struct net *net, struct ip_tunnel_parm_kern *p) { if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (!ipip6_valid_ip_proto(p->iph.protocol)) return -EINVAL; if (p->iph.version != 4 || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF))) return -EINVAL; if (p->iph.ttl) p->iph.frag_off |= htons(IP_DF); return 0; } static int ipip6_tunnel_get(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) t = ipip6_tunnel_locate(t->net, p, 0); if (!t) t = netdev_priv(dev); memcpy(p, &t->parms, sizeof(*p)); return 0; } static int ipip6_tunnel_add(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); int err; err = __ipip6_tunnel_ioctl_validate(t->net, p); if (err) return err; t = ipip6_tunnel_locate(t->net, p, 1); if (!t) return -ENOBUFS; return 0; } static int ipip6_tunnel_change(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); int err; err = __ipip6_tunnel_ioctl_validate(t->net, p); if (err) return err; t = ipip6_tunnel_locate(t->net, p, 0); if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { if (!t) return -ENOENT; } else { if (t) { if (t->dev != dev) return -EEXIST; } else { if (((dev->flags & IFF_POINTOPOINT) && !p->iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p->iph.daddr)) return -EINVAL; t = netdev_priv(dev); } ipip6_tunnel_update(t, p, t->fwmark); } return 0; } static int ipip6_tunnel_del(struct net_device *dev, struct ip_tunnel_parm_kern *p) { struct ip_tunnel *t = netdev_priv(dev); if (!ns_capable(t->net->user_ns, CAP_NET_ADMIN)) return -EPERM; if (dev == dev_to_sit_net(dev)->fb_tunnel_dev) { t = ipip6_tunnel_locate(t->net, p, 0); if (!t) return -ENOENT; if (t == netdev_priv(dev_to_sit_net(dev)->fb_tunnel_dev)) return -EPERM; dev = t->dev; } unregister_netdevice(dev); return 0; } static int ipip6_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { switch (cmd) { case SIOCGETTUNNEL: return ipip6_tunnel_get(dev, p); case SIOCADDTUNNEL: return ipip6_tunnel_add(dev, p); case SIOCCHGTUNNEL: return ipip6_tunnel_change(dev, p); case SIOCDELTUNNEL: return ipip6_tunnel_del(dev, p); default: return -EINVAL; } } static int ipip6_tunnel_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { switch (cmd) { case SIOCGETTUNNEL: case SIOCADDTUNNEL: case SIOCCHGTUNNEL: case SIOCDELTUNNEL: return ip_tunnel_siocdevprivate(dev, ifr, data, cmd); case SIOCGETPRL: return ipip6_tunnel_get_prl(dev, data); case SIOCADDPRL: case SIOCDELPRL: case SIOCCHGPRL: return ipip6_tunnel_prl_ctl(dev, data, cmd); #ifdef CONFIG_IPV6_SIT_6RD case SIOCGET6RD: return ipip6_tunnel_get6rd(dev, data); case SIOCADD6RD: case SIOCCHG6RD: case SIOCDEL6RD: return ipip6_tunnel_6rdctl(dev, data, cmd); #endif default: return -EINVAL; } } static const struct net_device_ops ipip6_netdev_ops = { .ndo_init = ipip6_tunnel_init, .ndo_uninit = ipip6_tunnel_uninit, .ndo_start_xmit = sit_tunnel_xmit, .ndo_siocdevprivate = ipip6_tunnel_siocdevprivate, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipip6_tunnel_ctl, }; static void ipip6_dev_free(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); dst_cache_destroy(&tunnel->dst_cache); } #define SIT_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) static void ipip6_tunnel_setup(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); dev->netdev_ops = &ipip6_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ipip6_dev_free; dev->type = ARPHRD_SIT; dev->mtu = ETH_DATA_LEN - t_hlen; dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - t_hlen; dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; dev->features |= NETIF_F_LLTX; dev->features |= SIT_FEATURES; dev->hw_features |= SIT_FEATURES; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; } static int ipip6_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); int err; tunnel->dev = dev; tunnel->net = dev_net(dev); strcpy(tunnel->parms.name, dev->name); ipip6_tunnel_bind_dev(dev); err = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); if (err) return err; netdev_hold(dev, &tunnel->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); return 0; } static void __net_init ipip6_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); iph->version = 4; iph->protocol = IPPROTO_IPV6; iph->ihl = 5; iph->ttl = 64; rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); } static int ipip6_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u8 proto; if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (!ipip6_valid_ip_proto(proto)) return -EINVAL; return 0; } static void ipip6_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); parms->iph.version = 4; parms->iph.protocol = IPPROTO_IPV6; parms->iph.ihl = 5; parms->iph.ttl = 64; if (!data) return; ip_tunnel_netlink_parms(data, parms); if (data[IFLA_IPTUN_FWMARK]) *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } #ifdef CONFIG_IPV6_SIT_6RD /* This function returns true when 6RD attributes are present in the nl msg */ static bool ipip6_netlink_6rd_parms(struct nlattr *data[], struct ip_tunnel_6rd *ip6rd) { bool ret = false; memset(ip6rd, 0, sizeof(*ip6rd)); if (!data) return ret; if (data[IFLA_IPTUN_6RD_PREFIX]) { ret = true; ip6rd->prefix = nla_get_in6_addr(data[IFLA_IPTUN_6RD_PREFIX]); } if (data[IFLA_IPTUN_6RD_RELAY_PREFIX]) { ret = true; ip6rd->relay_prefix = nla_get_be32(data[IFLA_IPTUN_6RD_RELAY_PREFIX]); } if (data[IFLA_IPTUN_6RD_PREFIXLEN]) { ret = true; ip6rd->prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_PREFIXLEN]); } if (data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]) { ret = true; ip6rd->relay_prefixlen = nla_get_u16(data[IFLA_IPTUN_6RD_RELAY_PREFIXLEN]); } return ret; } #endif static int ipip6_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip_tunnel *nt; struct ip_tunnel_encap ipencap; #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif int err; nt = netdev_priv(dev); if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { err = ip_tunnel_encap_setup(nt, &ipencap); if (err < 0) return err; } ipip6_netlink_parms(data, &nt->parms, &nt->fwmark); if (ipip6_tunnel_locate(net, &nt->parms, 0)) return -EEXIST; err = ipip6_tunnel_create(dev); if (err < 0) return err; if (tb[IFLA_MTU]) { u32 mtu = nla_get_u32(tb[IFLA_MTU]); if (mtu >= IPV6_MIN_MTU && mtu <= IP6_MAX_MTU - dev->hard_header_len) dev->mtu = mtu; } #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) { err = ipip6_tunnel_update_6rd(nt, &ip6rd); if (err < 0) unregister_netdevice_queue(dev, NULL); } #endif return err; } static int ipip6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_encap ipencap; struct ip_tunnel_parm_kern p; struct net *net = t->net; struct sit_net *sitn = net_generic(net, sit_net_id); #ifdef CONFIG_IPV6_SIT_6RD struct ip_tunnel_6rd ip6rd; #endif __u32 fwmark = t->fwmark; int err; if (dev == sitn->fb_tunnel_dev) return -EINVAL; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } ipip6_netlink_parms(data, &p, &fwmark); if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) return -EINVAL; t = ipip6_tunnel_locate(net, &p, 0); if (t) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); ipip6_tunnel_update(t, &p, fwmark); #ifdef CONFIG_IPV6_SIT_6RD if (ipip6_netlink_6rd_parms(data, &ip6rd)) return ipip6_tunnel_update_6rd(t, &ip6rd); #endif return 0; } static size_t ipip6_get_size(const struct net_device *dev) { return /* IFLA_IPTUN_LINK */ nla_total_size(4) + /* IFLA_IPTUN_LOCAL */ nla_total_size(4) + /* IFLA_IPTUN_REMOTE */ nla_total_size(4) + /* IFLA_IPTUN_TTL */ nla_total_size(1) + /* IFLA_IPTUN_TOS */ nla_total_size(1) + /* IFLA_IPTUN_PMTUDISC */ nla_total_size(1) + /* IFLA_IPTUN_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_PROTO */ nla_total_size(1) + #ifdef CONFIG_IPV6_SIT_6RD /* IFLA_IPTUN_6RD_PREFIX */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_6RD_RELAY_PREFIX */ nla_total_size(4) + /* IFLA_IPTUN_6RD_PREFIXLEN */ nla_total_size(2) + /* IFLA_IPTUN_6RD_RELAY_PREFIXLEN */ nla_total_size(2) + #endif /* IFLA_IPTUN_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_IPTUN_FWMARK */ nla_total_size(4) + 0; } static int ipip6_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_parm_kern *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || nla_put_be16(skb, IFLA_IPTUN_FLAGS, ip_tunnel_flags_to_be16(parm->i_flags)) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark)) goto nla_put_failure; #ifdef CONFIG_IPV6_SIT_6RD if (nla_put_in6_addr(skb, IFLA_IPTUN_6RD_PREFIX, &tunnel->ip6rd.prefix) || nla_put_in_addr(skb, IFLA_IPTUN_6RD_RELAY_PREFIX, tunnel->ip6rd.relay_prefix) || nla_put_u16(skb, IFLA_IPTUN_6RD_PREFIXLEN, tunnel->ip6rd.prefixlen) || nla_put_u16(skb, IFLA_IPTUN_6RD_RELAY_PREFIXLEN, tunnel->ip6rd.relay_prefixlen)) goto nla_put_failure; #endif if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) || nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy ipip6_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, [IFLA_IPTUN_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, #ifdef CONFIG_IPV6_SIT_6RD [IFLA_IPTUN_6RD_PREFIX] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_6RD_RELAY_PREFIX] = { .type = NLA_U32 }, [IFLA_IPTUN_6RD_PREFIXLEN] = { .type = NLA_U16 }, [IFLA_IPTUN_6RD_RELAY_PREFIXLEN] = { .type = NLA_U16 }, #endif [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_FWMARK] = { .type = NLA_U32 }, }; static void ipip6_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); if (dev != sitn->fb_tunnel_dev) unregister_netdevice_queue(dev, head); } static struct rtnl_link_ops sit_link_ops __read_mostly = { .kind = "sit", .maxtype = IFLA_IPTUN_MAX, .policy = ipip6_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipip6_tunnel_setup, .validate = ipip6_validate, .newlink = ipip6_newlink, .changelink = ipip6_changelink, .get_size = ipip6_get_size, .fill_info = ipip6_fill_info, .dellink = ipip6_dellink, .get_link_net = ip_tunnel_get_link_net, }; static struct xfrm_tunnel sit_handler __read_mostly = { .handler = ipip6_rcv, .err_handler = ipip6_err, .priority = 1, }; static struct xfrm_tunnel ipip_handler __read_mostly = { .handler = ipip_rcv, .err_handler = ipip6_err, .priority = 2, }; #if IS_ENABLED(CONFIG_MPLS) static struct xfrm_tunnel mplsip_handler __read_mostly = { .handler = mplsip_rcv, .err_handler = ipip6_err, .priority = 2, }; #endif static void __net_exit sit_destroy_tunnels(struct net *net, struct list_head *head) { struct sit_net *sitn = net_generic(net, sit_net_id); struct net_device *dev, *aux; int prio; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &sit_link_ops) unregister_netdevice_queue(dev, head); for (prio = 0; prio < 4; prio++) { int h; for (h = 0; h < (prio ? IP6_SIT_HASH_SIZE : 1); h++) { struct ip_tunnel *t; t = rtnl_dereference(sitn->tunnels[prio][h]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, head); t = rtnl_dereference(t->next); } } } } static int __net_init sit_init_net(struct net *net) { struct sit_net *sitn = net_generic(net, sit_net_id); struct ip_tunnel *t; int err; sitn->tunnels[0] = sitn->tunnels_wc; sitn->tunnels[1] = sitn->tunnels_l; sitn->tunnels[2] = sitn->tunnels_r; sitn->tunnels[3] = sitn->tunnels_r_l; if (!net_has_fallback_tunnels(net)) return 0; sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0", NET_NAME_UNKNOWN, ipip6_tunnel_setup); if (!sitn->fb_tunnel_dev) { err = -ENOMEM; goto err_alloc_dev; } dev_net_set(sitn->fb_tunnel_dev, net); sitn->fb_tunnel_dev->rtnl_link_ops = &sit_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ sitn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL; err = register_netdev(sitn->fb_tunnel_dev); if (err) goto err_reg_dev; ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); t = netdev_priv(sitn->fb_tunnel_dev); strcpy(t->parms.name, sitn->fb_tunnel_dev->name); return 0; err_reg_dev: free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: return err; } static void __net_exit sit_exit_batch_rtnl(struct list_head *net_list, struct list_head *dev_to_kill) { struct net *net; ASSERT_RTNL(); list_for_each_entry(net, net_list, exit_list) sit_destroy_tunnels(net, dev_to_kill); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, .exit_batch_rtnl = sit_exit_batch_rtnl, .id = &sit_net_id, .size = sizeof(struct sit_net), }; static void __exit sit_cleanup(void) { rtnl_link_unregister(&sit_link_ops); xfrm4_tunnel_deregister(&sit_handler, AF_INET6); xfrm4_tunnel_deregister(&ipip_handler, AF_INET); #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); #endif unregister_pernet_device(&sit_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } static int __init sit_init(void) { int err; pr_info("IPv6, IPv4 and MPLS over IPv4 tunneling driver\n"); err = register_pernet_device(&sit_net_ops); if (err < 0) return err; err = xfrm4_tunnel_register(&sit_handler, AF_INET6); if (err < 0) { pr_info("%s: can't register ip6ip4\n", __func__); goto xfrm_tunnel_failed; } err = xfrm4_tunnel_register(&ipip_handler, AF_INET); if (err < 0) { pr_info("%s: can't register ip4ip4\n", __func__); goto xfrm_tunnel4_failed; } #if IS_ENABLED(CONFIG_MPLS) err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS); if (err < 0) { pr_info("%s: can't register mplsip\n", __func__); goto xfrm_tunnel_mpls_failed; } #endif err = rtnl_link_register(&sit_link_ops); if (err < 0) goto rtnl_link_failed; out: return err; rtnl_link_failed: #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); xfrm_tunnel_mpls_failed: #endif xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm_tunnel4_failed: xfrm4_tunnel_deregister(&sit_handler, AF_INET6); xfrm_tunnel_failed: unregister_pernet_device(&sit_net_ops); goto out; } module_init(sit_init); module_exit(sit_cleanup); MODULE_DESCRIPTION("IPv6-in-IPv4 tunnel SIT driver"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("sit"); MODULE_ALIAS_NETDEV("sit0"); |
| 22 23 21 | 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 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion, adapted for tracing. * * Copyright (C) 2020 Paul E. McKenney. */ #ifndef __LINUX_RCUPDATE_TRACE_H #define __LINUX_RCUPDATE_TRACE_H #include <linux/sched.h> #include <linux/rcupdate.h> extern struct lockdep_map rcu_trace_lock_map; #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline int rcu_read_lock_trace_held(void) { return lock_is_held(&rcu_trace_lock_map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int rcu_read_lock_trace_held(void) { return 1; } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_TASKS_TRACE_RCU void rcu_read_unlock_trace_special(struct task_struct *t); /** * rcu_read_lock_trace - mark beginning of RCU-trace read-side critical section * * When synchronize_rcu_tasks_trace() is invoked by one task, then that * task is guaranteed to block until all other tasks exit their read-side * critical sections. Similarly, if call_rcu_trace() is invoked on one * task while other tasks are within RCU read-side critical sections, * invocation of the corresponding RCU callback is deferred until after * the all the other tasks exit their critical sections. * * For more details, please see the documentation for rcu_read_lock(). */ static inline void rcu_read_lock_trace(void) { struct task_struct *t = current; WRITE_ONCE(t->trc_reader_nesting, READ_ONCE(t->trc_reader_nesting) + 1); barrier(); if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB) && t->trc_reader_special.b.need_mb) smp_mb(); // Pairs with update-side barriers rcu_lock_acquire(&rcu_trace_lock_map); } /** * rcu_read_unlock_trace - mark end of RCU-trace read-side critical section * * Pairs with a preceding call to rcu_read_lock_trace(), and nesting is * allowed. Invoking a rcu_read_unlock_trace() when there is no matching * rcu_read_lock_trace() is verboten, and will result in lockdep complaints. * * For more details, please see the documentation for rcu_read_unlock(). */ static inline void rcu_read_unlock_trace(void) { int nesting; struct task_struct *t = current; rcu_lock_release(&rcu_trace_lock_map); nesting = READ_ONCE(t->trc_reader_nesting) - 1; barrier(); // Critical section before disabling. // Disable IPI-based setting of .need_qs. WRITE_ONCE(t->trc_reader_nesting, INT_MIN + nesting); if (likely(!READ_ONCE(t->trc_reader_special.s)) || nesting) { WRITE_ONCE(t->trc_reader_nesting, nesting); return; // We assume shallow reader nesting. } WARN_ON_ONCE(nesting != 0); rcu_read_unlock_trace_special(t); } void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func); void synchronize_rcu_tasks_trace(void); void rcu_barrier_tasks_trace(void); struct task_struct *get_rcu_tasks_trace_gp_kthread(void); #else /* * The BPF JIT forms these addresses even when it doesn't call these * functions, so provide definitions that result in runtime errors. */ static inline void call_rcu_tasks_trace(struct rcu_head *rhp, rcu_callback_t func) { BUG(); } static inline void rcu_read_lock_trace(void) { BUG(); } static inline void rcu_read_unlock_trace(void) { BUG(); } #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ #endif /* __LINUX_RCUPDATE_TRACE_H */ |
| 1 2 2 18 16 2 23 34 35 36 2 10 16 19 19 40 40 41 22 20 5 5 5 3 3 3 5 21 22 12 10 10 1 1 2 2 10 4 3 4 1 3 20 3 17 2 2 2 2 2 2 5 5 3 1 3 3 2 2 2 2 2 1 1 1 1 1 2 2 2 2 2 1 1 2 13 8 2 3 11 12 12 2 8 2 1 12 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 5 6 6 1 1 1 2 6 3 2 1 5 2 3 10 1 6 3 9 9 9 5 2 3 5 10 10 2 3 3 2 1 3 5 2 2 3 2 2 1 3 3 1 2 1 2 1 5 4 23 21 23 23 1 1 15 14 23 1 9 14 17 11 2 8 11 11 4 6 7 1 6 6 5 1 5 5 5 5 2 4 11 12 13 13 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 | // SPDX-License-Identifier: GPL-2.0-only /* L2TP core. * * Copyright (c) 2008,2009,2010 Katalix Systems Ltd * * This file contains some code of the original L2TPv2 pppol2tp * driver, which has the following copyright: * * Authors: Martijn van Oosterhout <kleptog@svana.org> * James Chapman (jchapman@katalix.com) * Contributors: * Michal Ostrowski <mostrows@speakeasy.net> * Arnaldo Carvalho de Melo <acme@xconectiva.com.br> * David S. Miller (davem@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/string.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/spinlock.h> #include <linux/kthread.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/errno.h> #include <linux/jiffies.h> #include <linux/netdevice.h> #include <linux/net.h> #include <linux/inetdevice.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/udp.h> #include <linux/l2tp.h> #include <linux/sort.h> #include <linux/file.h> #include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/dst.h> #include <net/ip.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/inet_common.h> #include <net/xfrm.h> #include <net/protocol.h> #include <net/inet6_connection_sock.h> #include <net/inet_ecn.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <asm/byteorder.h> #include <linux/atomic.h> #include "l2tp_core.h" #define CREATE_TRACE_POINTS #include "trace.h" #define L2TP_DRV_VERSION "V2.0" /* L2TP header constants */ #define L2TP_HDRFLAG_T 0x8000 #define L2TP_HDRFLAG_L 0x4000 #define L2TP_HDRFLAG_S 0x0800 #define L2TP_HDRFLAG_O 0x0200 #define L2TP_HDRFLAG_P 0x0100 #define L2TP_HDR_VER_MASK 0x000F #define L2TP_HDR_VER_2 0x0002 #define L2TP_HDR_VER_3 0x0003 /* L2TPv3 default L2-specific sublayer */ #define L2TP_SLFLAG_S 0x40000000 #define L2TP_SL_SEQ_MASK 0x00ffffff #define L2TP_HDR_SIZE_MAX 14 /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 #define L2TP_DEPTH_NESTING 2 #if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING #error "L2TP requires its own lockdep subclass" #endif /* Private data stored for received packets in the skb. */ struct l2tp_skb_cb { u32 ns; u16 has_seq; u16 length; unsigned long expires; }; #define L2TP_SKB_CB(skb) ((struct l2tp_skb_cb *)&(skb)->cb[sizeof(struct inet_skb_parm)]) static struct workqueue_struct *l2tp_wq; /* per-net private data for this module */ static unsigned int l2tp_net_id; struct l2tp_net { /* Lock for write access to l2tp_tunnel_idr */ spinlock_t l2tp_tunnel_idr_lock; struct idr l2tp_tunnel_idr; /* Lock for write access to l2tp_v[23]_session_idr/htable */ spinlock_t l2tp_session_idr_lock; struct idr l2tp_v2_session_idr; struct idr l2tp_v3_session_idr; struct hlist_head l2tp_v3_session_htable[16]; }; static inline u32 l2tp_v2_session_key(u16 tunnel_id, u16 session_id) { return ((u32)tunnel_id) << 16 | session_id; } static inline unsigned long l2tp_v3_session_hashkey(struct sock *sk, u32 session_id) { return ((unsigned long)sk) + session_id; } #if IS_ENABLED(CONFIG_IPV6) static bool l2tp_sk_is_v6(struct sock *sk) { return sk->sk_family == PF_INET6 && !ipv6_addr_v4mapped(&sk->sk_v6_daddr); } #endif static inline struct l2tp_net *l2tp_pernet(const struct net *net) { return net_generic(net, l2tp_net_id); } static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel) { trace_free_tunnel(tunnel); sock_put(tunnel->sock); /* the tunnel is freed in the socket destructor */ } static void l2tp_session_free(struct l2tp_session *session) { trace_free_session(session); if (session->tunnel) l2tp_tunnel_dec_refcount(session->tunnel); kfree(session); } struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk) { struct l2tp_tunnel *tunnel = sk->sk_user_data; if (tunnel) if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC)) return NULL; return tunnel; } EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel); void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel) { refcount_inc(&tunnel->ref_count); } EXPORT_SYMBOL_GPL(l2tp_tunnel_inc_refcount); void l2tp_tunnel_dec_refcount(struct l2tp_tunnel *tunnel) { if (refcount_dec_and_test(&tunnel->ref_count)) l2tp_tunnel_free(tunnel); } EXPORT_SYMBOL_GPL(l2tp_tunnel_dec_refcount); void l2tp_session_inc_refcount(struct l2tp_session *session) { refcount_inc(&session->ref_count); } EXPORT_SYMBOL_GPL(l2tp_session_inc_refcount); void l2tp_session_dec_refcount(struct l2tp_session *session) { if (refcount_dec_and_test(&session->ref_count)) l2tp_session_free(session); } EXPORT_SYMBOL_GPL(l2tp_session_dec_refcount); /* Lookup a tunnel. A new reference is held on the returned tunnel. */ struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id) { const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); tunnel = idr_find(&pn->l2tp_tunnel_idr, tunnel_id); if (tunnel && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_tunnel_get); struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth) { struct l2tp_net *pn = l2tp_pernet(net); unsigned long tunnel_id, tmp; struct l2tp_tunnel *tunnel; int count = 0; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel && ++count > nth && refcount_inc_not_zero(&tunnel->ref_count)) { rcu_read_unlock_bh(); return tunnel; } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth); struct l2tp_session *l2tp_v3_session_get(const struct net *net, struct sock *sk, u32 session_id) { const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; rcu_read_lock_bh(); session = idr_find(&pn->l2tp_v3_session_idr, session_id); if (session && !hash_hashed(&session->hlist) && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } /* If we get here and session is non-NULL, the session_id * collides with one in another tunnel. If sk is non-NULL, * find the session matching sk. */ if (session && sk) { unsigned long key = l2tp_v3_session_hashkey(sk, session->session_id); hash_for_each_possible_rcu(pn->l2tp_v3_session_htable, session, hlist, key) { if (session->tunnel->sock == sk && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_v3_session_get); struct l2tp_session *l2tp_v2_session_get(const struct net *net, u16 tunnel_id, u16 session_id) { u32 session_key = l2tp_v2_session_key(tunnel_id, session_id); const struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_session *session; rcu_read_lock_bh(); session = idr_find(&pn->l2tp_v2_session_idr, session_key); if (session && refcount_inc_not_zero(&session->ref_count)) { rcu_read_unlock_bh(); return session; } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_v2_session_get); struct l2tp_session *l2tp_session_get(const struct net *net, struct sock *sk, int pver, u32 tunnel_id, u32 session_id) { if (pver == L2TP_HDR_VER_2) return l2tp_v2_session_get(net, tunnel_id, session_id); else return l2tp_v3_session_get(net, sk, session_id); } EXPORT_SYMBOL_GPL(l2tp_session_get); struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth) { struct l2tp_session *session; int count = 0; rcu_read_lock_bh(); list_for_each_entry_rcu(session, &tunnel->session_list, list) { if (++count > nth) { l2tp_session_inc_refcount(session); rcu_read_unlock_bh(); return session; } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_session_get_nth); /* Lookup a session by interface name. * This is very inefficient but is only used by management interfaces. */ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net, const char *ifname) { struct l2tp_net *pn = l2tp_pernet(net); unsigned long tunnel_id, tmp; struct l2tp_session *session; struct l2tp_tunnel *tunnel; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel) { list_for_each_entry_rcu(session, &tunnel->session_list, list) { if (!strcmp(session->ifname, ifname)) { l2tp_session_inc_refcount(session); rcu_read_unlock_bh(); return session; } } } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(l2tp_session_get_by_ifname); static void l2tp_session_coll_list_add(struct l2tp_session_coll_list *clist, struct l2tp_session *session) { l2tp_session_inc_refcount(session); WARN_ON_ONCE(session->coll_list); session->coll_list = clist; spin_lock(&clist->lock); list_add(&session->clist, &clist->list); spin_unlock(&clist->lock); } static int l2tp_session_collision_add(struct l2tp_net *pn, struct l2tp_session *session1, struct l2tp_session *session2) { struct l2tp_session_coll_list *clist; lockdep_assert_held(&pn->l2tp_session_idr_lock); if (!session2) return -EEXIST; /* If existing session is in IP-encap tunnel, refuse new session */ if (session2->tunnel->encap == L2TP_ENCAPTYPE_IP) return -EEXIST; clist = session2->coll_list; if (!clist) { /* First collision. Allocate list to manage the collided sessions * and add the existing session to the list. */ clist = kmalloc(sizeof(*clist), GFP_ATOMIC); if (!clist) return -ENOMEM; spin_lock_init(&clist->lock); INIT_LIST_HEAD(&clist->list); refcount_set(&clist->ref_count, 1); l2tp_session_coll_list_add(clist, session2); } /* If existing session isn't already in the session hlist, add it. */ if (!hash_hashed(&session2->hlist)) hash_add(pn->l2tp_v3_session_htable, &session2->hlist, session2->hlist_key); /* Add new session to the hlist and collision list */ hash_add(pn->l2tp_v3_session_htable, &session1->hlist, session1->hlist_key); refcount_inc(&clist->ref_count); l2tp_session_coll_list_add(clist, session1); return 0; } static void l2tp_session_collision_del(struct l2tp_net *pn, struct l2tp_session *session) { struct l2tp_session_coll_list *clist = session->coll_list; unsigned long session_key = session->session_id; struct l2tp_session *session2; lockdep_assert_held(&pn->l2tp_session_idr_lock); hash_del(&session->hlist); if (clist) { /* Remove session from its collision list. If there * are other sessions with the same ID, replace this * session's IDR entry with that session, otherwise * remove the IDR entry. If this is the last session, * the collision list data is freed. */ spin_lock(&clist->lock); list_del_init(&session->clist); session2 = list_first_entry_or_null(&clist->list, struct l2tp_session, clist); if (session2) { void *old = idr_replace(&pn->l2tp_v3_session_idr, session2, session_key); WARN_ON_ONCE(IS_ERR_VALUE(old)); } else { void *removed = idr_remove(&pn->l2tp_v3_session_idr, session_key); WARN_ON_ONCE(removed != session); } session->coll_list = NULL; spin_unlock(&clist->lock); if (refcount_dec_and_test(&clist->ref_count)) kfree(clist); l2tp_session_dec_refcount(session); } } int l2tp_session_register(struct l2tp_session *session, struct l2tp_tunnel *tunnel) { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); struct l2tp_session *other_session = NULL; u32 session_key; int err; spin_lock_bh(&tunnel->list_lock); spin_lock_bh(&pn->l2tp_session_idr_lock); if (!tunnel->acpt_newsess) { err = -ENODEV; goto out; } if (tunnel->version == L2TP_HDR_VER_3) { session_key = session->session_id; err = idr_alloc_u32(&pn->l2tp_v3_session_idr, NULL, &session_key, session_key, GFP_ATOMIC); /* IP encap expects session IDs to be globally unique, while * UDP encap doesn't. This isn't per the RFC, which says that * sessions are identified only by the session ID, but is to * support existing userspace which depends on it. */ if (err == -ENOSPC && tunnel->encap == L2TP_ENCAPTYPE_UDP) { other_session = idr_find(&pn->l2tp_v3_session_idr, session_key); err = l2tp_session_collision_add(pn, session, other_session); } } else { session_key = l2tp_v2_session_key(tunnel->tunnel_id, session->session_id); err = idr_alloc_u32(&pn->l2tp_v2_session_idr, NULL, &session_key, session_key, GFP_ATOMIC); } if (err) { if (err == -ENOSPC) err = -EEXIST; goto out; } l2tp_tunnel_inc_refcount(tunnel); list_add(&session->list, &tunnel->session_list); if (tunnel->version == L2TP_HDR_VER_3) { if (!other_session) idr_replace(&pn->l2tp_v3_session_idr, session, session_key); } else { idr_replace(&pn->l2tp_v2_session_idr, session, session_key); } out: spin_unlock_bh(&pn->l2tp_session_idr_lock); spin_unlock_bh(&tunnel->list_lock); if (!err) trace_register_session(session); return err; } EXPORT_SYMBOL_GPL(l2tp_session_register); /***************************************************************************** * Receive data handling *****************************************************************************/ /* Queue a skb in order. We come here only if the skb has an L2TP sequence * number. */ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *skb) { struct sk_buff *skbp; struct sk_buff *tmp; u32 ns = L2TP_SKB_CB(skb)->ns; spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skbp, tmp) { if (L2TP_SKB_CB(skbp)->ns > ns) { __skb_queue_before(&session->reorder_q, skbp, skb); atomic_long_inc(&session->stats.rx_oos_packets); goto out; } } __skb_queue_tail(&session->reorder_q, skb); out: spin_unlock_bh(&session->reorder_q.lock); } /* Dequeue a single skb. */ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *skb) { struct l2tp_tunnel *tunnel = session->tunnel; int length = L2TP_SKB_CB(skb)->length; /* We're about to requeue the skb, so return resources * to its current owner (a socket receive buffer). */ skb_orphan(skb); atomic_long_inc(&tunnel->stats.rx_packets); atomic_long_add(length, &tunnel->stats.rx_bytes); atomic_long_inc(&session->stats.rx_packets); atomic_long_add(length, &session->stats.rx_bytes); if (L2TP_SKB_CB(skb)->has_seq) { /* Bump our Nr */ session->nr++; session->nr &= session->nr_max; trace_session_seqnum_update(session); } /* call private receive handler */ if (session->recv_skb) (*session->recv_skb)(session, skb, L2TP_SKB_CB(skb)->length); else kfree_skb(skb); } /* Dequeue skbs from the session's reorder_q, subject to packet order. * Skbs that have been in the queue for too long are simply discarded. */ static void l2tp_recv_dequeue(struct l2tp_session *session) { struct sk_buff *skb; struct sk_buff *tmp; /* If the pkt at the head of the queue has the nr that we * expect to send up next, dequeue it and any other * in-sequence packets behind it. */ start: spin_lock_bh(&session->reorder_q.lock); skb_queue_walk_safe(&session->reorder_q, skb, tmp) { struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); /* If the packet has been pending on the queue for too long, discard it */ if (time_after(jiffies, cb->expires)) { atomic_long_inc(&session->stats.rx_seq_discards); atomic_long_inc(&session->stats.rx_errors); trace_session_pkt_expired(session, cb->ns); session->reorder_skip = 1; __skb_unlink(skb, &session->reorder_q); kfree_skb(skb); continue; } if (cb->has_seq) { if (session->reorder_skip) { session->reorder_skip = 0; session->nr = cb->ns; trace_session_seqnum_reset(session); } if (cb->ns != session->nr) goto out; } __skb_unlink(skb, &session->reorder_q); /* Process the skb. We release the queue lock while we * do so to let other contexts process the queue. */ spin_unlock_bh(&session->reorder_q.lock); l2tp_recv_dequeue_skb(session, skb); goto start; } out: spin_unlock_bh(&session->reorder_q.lock); } static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr) { u32 nws; if (nr >= session->nr) nws = nr - session->nr; else nws = (session->nr_max + 1) - (session->nr - nr); return nws < session->nr_window_size; } /* If packet has sequence numbers, queue it if acceptable. Returns 0 if * acceptable, else non-zero. */ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb) { struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb); if (!l2tp_seq_check_rx_window(session, cb->ns)) { /* Packet sequence number is outside allowed window. * Discard it. */ trace_session_pkt_outside_rx_window(session, cb->ns); goto discard; } if (session->reorder_timeout != 0) { /* Packet reordering enabled. Add skb to session's * reorder queue, in order of ns. */ l2tp_recv_queue_skb(session, skb); goto out; } /* Packet reordering disabled. Discard out-of-sequence packets, while * tracking the number if in-sequence packets after the first OOS packet * is seen. After nr_oos_count_max in-sequence packets, reset the * sequence number to re-enable packet reception. */ if (cb->ns == session->nr) { skb_queue_tail(&session->reorder_q, skb); } else { u32 nr_oos = cb->ns; u32 nr_next = (session->nr_oos + 1) & session->nr_max; if (nr_oos == nr_next) session->nr_oos_count++; else session->nr_oos_count = 0; session->nr_oos = nr_oos; if (session->nr_oos_count > session->nr_oos_count_max) { session->reorder_skip = 1; } if (!session->reorder_skip) { atomic_long_inc(&session->stats.rx_seq_discards); trace_session_pkt_oos(session, cb->ns); goto discard; } skb_queue_tail(&session->reorder_q, skb); } out: return 0; discard: return 1; } /* Do receive processing of L2TP data frames. We handle both L2TPv2 * and L2TPv3 data frames here. * * L2TPv2 Data Message Header * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |T|L|x|x|S|x|O|P|x|x|x|x| Ver | Length (opt) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Tunnel ID | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Ns (opt) | Nr (opt) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Offset Size (opt) | Offset pad... (opt) * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Data frames are marked by T=0. All other fields are the same as * those in L2TP control frames. * * L2TPv3 Data Message Header * * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | L2TP Session Header | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | L2-Specific Sublayer | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Tunnel Payload ... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 Session Header Over IP * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Session ID | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Cookie (optional, maximum 64 bits)... * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * L2TPv3 L2-Specific Sublayer Format * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |x|S|x|x|x|x|x|x| Sequence Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Cookie value and sublayer format are negotiated with the peer when * the session is set up. Unlike L2TPv2, we do not need to parse the * packet header to determine if optional fields are present. * * Caller must already have parsed the frame and determined that it is * a data (not control) frame before coming here. Fields up to the * session-id have already been parsed and ptr points to the data * after the session-id. */ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb, unsigned char *ptr, unsigned char *optr, u16 hdrflags, int length) { struct l2tp_tunnel *tunnel = session->tunnel; int offset; /* Parse and check optional cookie */ if (session->peer_cookie_len > 0) { if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) { pr_debug_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n", tunnel->name, tunnel->tunnel_id, session->session_id); atomic_long_inc(&session->stats.rx_cookie_discards); goto discard; } ptr += session->peer_cookie_len; } /* Handle the optional sequence numbers. Sequence numbers are * in different places for L2TPv2 and L2TPv3. * * If we are the LAC, enable/disable sequence numbers under * the control of the LNS. If no sequence numbers present but * we were expecting them, discard frame. */ L2TP_SKB_CB(skb)->has_seq = 0; if (tunnel->version == L2TP_HDR_VER_2) { if (hdrflags & L2TP_HDRFLAG_S) { /* Store L2TP info in the skb */ L2TP_SKB_CB(skb)->ns = ntohs(*(__be16 *)ptr); L2TP_SKB_CB(skb)->has_seq = 1; ptr += 2; /* Skip past nr in the header */ ptr += 2; } } else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = ntohl(*(__be32 *)ptr); if (l2h & 0x40000000) { /* Store L2TP info in the skb */ L2TP_SKB_CB(skb)->ns = l2h & 0x00ffffff; L2TP_SKB_CB(skb)->has_seq = 1; } ptr += 4; } if (L2TP_SKB_CB(skb)->has_seq) { /* Received a packet with sequence numbers. If we're the LAC, * check if we sre sending sequence numbers and if not, * configure it so. */ if (!session->lns_mode && !session->send_seq) { trace_session_seqnum_lns_enable(session); session->send_seq = 1; l2tp_session_set_header_len(session, tunnel->version); } } else { /* No sequence numbers. * If user has configured mandatory sequence numbers, discard. */ if (session->recv_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } /* If we're the LAC and we're sending sequence numbers, the * LNS has requested that we no longer send sequence numbers. * If we're the LNS and we're sending sequence numbers, the * LAC is broken. Discard the frame. */ if (!session->lns_mode && session->send_seq) { trace_session_seqnum_lns_disable(session); session->send_seq = 0; l2tp_session_set_header_len(session, tunnel->version); } else if (session->send_seq) { pr_debug_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n", session->name); atomic_long_inc(&session->stats.rx_seq_discards); goto discard; } } /* Session data offset is defined only for L2TPv2 and is * indicated by an optional 16-bit value in the header. */ if (tunnel->version == L2TP_HDR_VER_2) { /* If offset bit set, skip it. */ if (hdrflags & L2TP_HDRFLAG_O) { offset = ntohs(*(__be16 *)ptr); ptr += 2 + offset; } } offset = ptr - optr; if (!pskb_may_pull(skb, offset)) goto discard; __skb_pull(skb, offset); /* Prepare skb for adding to the session's reorder_q. Hold * packets for max reorder_timeout or 1 second if not * reordering. */ L2TP_SKB_CB(skb)->length = length; L2TP_SKB_CB(skb)->expires = jiffies + (session->reorder_timeout ? session->reorder_timeout : HZ); /* Add packet to the session's receive queue. Reordering is done here, if * enabled. Saved L2TP protocol info is stored in skb->sb[]. */ if (L2TP_SKB_CB(skb)->has_seq) { if (l2tp_recv_data_seq(session, skb)) goto discard; } else { /* No sequence numbers. Add the skb to the tail of the * reorder queue. This ensures that it will be * delivered after all previous sequenced skbs. */ skb_queue_tail(&session->reorder_q, skb); } /* Try to dequeue as many skbs from reorder_q as we can. */ l2tp_recv_dequeue(session); return; discard: atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } EXPORT_SYMBOL_GPL(l2tp_recv_common); /* Drop skbs from the session's reorder_q */ static void l2tp_session_queue_purge(struct l2tp_session *session) { struct sk_buff *skb = NULL; while ((skb = skb_dequeue(&session->reorder_q))) { atomic_long_inc(&session->stats.rx_errors); kfree_skb(skb); } } /* UDP encapsulation receive handler. See net/ipv4/udp.c for details. */ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb) { struct l2tp_session *session = NULL; struct l2tp_tunnel *tunnel = NULL; struct net *net = sock_net(sk); unsigned char *ptr, *optr; u16 hdrflags; u16 version; int length; /* UDP has verified checksum */ /* UDP always verifies the packet length. */ __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) goto pass; /* Point to L2TP header */ optr = skb->data; ptr = skb->data; /* Get L2TP header flags */ hdrflags = ntohs(*(__be16 *)ptr); /* Get protocol version */ version = hdrflags & L2TP_HDR_VER_MASK; /* Get length of L2TP packet */ length = skb->len; /* If type is control packet, it is handled by userspace. */ if (hdrflags & L2TP_HDRFLAG_T) goto pass; /* Skip flags */ ptr += 2; if (version == L2TP_HDR_VER_2) { u16 tunnel_id, session_id; /* If length is present, skip it */ if (hdrflags & L2TP_HDRFLAG_L) ptr += 2; /* Extract tunnel and session ID */ tunnel_id = ntohs(*(__be16 *)ptr); ptr += 2; session_id = ntohs(*(__be16 *)ptr); ptr += 2; session = l2tp_v2_session_get(net, tunnel_id, session_id); } else { u32 session_id; ptr += 2; /* skip reserved bits */ session_id = ntohl(*(__be32 *)ptr); ptr += 4; session = l2tp_v3_session_get(net, sk, session_id); } if (!session || !session->recv_skb) { if (session) l2tp_session_dec_refcount(session); /* Not found? Pass to userspace to deal with */ goto pass; } tunnel = session->tunnel; /* Check protocol version */ if (version != tunnel->version) goto invalid; if (version == L2TP_HDR_VER_3 && l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) { l2tp_session_dec_refcount(session); goto invalid; } l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); return 0; invalid: atomic_long_inc(&tunnel->stats.rx_invalid); pass: /* Put UDP header back */ __skb_push(skb, sizeof(struct udphdr)); return 1; } EXPORT_SYMBOL_GPL(l2tp_udp_encap_recv); /* UDP encapsulation receive error handler. See net/ipv4/udp.c for details. */ static void l2tp_udp_encap_err_recv(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload) { sk->sk_err = err; sk_error_report(sk); if (ip_hdr(skb)->version == IPVERSION) { if (inet_test_bit(RECVERR, sk)) return ip_icmp_error(sk, skb, err, port, info, payload); #if IS_ENABLED(CONFIG_IPV6) } else { if (inet6_test_bit(RECVERR6, sk)) return ipv6_icmp_error(sk, skb, err, port, info, payload); #endif } } /************************************************************************ * Transmit handling ***********************************************************************/ /* Build an L2TP header for the session into the buffer provided. */ static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf) { struct l2tp_tunnel *tunnel = session->tunnel; __be16 *bufp = buf; __be16 *optr = buf; u16 flags = L2TP_HDR_VER_2; u32 tunnel_id = tunnel->peer_tunnel_id; u32 session_id = session->peer_session_id; if (session->send_seq) flags |= L2TP_HDRFLAG_S; /* Setup L2TP header. */ *bufp++ = htons(flags); *bufp++ = htons(tunnel_id); *bufp++ = htons(session_id); if (session->send_seq) { *bufp++ = htons(session->ns); *bufp++ = 0; session->ns++; session->ns &= 0xffff; trace_session_seqnum_update(session); } return bufp - optr; } static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf) { struct l2tp_tunnel *tunnel = session->tunnel; char *bufp = buf; char *optr = bufp; /* Setup L2TP header. The header differs slightly for UDP and * IP encapsulations. For UDP, there is 4 bytes of flags. */ if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { u16 flags = L2TP_HDR_VER_3; *((__be16 *)bufp) = htons(flags); bufp += 2; *((__be16 *)bufp) = 0; bufp += 2; } *((__be32 *)bufp) = htonl(session->peer_session_id); bufp += 4; if (session->cookie_len) { memcpy(bufp, &session->cookie[0], session->cookie_len); bufp += session->cookie_len; } if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) { u32 l2h = 0; if (session->send_seq) { l2h = 0x40000000 | session->ns; session->ns++; session->ns &= 0xffffff; trace_session_seqnum_update(session); } *((__be32 *)bufp) = htonl(l2h); bufp += 4; } return bufp - optr; } /* Queue the packet to IP for output: tunnel socket lock must be held */ static int l2tp_xmit_queue(struct l2tp_tunnel *tunnel, struct sk_buff *skb, struct flowi *fl) { int err; skb->ignore_df = 1; skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) err = inet6_csk_xmit(tunnel->sock, skb, NULL); else #endif err = ip_queue_xmit(tunnel->sock, skb, fl); return err >= 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; } static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, unsigned int *len) { struct l2tp_tunnel *tunnel = session->tunnel; unsigned int data_len = skb->len; struct sock *sk = tunnel->sock; int headroom, uhlen, udp_len; int ret = NET_XMIT_SUCCESS; struct inet_sock *inet; struct udphdr *uh; /* Check that there's enough headroom in the skb to insert IP, * UDP and L2TP headers. If not enough, expand it to * make room. Adjust truesize. */ uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(*uh) : 0; headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + session->hdr_len; if (skb_cow_head(skb, headroom)) { kfree_skb(skb); return NET_XMIT_DROP; } /* Setup L2TP header */ if (tunnel->version == L2TP_HDR_VER_2) l2tp_build_l2tpv2_header(session, __skb_push(skb, session->hdr_len)); else l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len)); /* Reset skb netfilter state */ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED); nf_reset_ct(skb); /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by * nested socket calls on the same lockdep socket class. This can * happen when data from a user socket is routed over l2tp, which uses * another userspace socket. */ spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING); if (sock_owned_by_user(sk)) { kfree_skb(skb); ret = NET_XMIT_DROP; goto out_unlock; } /* The user-space may change the connection status for the user-space * provided socket at run time: we must check it under the socket lock */ if (tunnel->fd >= 0 && sk->sk_state != TCP_ESTABLISHED) { kfree_skb(skb); ret = NET_XMIT_DROP; goto out_unlock; } /* Report transmitted length before we add encap header, which keeps * statistics consistent for both UDP and IP encap tx/rx paths. */ *len = skb->len; inet = inet_sk(sk); switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* Setup UDP header */ __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->source = inet->inet_sport; uh->dest = inet->inet_dport; udp_len = uhlen + session->hdr_len + data_len; uh->len = htons(udp_len); /* Calculate UDP checksum if configured to do so */ #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(sk)) udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr, &sk->sk_v6_daddr, udp_len); else #endif udp_set_csum(sk->sk_no_check_tx, skb, inet->inet_saddr, inet->inet_daddr, udp_len); break; case L2TP_ENCAPTYPE_IP: break; } ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl); out_unlock: spin_unlock(&sk->sk_lock.slock); return ret; } /* If caller requires the skb to have a ppp header, the header must be * inserted in the skb data before calling this function. */ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb) { unsigned int len = 0; int ret; ret = l2tp_xmit_core(session, skb, &len); if (ret == NET_XMIT_SUCCESS) { atomic_long_inc(&session->tunnel->stats.tx_packets); atomic_long_add(len, &session->tunnel->stats.tx_bytes); atomic_long_inc(&session->stats.tx_packets); atomic_long_add(len, &session->stats.tx_bytes); } else { atomic_long_inc(&session->tunnel->stats.tx_errors); atomic_long_inc(&session->stats.tx_errors); } return ret; } EXPORT_SYMBOL_GPL(l2tp_xmit_skb); /***************************************************************************** * Tinnel and session create/destroy. *****************************************************************************/ /* Tunnel socket destruct hook. * The tunnel context is deleted only when all session sockets have been * closed. */ static void l2tp_tunnel_destruct(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); if (!tunnel) goto end; /* Disable udp encapsulation */ switch (tunnel->encap) { case L2TP_ENCAPTYPE_UDP: /* No longer an encapsulation socket. See net/ipv4/udp.c */ WRITE_ONCE(udp_sk(sk)->encap_type, 0); udp_sk(sk)->encap_rcv = NULL; udp_sk(sk)->encap_destroy = NULL; break; case L2TP_ENCAPTYPE_IP: break; } /* Remove hooks into tunnel socket */ write_lock_bh(&sk->sk_callback_lock); sk->sk_destruct = tunnel->old_sk_destruct; sk->sk_user_data = NULL; write_unlock_bh(&sk->sk_callback_lock); /* Call the original destructor */ if (sk->sk_destruct) (*sk->sk_destruct)(sk); kfree_rcu(tunnel, rcu); end: return; } /* Remove an l2tp session from l2tp_core's lists. */ static void l2tp_session_unhash(struct l2tp_session *session) { struct l2tp_tunnel *tunnel = session->tunnel; if (tunnel) { struct l2tp_net *pn = l2tp_pernet(tunnel->l2tp_net); struct l2tp_session *removed = session; spin_lock_bh(&tunnel->list_lock); spin_lock_bh(&pn->l2tp_session_idr_lock); /* Remove from the per-tunnel list */ list_del_init(&session->list); /* Remove from per-net IDR */ if (tunnel->version == L2TP_HDR_VER_3) { if (hash_hashed(&session->hlist)) l2tp_session_collision_del(pn, session); else removed = idr_remove(&pn->l2tp_v3_session_idr, session->session_id); } else { u32 session_key = l2tp_v2_session_key(tunnel->tunnel_id, session->session_id); removed = idr_remove(&pn->l2tp_v2_session_idr, session_key); } WARN_ON_ONCE(removed && removed != session); spin_unlock_bh(&pn->l2tp_session_idr_lock); spin_unlock_bh(&tunnel->list_lock); synchronize_rcu(); } } /* When the tunnel is closed, all the attached sessions need to go too. */ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel) { struct l2tp_session *session; spin_lock_bh(&tunnel->list_lock); tunnel->acpt_newsess = false; for (;;) { session = list_first_entry_or_null(&tunnel->session_list, struct l2tp_session, list); if (!session) break; l2tp_session_inc_refcount(session); list_del_init(&session->list); spin_unlock_bh(&tunnel->list_lock); l2tp_session_delete(session); spin_lock_bh(&tunnel->list_lock); l2tp_session_dec_refcount(session); } spin_unlock_bh(&tunnel->list_lock); } /* Tunnel socket destroy hook for UDP encapsulation */ static void l2tp_udp_encap_destroy(struct sock *sk) { struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk); if (tunnel) l2tp_tunnel_delete(tunnel); } static void l2tp_tunnel_remove(struct net *net, struct l2tp_tunnel *tunnel) { struct l2tp_net *pn = l2tp_pernet(net); spin_lock_bh(&pn->l2tp_tunnel_idr_lock); idr_remove(&pn->l2tp_tunnel_idr, tunnel->tunnel_id); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); } /* Workqueue tunnel deletion function */ static void l2tp_tunnel_del_work(struct work_struct *work) { struct l2tp_tunnel *tunnel = container_of(work, struct l2tp_tunnel, del_work); struct sock *sk = tunnel->sock; struct socket *sock = sk->sk_socket; l2tp_tunnel_closeall(tunnel); /* If the tunnel socket was created within the kernel, use * the sk API to release it here. */ if (tunnel->fd < 0) { if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } } l2tp_tunnel_remove(tunnel->l2tp_net, tunnel); /* drop initial ref */ l2tp_tunnel_dec_refcount(tunnel); /* drop workqueue ref */ l2tp_tunnel_dec_refcount(tunnel); } /* Create a socket for the tunnel, if one isn't set up by * userspace. This is used for static tunnels where there is no * managing L2TP daemon. * * Since we don't want these sockets to keep a namespace alive by * themselves, we drop the socket's namespace refcount after creation. * These sockets are freed when the namespace exits using the pernet * exit hook. */ static int l2tp_tunnel_sock_create(struct net *net, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct socket **sockp) { int err = -EINVAL; struct socket *sock = NULL; struct udp_port_cfg udp_conf; switch (cfg->encap) { case L2TP_ENCAPTYPE_UDP: memset(&udp_conf, 0, sizeof(udp_conf)); #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { udp_conf.family = AF_INET6; memcpy(&udp_conf.local_ip6, cfg->local_ip6, sizeof(udp_conf.local_ip6)); memcpy(&udp_conf.peer_ip6, cfg->peer_ip6, sizeof(udp_conf.peer_ip6)); udp_conf.use_udp6_tx_checksums = !cfg->udp6_zero_tx_checksums; udp_conf.use_udp6_rx_checksums = !cfg->udp6_zero_rx_checksums; } else #endif { udp_conf.family = AF_INET; udp_conf.local_ip = cfg->local_ip; udp_conf.peer_ip = cfg->peer_ip; udp_conf.use_udp_checksums = cfg->use_udp_checksums; } udp_conf.local_udp_port = htons(cfg->local_udp_port); udp_conf.peer_udp_port = htons(cfg->peer_udp_port); err = udp_sock_create(net, &udp_conf, &sock); if (err < 0) goto out; break; case L2TP_ENCAPTYPE_IP: #if IS_ENABLED(CONFIG_IPV6) if (cfg->local_ip6 && cfg->peer_ip6) { struct sockaddr_l2tpip6 ip6_addr = {0}; err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) goto out; ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = tunnel_id; err = kernel_bind(sock, (struct sockaddr *)&ip6_addr, sizeof(ip6_addr)); if (err < 0) goto out; ip6_addr.l2tp_family = AF_INET6; memcpy(&ip6_addr.l2tp_addr, cfg->peer_ip6, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = peer_tunnel_id; err = kernel_connect(sock, (struct sockaddr *)&ip6_addr, sizeof(ip6_addr), 0); if (err < 0) goto out; } else #endif { struct sockaddr_l2tpip ip_addr = {0}; err = sock_create_kern(net, AF_INET, SOCK_DGRAM, IPPROTO_L2TP, &sock); if (err < 0) goto out; ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->local_ip; ip_addr.l2tp_conn_id = tunnel_id; err = kernel_bind(sock, (struct sockaddr *)&ip_addr, sizeof(ip_addr)); if (err < 0) goto out; ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->peer_ip; ip_addr.l2tp_conn_id = peer_tunnel_id; err = kernel_connect(sock, (struct sockaddr *)&ip_addr, sizeof(ip_addr), 0); if (err < 0) goto out; } break; default: goto out; } out: *sockp = sock; if (err < 0 && sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); *sockp = NULL; } return err; } int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp) { struct l2tp_tunnel *tunnel = NULL; int err; enum l2tp_encap_type encap = L2TP_ENCAPTYPE_UDP; if (cfg) encap = cfg->encap; tunnel = kzalloc(sizeof(*tunnel), GFP_KERNEL); if (!tunnel) { err = -ENOMEM; goto err; } tunnel->version = version; tunnel->tunnel_id = tunnel_id; tunnel->peer_tunnel_id = peer_tunnel_id; tunnel->magic = L2TP_TUNNEL_MAGIC; sprintf(&tunnel->name[0], "tunl %u", tunnel_id); spin_lock_init(&tunnel->list_lock); tunnel->acpt_newsess = true; INIT_LIST_HEAD(&tunnel->session_list); tunnel->encap = encap; refcount_set(&tunnel->ref_count, 1); tunnel->fd = fd; /* Init delete workqueue struct */ INIT_WORK(&tunnel->del_work, l2tp_tunnel_del_work); err = 0; err: if (tunnelp) *tunnelp = tunnel; return err; } EXPORT_SYMBOL_GPL(l2tp_tunnel_create); static int l2tp_validate_socket(const struct sock *sk, const struct net *net, enum l2tp_encap_type encap) { if (!net_eq(sock_net(sk), net)) return -EINVAL; if (sk->sk_type != SOCK_DGRAM) return -EPROTONOSUPPORT; if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6) return -EPROTONOSUPPORT; if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) || (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP)) return -EPROTONOSUPPORT; if (sk->sk_user_data) return -EBUSY; return 0; } int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net, struct l2tp_tunnel_cfg *cfg) { struct l2tp_net *pn = l2tp_pernet(net); u32 tunnel_id = tunnel->tunnel_id; struct socket *sock; struct sock *sk; int ret; spin_lock_bh(&pn->l2tp_tunnel_idr_lock); ret = idr_alloc_u32(&pn->l2tp_tunnel_idr, NULL, &tunnel_id, tunnel_id, GFP_ATOMIC); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); if (ret) return ret == -ENOSPC ? -EEXIST : ret; if (tunnel->fd < 0) { ret = l2tp_tunnel_sock_create(net, tunnel->tunnel_id, tunnel->peer_tunnel_id, cfg, &sock); if (ret < 0) goto err; } else { sock = sockfd_lookup(tunnel->fd, &ret); if (!sock) goto err; } sk = sock->sk; lock_sock(sk); write_lock_bh(&sk->sk_callback_lock); ret = l2tp_validate_socket(sk, net, tunnel->encap); if (ret < 0) goto err_inval_sock; rcu_assign_sk_user_data(sk, tunnel); write_unlock_bh(&sk->sk_callback_lock); if (tunnel->encap == L2TP_ENCAPTYPE_UDP) { struct udp_tunnel_sock_cfg udp_cfg = { .sk_user_data = tunnel, .encap_type = UDP_ENCAP_L2TPINUDP, .encap_rcv = l2tp_udp_encap_recv, .encap_err_rcv = l2tp_udp_encap_err_recv, .encap_destroy = l2tp_udp_encap_destroy, }; setup_udp_tunnel_sock(net, sock, &udp_cfg); } tunnel->old_sk_destruct = sk->sk_destruct; sk->sk_destruct = &l2tp_tunnel_destruct; sk->sk_allocation = GFP_ATOMIC; release_sock(sk); sock_hold(sk); tunnel->sock = sk; tunnel->l2tp_net = net; spin_lock_bh(&pn->l2tp_tunnel_idr_lock); idr_replace(&pn->l2tp_tunnel_idr, tunnel, tunnel->tunnel_id); spin_unlock_bh(&pn->l2tp_tunnel_idr_lock); trace_register_tunnel(tunnel); if (tunnel->fd >= 0) sockfd_put(sock); return 0; err_inval_sock: write_unlock_bh(&sk->sk_callback_lock); release_sock(sk); if (tunnel->fd < 0) sock_release(sock); else sockfd_put(sock); err: l2tp_tunnel_remove(net, tunnel); return ret; } EXPORT_SYMBOL_GPL(l2tp_tunnel_register); /* This function is used by the netlink TUNNEL_DELETE command. */ void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { if (!test_and_set_bit(0, &tunnel->dead)) { trace_delete_tunnel(tunnel); l2tp_tunnel_inc_refcount(tunnel); queue_work(l2tp_wq, &tunnel->del_work); } } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); void l2tp_session_delete(struct l2tp_session *session) { if (test_and_set_bit(0, &session->dead)) return; trace_delete_session(session); l2tp_session_unhash(session); l2tp_session_queue_purge(session); if (session->session_close) (*session->session_close)(session); l2tp_session_dec_refcount(session); } EXPORT_SYMBOL_GPL(l2tp_session_delete); /* We come here whenever a session's send_seq, cookie_len or * l2specific_type parameters are set. */ void l2tp_session_set_header_len(struct l2tp_session *session, int version) { if (version == L2TP_HDR_VER_2) { session->hdr_len = 6; if (session->send_seq) session->hdr_len += 4; } else { session->hdr_len = 4 + session->cookie_len; session->hdr_len += l2tp_get_l2specific_len(session); if (session->tunnel->encap == L2TP_ENCAPTYPE_UDP) session->hdr_len += 4; } } EXPORT_SYMBOL_GPL(l2tp_session_set_header_len); struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunnel, u32 session_id, u32 peer_session_id, struct l2tp_session_cfg *cfg) { struct l2tp_session *session; session = kzalloc(sizeof(*session) + priv_size, GFP_KERNEL); if (session) { session->magic = L2TP_SESSION_MAGIC; session->tunnel = tunnel; session->session_id = session_id; session->peer_session_id = peer_session_id; session->nr = 0; if (tunnel->version == L2TP_HDR_VER_2) session->nr_max = 0xffff; else session->nr_max = 0xffffff; session->nr_window_size = session->nr_max / 2; session->nr_oos_count_max = 4; /* Use NR of first received packet */ session->reorder_skip = 1; sprintf(&session->name[0], "sess %u/%u", tunnel->tunnel_id, session->session_id); skb_queue_head_init(&session->reorder_q); session->hlist_key = l2tp_v3_session_hashkey(tunnel->sock, session->session_id); INIT_HLIST_NODE(&session->hlist); INIT_LIST_HEAD(&session->clist); INIT_LIST_HEAD(&session->list); if (cfg) { session->pwtype = cfg->pw_type; session->send_seq = cfg->send_seq; session->recv_seq = cfg->recv_seq; session->lns_mode = cfg->lns_mode; session->reorder_timeout = cfg->reorder_timeout; session->l2specific_type = cfg->l2specific_type; session->cookie_len = cfg->cookie_len; memcpy(&session->cookie[0], &cfg->cookie[0], cfg->cookie_len); session->peer_cookie_len = cfg->peer_cookie_len; memcpy(&session->peer_cookie[0], &cfg->peer_cookie[0], cfg->peer_cookie_len); } l2tp_session_set_header_len(session, tunnel->version); refcount_set(&session->ref_count, 1); return session; } return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL_GPL(l2tp_session_create); /***************************************************************************** * Init and cleanup *****************************************************************************/ static __net_init int l2tp_init_net(struct net *net) { struct l2tp_net *pn = net_generic(net, l2tp_net_id); idr_init(&pn->l2tp_tunnel_idr); spin_lock_init(&pn->l2tp_tunnel_idr_lock); idr_init(&pn->l2tp_v2_session_idr); idr_init(&pn->l2tp_v3_session_idr); spin_lock_init(&pn->l2tp_session_idr_lock); return 0; } static __net_exit void l2tp_exit_net(struct net *net) { struct l2tp_net *pn = l2tp_pernet(net); struct l2tp_tunnel *tunnel = NULL; unsigned long tunnel_id, tmp; rcu_read_lock_bh(); idr_for_each_entry_ul(&pn->l2tp_tunnel_idr, tunnel, tmp, tunnel_id) { if (tunnel) l2tp_tunnel_delete(tunnel); } rcu_read_unlock_bh(); if (l2tp_wq) flush_workqueue(l2tp_wq); rcu_barrier(); idr_destroy(&pn->l2tp_v2_session_idr); idr_destroy(&pn->l2tp_v3_session_idr); idr_destroy(&pn->l2tp_tunnel_idr); } static struct pernet_operations l2tp_net_ops = { .init = l2tp_init_net, .exit = l2tp_exit_net, .id = &l2tp_net_id, .size = sizeof(struct l2tp_net), }; static int __init l2tp_init(void) { int rc = 0; rc = register_pernet_device(&l2tp_net_ops); if (rc) goto out; l2tp_wq = alloc_workqueue("l2tp", WQ_UNBOUND, 0); if (!l2tp_wq) { pr_err("alloc_workqueue failed\n"); unregister_pernet_device(&l2tp_net_ops); rc = -ENOMEM; goto out; } pr_info("L2TP core driver, %s\n", L2TP_DRV_VERSION); out: return rc; } static void __exit l2tp_exit(void) { unregister_pernet_device(&l2tp_net_ops); if (l2tp_wq) { destroy_workqueue(l2tp_wq); l2tp_wq = NULL; } } module_init(l2tp_init); module_exit(l2tp_exit); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP core"); MODULE_LICENSE("GPL"); MODULE_VERSION(L2TP_DRV_VERSION); |
| 3203 | 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 | #undef TRACE_SYSTEM #define TRACE_SYSTEM netlink #if !defined(_TRACE_NETLINK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NETLINK_H #include <linux/tracepoint.h> TRACE_EVENT(netlink_extack, TP_PROTO(const char *msg), TP_ARGS(msg), TP_STRUCT__entry( __string( msg, msg ) ), TP_fast_assign( __assign_str(msg); ), TP_printk("msg=%s", __get_str(msg)) ); #endif /* _TRACE_NETLINK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ebt_snat * * Authors: * Bart De Schuymer <bdschuym@pandora.be> * * June, 2002 * */ #include <linux/module.h> #include <net/sock.h> #include <linux/if_arp.h> #include <net/arp.h> #include <linux/netfilter.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_bridge/ebt_nat.h> static unsigned int ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; if (skb_ensure_writable(skb, 0)) return EBT_DROP; ether_addr_copy(eth_hdr(skb)->h_source, info->mac); if (!(info->target & NAT_ARP_BIT) && eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) { const struct arphdr *ap; struct arphdr _ah; ap = skb_header_pointer(skb, 0, sizeof(_ah), &_ah); if (ap == NULL) return EBT_DROP; if (ap->ar_hln != ETH_ALEN) goto out; if (skb_store_bits(skb, sizeof(_ah), info->mac, ETH_ALEN)) return EBT_DROP; } out: return info->target | ~EBT_VERDICT_BITS; } static int ebt_snat_tg_check(const struct xt_tgchk_param *par) { const struct ebt_nat_info *info = par->targinfo; int tmp; tmp = info->target | ~EBT_VERDICT_BITS; if (BASE_CHAIN && tmp == EBT_RETURN) return -EINVAL; if (ebt_invalid_target(tmp)) return -EINVAL; tmp = info->target | EBT_VERDICT_BITS; if ((tmp & ~NAT_ARP_BIT) != ~NAT_ARP_BIT) return -EINVAL; return 0; } static struct xt_target ebt_snat_tg_reg __read_mostly = { .name = "snat", .revision = 0, .family = NFPROTO_BRIDGE, .table = "nat", .hooks = (1 << NF_BR_NUMHOOKS) | (1 << NF_BR_POST_ROUTING), .target = ebt_snat_tg, .checkentry = ebt_snat_tg_check, .targetsize = sizeof(struct ebt_nat_info), .me = THIS_MODULE, }; static int __init ebt_snat_init(void) { return xt_register_target(&ebt_snat_tg_reg); } static void __exit ebt_snat_fini(void) { xt_unregister_target(&ebt_snat_tg_reg); } module_init(ebt_snat_init); module_exit(ebt_snat_fini); MODULE_DESCRIPTION("Ebtables: Source MAC address translation"); MODULE_LICENSE("GPL"); |
| 8 2 8 1 1 4 8 8 10 12 8 1 1 1 1 10 10 12 14 14 5 8 12 6 1 2 1 1 2 4 2 2 8 8 5 1 4 1 4 2 1 2 6 3 3 9 1 5 3 6 2 5 3 6 2 4 4 6 2 5 5 4 4 18 66 1 1 1 66 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: IP/IP protocol decoder modified to support * virtual tunnel interface * * Authors: * Saurabh Mohan (saurabh.mohan@vyatta.com) 05/07/2012 */ /* This version of net/ipv4/ip_vti.c is cloned of net/ipv4/ipip.c For comments look at net/ipv4/ip_gre.c --ANK */ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> #include <linux/icmpv6.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/ip_tunnels.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> static struct rtnl_link_ops vti_link_ops __read_mostly; static unsigned int vti_net_id __read_mostly; static int vti_tunnel_init(struct net_device *dev); static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type, bool update_skb_dev) { struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, vti_net_id); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); if (tunnel) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; if (update_skb_dev) skb->dev = tunnel->dev; return xfrm_input(skb, nexthdr, spi, encap_type); } return -EINVAL; drop: kfree_skb(skb); return 0; } static int vti_input_proto(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) { return vti_input(skb, nexthdr, spi, encap_type, false); } static int vti_rcv(struct sk_buff *skb, __be32 spi, bool update_skb_dev) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); return vti_input(skb, ip_hdr(skb)->protocol, spi, 0, update_skb_dev); } static int vti_rcv_proto(struct sk_buff *skb) { return vti_rcv(skb, 0, false); } static int vti_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; struct net_device *dev; struct xfrm_state *x; const struct xfrm_mode *inner_mode; struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4; u32 orig_mark = skb->mark; int ret; if (!tunnel) return 1; dev = tunnel->dev; if (err) { DEV_STATS_INC(dev, rx_errors); DEV_STATS_INC(dev, rx_dropped); return 0; } x = xfrm_input_state(skb); inner_mode = &x->inner_mode; if (x->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); if (inner_mode == NULL) { XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINSTATEMODEERROR); return -EINVAL; } } family = inner_mode->family; skb->mark = be32_to_cpu(tunnel->parms.i_key); ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); skb->mark = orig_mark; if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev))); skb->dev = dev; dev_sw_netstats_rx_add(dev, skb->len); return 0; } static bool vti_state_check(const struct xfrm_state *x, __be32 dst, __be32 src) { xfrm_address_t *daddr = (xfrm_address_t *)&dst; xfrm_address_t *saddr = (xfrm_address_t *)&src; /* if there is no transform then this tunnel is not functional. * Or if the xfrm is not mode tunnel. */ if (!x || x->props.mode != XFRM_MODE_TUNNEL || x->props.family != AF_INET) return false; if (!dst) return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET); if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET)) return false; return true; } static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_parm_kern *parms = &tunnel->parms; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; /* Device to other host */ int pkt_len = skb->len; int err; int mtu; if (!dst) { switch (skb->protocol) { case htons(ETH_P_IP): { struct rtable *rt; fl->u.ip4.flowi4_oif = dev->ifindex; fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); if (IS_ERR(rt)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } dst = &rt->dst; skb_dst_set(skb, dst); break; } #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): fl->u.ip6.flowi6_oif = dev->ifindex; fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); if (dst->error) { dst_release(dst); dst = NULL; DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } skb_dst_set(skb, dst); break; #endif default: DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } } dst_hold(dst); dst = xfrm_lookup_route(tunnel->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { DEV_STATS_INC(dev, tx_carrier_errors); goto tx_error_icmp; } if (dst->flags & DST_XFRM_QUEUE) goto xmit; if (!vti_state_check(dst->xfrm, parms->iph.daddr, parms->iph.saddr)) { DEV_STATS_INC(dev, tx_carrier_errors); dst_release(dst); goto tx_error_icmp; } tdev = dst->dev; if (tdev == dev) { dst_release(dst); DEV_STATS_INC(dev, collisions); goto tx_error; } mtu = dst_mtu(dst); if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } else { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } dst_release(dst); goto tx_error; } xmit: skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; err = dst_output(tunnel->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = pkt_len; iptunnel_xmit_stats(dev, err); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } /* This function assumes it is being called from dev_queue_xmit() * and that skb is filled properly by that function. */ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct flowi fl; if (!pskb_inet_may_pull(skb)) goto tx_err; memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IP): memset(IPCB(skb), 0, sizeof(*IPCB(skb))); xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET); break; case htons(ETH_P_IPV6): memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); xfrm_decode_session(dev_net(dev), skb, &fl, AF_INET6); break; default: goto tx_err; } /* override mark with tunnel output key */ fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key); return vti_xmit(skb, dev, &fl); tx_err: DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return NETDEV_TX_OK; } static int vti4_err(struct sk_buff *skb, u32 info) { __be32 spi; __u32 mark; struct xfrm_state *x; struct ip_tunnel *tunnel; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah ; struct ip_comp_hdr *ipch; struct net *net = dev_net(skb->dev); const struct iphdr *iph = (const struct iphdr *)skb->data; int protocol = iph->protocol; struct ip_tunnel_net *itn = net_generic(net, vti_net_id); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, iph->saddr, 0); if (!tunnel) return -1; mark = be32_to_cpu(tunnel->parms.o_key); switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return 0; break; case ICMP_REDIRECT: break; default: return 0; } x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET); if (!x) return 0; if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, protocol); else ipv4_redirect(skb, net, 0, protocol); xfrm_state_put(x); return 0; } static int vti_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; int err = 0; if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || p->iph.protocol != IPPROTO_IPIP || p->iph.ihl != 5) return -EINVAL; } if (!ip_tunnel_flags_is_be16_compat(p->i_flags) || !ip_tunnel_flags_is_be16_compat(p->o_flags)) return -EOVERFLOW; if (!(ip_tunnel_flags_to_be16(p->i_flags) & GRE_KEY)) p->i_key = 0; if (!(ip_tunnel_flags_to_be16(p->o_flags) & GRE_KEY)) p->o_key = 0; __set_bit(IP_TUNNEL_VTI_BIT, flags); ip_tunnel_flags_copy(p->i_flags, flags); err = ip_tunnel_ctl(dev, p, cmd); if (err) return err; if (cmd != SIOCDELTUNNEL) { ip_tunnel_flags_from_be16(flags, GRE_KEY); ip_tunnel_flags_or(p->i_flags, p->i_flags, flags); ip_tunnel_flags_or(p->o_flags, p->o_flags, flags); } return 0; } static const struct net_device_ops vti_netdev_ops = { .ndo_init = vti_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = vti_tunnel_xmit, .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = vti_tunnel_ctl, }; static void vti_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &vti_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; ip_tunnel_setup(dev, vti_net_id); } static int vti_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; __dev_addr_set(dev, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; dev->addr_len = 4; dev->features |= NETIF_F_LLTX; netif_keep_dst(dev); return ip_tunnel_init(dev); } static void __net_init vti_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; iph->version = 4; iph->protocol = IPPROTO_IPIP; iph->ihl = 5; } static struct xfrm4_protocol vti_esp4_protocol __read_mostly = { .handler = vti_rcv_proto, .input_handler = vti_input_proto, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 100, }; static struct xfrm4_protocol vti_ah4_protocol __read_mostly = { .handler = vti_rcv_proto, .input_handler = vti_input_proto, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 100, }; static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { .handler = vti_rcv_proto, .input_handler = vti_input_proto, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 100, }; #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) static int vti_rcv_tunnel(struct sk_buff *skb) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); return vti_input(skb, IPPROTO_IPIP, ip_hdr(skb)->saddr, 0, false); } static struct xfrm_tunnel vti_ipip_handler __read_mostly = { .handler = vti_rcv_tunnel, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 0, }; #if IS_ENABLED(CONFIG_IPV6) static struct xfrm_tunnel vti_ipip6_handler __read_mostly = { .handler = vti_rcv_tunnel, .cb_handler = vti_rcv_cb, .err_handler = vti4_err, .priority = 0, }; #endif #endif static int __net_init vti_init_net(struct net *net) { int err; struct ip_tunnel_net *itn; err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0"); if (err) return err; itn = net_generic(net, vti_net_id); if (itn->fb_tunnel_dev) vti_fb_tunnel_init(itn->fb_tunnel_dev); return 0; } static void __net_exit vti_exit_batch_rtnl(struct list_head *list_net, struct list_head *dev_to_kill) { ip_tunnel_delete_nets(list_net, vti_net_id, &vti_link_ops, dev_to_kill); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, .exit_batch_rtnl = vti_exit_batch_rtnl, .id = &vti_net_id, .size = sizeof(struct ip_tunnel_net), }; static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return 0; } static void vti_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm_kern *parms, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); parms->iph.protocol = IPPROTO_IPIP; if (!data) return; __set_bit(IP_TUNNEL_VTI_BIT, parms->i_flags); if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); if (data[IFLA_VTI_IKEY]) parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); if (data[IFLA_VTI_OKEY]) parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); if (data[IFLA_VTI_LOCAL]) parms->iph.saddr = nla_get_in_addr(data[IFLA_VTI_LOCAL]); if (data[IFLA_VTI_REMOTE]) parms->iph.daddr = nla_get_in_addr(data[IFLA_VTI_REMOTE]); if (data[IFLA_VTI_FWMARK]) *fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]); } static int vti_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm_kern parms; __u32 fwmark = 0; vti_netlink_parms(data, &parms, &fwmark); return ip_tunnel_newlink(dev, tb, &parms, fwmark); } static int vti_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern p; __u32 fwmark = t->fwmark; vti_netlink_parms(data, &p, &fwmark); return ip_tunnel_changelink(dev, tb, &p, fwmark); } static size_t vti_get_size(const struct net_device *dev) { return /* IFLA_VTI_LINK */ nla_total_size(4) + /* IFLA_VTI_IKEY */ nla_total_size(4) + /* IFLA_VTI_OKEY */ nla_total_size(4) + /* IFLA_VTI_LOCAL */ nla_total_size(4) + /* IFLA_VTI_REMOTE */ nla_total_size(4) + /* IFLA_VTI_FWMARK */ nla_total_size(4) + 0; } static int vti_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm_kern *p = &t->parms; if (nla_put_u32(skb, IFLA_VTI_LINK, p->link) || nla_put_be32(skb, IFLA_VTI_IKEY, p->i_key) || nla_put_be32(skb, IFLA_VTI_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_VTI_LOCAL, p->iph.saddr) || nla_put_in_addr(skb, IFLA_VTI_REMOTE, p->iph.daddr) || nla_put_u32(skb, IFLA_VTI_FWMARK, t->fwmark)) return -EMSGSIZE; return 0; } static const struct nla_policy vti_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, [IFLA_VTI_LOCAL] = { .len = sizeof_field(struct iphdr, saddr) }, [IFLA_VTI_REMOTE] = { .len = sizeof_field(struct iphdr, daddr) }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vti_link_ops __read_mostly = { .kind = "vti", .maxtype = IFLA_VTI_MAX, .policy = vti_policy, .priv_size = sizeof(struct ip_tunnel), .setup = vti_tunnel_setup, .validate = vti_tunnel_validate, .newlink = vti_newlink, .changelink = vti_changelink, .dellink = ip_tunnel_dellink, .get_size = vti_get_size, .fill_info = vti_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static int __init vti_init(void) { const char *msg; int err; pr_info("IPv4 over IPsec tunneling driver\n"); msg = "tunnel device"; err = register_pernet_device(&vti_net_ops); if (err < 0) goto pernet_dev_failed; msg = "tunnel protocols"; err = xfrm4_protocol_register(&vti_esp4_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm4_protocol_register(&vti_ah4_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm4_protocol_register(&vti_ipcomp4_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) msg = "ipip tunnel"; err = xfrm4_tunnel_register(&vti_ipip_handler, AF_INET); if (err < 0) goto xfrm_tunnel_ipip_failed; #if IS_ENABLED(CONFIG_IPV6) err = xfrm4_tunnel_register(&vti_ipip6_handler, AF_INET6); if (err < 0) goto xfrm_tunnel_ipip6_failed; #endif #endif msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); if (err < 0) goto rtnl_link_failed; return err; rtnl_link_failed: #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) #if IS_ENABLED(CONFIG_IPV6) xfrm4_tunnel_deregister(&vti_ipip6_handler, AF_INET6); xfrm_tunnel_ipip6_failed: #endif xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET); xfrm_tunnel_ipip_failed: #endif xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: unregister_pernet_device(&vti_net_ops); pernet_dev_failed: pr_err("vti init: failed to register %s\n", msg); return err; } static void __exit vti_fini(void) { rtnl_link_unregister(&vti_link_ops); #if IS_ENABLED(CONFIG_INET_XFRM_TUNNEL) #if IS_ENABLED(CONFIG_IPV6) xfrm4_tunnel_deregister(&vti_ipip6_handler, AF_INET6); #endif xfrm4_tunnel_deregister(&vti_ipip_handler, AF_INET); #endif xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&vti_esp4_protocol, IPPROTO_ESP); unregister_pernet_device(&vti_net_ops); } module_init(vti_init); module_exit(vti_fini); MODULE_DESCRIPTION("Virtual (secure) IP tunneling library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("vti"); MODULE_ALIAS_NETDEV("ip_vti0"); |
| 33 33 34 34 42 42 16 8 15 2 16 16 16 2 2 2 2 15 16 16 16 8 8 8 2 2 2 2 2 2 3 3 16 3 1 2 16 16 16 16 119 1 118 16 16 16 16 16 6 10 14 15 15 14 2 9 2 10 3 3 3 3 3 3 1 7 3 1 6 2 2 2 2 4 4 4 1 1 23 1 23 22 27 27 27 4 4 23 15 17 17 17 11 11 40 40 40 8 38 38 38 1 37 1 37 22 22 15 22 22 22 21 1 3 3 3 3 2 3 3 3 3 1 3 3 4 3 1 26 27 94 135 10 132 2 131 132 23 3 131 23 2 27 127 1 3 2 1 2 2 2 5 5 1 3 1 3 3 1 1 5 5 5 3 2 1 1 1 1 3 1 5 5 5 2 2 2 3 3 3 3 1 1 2 3 3 2 1 1 1 1 1 16 15 2 1 1 1 27 2 2 1 2 1 9 10 10 2 2 1 5 2 32 16 4 12 16 7 9 3 5 1 61 60 2 27 32 69 22 54 12 12 12 14 15 14 2 4 2 12 12 13 13 3 3 2 2 10 91 31 5 66 23 23 1 2 2 1 1 1 2 5 1 3 1 3 3 3 1 3 14 14 1 1 13 14 14 2 14 14 5 3 2 23 1 5 5 1 1 1 1 1 1 5 5 5 5 3 3 3 3 5 3 1 2 2 6 1 5 5 2 1 1 4 2 2 4 2 2 6 5 1 57 57 52 52 14 9 9 9 52 52 14 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Bridge multicast support. * * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au> */ #include <linux/err.h> #include <linux/export.h> #include <linux/if_ether.h> #include <linux/igmp.h> #include <linux/in.h> #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/netdevice.h> #include <linux/netfilter_bridge.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/inetdevice.h> #include <linux/mroute.h> #include <net/ip.h> #include <net/switchdev.h> #if IS_ENABLED(CONFIG_IPV6) #include <linux/icmpv6.h> #include <net/ipv6.h> #include <net/mld.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #endif #include <trace/events/bridge.h> #include "br_private.h" #include "br_private_mcast_eht.h" static const struct rhashtable_params br_mdb_rht_params = { .head_offset = offsetof(struct net_bridge_mdb_entry, rhnode), .key_offset = offsetof(struct net_bridge_mdb_entry, addr), .key_len = sizeof(struct br_ip), .automatic_shrinking = true, }; static const struct rhashtable_params br_sg_port_rht_params = { .head_offset = offsetof(struct net_bridge_port_group, rhnode), .key_offset = offsetof(struct net_bridge_port_group, key), .key_len = sizeof(struct net_bridge_port_group_sg_key), .automatic_shrinking = true, }; static void br_multicast_start_querier(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query); static void br_ip4_multicast_add_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx); static void br_ip4_multicast_leave_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, __be32 group, __u16 vid, const unsigned char *src); static void br_multicast_port_group_rexmit(struct timer_list *t); static void br_multicast_rport_del_notify(struct net_bridge_mcast_port *pmctx, bool deleted); static void br_ip6_multicast_add_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx); #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, const struct in6_addr *group, __u16 vid, const unsigned char *src); #endif static struct net_bridge_port_group * __br_multicast_add_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct br_ip *group, const unsigned char *src, u8 filter_mode, bool igmpv2_mldv1, bool blocked); static void br_multicast_find_del_pg(struct net_bridge *br, struct net_bridge_port_group *pg); static void __br_multicast_stop(struct net_bridge_mcast *brmctx); static int br_mc_disabled_update(struct net_device *dev, bool value, struct netlink_ext_ack *extack); static struct net_bridge_port_group * br_sg_port_find(struct net_bridge *br, struct net_bridge_port_group_sg_key *sg_p) { lockdep_assert_held_once(&br->multicast_lock); return rhashtable_lookup_fast(&br->sg_port_tbl, sg_p, br_sg_port_rht_params); } static struct net_bridge_mdb_entry *br_mdb_ip_get_rcu(struct net_bridge *br, struct br_ip *dst) { return rhashtable_lookup(&br->mdb_hash_tbl, dst, br_mdb_rht_params); } struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge *br, struct br_ip *dst) { struct net_bridge_mdb_entry *ent; lockdep_assert_held_once(&br->multicast_lock); rcu_read_lock(); ent = rhashtable_lookup(&br->mdb_hash_tbl, dst, br_mdb_rht_params); rcu_read_unlock(); return ent; } static struct net_bridge_mdb_entry *br_mdb_ip4_get(struct net_bridge *br, __be32 dst, __u16 vid) { struct br_ip br_dst; memset(&br_dst, 0, sizeof(br_dst)); br_dst.dst.ip4 = dst; br_dst.proto = htons(ETH_P_IP); br_dst.vid = vid; return br_mdb_ip_get(br, &br_dst); } #if IS_ENABLED(CONFIG_IPV6) static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br, const struct in6_addr *dst, __u16 vid) { struct br_ip br_dst; memset(&br_dst, 0, sizeof(br_dst)); br_dst.dst.ip6 = *dst; br_dst.proto = htons(ETH_P_IPV6); br_dst.vid = vid; return br_mdb_ip_get(br, &br_dst); } #endif struct net_bridge_mdb_entry * br_mdb_entry_skb_get(struct net_bridge_mcast *brmctx, struct sk_buff *skb, u16 vid) { struct net_bridge *br = brmctx->br; struct br_ip ip; if (!br_opt_get(br, BROPT_MULTICAST_ENABLED) || br_multicast_ctx_vlan_global_disabled(brmctx)) return NULL; if (BR_INPUT_SKB_CB(skb)->igmp) return NULL; memset(&ip, 0, sizeof(ip)); ip.proto = skb->protocol; ip.vid = vid; switch (skb->protocol) { case htons(ETH_P_IP): ip.dst.ip4 = ip_hdr(skb)->daddr; if (brmctx->multicast_igmp_version == 3) { struct net_bridge_mdb_entry *mdb; ip.src.ip4 = ip_hdr(skb)->saddr; mdb = br_mdb_ip_get_rcu(br, &ip); if (mdb) return mdb; ip.src.ip4 = 0; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ip.dst.ip6 = ipv6_hdr(skb)->daddr; if (brmctx->multicast_mld_version == 2) { struct net_bridge_mdb_entry *mdb; ip.src.ip6 = ipv6_hdr(skb)->saddr; mdb = br_mdb_ip_get_rcu(br, &ip); if (mdb) return mdb; memset(&ip.src.ip6, 0, sizeof(ip.src.ip6)); } break; #endif default: ip.proto = 0; ether_addr_copy(ip.dst.mac_addr, eth_hdr(skb)->h_dest); } return br_mdb_ip_get_rcu(br, &ip); } /* IMPORTANT: this function must be used only when the contexts cannot be * passed down (e.g. timer) and must be used for read-only purposes because * the vlan snooping option can change, so it can return any context * (non-vlan or vlan). Its initial intended purpose is to read timer values * from the *current* context based on the option. At worst that could lead * to inconsistent timers when the contexts are changed, i.e. src timer * which needs to re-arm with a specific delay taken from the old context */ static struct net_bridge_mcast_port * br_multicast_pg_to_port_ctx(const struct net_bridge_port_group *pg) { struct net_bridge_mcast_port *pmctx = &pg->key.port->multicast_ctx; struct net_bridge_vlan *vlan; lockdep_assert_held_once(&pg->key.port->br->multicast_lock); /* if vlan snooping is disabled use the port's multicast context */ if (!pg->key.addr.vid || !br_opt_get(pg->key.port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) goto out; /* locking is tricky here, due to different rules for multicast and * vlans we need to take rcu to find the vlan and make sure it has * the BR_VLFLAG_MCAST_ENABLED flag set, it can only change under * multicast_lock which must be already held here, so the vlan's pmctx * can safely be used on return */ rcu_read_lock(); vlan = br_vlan_find(nbp_vlan_group_rcu(pg->key.port), pg->key.addr.vid); if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx)) pmctx = &vlan->port_mcast_ctx; else pmctx = NULL; rcu_read_unlock(); out: return pmctx; } static struct net_bridge_mcast_port * br_multicast_port_vid_to_port_ctx(struct net_bridge_port *port, u16 vid) { struct net_bridge_mcast_port *pmctx = NULL; struct net_bridge_vlan *vlan; lockdep_assert_held_once(&port->br->multicast_lock); if (!br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) return NULL; /* Take RCU to access the vlan. */ rcu_read_lock(); vlan = br_vlan_find(nbp_vlan_group_rcu(port), vid); if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx)) pmctx = &vlan->port_mcast_ctx; rcu_read_unlock(); return pmctx; } /* when snooping we need to check if the contexts should be used * in the following order: * - if pmctx is non-NULL (port), check if it should be used * - if pmctx is NULL (bridge), check if brmctx should be used */ static bool br_multicast_ctx_should_use(const struct net_bridge_mcast *brmctx, const struct net_bridge_mcast_port *pmctx) { if (!netif_running(brmctx->br->dev)) return false; if (pmctx) return !br_multicast_port_ctx_state_disabled(pmctx); else return !br_multicast_ctx_vlan_disabled(brmctx); } static bool br_port_group_equal(struct net_bridge_port_group *p, struct net_bridge_port *port, const unsigned char *src) { if (p->key.port != port) return false; if (!(port->flags & BR_MULTICAST_TO_UNICAST)) return true; return ether_addr_equal(src, p->eth_addr); } static void __fwd_add_star_excl(struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, struct br_ip *sg_ip) { struct net_bridge_port_group_sg_key sg_key; struct net_bridge_port_group *src_pg; struct net_bridge_mcast *brmctx; memset(&sg_key, 0, sizeof(sg_key)); brmctx = br_multicast_port_ctx_get_global(pmctx); sg_key.port = pg->key.port; sg_key.addr = *sg_ip; if (br_sg_port_find(brmctx->br, &sg_key)) return; src_pg = __br_multicast_add_group(brmctx, pmctx, sg_ip, pg->eth_addr, MCAST_INCLUDE, false, false); if (IS_ERR_OR_NULL(src_pg) || src_pg->rt_protocol != RTPROT_KERNEL) return; src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL; } static void __fwd_del_star_excl(struct net_bridge_port_group *pg, struct br_ip *sg_ip) { struct net_bridge_port_group_sg_key sg_key; struct net_bridge *br = pg->key.port->br; struct net_bridge_port_group *src_pg; memset(&sg_key, 0, sizeof(sg_key)); sg_key.port = pg->key.port; sg_key.addr = *sg_ip; src_pg = br_sg_port_find(br, &sg_key); if (!src_pg || !(src_pg->flags & MDB_PG_FLAGS_STAR_EXCL) || src_pg->rt_protocol != RTPROT_KERNEL) return; br_multicast_find_del_pg(br, src_pg); } /* When a port group transitions to (or is added as) EXCLUDE we need to add it * to all other ports' S,G entries which are not blocked by the current group * for proper replication, the assumption is that any S,G blocked entries * are already added so the S,G,port lookup should skip them. * When a port group transitions from EXCLUDE -> INCLUDE mode or is being * deleted we need to remove it from all ports' S,G entries where it was * automatically installed before (i.e. where it's MDB_PG_FLAGS_STAR_EXCL). */ void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg, u8 filter_mode) { struct net_bridge *br = pg->key.port->br; struct net_bridge_port_group *pg_lst; struct net_bridge_mcast_port *pmctx; struct net_bridge_mdb_entry *mp; struct br_ip sg_ip; if (WARN_ON(!br_multicast_is_star_g(&pg->key.addr))) return; mp = br_mdb_ip_get(br, &pg->key.addr); if (!mp) return; pmctx = br_multicast_pg_to_port_ctx(pg); if (!pmctx) return; memset(&sg_ip, 0, sizeof(sg_ip)); sg_ip = pg->key.addr; for (pg_lst = mlock_dereference(mp->ports, br); pg_lst; pg_lst = mlock_dereference(pg_lst->next, br)) { struct net_bridge_group_src *src_ent; if (pg_lst == pg) continue; hlist_for_each_entry(src_ent, &pg_lst->src_list, node) { if (!(src_ent->flags & BR_SGRP_F_INSTALLED)) continue; sg_ip.src = src_ent->addr.src; switch (filter_mode) { case MCAST_INCLUDE: __fwd_del_star_excl(pg, &sg_ip); break; case MCAST_EXCLUDE: __fwd_add_star_excl(pmctx, pg, &sg_ip); break; } } } } /* called when adding a new S,G with host_joined == false by default */ static void br_multicast_sg_host_state(struct net_bridge_mdb_entry *star_mp, struct net_bridge_port_group *sg) { struct net_bridge_mdb_entry *sg_mp; if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr))) return; if (!star_mp->host_joined) return; sg_mp = br_mdb_ip_get(star_mp->br, &sg->key.addr); if (!sg_mp) return; sg_mp->host_joined = true; } /* set the host_joined state of all of *,G's S,G entries */ static void br_multicast_star_g_host_state(struct net_bridge_mdb_entry *star_mp) { struct net_bridge *br = star_mp->br; struct net_bridge_mdb_entry *sg_mp; struct net_bridge_port_group *pg; struct br_ip sg_ip; if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr))) return; memset(&sg_ip, 0, sizeof(sg_ip)); sg_ip = star_mp->addr; for (pg = mlock_dereference(star_mp->ports, br); pg; pg = mlock_dereference(pg->next, br)) { struct net_bridge_group_src *src_ent; hlist_for_each_entry(src_ent, &pg->src_list, node) { if (!(src_ent->flags & BR_SGRP_F_INSTALLED)) continue; sg_ip.src = src_ent->addr.src; sg_mp = br_mdb_ip_get(br, &sg_ip); if (!sg_mp) continue; sg_mp->host_joined = star_mp->host_joined; } } } static void br_multicast_sg_del_exclude_ports(struct net_bridge_mdb_entry *sgmp) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p; /* *,G exclude ports are only added to S,G entries */ if (WARN_ON(br_multicast_is_star_g(&sgmp->addr))) return; /* we need the STAR_EXCLUDE ports if there are non-STAR_EXCLUDE ports * we should ignore perm entries since they're managed by user-space */ for (pp = &sgmp->ports; (p = mlock_dereference(*pp, sgmp->br)) != NULL; pp = &p->next) if (!(p->flags & (MDB_PG_FLAGS_STAR_EXCL | MDB_PG_FLAGS_PERMANENT))) return; /* currently the host can only have joined the *,G which means * we treat it as EXCLUDE {}, so for an S,G it's considered a * STAR_EXCLUDE entry and we can safely leave it */ sgmp->host_joined = false; for (pp = &sgmp->ports; (p = mlock_dereference(*pp, sgmp->br)) != NULL;) { if (!(p->flags & MDB_PG_FLAGS_PERMANENT)) br_multicast_del_pg(sgmp, p, pp); else pp = &p->next; } } void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp, struct net_bridge_port_group *sg) { struct net_bridge_port_group_sg_key sg_key; struct net_bridge *br = star_mp->br; struct net_bridge_mcast_port *pmctx; struct net_bridge_port_group *pg; struct net_bridge_mcast *brmctx; if (WARN_ON(br_multicast_is_star_g(&sg->key.addr))) return; if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr))) return; br_multicast_sg_host_state(star_mp, sg); memset(&sg_key, 0, sizeof(sg_key)); sg_key.addr = sg->key.addr; /* we need to add all exclude ports to the S,G */ for (pg = mlock_dereference(star_mp->ports, br); pg; pg = mlock_dereference(pg->next, br)) { struct net_bridge_port_group *src_pg; if (pg == sg || pg->filter_mode == MCAST_INCLUDE) continue; sg_key.port = pg->key.port; if (br_sg_port_find(br, &sg_key)) continue; pmctx = br_multicast_pg_to_port_ctx(pg); if (!pmctx) continue; brmctx = br_multicast_port_ctx_get_global(pmctx); src_pg = __br_multicast_add_group(brmctx, pmctx, &sg->key.addr, sg->eth_addr, MCAST_INCLUDE, false, false); if (IS_ERR_OR_NULL(src_pg) || src_pg->rt_protocol != RTPROT_KERNEL) continue; src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL; } } static void br_multicast_fwd_src_add(struct net_bridge_group_src *src) { struct net_bridge_mdb_entry *star_mp; struct net_bridge_mcast_port *pmctx; struct net_bridge_port_group *sg; struct net_bridge_mcast *brmctx; struct br_ip sg_ip; if (src->flags & BR_SGRP_F_INSTALLED) return; memset(&sg_ip, 0, sizeof(sg_ip)); pmctx = br_multicast_pg_to_port_ctx(src->pg); if (!pmctx) return; brmctx = br_multicast_port_ctx_get_global(pmctx); sg_ip = src->pg->key.addr; sg_ip.src = src->addr.src; sg = __br_multicast_add_group(brmctx, pmctx, &sg_ip, src->pg->eth_addr, MCAST_INCLUDE, false, !timer_pending(&src->timer)); if (IS_ERR_OR_NULL(sg)) return; src->flags |= BR_SGRP_F_INSTALLED; sg->flags &= ~MDB_PG_FLAGS_STAR_EXCL; /* if it was added by user-space as perm we can skip next steps */ if (sg->rt_protocol != RTPROT_KERNEL && (sg->flags & MDB_PG_FLAGS_PERMANENT)) return; /* the kernel is now responsible for removing this S,G */ del_timer(&sg->timer); star_mp = br_mdb_ip_get(src->br, &src->pg->key.addr); if (!star_mp) return; br_multicast_sg_add_exclude_ports(star_mp, sg); } static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src, bool fastleave) { struct net_bridge_port_group *p, *pg = src->pg; struct net_bridge_port_group __rcu **pp; struct net_bridge_mdb_entry *mp; struct br_ip sg_ip; memset(&sg_ip, 0, sizeof(sg_ip)); sg_ip = pg->key.addr; sg_ip.src = src->addr.src; mp = br_mdb_ip_get(src->br, &sg_ip); if (!mp) return; for (pp = &mp->ports; (p = mlock_dereference(*pp, src->br)) != NULL; pp = &p->next) { if (!br_port_group_equal(p, pg->key.port, pg->eth_addr)) continue; if (p->rt_protocol != RTPROT_KERNEL && (p->flags & MDB_PG_FLAGS_PERMANENT) && !(src->flags & BR_SGRP_F_USER_ADDED)) break; if (fastleave) p->flags |= MDB_PG_FLAGS_FAST_LEAVE; br_multicast_del_pg(mp, p, pp); break; } src->flags &= ~BR_SGRP_F_INSTALLED; } /* install S,G and based on src's timer enable or disable forwarding */ static void br_multicast_fwd_src_handle(struct net_bridge_group_src *src) { struct net_bridge_port_group_sg_key sg_key; struct net_bridge_port_group *sg; u8 old_flags; br_multicast_fwd_src_add(src); memset(&sg_key, 0, sizeof(sg_key)); sg_key.addr = src->pg->key.addr; sg_key.addr.src = src->addr.src; sg_key.port = src->pg->key.port; sg = br_sg_port_find(src->br, &sg_key); if (!sg || (sg->flags & MDB_PG_FLAGS_PERMANENT)) return; old_flags = sg->flags; if (timer_pending(&src->timer)) sg->flags &= ~MDB_PG_FLAGS_BLOCKED; else sg->flags |= MDB_PG_FLAGS_BLOCKED; if (old_flags != sg->flags) { struct net_bridge_mdb_entry *sg_mp; sg_mp = br_mdb_ip_get(src->br, &sg_key.addr); if (!sg_mp) return; br_mdb_notify(src->br->dev, sg_mp, sg, RTM_NEWMDB); } } static void br_multicast_destroy_mdb_entry(struct net_bridge_mcast_gc *gc) { struct net_bridge_mdb_entry *mp; mp = container_of(gc, struct net_bridge_mdb_entry, mcast_gc); WARN_ON(!hlist_unhashed(&mp->mdb_node)); WARN_ON(mp->ports); timer_shutdown_sync(&mp->timer); kfree_rcu(mp, rcu); } static void br_multicast_del_mdb_entry(struct net_bridge_mdb_entry *mp) { struct net_bridge *br = mp->br; rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode, br_mdb_rht_params); hlist_del_init_rcu(&mp->mdb_node); hlist_add_head(&mp->mcast_gc.gc_node, &br->mcast_gc_list); queue_work(system_long_wq, &br->mcast_gc_work); } static void br_multicast_group_expired(struct timer_list *t) { struct net_bridge_mdb_entry *mp = from_timer(mp, t, timer); struct net_bridge *br = mp->br; spin_lock(&br->multicast_lock); if (hlist_unhashed(&mp->mdb_node) || !netif_running(br->dev) || timer_pending(&mp->timer)) goto out; br_multicast_host_leave(mp, true); if (mp->ports) goto out; br_multicast_del_mdb_entry(mp); out: spin_unlock(&br->multicast_lock); } static void br_multicast_destroy_group_src(struct net_bridge_mcast_gc *gc) { struct net_bridge_group_src *src; src = container_of(gc, struct net_bridge_group_src, mcast_gc); WARN_ON(!hlist_unhashed(&src->node)); timer_shutdown_sync(&src->timer); kfree_rcu(src, rcu); } void __br_multicast_del_group_src(struct net_bridge_group_src *src) { struct net_bridge *br = src->pg->key.port->br; hlist_del_init_rcu(&src->node); src->pg->src_ents--; hlist_add_head(&src->mcast_gc.gc_node, &br->mcast_gc_list); queue_work(system_long_wq, &br->mcast_gc_work); } void br_multicast_del_group_src(struct net_bridge_group_src *src, bool fastleave) { br_multicast_fwd_src_remove(src, fastleave); __br_multicast_del_group_src(src); } static int br_multicast_port_ngroups_inc_one(struct net_bridge_mcast_port *pmctx, struct netlink_ext_ack *extack, const char *what) { u32 max = READ_ONCE(pmctx->mdb_max_entries); u32 n = READ_ONCE(pmctx->mdb_n_entries); if (max && n >= max) { NL_SET_ERR_MSG_FMT_MOD(extack, "%s is already in %u groups, and mcast_max_groups=%u", what, n, max); return -E2BIG; } WRITE_ONCE(pmctx->mdb_n_entries, n + 1); return 0; } static void br_multicast_port_ngroups_dec_one(struct net_bridge_mcast_port *pmctx) { u32 n = READ_ONCE(pmctx->mdb_n_entries); WARN_ON_ONCE(n == 0); WRITE_ONCE(pmctx->mdb_n_entries, n - 1); } static int br_multicast_port_ngroups_inc(struct net_bridge_port *port, const struct br_ip *group, struct netlink_ext_ack *extack) { struct net_bridge_mcast_port *pmctx; int err; lockdep_assert_held_once(&port->br->multicast_lock); /* Always count on the port context. */ err = br_multicast_port_ngroups_inc_one(&port->multicast_ctx, extack, "Port"); if (err) { trace_br_mdb_full(port->dev, group); return err; } /* Only count on the VLAN context if VID is given, and if snooping on * that VLAN is enabled. */ if (!group->vid) return 0; pmctx = br_multicast_port_vid_to_port_ctx(port, group->vid); if (!pmctx) return 0; err = br_multicast_port_ngroups_inc_one(pmctx, extack, "Port-VLAN"); if (err) { trace_br_mdb_full(port->dev, group); goto dec_one_out; } return 0; dec_one_out: br_multicast_port_ngroups_dec_one(&port->multicast_ctx); return err; } static void br_multicast_port_ngroups_dec(struct net_bridge_port *port, u16 vid) { struct net_bridge_mcast_port *pmctx; lockdep_assert_held_once(&port->br->multicast_lock); if (vid) { pmctx = br_multicast_port_vid_to_port_ctx(port, vid); if (pmctx) br_multicast_port_ngroups_dec_one(pmctx); } br_multicast_port_ngroups_dec_one(&port->multicast_ctx); } u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx) { return READ_ONCE(pmctx->mdb_n_entries); } void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max) { WRITE_ONCE(pmctx->mdb_max_entries, max); } u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx) { return READ_ONCE(pmctx->mdb_max_entries); } static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc) { struct net_bridge_port_group *pg; pg = container_of(gc, struct net_bridge_port_group, mcast_gc); WARN_ON(!hlist_unhashed(&pg->mglist)); WARN_ON(!hlist_empty(&pg->src_list)); timer_shutdown_sync(&pg->rexmit_timer); timer_shutdown_sync(&pg->timer); kfree_rcu(pg, rcu); } void br_multicast_del_pg(struct net_bridge_mdb_entry *mp, struct net_bridge_port_group *pg, struct net_bridge_port_group __rcu **pp) { struct net_bridge *br = pg->key.port->br; struct net_bridge_group_src *ent; struct hlist_node *tmp; rcu_assign_pointer(*pp, pg->next); hlist_del_init(&pg->mglist); br_multicast_eht_clean_sets(pg); hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) br_multicast_del_group_src(ent, false); br_mdb_notify(br->dev, mp, pg, RTM_DELMDB); if (!br_multicast_is_star_g(&mp->addr)) { rhashtable_remove_fast(&br->sg_port_tbl, &pg->rhnode, br_sg_port_rht_params); br_multicast_sg_del_exclude_ports(mp); } else { br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE); } br_multicast_port_ngroups_dec(pg->key.port, pg->key.addr.vid); hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list); queue_work(system_long_wq, &br->mcast_gc_work); if (!mp->ports && !mp->host_joined && netif_running(br->dev)) mod_timer(&mp->timer, jiffies); } static void br_multicast_find_del_pg(struct net_bridge *br, struct net_bridge_port_group *pg) { struct net_bridge_port_group __rcu **pp; struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; mp = br_mdb_ip_get(br, &pg->key.addr); if (WARN_ON(!mp)) return; for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p != pg) continue; br_multicast_del_pg(mp, pg, pp); return; } WARN_ON(1); } static void br_multicast_port_group_expired(struct timer_list *t) { struct net_bridge_port_group *pg = from_timer(pg, t, timer); struct net_bridge_group_src *src_ent; struct net_bridge *br = pg->key.port->br; struct hlist_node *tmp; bool changed; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || timer_pending(&pg->timer) || hlist_unhashed(&pg->mglist) || pg->flags & MDB_PG_FLAGS_PERMANENT) goto out; changed = !!(pg->filter_mode == MCAST_EXCLUDE); pg->filter_mode = MCAST_INCLUDE; hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) { if (!timer_pending(&src_ent->timer)) { br_multicast_del_group_src(src_ent, false); changed = true; } } if (hlist_empty(&pg->src_list)) { br_multicast_find_del_pg(br, pg); } else if (changed) { struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->key.addr); if (changed && br_multicast_is_star_g(&pg->key.addr)) br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE); if (WARN_ON(!mp)) goto out; br_mdb_notify(br->dev, mp, pg, RTM_NEWMDB); } out: spin_unlock(&br->multicast_lock); } static void br_multicast_gc(struct hlist_head *head) { struct net_bridge_mcast_gc *gcent; struct hlist_node *tmp; hlist_for_each_entry_safe(gcent, tmp, head, gc_node) { hlist_del_init(&gcent->gc_node); gcent->destroy(gcent); } } static void __br_multicast_query_handle_vlan(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb) { struct net_bridge_vlan *vlan = NULL; if (pmctx && br_multicast_port_ctx_is_vlan(pmctx)) vlan = pmctx->vlan; else if (br_multicast_ctx_is_vlan(brmctx)) vlan = brmctx->vlan; if (vlan && !(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED)) { u16 vlan_proto; if (br_vlan_get_proto(brmctx->br->dev, &vlan_proto) != 0) return; __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan->vid); } } static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, __be32 ip_dst, __be32 group, bool with_srcs, bool over_lmqt, u8 sflag, u8 *igmp_type, bool *need_rexmit) { struct net_bridge_port *p = pg ? pg->key.port : NULL; struct net_bridge_group_src *ent; size_t pkt_size, igmp_hdr_size; unsigned long now = jiffies; struct igmpv3_query *ihv3; void *csum_start = NULL; __sum16 *csum = NULL; struct sk_buff *skb; struct igmphdr *ih; struct ethhdr *eth; unsigned long lmqt; struct iphdr *iph; u16 lmqt_srcs = 0; igmp_hdr_size = sizeof(*ih); if (brmctx->multicast_igmp_version == 3) { igmp_hdr_size = sizeof(*ihv3); if (pg && with_srcs) { lmqt = now + (brmctx->multicast_last_member_interval * brmctx->multicast_last_member_count); hlist_for_each_entry(ent, &pg->src_list, node) { if (over_lmqt == time_after(ent->timer.expires, lmqt) && ent->src_query_rexmit_cnt > 0) lmqt_srcs++; } if (!lmqt_srcs) return NULL; igmp_hdr_size += lmqt_srcs * sizeof(__be32); } } pkt_size = sizeof(*eth) + sizeof(*iph) + 4 + igmp_hdr_size; if ((p && pkt_size > p->dev->mtu) || pkt_size > brmctx->br->dev->mtu) return NULL; skb = netdev_alloc_skb_ip_align(brmctx->br->dev, pkt_size); if (!skb) goto out; __br_multicast_query_handle_vlan(brmctx, pmctx, skb); skb->protocol = htons(ETH_P_IP); skb_reset_mac_header(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_source, brmctx->br->dev->dev_addr); ip_eth_mc_map(ip_dst, eth->h_dest); eth->h_proto = htons(ETH_P_IP); skb_put(skb, sizeof(*eth)); skb_set_network_header(skb, skb->len); iph = ip_hdr(skb); iph->tot_len = htons(pkt_size - sizeof(*eth)); iph->version = 4; iph->ihl = 6; iph->tos = 0xc0; iph->id = 0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->protocol = IPPROTO_IGMP; iph->saddr = br_opt_get(brmctx->br, BROPT_MULTICAST_QUERY_USE_IFADDR) ? inet_select_addr(brmctx->br->dev, 0, RT_SCOPE_LINK) : 0; iph->daddr = ip_dst; ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; ip_send_check(iph); skb_put(skb, 24); skb_set_transport_header(skb, skb->len); *igmp_type = IGMP_HOST_MEMBERSHIP_QUERY; switch (brmctx->multicast_igmp_version) { case 2: ih = igmp_hdr(skb); ih->type = IGMP_HOST_MEMBERSHIP_QUERY; ih->code = (group ? brmctx->multicast_last_member_interval : brmctx->multicast_query_response_interval) / (HZ / IGMP_TIMER_SCALE); ih->group = group; ih->csum = 0; csum = &ih->csum; csum_start = (void *)ih; break; case 3: ihv3 = igmpv3_query_hdr(skb); ihv3->type = IGMP_HOST_MEMBERSHIP_QUERY; ihv3->code = (group ? brmctx->multicast_last_member_interval : brmctx->multicast_query_response_interval) / (HZ / IGMP_TIMER_SCALE); ihv3->group = group; ihv3->qqic = brmctx->multicast_query_interval / HZ; ihv3->nsrcs = htons(lmqt_srcs); ihv3->resv = 0; ihv3->suppress = sflag; ihv3->qrv = 2; ihv3->csum = 0; csum = &ihv3->csum; csum_start = (void *)ihv3; if (!pg || !with_srcs) break; lmqt_srcs = 0; hlist_for_each_entry(ent, &pg->src_list, node) { if (over_lmqt == time_after(ent->timer.expires, lmqt) && ent->src_query_rexmit_cnt > 0) { ihv3->srcs[lmqt_srcs++] = ent->addr.src.ip4; ent->src_query_rexmit_cnt--; if (need_rexmit && ent->src_query_rexmit_cnt) *need_rexmit = true; } } if (WARN_ON(lmqt_srcs != ntohs(ihv3->nsrcs))) { kfree_skb(skb); return NULL; } break; } if (WARN_ON(!csum || !csum_start)) { kfree_skb(skb); return NULL; } *csum = ip_compute_csum(csum_start, igmp_hdr_size); skb_put(skb, igmp_hdr_size); __skb_pull(skb, sizeof(*eth)); out: return skb; } #if IS_ENABLED(CONFIG_IPV6) static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, const struct in6_addr *ip6_dst, const struct in6_addr *group, bool with_srcs, bool over_llqt, u8 sflag, u8 *igmp_type, bool *need_rexmit) { struct net_bridge_port *p = pg ? pg->key.port : NULL; struct net_bridge_group_src *ent; size_t pkt_size, mld_hdr_size; unsigned long now = jiffies; struct mld2_query *mld2q; void *csum_start = NULL; unsigned long interval; __sum16 *csum = NULL; struct ipv6hdr *ip6h; struct mld_msg *mldq; struct sk_buff *skb; unsigned long llqt; struct ethhdr *eth; u16 llqt_srcs = 0; u8 *hopopt; mld_hdr_size = sizeof(*mldq); if (brmctx->multicast_mld_version == 2) { mld_hdr_size = sizeof(*mld2q); if (pg && with_srcs) { llqt = now + (brmctx->multicast_last_member_interval * brmctx->multicast_last_member_count); hlist_for_each_entry(ent, &pg->src_list, node) { if (over_llqt == time_after(ent->timer.expires, llqt) && ent->src_query_rexmit_cnt > 0) llqt_srcs++; } if (!llqt_srcs) return NULL; mld_hdr_size += llqt_srcs * sizeof(struct in6_addr); } } pkt_size = sizeof(*eth) + sizeof(*ip6h) + 8 + mld_hdr_size; if ((p && pkt_size > p->dev->mtu) || pkt_size > brmctx->br->dev->mtu) return NULL; skb = netdev_alloc_skb_ip_align(brmctx->br->dev, pkt_size); if (!skb) goto out; __br_multicast_query_handle_vlan(brmctx, pmctx, skb); skb->protocol = htons(ETH_P_IPV6); /* Ethernet header */ skb_reset_mac_header(skb); eth = eth_hdr(skb); ether_addr_copy(eth->h_source, brmctx->br->dev->dev_addr); eth->h_proto = htons(ETH_P_IPV6); skb_put(skb, sizeof(*eth)); /* IPv6 header + HbH option */ skb_set_network_header(skb, skb->len); ip6h = ipv6_hdr(skb); *(__force __be32 *)ip6h = htonl(0x60000000); ip6h->payload_len = htons(8 + mld_hdr_size); ip6h->nexthdr = IPPROTO_HOPOPTS; ip6h->hop_limit = 1; ip6h->daddr = *ip6_dst; if (ipv6_dev_get_saddr(dev_net(brmctx->br->dev), brmctx->br->dev, &ip6h->daddr, 0, &ip6h->saddr)) { kfree_skb(skb); br_opt_toggle(brmctx->br, BROPT_HAS_IPV6_ADDR, false); return NULL; } br_opt_toggle(brmctx->br, BROPT_HAS_IPV6_ADDR, true); ipv6_eth_mc_map(&ip6h->daddr, eth->h_dest); hopopt = (u8 *)(ip6h + 1); hopopt[0] = IPPROTO_ICMPV6; /* next hdr */ hopopt[1] = 0; /* length of HbH */ hopopt[2] = IPV6_TLV_ROUTERALERT; /* Router Alert */ hopopt[3] = 2; /* Length of RA Option */ hopopt[4] = 0; /* Type = 0x0000 (MLD) */ hopopt[5] = 0; hopopt[6] = IPV6_TLV_PAD1; /* Pad1 */ hopopt[7] = IPV6_TLV_PAD1; /* Pad1 */ skb_put(skb, sizeof(*ip6h) + 8); /* ICMPv6 */ skb_set_transport_header(skb, skb->len); interval = ipv6_addr_any(group) ? brmctx->multicast_query_response_interval : brmctx->multicast_last_member_interval; *igmp_type = ICMPV6_MGM_QUERY; switch (brmctx->multicast_mld_version) { case 1: mldq = (struct mld_msg *)icmp6_hdr(skb); mldq->mld_type = ICMPV6_MGM_QUERY; mldq->mld_code = 0; mldq->mld_cksum = 0; mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval)); mldq->mld_reserved = 0; mldq->mld_mca = *group; csum = &mldq->mld_cksum; csum_start = (void *)mldq; break; case 2: mld2q = (struct mld2_query *)icmp6_hdr(skb); mld2q->mld2q_mrc = htons((u16)jiffies_to_msecs(interval)); mld2q->mld2q_type = ICMPV6_MGM_QUERY; mld2q->mld2q_code = 0; mld2q->mld2q_cksum = 0; mld2q->mld2q_resv1 = 0; mld2q->mld2q_resv2 = 0; mld2q->mld2q_suppress = sflag; mld2q->mld2q_qrv = 2; mld2q->mld2q_nsrcs = htons(llqt_srcs); mld2q->mld2q_qqic = brmctx->multicast_query_interval / HZ; mld2q->mld2q_mca = *group; csum = &mld2q->mld2q_cksum; csum_start = (void *)mld2q; if (!pg || !with_srcs) break; llqt_srcs = 0; hlist_for_each_entry(ent, &pg->src_list, node) { if (over_llqt == time_after(ent->timer.expires, llqt) && ent->src_query_rexmit_cnt > 0) { mld2q->mld2q_srcs[llqt_srcs++] = ent->addr.src.ip6; ent->src_query_rexmit_cnt--; if (need_rexmit && ent->src_query_rexmit_cnt) *need_rexmit = true; } } if (WARN_ON(llqt_srcs != ntohs(mld2q->mld2q_nsrcs))) { kfree_skb(skb); return NULL; } break; } if (WARN_ON(!csum || !csum_start)) { kfree_skb(skb); return NULL; } *csum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, mld_hdr_size, IPPROTO_ICMPV6, csum_partial(csum_start, mld_hdr_size, 0)); skb_put(skb, mld_hdr_size); __skb_pull(skb, sizeof(*eth)); out: return skb; } #endif static struct sk_buff *br_multicast_alloc_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, struct br_ip *ip_dst, struct br_ip *group, bool with_srcs, bool over_lmqt, u8 sflag, u8 *igmp_type, bool *need_rexmit) { __be32 ip4_dst; switch (group->proto) { case htons(ETH_P_IP): ip4_dst = ip_dst ? ip_dst->dst.ip4 : htonl(INADDR_ALLHOSTS_GROUP); return br_ip4_multicast_alloc_query(brmctx, pmctx, pg, ip4_dst, group->dst.ip4, with_srcs, over_lmqt, sflag, igmp_type, need_rexmit); #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): { struct in6_addr ip6_dst; if (ip_dst) ip6_dst = ip_dst->dst.ip6; else ipv6_addr_set(&ip6_dst, htonl(0xff020000), 0, 0, htonl(1)); return br_ip6_multicast_alloc_query(brmctx, pmctx, pg, &ip6_dst, &group->dst.ip6, with_srcs, over_lmqt, sflag, igmp_type, need_rexmit); } #endif } return NULL; } struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br, struct br_ip *group) { struct net_bridge_mdb_entry *mp; int err; mp = br_mdb_ip_get(br, group); if (mp) return mp; if (atomic_read(&br->mdb_hash_tbl.nelems) >= br->hash_max) { trace_br_mdb_full(br->dev, group); br_mc_disabled_update(br->dev, false, NULL); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, false); return ERR_PTR(-E2BIG); } mp = kzalloc(sizeof(*mp), GFP_ATOMIC); if (unlikely(!mp)) return ERR_PTR(-ENOMEM); mp->br = br; mp->addr = *group; mp->mcast_gc.destroy = br_multicast_destroy_mdb_entry; timer_setup(&mp->timer, br_multicast_group_expired, 0); err = rhashtable_lookup_insert_fast(&br->mdb_hash_tbl, &mp->rhnode, br_mdb_rht_params); if (err) { kfree(mp); mp = ERR_PTR(err); } else { hlist_add_head_rcu(&mp->mdb_node, &br->mdb_list); } return mp; } static void br_multicast_group_src_expired(struct timer_list *t) { struct net_bridge_group_src *src = from_timer(src, t, timer); struct net_bridge_port_group *pg; struct net_bridge *br = src->br; spin_lock(&br->multicast_lock); if (hlist_unhashed(&src->node) || !netif_running(br->dev) || timer_pending(&src->timer)) goto out; pg = src->pg; if (pg->filter_mode == MCAST_INCLUDE) { br_multicast_del_group_src(src, false); if (!hlist_empty(&pg->src_list)) goto out; br_multicast_find_del_pg(br, pg); } else { br_multicast_fwd_src_handle(src); } out: spin_unlock(&br->multicast_lock); } struct net_bridge_group_src * br_multicast_find_group_src(struct net_bridge_port_group *pg, struct br_ip *ip) { struct net_bridge_group_src *ent; switch (ip->proto) { case htons(ETH_P_IP): hlist_for_each_entry(ent, &pg->src_list, node) if (ip->src.ip4 == ent->addr.src.ip4) return ent; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): hlist_for_each_entry(ent, &pg->src_list, node) if (!ipv6_addr_cmp(&ent->addr.src.ip6, &ip->src.ip6)) return ent; break; #endif } return NULL; } struct net_bridge_group_src * br_multicast_new_group_src(struct net_bridge_port_group *pg, struct br_ip *src_ip) { struct net_bridge_group_src *grp_src; if (unlikely(pg->src_ents >= PG_SRC_ENT_LIMIT)) return NULL; switch (src_ip->proto) { case htons(ETH_P_IP): if (ipv4_is_zeronet(src_ip->src.ip4) || ipv4_is_multicast(src_ip->src.ip4)) return NULL; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): if (ipv6_addr_any(&src_ip->src.ip6) || ipv6_addr_is_multicast(&src_ip->src.ip6)) return NULL; break; #endif } grp_src = kzalloc(sizeof(*grp_src), GFP_ATOMIC); if (unlikely(!grp_src)) return NULL; grp_src->pg = pg; grp_src->br = pg->key.port->br; grp_src->addr = *src_ip; grp_src->mcast_gc.destroy = br_multicast_destroy_group_src; timer_setup(&grp_src->timer, br_multicast_group_src_expired, 0); hlist_add_head_rcu(&grp_src->node, &pg->src_list); pg->src_ents++; return grp_src; } struct net_bridge_port_group *br_multicast_new_port_group( struct net_bridge_port *port, const struct br_ip *group, struct net_bridge_port_group __rcu *next, unsigned char flags, const unsigned char *src, u8 filter_mode, u8 rt_protocol, struct netlink_ext_ack *extack) { struct net_bridge_port_group *p; int err; err = br_multicast_port_ngroups_inc(port, group, extack); if (err) return NULL; p = kzalloc(sizeof(*p), GFP_ATOMIC); if (unlikely(!p)) { NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group"); goto dec_out; } p->key.addr = *group; p->key.port = port; p->flags = flags; p->filter_mode = filter_mode; p->rt_protocol = rt_protocol; p->eht_host_tree = RB_ROOT; p->eht_set_tree = RB_ROOT; p->mcast_gc.destroy = br_multicast_destroy_port_group; INIT_HLIST_HEAD(&p->src_list); if (!br_multicast_is_star_g(group) && rhashtable_lookup_insert_fast(&port->br->sg_port_tbl, &p->rhnode, br_sg_port_rht_params)) { NL_SET_ERR_MSG_MOD(extack, "Couldn't insert new port group"); goto free_out; } rcu_assign_pointer(p->next, next); timer_setup(&p->timer, br_multicast_port_group_expired, 0); timer_setup(&p->rexmit_timer, br_multicast_port_group_rexmit, 0); hlist_add_head(&p->mglist, &port->mglist); if (src) memcpy(p->eth_addr, src, ETH_ALEN); else eth_broadcast_addr(p->eth_addr); return p; free_out: kfree(p); dec_out: br_multicast_port_ngroups_dec(port, group->vid); return NULL; } void br_multicast_del_port_group(struct net_bridge_port_group *p) { struct net_bridge_port *port = p->key.port; __u16 vid = p->key.addr.vid; hlist_del_init(&p->mglist); if (!br_multicast_is_star_g(&p->key.addr)) rhashtable_remove_fast(&port->br->sg_port_tbl, &p->rhnode, br_sg_port_rht_params); kfree(p); br_multicast_port_ngroups_dec(port, vid); } void br_multicast_host_join(const struct net_bridge_mcast *brmctx, struct net_bridge_mdb_entry *mp, bool notify) { if (!mp->host_joined) { mp->host_joined = true; if (br_multicast_is_star_g(&mp->addr)) br_multicast_star_g_host_state(mp); if (notify) br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB); } if (br_group_is_l2(&mp->addr)) return; mod_timer(&mp->timer, jiffies + brmctx->multicast_membership_interval); } void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify) { if (!mp->host_joined) return; mp->host_joined = false; if (br_multicast_is_star_g(&mp->addr)) br_multicast_star_g_host_state(mp); if (notify) br_mdb_notify(mp->br->dev, mp, NULL, RTM_DELMDB); } static struct net_bridge_port_group * __br_multicast_add_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct br_ip *group, const unsigned char *src, u8 filter_mode, bool igmpv2_mldv1, bool blocked) { struct net_bridge_port_group __rcu **pp; struct net_bridge_port_group *p = NULL; struct net_bridge_mdb_entry *mp; unsigned long now = jiffies; if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; mp = br_multicast_new_group(brmctx->br, group); if (IS_ERR(mp)) return ERR_CAST(mp); if (!pmctx) { br_multicast_host_join(brmctx, mp, true); goto out; } for (pp = &mp->ports; (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { if (br_port_group_equal(p, pmctx->port, src)) goto found; if ((unsigned long)p->key.port < (unsigned long)pmctx->port) break; } p = br_multicast_new_port_group(pmctx->port, group, *pp, 0, src, filter_mode, RTPROT_KERNEL, NULL); if (unlikely(!p)) { p = ERR_PTR(-ENOMEM); goto out; } rcu_assign_pointer(*pp, p); if (blocked) p->flags |= MDB_PG_FLAGS_BLOCKED; br_mdb_notify(brmctx->br->dev, mp, p, RTM_NEWMDB); found: if (igmpv2_mldv1) mod_timer(&p->timer, now + brmctx->multicast_membership_interval); out: return p; } static int br_multicast_add_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct br_ip *group, const unsigned char *src, u8 filter_mode, bool igmpv2_mldv1) { struct net_bridge_port_group *pg; int err; spin_lock(&brmctx->br->multicast_lock); pg = __br_multicast_add_group(brmctx, pmctx, group, src, filter_mode, igmpv2_mldv1, false); /* NULL is considered valid for host joined groups */ err = PTR_ERR_OR_ZERO(pg); spin_unlock(&brmctx->br->multicast_lock); return err; } static int br_ip4_multicast_add_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, __be32 group, __u16 vid, const unsigned char *src, bool igmpv2) { struct br_ip br_group; u8 filter_mode; if (ipv4_is_local_multicast(group)) return 0; memset(&br_group, 0, sizeof(br_group)); br_group.dst.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; filter_mode = igmpv2 ? MCAST_EXCLUDE : MCAST_INCLUDE; return br_multicast_add_group(brmctx, pmctx, &br_group, src, filter_mode, igmpv2); } #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_add_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, const struct in6_addr *group, __u16 vid, const unsigned char *src, bool mldv1) { struct br_ip br_group; u8 filter_mode; if (ipv6_addr_is_ll_all_nodes(group)) return 0; memset(&br_group, 0, sizeof(br_group)); br_group.dst.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; filter_mode = mldv1 ? MCAST_EXCLUDE : MCAST_INCLUDE; return br_multicast_add_group(brmctx, pmctx, &br_group, src, filter_mode, mldv1); } #endif static bool br_multicast_rport_del(struct hlist_node *rlist) { if (hlist_unhashed(rlist)) return false; hlist_del_init_rcu(rlist); return true; } static bool br_ip4_multicast_rport_del(struct net_bridge_mcast_port *pmctx) { return br_multicast_rport_del(&pmctx->ip4_rlist); } static bool br_ip6_multicast_rport_del(struct net_bridge_mcast_port *pmctx) { #if IS_ENABLED(CONFIG_IPV6) return br_multicast_rport_del(&pmctx->ip6_rlist); #else return false; #endif } static void br_multicast_router_expired(struct net_bridge_mcast_port *pmctx, struct timer_list *t, struct hlist_node *rlist) { struct net_bridge *br = pmctx->port->br; bool del; spin_lock(&br->multicast_lock); if (pmctx->multicast_router == MDB_RTR_TYPE_DISABLED || pmctx->multicast_router == MDB_RTR_TYPE_PERM || timer_pending(t)) goto out; del = br_multicast_rport_del(rlist); br_multicast_rport_del_notify(pmctx, del); out: spin_unlock(&br->multicast_lock); } static void br_ip4_multicast_router_expired(struct timer_list *t) { struct net_bridge_mcast_port *pmctx = from_timer(pmctx, t, ip4_mc_router_timer); br_multicast_router_expired(pmctx, t, &pmctx->ip4_rlist); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_router_expired(struct timer_list *t) { struct net_bridge_mcast_port *pmctx = from_timer(pmctx, t, ip6_mc_router_timer); br_multicast_router_expired(pmctx, t, &pmctx->ip6_rlist); } #endif static void br_mc_router_state_change(struct net_bridge *p, bool is_mc_router) { struct switchdev_attr attr = { .orig_dev = p->dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_MROUTER, .flags = SWITCHDEV_F_DEFER, .u.mrouter = is_mc_router, }; switchdev_port_attr_set(p->dev, &attr, NULL); } static void br_multicast_local_router_expired(struct net_bridge_mcast *brmctx, struct timer_list *timer) { spin_lock(&brmctx->br->multicast_lock); if (brmctx->multicast_router == MDB_RTR_TYPE_DISABLED || brmctx->multicast_router == MDB_RTR_TYPE_PERM || br_ip4_multicast_is_router(brmctx) || br_ip6_multicast_is_router(brmctx)) goto out; br_mc_router_state_change(brmctx->br, false); out: spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_local_router_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = from_timer(brmctx, t, ip4_mc_router_timer); br_multicast_local_router_expired(brmctx, t); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_local_router_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = from_timer(brmctx, t, ip6_mc_router_timer); br_multicast_local_router_expired(brmctx, t); } #endif static void br_multicast_querier_expired(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query) { spin_lock(&brmctx->br->multicast_lock); if (!netif_running(brmctx->br->dev) || br_multicast_ctx_vlan_global_disabled(brmctx) || !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED)) goto out; br_multicast_start_querier(brmctx, query); out: spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_querier_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = from_timer(brmctx, t, ip4_other_query.timer); br_multicast_querier_expired(brmctx, &brmctx->ip4_own_query); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_querier_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = from_timer(brmctx, t, ip6_other_query.timer); br_multicast_querier_expired(brmctx, &brmctx->ip6_own_query); } #endif static void br_multicast_query_delay_expired(struct timer_list *t) { } static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx, struct br_ip *ip, struct sk_buff *skb) { if (ip->proto == htons(ETH_P_IP)) brmctx->ip4_querier.addr.src.ip4 = ip_hdr(skb)->saddr; #if IS_ENABLED(CONFIG_IPV6) else brmctx->ip6_querier.addr.src.ip6 = ipv6_hdr(skb)->saddr; #endif } static void __br_multicast_send_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, struct br_ip *ip_dst, struct br_ip *group, bool with_srcs, u8 sflag, bool *need_rexmit) { bool over_lmqt = !!sflag; struct sk_buff *skb; u8 igmp_type; if (!br_multicast_ctx_should_use(brmctx, pmctx) || !br_multicast_ctx_matches_vlan_snooping(brmctx)) return; again_under_lmqt: skb = br_multicast_alloc_query(brmctx, pmctx, pg, ip_dst, group, with_srcs, over_lmqt, sflag, &igmp_type, need_rexmit); if (!skb) return; if (pmctx) { skb->dev = pmctx->port->dev; br_multicast_count(brmctx->br, pmctx->port, skb, igmp_type, BR_MCAST_DIR_TX); NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, dev_net(pmctx->port->dev), NULL, skb, NULL, skb->dev, br_dev_queue_push_xmit); if (over_lmqt && with_srcs && sflag) { over_lmqt = false; goto again_under_lmqt; } } else { br_multicast_select_own_querier(brmctx, group, skb); br_multicast_count(brmctx->br, NULL, skb, igmp_type, BR_MCAST_DIR_RX); netif_rx(skb); } } static void br_multicast_read_querier(const struct bridge_mcast_querier *querier, struct bridge_mcast_querier *dest) { unsigned int seq; memset(dest, 0, sizeof(*dest)); do { seq = read_seqcount_begin(&querier->seq); dest->port_ifidx = querier->port_ifidx; memcpy(&dest->addr, &querier->addr, sizeof(struct br_ip)); } while (read_seqcount_retry(&querier->seq, seq)); } static void br_multicast_update_querier(struct net_bridge_mcast *brmctx, struct bridge_mcast_querier *querier, int ifindex, struct br_ip *saddr) { write_seqcount_begin(&querier->seq); querier->port_ifidx = ifindex; memcpy(&querier->addr, saddr, sizeof(*saddr)); write_seqcount_end(&querier->seq); } static void br_multicast_send_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct bridge_mcast_own_query *own_query) { struct bridge_mcast_other_query *other_query = NULL; struct bridge_mcast_querier *querier; struct br_ip br_group; unsigned long time; if (!br_multicast_ctx_should_use(brmctx, pmctx) || !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED) || !brmctx->multicast_querier) return; memset(&br_group.dst, 0, sizeof(br_group.dst)); if (pmctx ? (own_query == &pmctx->ip4_own_query) : (own_query == &brmctx->ip4_own_query)) { querier = &brmctx->ip4_querier; other_query = &brmctx->ip4_other_query; br_group.proto = htons(ETH_P_IP); #if IS_ENABLED(CONFIG_IPV6) } else { querier = &brmctx->ip6_querier; other_query = &brmctx->ip6_other_query; br_group.proto = htons(ETH_P_IPV6); #endif } if (!other_query || timer_pending(&other_query->timer)) return; /* we're about to select ourselves as querier */ if (!pmctx && querier->port_ifidx) { struct br_ip zeroip = {}; br_multicast_update_querier(brmctx, querier, 0, &zeroip); } __br_multicast_send_query(brmctx, pmctx, NULL, NULL, &br_group, false, 0, NULL); time = jiffies; time += own_query->startup_sent < brmctx->multicast_startup_query_count ? brmctx->multicast_startup_query_interval : brmctx->multicast_query_interval; mod_timer(&own_query->timer, time); } static void br_multicast_port_query_expired(struct net_bridge_mcast_port *pmctx, struct bridge_mcast_own_query *query) { struct net_bridge *br = pmctx->port->br; struct net_bridge_mcast *brmctx; spin_lock(&br->multicast_lock); if (br_multicast_port_ctx_state_stopped(pmctx)) goto out; brmctx = br_multicast_port_ctx_get_global(pmctx); if (query->startup_sent < brmctx->multicast_startup_query_count) query->startup_sent++; br_multicast_send_query(brmctx, pmctx, query); out: spin_unlock(&br->multicast_lock); } static void br_ip4_multicast_port_query_expired(struct timer_list *t) { struct net_bridge_mcast_port *pmctx = from_timer(pmctx, t, ip4_own_query.timer); br_multicast_port_query_expired(pmctx, &pmctx->ip4_own_query); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_port_query_expired(struct timer_list *t) { struct net_bridge_mcast_port *pmctx = from_timer(pmctx, t, ip6_own_query.timer); br_multicast_port_query_expired(pmctx, &pmctx->ip6_own_query); } #endif static void br_multicast_port_group_rexmit(struct timer_list *t) { struct net_bridge_port_group *pg = from_timer(pg, t, rexmit_timer); struct bridge_mcast_other_query *other_query = NULL; struct net_bridge *br = pg->key.port->br; struct net_bridge_mcast_port *pmctx; struct net_bridge_mcast *brmctx; bool need_rexmit = false; spin_lock(&br->multicast_lock); if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) || !br_opt_get(br, BROPT_MULTICAST_ENABLED)) goto out; pmctx = br_multicast_pg_to_port_ctx(pg); if (!pmctx) goto out; brmctx = br_multicast_port_ctx_get_global(pmctx); if (!brmctx->multicast_querier) goto out; if (pg->key.addr.proto == htons(ETH_P_IP)) other_query = &brmctx->ip4_other_query; #if IS_ENABLED(CONFIG_IPV6) else other_query = &brmctx->ip6_other_query; #endif if (!other_query || timer_pending(&other_query->timer)) goto out; if (pg->grp_query_rexmit_cnt) { pg->grp_query_rexmit_cnt--; __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, false, 1, NULL); } __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, true, 0, &need_rexmit); if (pg->grp_query_rexmit_cnt || need_rexmit) mod_timer(&pg->rexmit_timer, jiffies + brmctx->multicast_last_member_interval); out: spin_unlock(&br->multicast_lock); } static int br_mc_disabled_update(struct net_device *dev, bool value, struct netlink_ext_ack *extack) { struct switchdev_attr attr = { .orig_dev = dev, .id = SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED, .flags = SWITCHDEV_F_DEFER, .u.mc_disabled = !value, }; return switchdev_port_attr_set(dev, &attr, extack); } void br_multicast_port_ctx_init(struct net_bridge_port *port, struct net_bridge_vlan *vlan, struct net_bridge_mcast_port *pmctx) { pmctx->port = port; pmctx->vlan = vlan; pmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; timer_setup(&pmctx->ip4_mc_router_timer, br_ip4_multicast_router_expired, 0); timer_setup(&pmctx->ip4_own_query.timer, br_ip4_multicast_port_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) timer_setup(&pmctx->ip6_mc_router_timer, br_ip6_multicast_router_expired, 0); timer_setup(&pmctx->ip6_own_query.timer, br_ip6_multicast_port_query_expired, 0); #endif } void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx) { #if IS_ENABLED(CONFIG_IPV6) del_timer_sync(&pmctx->ip6_mc_router_timer); #endif del_timer_sync(&pmctx->ip4_mc_router_timer); } int br_multicast_add_port(struct net_bridge_port *port) { int err; port->multicast_eht_hosts_limit = BR_MCAST_DEFAULT_EHT_HOSTS_LIMIT; br_multicast_port_ctx_init(port, NULL, &port->multicast_ctx); err = br_mc_disabled_update(port->dev, br_opt_get(port->br, BROPT_MULTICAST_ENABLED), NULL); if (err && err != -EOPNOTSUPP) return err; port->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats); if (!port->mcast_stats) return -ENOMEM; return 0; } void br_multicast_del_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; struct net_bridge_port_group *pg; struct hlist_node *n; /* Take care of the remaining groups, only perm ones should be left */ spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(pg, n, &port->mglist, mglist) br_multicast_find_del_pg(br, pg); spin_unlock_bh(&br->multicast_lock); flush_work(&br->mcast_gc_work); br_multicast_port_ctx_deinit(&port->multicast_ctx); free_percpu(port->mcast_stats); } static void br_multicast_enable(struct bridge_mcast_own_query *query) { query->startup_sent = 0; if (try_to_del_timer_sync(&query->timer) >= 0 || del_timer(&query->timer)) mod_timer(&query->timer, jiffies); } static void __br_multicast_enable_port_ctx(struct net_bridge_mcast_port *pmctx) { struct net_bridge *br = pmctx->port->br; struct net_bridge_mcast *brmctx; brmctx = br_multicast_port_ctx_get_global(pmctx); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED) || !netif_running(br->dev)) return; br_multicast_enable(&pmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) br_multicast_enable(&pmctx->ip6_own_query); #endif if (pmctx->multicast_router == MDB_RTR_TYPE_PERM) { br_ip4_multicast_add_router(brmctx, pmctx); br_ip6_multicast_add_router(brmctx, pmctx); } if (br_multicast_port_ctx_is_vlan(pmctx)) { struct net_bridge_port_group *pg; u32 n = 0; /* The mcast_n_groups counter might be wrong. First, * BR_VLFLAG_MCAST_ENABLED is toggled before temporary entries * are flushed, thus mcast_n_groups after the toggle does not * reflect the true values. And second, permanent entries added * while BR_VLFLAG_MCAST_ENABLED was disabled, are not reflected * either. Thus we have to refresh the counter. */ hlist_for_each_entry(pg, &pmctx->port->mglist, mglist) { if (pg->key.addr.vid == pmctx->vlan->vid) n++; } WRITE_ONCE(pmctx->mdb_n_entries, n); } } void br_multicast_enable_port(struct net_bridge_port *port) { struct net_bridge *br = port->br; spin_lock_bh(&br->multicast_lock); __br_multicast_enable_port_ctx(&port->multicast_ctx); spin_unlock_bh(&br->multicast_lock); } static void __br_multicast_disable_port_ctx(struct net_bridge_mcast_port *pmctx) { struct net_bridge_port_group *pg; struct hlist_node *n; bool del = false; hlist_for_each_entry_safe(pg, n, &pmctx->port->mglist, mglist) if (!(pg->flags & MDB_PG_FLAGS_PERMANENT) && (!br_multicast_port_ctx_is_vlan(pmctx) || pg->key.addr.vid == pmctx->vlan->vid)) br_multicast_find_del_pg(pmctx->port->br, pg); del |= br_ip4_multicast_rport_del(pmctx); del_timer(&pmctx->ip4_mc_router_timer); del_timer(&pmctx->ip4_own_query.timer); del |= br_ip6_multicast_rport_del(pmctx); #if IS_ENABLED(CONFIG_IPV6) del_timer(&pmctx->ip6_mc_router_timer); del_timer(&pmctx->ip6_own_query.timer); #endif br_multicast_rport_del_notify(pmctx, del); } void br_multicast_disable_port(struct net_bridge_port *port) { spin_lock_bh(&port->br->multicast_lock); __br_multicast_disable_port_ctx(&port->multicast_ctx); spin_unlock_bh(&port->br->multicast_lock); } static int __grp_src_delete_marked(struct net_bridge_port_group *pg) { struct net_bridge_group_src *ent; struct hlist_node *tmp; int deleted = 0; hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node) if (ent->flags & BR_SGRP_F_DELETE) { br_multicast_del_group_src(ent, false); deleted++; } return deleted; } static void __grp_src_mod_timer(struct net_bridge_group_src *src, unsigned long expires) { mod_timer(&src->timer, expires); br_multicast_fwd_src_handle(src); } static void __grp_src_query_marked_and_rexmit(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg) { struct bridge_mcast_other_query *other_query = NULL; u32 lmqc = brmctx->multicast_last_member_count; unsigned long lmqt, lmi, now = jiffies; struct net_bridge_group_src *ent; if (!netif_running(brmctx->br->dev) || !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED)) return; if (pg->key.addr.proto == htons(ETH_P_IP)) other_query = &brmctx->ip4_other_query; #if IS_ENABLED(CONFIG_IPV6) else other_query = &brmctx->ip6_other_query; #endif lmqt = now + br_multicast_lmqt(brmctx); hlist_for_each_entry(ent, &pg->src_list, node) { if (ent->flags & BR_SGRP_F_SEND) { ent->flags &= ~BR_SGRP_F_SEND; if (ent->timer.expires > lmqt) { if (brmctx->multicast_querier && other_query && !timer_pending(&other_query->timer)) ent->src_query_rexmit_cnt = lmqc; __grp_src_mod_timer(ent, lmqt); } } } if (!brmctx->multicast_querier || !other_query || timer_pending(&other_query->timer)) return; __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, true, 1, NULL); lmi = now + brmctx->multicast_last_member_interval; if (!timer_pending(&pg->rexmit_timer) || time_after(pg->rexmit_timer.expires, lmi)) mod_timer(&pg->rexmit_timer, lmi); } static void __grp_send_query_and_rexmit(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg) { struct bridge_mcast_other_query *other_query = NULL; unsigned long now = jiffies, lmi; if (!netif_running(brmctx->br->dev) || !br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED)) return; if (pg->key.addr.proto == htons(ETH_P_IP)) other_query = &brmctx->ip4_other_query; #if IS_ENABLED(CONFIG_IPV6) else other_query = &brmctx->ip6_other_query; #endif if (brmctx->multicast_querier && other_query && !timer_pending(&other_query->timer)) { lmi = now + brmctx->multicast_last_member_interval; pg->grp_query_rexmit_cnt = brmctx->multicast_last_member_count - 1; __br_multicast_send_query(brmctx, pmctx, pg, &pg->key.addr, &pg->key.addr, false, 0, NULL); if (!timer_pending(&pg->rexmit_timer) || time_after(pg->rexmit_timer.expires, lmi)) mod_timer(&pg->rexmit_timer, lmi); } if (pg->filter_mode == MCAST_EXCLUDE && (!timer_pending(&pg->timer) || time_after(pg->timer.expires, now + br_multicast_lmqt(brmctx)))) mod_timer(&pg->timer, now + br_multicast_lmqt(brmctx)); } /* State Msg type New state Actions * INCLUDE (A) IS_IN (B) INCLUDE (A+B) (B)=GMI * INCLUDE (A) ALLOW (B) INCLUDE (A+B) (B)=GMI * EXCLUDE (X,Y) ALLOW (A) EXCLUDE (X+A,Y-A) (A)=GMI */ static bool br_multicast_isinc_allow(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; unsigned long now = jiffies; bool changed = false; struct br_ip src_ip; u32 src_idx; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (!ent) { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) changed = true; } if (ent) __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; return changed; } /* State Msg type New state Actions * INCLUDE (A) IS_EX (B) EXCLUDE (A*B,B-A) (B-A)=0 * Delete (A-B) * Group Timer=GMI */ static void __grp_src_isexc_incl(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; struct br_ip src_ip; u32 src_idx; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags |= BR_SGRP_F_DELETE; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) ent->flags &= ~BR_SGRP_F_DELETE; else ent = br_multicast_new_group_src(pg, &src_ip); if (ent) br_multicast_fwd_src_handle(ent); } br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); __grp_src_delete_marked(pg); } /* State Msg type New state Actions * EXCLUDE (X,Y) IS_EX (A) EXCLUDE (A-Y,Y*A) (A-X-Y)=GMI * Delete (X-A) * Delete (Y-A) * Group Timer=GMI */ static bool __grp_src_isexc_excl(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; unsigned long now = jiffies; bool changed = false; struct br_ip src_ip; u32 src_idx; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags |= BR_SGRP_F_DELETE; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags &= ~BR_SGRP_F_DELETE; } else { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) { __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); changed = true; } } } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (__grp_src_delete_marked(pg)) changed = true; return changed; } static bool br_multicast_isexc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: __grp_src_isexc_incl(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE); changed = true; break; case MCAST_EXCLUDE: changed = __grp_src_isexc_excl(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; } pg->filter_mode = MCAST_EXCLUDE; mod_timer(&pg->timer, jiffies + br_multicast_gmi(brmctx)); return changed; } /* State Msg type New state Actions * INCLUDE (A) TO_IN (B) INCLUDE (A+B) (B)=GMI * Send Q(G,A-B) */ static bool __grp_src_toin_incl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { u32 src_idx, to_send = pg->src_ents; struct net_bridge_group_src *ent; unsigned long now = jiffies; bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags |= BR_SGRP_F_SEND; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags &= ~BR_SGRP_F_SEND; to_send--; } else { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) changed = true; } if (ent) __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } /* State Msg type New state Actions * EXCLUDE (X,Y) TO_IN (A) EXCLUDE (X+A,Y-A) (A)=GMI * Send Q(G,X-A) * Send Q(G) */ static bool __grp_src_toin_excl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { u32 src_idx, to_send = pg->src_ents; struct net_bridge_group_src *ent; unsigned long now = jiffies; bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) if (timer_pending(&ent->timer)) ent->flags |= BR_SGRP_F_SEND; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { if (timer_pending(&ent->timer)) { ent->flags &= ~BR_SGRP_F_SEND; to_send--; } } else { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) changed = true; } if (ent) __grp_src_mod_timer(ent, now + br_multicast_gmi(brmctx)); } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); __grp_send_query_and_rexmit(brmctx, pmctx, pg); return changed; } static bool br_multicast_toin(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: changed = __grp_src_toin_incl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; case MCAST_EXCLUDE: changed = __grp_src_toin_excl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; } if (br_multicast_eht_should_del_pg(pg)) { pg->flags |= MDB_PG_FLAGS_FAST_LEAVE; br_multicast_find_del_pg(pg->key.port->br, pg); /* a notification has already been sent and we shouldn't * access pg after the delete so we have to return false */ changed = false; } return changed; } /* State Msg type New state Actions * INCLUDE (A) TO_EX (B) EXCLUDE (A*B,B-A) (B-A)=0 * Delete (A-B) * Send Q(G,A*B) * Group Timer=GMI */ static void __grp_src_toex_incl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags = (ent->flags & ~BR_SGRP_F_DELETE) | BR_SGRP_F_SEND; to_send++; } else { ent = br_multicast_new_group_src(pg, &src_ip); } if (ent) br_multicast_fwd_src_handle(ent); } br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); __grp_src_delete_marked(pg); if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); } /* State Msg type New state Actions * EXCLUDE (X,Y) TO_EX (A) EXCLUDE (A-Y,Y*A) (A-X-Y)=Group Timer * Delete (X-A) * Delete (Y-A) * Send Q(G,A-Y) * Group Timer=GMI */ static bool __grp_src_toex_excl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags &= ~BR_SGRP_F_DELETE; } else { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) { __grp_src_mod_timer(ent, pg->timer.expires); changed = true; } } if (ent && timer_pending(&ent->timer)) { ent->flags |= BR_SGRP_F_SEND; to_send++; } } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (__grp_src_delete_marked(pg)) changed = true; if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } static bool br_multicast_toex(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: __grp_src_toex_incl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE); changed = true; break; case MCAST_EXCLUDE: changed = __grp_src_toex_excl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; } pg->filter_mode = MCAST_EXCLUDE; mod_timer(&pg->timer, jiffies + br_multicast_gmi(brmctx)); return changed; } /* State Msg type New state Actions * INCLUDE (A) BLOCK (B) INCLUDE (A) Send Q(G,A*B) */ static bool __grp_src_block_incl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags &= ~BR_SGRP_F_SEND; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (ent) { ent->flags |= BR_SGRP_F_SEND; to_send++; } } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } /* State Msg type New state Actions * EXCLUDE (X,Y) BLOCK (A) EXCLUDE (X+(A-Y),Y) (A-X-Y)=Group Timer * Send Q(G,A-Y) */ static bool __grp_src_block_excl(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { struct net_bridge_group_src *ent; u32 src_idx, to_send = 0; bool changed = false; struct br_ip src_ip; hlist_for_each_entry(ent, &pg->src_list, node) ent->flags &= ~BR_SGRP_F_SEND; memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&src_ip.src, srcs + (src_idx * addr_size), addr_size); ent = br_multicast_find_group_src(pg, &src_ip); if (!ent) { ent = br_multicast_new_group_src(pg, &src_ip); if (ent) { __grp_src_mod_timer(ent, pg->timer.expires); changed = true; } } if (ent && timer_pending(&ent->timer)) { ent->flags |= BR_SGRP_F_SEND; to_send++; } } if (br_multicast_eht_handle(brmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type)) changed = true; if (to_send) __grp_src_query_marked_and_rexmit(brmctx, pmctx, pg); return changed; } static bool br_multicast_block(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool changed = false; switch (pg->filter_mode) { case MCAST_INCLUDE: changed = __grp_src_block_incl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; case MCAST_EXCLUDE: changed = __grp_src_block_excl(brmctx, pmctx, pg, h_addr, srcs, nsrcs, addr_size, grec_type); break; } if ((pg->filter_mode == MCAST_INCLUDE && hlist_empty(&pg->src_list)) || br_multicast_eht_should_del_pg(pg)) { if (br_multicast_eht_should_del_pg(pg)) pg->flags |= MDB_PG_FLAGS_FAST_LEAVE; br_multicast_find_del_pg(pg->key.port->br, pg); /* a notification has already been sent and we shouldn't * access pg after the delete so we have to return false */ changed = false; } return changed; } static struct net_bridge_port_group * br_multicast_find_port(struct net_bridge_mdb_entry *mp, struct net_bridge_port *p, const unsigned char *src) { struct net_bridge *br __maybe_unused = mp->br; struct net_bridge_port_group *pg; for (pg = mlock_dereference(mp->ports, br); pg; pg = mlock_dereference(pg->next, br)) if (br_port_group_equal(pg, p, src)) return pg; return NULL; } static int br_ip4_multicast_igmp3_report(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { bool igmpv2 = brmctx->multicast_igmp_version == 2; struct net_bridge_mdb_entry *mdst; struct net_bridge_port_group *pg; const unsigned char *src; struct igmpv3_report *ih; struct igmpv3_grec *grec; int i, len, num, type; __be32 group, *h_addr; bool changed = false; int err = 0; u16 nsrcs; ih = igmpv3_report_hdr(skb); num = ntohs(ih->ngrec); len = skb_transport_offset(skb) + sizeof(*ih); for (i = 0; i < num; i++) { len += sizeof(*grec); if (!ip_mc_may_pull(skb, len)) return -EINVAL; grec = (void *)(skb->data + len - sizeof(*grec)); group = grec->grec_mca; type = grec->grec_type; nsrcs = ntohs(grec->grec_nsrcs); len += nsrcs * 4; if (!ip_mc_may_pull(skb, len)) return -EINVAL; switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: case IGMPV3_CHANGE_TO_INCLUDE: case IGMPV3_CHANGE_TO_EXCLUDE: case IGMPV3_ALLOW_NEW_SOURCES: case IGMPV3_BLOCK_OLD_SOURCES: break; default: continue; } src = eth_hdr(skb)->h_source; if (nsrcs == 0 && (type == IGMPV3_CHANGE_TO_INCLUDE || type == IGMPV3_MODE_IS_INCLUDE)) { if (!pmctx || igmpv2) { br_ip4_multicast_leave_group(brmctx, pmctx, group, vid, src); continue; } } else { err = br_ip4_multicast_add_group(brmctx, pmctx, group, vid, src, igmpv2); if (err) break; } if (!pmctx || igmpv2) continue; spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto unlock_continue; mdst = br_mdb_ip4_get(brmctx->br, group, vid); if (!mdst) goto unlock_continue; pg = br_multicast_find_port(mdst, pmctx->port, src); if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) goto unlock_continue; /* reload grec and host addr */ grec = (void *)(skb->data + len - sizeof(*grec) - (nsrcs * 4)); h_addr = &ip_hdr(skb)->saddr; switch (type) { case IGMPV3_ALLOW_NEW_SOURCES: changed = br_multicast_isinc_allow(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_MODE_IS_INCLUDE: changed = br_multicast_isinc_allow(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_MODE_IS_EXCLUDE: changed = br_multicast_isexc(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_CHANGE_TO_INCLUDE: changed = br_multicast_toin(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_CHANGE_TO_EXCLUDE: changed = br_multicast_toex(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; case IGMPV3_BLOCK_OLD_SOURCES: changed = br_multicast_block(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(__be32), type); break; } if (changed) br_mdb_notify(brmctx->br->dev, mdst, pg, RTM_NEWMDB); unlock_continue: spin_unlock(&brmctx->br->multicast_lock); } return err; } #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_mld2_report(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { bool mldv1 = brmctx->multicast_mld_version == 1; struct net_bridge_mdb_entry *mdst; struct net_bridge_port_group *pg; unsigned int nsrcs_offset; struct mld2_report *mld2r; const unsigned char *src; struct in6_addr *h_addr; struct mld2_grec *grec; unsigned int grec_len; bool changed = false; int i, len, num; int err = 0; if (!ipv6_mc_may_pull(skb, sizeof(*mld2r))) return -EINVAL; mld2r = (struct mld2_report *)icmp6_hdr(skb); num = ntohs(mld2r->mld2r_ngrec); len = skb_transport_offset(skb) + sizeof(*mld2r); for (i = 0; i < num; i++) { __be16 *_nsrcs, __nsrcs; u16 nsrcs; nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs); if (skb_transport_offset(skb) + ipv6_transport_len(skb) < nsrcs_offset + sizeof(__nsrcs)) return -EINVAL; _nsrcs = skb_header_pointer(skb, nsrcs_offset, sizeof(__nsrcs), &__nsrcs); if (!_nsrcs) return -EINVAL; nsrcs = ntohs(*_nsrcs); grec_len = struct_size(grec, grec_src, nsrcs); if (!ipv6_mc_may_pull(skb, len + grec_len)) return -EINVAL; grec = (struct mld2_grec *)(skb->data + len); len += grec_len; switch (grec->grec_type) { case MLD2_MODE_IS_INCLUDE: case MLD2_MODE_IS_EXCLUDE: case MLD2_CHANGE_TO_INCLUDE: case MLD2_CHANGE_TO_EXCLUDE: case MLD2_ALLOW_NEW_SOURCES: case MLD2_BLOCK_OLD_SOURCES: break; default: continue; } src = eth_hdr(skb)->h_source; if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE || grec->grec_type == MLD2_MODE_IS_INCLUDE) && nsrcs == 0) { if (!pmctx || mldv1) { br_ip6_multicast_leave_group(brmctx, pmctx, &grec->grec_mca, vid, src); continue; } } else { err = br_ip6_multicast_add_group(brmctx, pmctx, &grec->grec_mca, vid, src, mldv1); if (err) break; } if (!pmctx || mldv1) continue; spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto unlock_continue; mdst = br_mdb_ip6_get(brmctx->br, &grec->grec_mca, vid); if (!mdst) goto unlock_continue; pg = br_multicast_find_port(mdst, pmctx->port, src); if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT)) goto unlock_continue; h_addr = &ipv6_hdr(skb)->saddr; switch (grec->grec_type) { case MLD2_ALLOW_NEW_SOURCES: changed = br_multicast_isinc_allow(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_MODE_IS_INCLUDE: changed = br_multicast_isinc_allow(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_MODE_IS_EXCLUDE: changed = br_multicast_isexc(brmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_CHANGE_TO_INCLUDE: changed = br_multicast_toin(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_CHANGE_TO_EXCLUDE: changed = br_multicast_toex(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; case MLD2_BLOCK_OLD_SOURCES: changed = br_multicast_block(brmctx, pmctx, pg, h_addr, grec->grec_src, nsrcs, sizeof(struct in6_addr), grec->grec_type); break; } if (changed) br_mdb_notify(brmctx->br->dev, mdst, pg, RTM_NEWMDB); unlock_continue: spin_unlock(&brmctx->br->multicast_lock); } return err; } #endif static bool br_multicast_select_querier(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct br_ip *saddr) { int port_ifidx = pmctx ? pmctx->port->dev->ifindex : 0; struct timer_list *own_timer, *other_timer; struct bridge_mcast_querier *querier; switch (saddr->proto) { case htons(ETH_P_IP): querier = &brmctx->ip4_querier; own_timer = &brmctx->ip4_own_query.timer; other_timer = &brmctx->ip4_other_query.timer; if (!querier->addr.src.ip4 || ntohl(saddr->src.ip4) <= ntohl(querier->addr.src.ip4)) goto update; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): querier = &brmctx->ip6_querier; own_timer = &brmctx->ip6_own_query.timer; other_timer = &brmctx->ip6_other_query.timer; if (ipv6_addr_cmp(&saddr->src.ip6, &querier->addr.src.ip6) <= 0) goto update; break; #endif default: return false; } if (!timer_pending(own_timer) && !timer_pending(other_timer)) goto update; return false; update: br_multicast_update_querier(brmctx, querier, port_ifidx, saddr); return true; } static struct net_bridge_port * __br_multicast_get_querier_port(struct net_bridge *br, const struct bridge_mcast_querier *querier) { int port_ifidx = READ_ONCE(querier->port_ifidx); struct net_bridge_port *p; struct net_device *dev; if (port_ifidx == 0) return NULL; dev = dev_get_by_index_rcu(dev_net(br->dev), port_ifidx); if (!dev) return NULL; p = br_port_get_rtnl_rcu(dev); if (!p || p->br != br) return NULL; return p; } size_t br_multicast_querier_state_size(void) { return nla_total_size(0) + /* nest attribute */ nla_total_size(sizeof(__be32)) + /* BRIDGE_QUERIER_IP_ADDRESS */ nla_total_size(sizeof(int)) + /* BRIDGE_QUERIER_IP_PORT */ nla_total_size_64bit(sizeof(u64)) + /* BRIDGE_QUERIER_IP_OTHER_TIMER */ #if IS_ENABLED(CONFIG_IPV6) nla_total_size(sizeof(struct in6_addr)) + /* BRIDGE_QUERIER_IPV6_ADDRESS */ nla_total_size(sizeof(int)) + /* BRIDGE_QUERIER_IPV6_PORT */ nla_total_size_64bit(sizeof(u64)) + /* BRIDGE_QUERIER_IPV6_OTHER_TIMER */ #endif 0; } /* protected by rtnl or rcu */ int br_multicast_dump_querier_state(struct sk_buff *skb, const struct net_bridge_mcast *brmctx, int nest_attr) { struct bridge_mcast_querier querier = {}; struct net_bridge_port *p; struct nlattr *nest; if (!br_opt_get(brmctx->br, BROPT_MULTICAST_ENABLED) || br_multicast_ctx_vlan_global_disabled(brmctx)) return 0; nest = nla_nest_start(skb, nest_attr); if (!nest) return -EMSGSIZE; rcu_read_lock(); if (!brmctx->multicast_querier && !timer_pending(&brmctx->ip4_other_query.timer)) goto out_v6; br_multicast_read_querier(&brmctx->ip4_querier, &querier); if (nla_put_in_addr(skb, BRIDGE_QUERIER_IP_ADDRESS, querier.addr.src.ip4)) { rcu_read_unlock(); goto out_err; } p = __br_multicast_get_querier_port(brmctx->br, &querier); if (timer_pending(&brmctx->ip4_other_query.timer) && (nla_put_u64_64bit(skb, BRIDGE_QUERIER_IP_OTHER_TIMER, br_timer_value(&brmctx->ip4_other_query.timer), BRIDGE_QUERIER_PAD) || (p && nla_put_u32(skb, BRIDGE_QUERIER_IP_PORT, p->dev->ifindex)))) { rcu_read_unlock(); goto out_err; } out_v6: #if IS_ENABLED(CONFIG_IPV6) if (!brmctx->multicast_querier && !timer_pending(&brmctx->ip6_other_query.timer)) goto out; br_multicast_read_querier(&brmctx->ip6_querier, &querier); if (nla_put_in6_addr(skb, BRIDGE_QUERIER_IPV6_ADDRESS, &querier.addr.src.ip6)) { rcu_read_unlock(); goto out_err; } p = __br_multicast_get_querier_port(brmctx->br, &querier); if (timer_pending(&brmctx->ip6_other_query.timer) && (nla_put_u64_64bit(skb, BRIDGE_QUERIER_IPV6_OTHER_TIMER, br_timer_value(&brmctx->ip6_other_query.timer), BRIDGE_QUERIER_PAD) || (p && nla_put_u32(skb, BRIDGE_QUERIER_IPV6_PORT, p->dev->ifindex)))) { rcu_read_unlock(); goto out_err; } out: #endif rcu_read_unlock(); nla_nest_end(skb, nest); if (!nla_len(nest)) nla_nest_cancel(skb, nest); return 0; out_err: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static void br_multicast_update_query_timer(struct net_bridge_mcast *brmctx, struct bridge_mcast_other_query *query, unsigned long max_delay) { if (!timer_pending(&query->timer)) mod_timer(&query->delay_timer, jiffies + max_delay); mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval); } static void br_port_mc_router_state_change(struct net_bridge_port *p, bool is_mc_router) { struct switchdev_attr attr = { .orig_dev = p->dev, .id = SWITCHDEV_ATTR_ID_PORT_MROUTER, .flags = SWITCHDEV_F_DEFER, .u.mrouter = is_mc_router, }; switchdev_port_attr_set(p->dev, &attr, NULL); } static struct net_bridge_port * br_multicast_rport_from_node(struct net_bridge_mcast *brmctx, struct hlist_head *mc_router_list, struct hlist_node *rlist) { struct net_bridge_mcast_port *pmctx; #if IS_ENABLED(CONFIG_IPV6) if (mc_router_list == &brmctx->ip6_mc_router_list) pmctx = hlist_entry(rlist, struct net_bridge_mcast_port, ip6_rlist); else #endif pmctx = hlist_entry(rlist, struct net_bridge_mcast_port, ip4_rlist); return pmctx->port; } static struct hlist_node * br_multicast_get_rport_slot(struct net_bridge_mcast *brmctx, struct net_bridge_port *port, struct hlist_head *mc_router_list) { struct hlist_node *slot = NULL; struct net_bridge_port *p; struct hlist_node *rlist; hlist_for_each(rlist, mc_router_list) { p = br_multicast_rport_from_node(brmctx, mc_router_list, rlist); if ((unsigned long)port >= (unsigned long)p) break; slot = rlist; } return slot; } static bool br_multicast_no_router_otherpf(struct net_bridge_mcast_port *pmctx, struct hlist_node *rnode) { #if IS_ENABLED(CONFIG_IPV6) if (rnode != &pmctx->ip6_rlist) return hlist_unhashed(&pmctx->ip6_rlist); else return hlist_unhashed(&pmctx->ip4_rlist); #else return true; #endif } /* Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ static void br_multicast_add_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct hlist_node *rlist, struct hlist_head *mc_router_list) { struct hlist_node *slot; if (!hlist_unhashed(rlist)) return; slot = br_multicast_get_rport_slot(brmctx, pmctx->port, mc_router_list); if (slot) hlist_add_behind_rcu(rlist, slot); else hlist_add_head_rcu(rlist, mc_router_list); /* For backwards compatibility for now, only notify if we * switched from no IPv4/IPv6 multicast router to a new * IPv4 or IPv6 multicast router. */ if (br_multicast_no_router_otherpf(pmctx, rlist)) { br_rtr_notify(pmctx->port->br->dev, pmctx, RTM_NEWMDB); br_port_mc_router_state_change(pmctx->port, true); } } /* Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ static void br_ip4_multicast_add_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx) { br_multicast_add_router(brmctx, pmctx, &pmctx->ip4_rlist, &brmctx->ip4_mc_router_list); } /* Add port to router_list * list is maintained ordered by pointer value * and locked by br->multicast_lock and RCU */ static void br_ip6_multicast_add_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx) { #if IS_ENABLED(CONFIG_IPV6) br_multicast_add_router(brmctx, pmctx, &pmctx->ip6_rlist, &brmctx->ip6_mc_router_list); #endif } static void br_multicast_mark_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct timer_list *timer, struct hlist_node *rlist, struct hlist_head *mc_router_list) { unsigned long now = jiffies; if (!br_multicast_ctx_should_use(brmctx, pmctx)) return; if (!pmctx) { if (brmctx->multicast_router == MDB_RTR_TYPE_TEMP_QUERY) { if (!br_ip4_multicast_is_router(brmctx) && !br_ip6_multicast_is_router(brmctx)) br_mc_router_state_change(brmctx->br, true); mod_timer(timer, now + brmctx->multicast_querier_interval); } return; } if (pmctx->multicast_router == MDB_RTR_TYPE_DISABLED || pmctx->multicast_router == MDB_RTR_TYPE_PERM) return; br_multicast_add_router(brmctx, pmctx, rlist, mc_router_list); mod_timer(timer, now + brmctx->multicast_querier_interval); } static void br_ip4_multicast_mark_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx) { struct timer_list *timer = &brmctx->ip4_mc_router_timer; struct hlist_node *rlist = NULL; if (pmctx) { timer = &pmctx->ip4_mc_router_timer; rlist = &pmctx->ip4_rlist; } br_multicast_mark_router(brmctx, pmctx, timer, rlist, &brmctx->ip4_mc_router_list); } static void br_ip6_multicast_mark_router(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx) { #if IS_ENABLED(CONFIG_IPV6) struct timer_list *timer = &brmctx->ip6_mc_router_timer; struct hlist_node *rlist = NULL; if (pmctx) { timer = &pmctx->ip6_mc_router_timer; rlist = &pmctx->ip6_rlist; } br_multicast_mark_router(brmctx, pmctx, timer, rlist, &brmctx->ip6_mc_router_list); #endif } static void br_ip4_multicast_query_received(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct bridge_mcast_other_query *query, struct br_ip *saddr, unsigned long max_delay) { if (!br_multicast_select_querier(brmctx, pmctx, saddr)) return; br_multicast_update_query_timer(brmctx, query, max_delay); br_ip4_multicast_mark_router(brmctx, pmctx); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_query_received(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct bridge_mcast_other_query *query, struct br_ip *saddr, unsigned long max_delay) { if (!br_multicast_select_querier(brmctx, pmctx, saddr)) return; br_multicast_update_query_timer(brmctx, query, max_delay); br_ip6_multicast_mark_router(brmctx, pmctx); } #endif static void br_ip4_multicast_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { unsigned int transport_len = ip_transport_len(skb); const struct iphdr *iph = ip_hdr(skb); struct igmphdr *ih = igmp_hdr(skb); struct net_bridge_mdb_entry *mp; struct igmpv3_query *ih3; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; struct br_ip saddr = {}; unsigned long max_delay; unsigned long now = jiffies; __be32 group; spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; group = ih->group; if (transport_len == sizeof(*ih)) { max_delay = ih->code * (HZ / IGMP_TIMER_SCALE); if (!max_delay) { max_delay = 10 * HZ; group = 0; } } else if (transport_len >= sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs || (brmctx->multicast_igmp_version == 3 && group && ih3->suppress)) goto out; max_delay = ih3->code ? IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE) : 1; } else { goto out; } if (!group) { saddr.proto = htons(ETH_P_IP); saddr.src.ip4 = iph->saddr; br_ip4_multicast_query_received(brmctx, pmctx, &brmctx->ip4_other_query, &saddr, max_delay); goto out; } mp = br_mdb_ip4_get(brmctx->br, group, vid); if (!mp) goto out; max_delay *= brmctx->multicast_last_member_count; if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) mod_timer(&mp->timer, now + max_delay); for (pp = &mp->ports; (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0 && (brmctx->multicast_igmp_version == 2 || p->filter_mode == MCAST_EXCLUDE)) mod_timer(&p->timer, now + max_delay); } out: spin_unlock(&brmctx->br->multicast_lock); } #if IS_ENABLED(CONFIG_IPV6) static int br_ip6_multicast_query(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { unsigned int transport_len = ipv6_transport_len(skb); struct mld_msg *mld; struct net_bridge_mdb_entry *mp; struct mld2_query *mld2q; struct net_bridge_port_group *p; struct net_bridge_port_group __rcu **pp; struct br_ip saddr = {}; unsigned long max_delay; unsigned long now = jiffies; unsigned int offset = skb_transport_offset(skb); const struct in6_addr *group = NULL; bool is_general_query; int err = 0; spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; if (transport_len == sizeof(*mld)) { if (!pskb_may_pull(skb, offset + sizeof(*mld))) { err = -EINVAL; goto out; } mld = (struct mld_msg *) icmp6_hdr(skb); max_delay = msecs_to_jiffies(ntohs(mld->mld_maxdelay)); if (max_delay) group = &mld->mld_mca; } else { if (!pskb_may_pull(skb, offset + sizeof(*mld2q))) { err = -EINVAL; goto out; } mld2q = (struct mld2_query *)icmp6_hdr(skb); if (!mld2q->mld2q_nsrcs) group = &mld2q->mld2q_mca; if (brmctx->multicast_mld_version == 2 && !ipv6_addr_any(&mld2q->mld2q_mca) && mld2q->mld2q_suppress) goto out; max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL); } is_general_query = group && ipv6_addr_any(group); if (is_general_query) { saddr.proto = htons(ETH_P_IPV6); saddr.src.ip6 = ipv6_hdr(skb)->saddr; br_ip6_multicast_query_received(brmctx, pmctx, &brmctx->ip6_other_query, &saddr, max_delay); goto out; } else if (!group) { goto out; } mp = br_mdb_ip6_get(brmctx->br, group, vid); if (!mp) goto out; max_delay *= brmctx->multicast_last_member_count; if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, now + max_delay) : try_to_del_timer_sync(&mp->timer) >= 0)) mod_timer(&mp->timer, now + max_delay); for (pp = &mp->ports; (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { if (timer_pending(&p->timer) ? time_after(p->timer.expires, now + max_delay) : try_to_del_timer_sync(&p->timer) >= 0 && (brmctx->multicast_mld_version == 1 || p->filter_mode == MCAST_EXCLUDE)) mod_timer(&p->timer, now + max_delay); } out: spin_unlock(&brmctx->br->multicast_lock); return err; } #endif static void br_multicast_leave_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct br_ip *group, struct bridge_mcast_other_query *other_query, struct bridge_mcast_own_query *own_query, const unsigned char *src) { struct net_bridge_mdb_entry *mp; struct net_bridge_port_group *p; unsigned long now; unsigned long time; spin_lock(&brmctx->br->multicast_lock); if (!br_multicast_ctx_should_use(brmctx, pmctx)) goto out; mp = br_mdb_ip_get(brmctx->br, group); if (!mp) goto out; if (pmctx && (pmctx->port->flags & BR_MULTICAST_FAST_LEAVE)) { struct net_bridge_port_group __rcu **pp; for (pp = &mp->ports; (p = mlock_dereference(*pp, brmctx->br)) != NULL; pp = &p->next) { if (!br_port_group_equal(p, pmctx->port, src)) continue; if (p->flags & MDB_PG_FLAGS_PERMANENT) break; p->flags |= MDB_PG_FLAGS_FAST_LEAVE; br_multicast_del_pg(mp, p, pp); } goto out; } if (timer_pending(&other_query->timer)) goto out; if (brmctx->multicast_querier) { __br_multicast_send_query(brmctx, pmctx, NULL, NULL, &mp->addr, false, 0, NULL); time = jiffies + brmctx->multicast_last_member_count * brmctx->multicast_last_member_interval; mod_timer(&own_query->timer, time); for (p = mlock_dereference(mp->ports, brmctx->br); p != NULL && pmctx != NULL; p = mlock_dereference(p->next, brmctx->br)) { if (!br_port_group_equal(p, pmctx->port, src)) continue; if (!hlist_unhashed(&p->mglist) && (timer_pending(&p->timer) ? time_after(p->timer.expires, time) : try_to_del_timer_sync(&p->timer) >= 0)) { mod_timer(&p->timer, time); } break; } } now = jiffies; time = now + brmctx->multicast_last_member_count * brmctx->multicast_last_member_interval; if (!pmctx) { if (mp->host_joined && (timer_pending(&mp->timer) ? time_after(mp->timer.expires, time) : try_to_del_timer_sync(&mp->timer) >= 0)) { mod_timer(&mp->timer, time); } goto out; } for (p = mlock_dereference(mp->ports, brmctx->br); p != NULL; p = mlock_dereference(p->next, brmctx->br)) { if (p->key.port != pmctx->port) continue; if (!hlist_unhashed(&p->mglist) && (timer_pending(&p->timer) ? time_after(p->timer.expires, time) : try_to_del_timer_sync(&p->timer) >= 0)) { mod_timer(&p->timer, time); } break; } out: spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_leave_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, __be32 group, __u16 vid, const unsigned char *src) { struct br_ip br_group; struct bridge_mcast_own_query *own_query; if (ipv4_is_local_multicast(group)) return; own_query = pmctx ? &pmctx->ip4_own_query : &brmctx->ip4_own_query; memset(&br_group, 0, sizeof(br_group)); br_group.dst.ip4 = group; br_group.proto = htons(ETH_P_IP); br_group.vid = vid; br_multicast_leave_group(brmctx, pmctx, &br_group, &brmctx->ip4_other_query, own_query, src); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_group(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, const struct in6_addr *group, __u16 vid, const unsigned char *src) { struct br_ip br_group; struct bridge_mcast_own_query *own_query; if (ipv6_addr_is_ll_all_nodes(group)) return; own_query = pmctx ? &pmctx->ip6_own_query : &brmctx->ip6_own_query; memset(&br_group, 0, sizeof(br_group)); br_group.dst.ip6 = *group; br_group.proto = htons(ETH_P_IPV6); br_group.vid = vid; br_multicast_leave_group(brmctx, pmctx, &br_group, &brmctx->ip6_other_query, own_query, src); } #endif static void br_multicast_err_count(const struct net_bridge *br, const struct net_bridge_port *p, __be16 proto) { struct bridge_mcast_stats __percpu *stats; struct bridge_mcast_stats *pstats; if (!br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) return; if (p) stats = p->mcast_stats; else stats = br->mcast_stats; if (WARN_ON(!stats)) return; pstats = this_cpu_ptr(stats); u64_stats_update_begin(&pstats->syncp); switch (proto) { case htons(ETH_P_IP): pstats->mstats.igmp_parse_errors++; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): pstats->mstats.mld_parse_errors++; break; #endif } u64_stats_update_end(&pstats->syncp); } static void br_multicast_pim(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, const struct sk_buff *skb) { unsigned int offset = skb_transport_offset(skb); struct pimhdr *pimhdr, _pimhdr; pimhdr = skb_header_pointer(skb, offset, sizeof(_pimhdr), &_pimhdr); if (!pimhdr || pim_hdr_version(pimhdr) != PIM_VERSION || pim_hdr_type(pimhdr) != PIM_TYPE_HELLO) return; spin_lock(&brmctx->br->multicast_lock); br_ip4_multicast_mark_router(brmctx, pmctx); spin_unlock(&brmctx->br->multicast_lock); } static int br_ip4_multicast_mrd_rcv(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb) { if (ip_hdr(skb)->protocol != IPPROTO_IGMP || igmp_hdr(skb)->type != IGMP_MRDISC_ADV) return -ENOMSG; spin_lock(&brmctx->br->multicast_lock); br_ip4_multicast_mark_router(brmctx, pmctx); spin_unlock(&brmctx->br->multicast_lock); return 0; } static int br_multicast_ipv4_rcv(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { struct net_bridge_port *p = pmctx ? pmctx->port : NULL; const unsigned char *src; struct igmphdr *ih; int err; err = ip_mc_check_igmp(skb); if (err == -ENOMSG) { if (!ipv4_is_local_multicast(ip_hdr(skb)->daddr)) { BR_INPUT_SKB_CB(skb)->mrouters_only = 1; } else if (pim_ipv4_all_pim_routers(ip_hdr(skb)->daddr)) { if (ip_hdr(skb)->protocol == IPPROTO_PIM) br_multicast_pim(brmctx, pmctx, skb); } else if (ipv4_is_all_snoopers(ip_hdr(skb)->daddr)) { br_ip4_multicast_mrd_rcv(brmctx, pmctx, skb); } return 0; } else if (err < 0) { br_multicast_err_count(brmctx->br, p, skb->protocol); return err; } ih = igmp_hdr(skb); src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->igmp = ih->type; switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip4_multicast_add_group(brmctx, pmctx, ih->group, vid, src, true); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: err = br_ip4_multicast_igmp3_report(brmctx, pmctx, skb, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: br_ip4_multicast_query(brmctx, pmctx, skb, vid); break; case IGMP_HOST_LEAVE_MESSAGE: br_ip4_multicast_leave_group(brmctx, pmctx, ih->group, vid, src); break; } br_multicast_count(brmctx->br, p, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); return err; } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_mrd_rcv(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb) { if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) return; spin_lock(&brmctx->br->multicast_lock); br_ip6_multicast_mark_router(brmctx, pmctx); spin_unlock(&brmctx->br->multicast_lock); } static int br_multicast_ipv6_rcv(struct net_bridge_mcast *brmctx, struct net_bridge_mcast_port *pmctx, struct sk_buff *skb, u16 vid) { struct net_bridge_port *p = pmctx ? pmctx->port : NULL; const unsigned char *src; struct mld_msg *mld; int err; err = ipv6_mc_check_mld(skb); if (err == -ENOMSG || err == -ENODATA) { if (!ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) BR_INPUT_SKB_CB(skb)->mrouters_only = 1; if (err == -ENODATA && ipv6_addr_is_all_snoopers(&ipv6_hdr(skb)->daddr)) br_ip6_multicast_mrd_rcv(brmctx, pmctx, skb); return 0; } else if (err < 0) { br_multicast_err_count(brmctx->br, p, skb->protocol); return err; } mld = (struct mld_msg *)skb_transport_header(skb); BR_INPUT_SKB_CB(skb)->igmp = mld->mld_type; switch (mld->mld_type) { case ICMPV6_MGM_REPORT: src = eth_hdr(skb)->h_source; BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip6_multicast_add_group(brmctx, pmctx, &mld->mld_mca, vid, src, true); break; case ICMPV6_MLD2_REPORT: err = br_ip6_multicast_mld2_report(brmctx, pmctx, skb, vid); break; case ICMPV6_MGM_QUERY: err = br_ip6_multicast_query(brmctx, pmctx, skb, vid); break; case ICMPV6_MGM_REDUCTION: src = eth_hdr(skb)->h_source; br_ip6_multicast_leave_group(brmctx, pmctx, &mld->mld_mca, vid, src); break; } br_multicast_count(brmctx->br, p, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); return err; } #endif int br_multicast_rcv(struct net_bridge_mcast **brmctx, struct net_bridge_mcast_port **pmctx, struct net_bridge_vlan *vlan, struct sk_buff *skb, u16 vid) { int ret = 0; BR_INPUT_SKB_CB(skb)->igmp = 0; BR_INPUT_SKB_CB(skb)->mrouters_only = 0; if (!br_opt_get((*brmctx)->br, BROPT_MULTICAST_ENABLED)) return 0; if (br_opt_get((*brmctx)->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) && vlan) { const struct net_bridge_vlan *masterv; /* the vlan has the master flag set only when transmitting * through the bridge device */ if (br_vlan_is_master(vlan)) { masterv = vlan; *brmctx = &vlan->br_mcast_ctx; *pmctx = NULL; } else { masterv = vlan->brvlan; *brmctx = &vlan->brvlan->br_mcast_ctx; *pmctx = &vlan->port_mcast_ctx; } if (!(masterv->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED)) return 0; } switch (skb->protocol) { case htons(ETH_P_IP): ret = br_multicast_ipv4_rcv(*brmctx, *pmctx, skb, vid); break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): ret = br_multicast_ipv6_rcv(*brmctx, *pmctx, skb, vid); break; #endif } return ret; } static void br_multicast_query_expired(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query, struct bridge_mcast_querier *querier) { spin_lock(&brmctx->br->multicast_lock); if (br_multicast_ctx_vlan_disabled(brmctx)) goto out; if (query->startup_sent < brmctx->multicast_startup_query_count) query->startup_sent++; br_multicast_send_query(brmctx, NULL, query); out: spin_unlock(&brmctx->br->multicast_lock); } static void br_ip4_multicast_query_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = from_timer(brmctx, t, ip4_own_query.timer); br_multicast_query_expired(brmctx, &brmctx->ip4_own_query, &brmctx->ip4_querier); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_query_expired(struct timer_list *t) { struct net_bridge_mcast *brmctx = from_timer(brmctx, t, ip6_own_query.timer); br_multicast_query_expired(brmctx, &brmctx->ip6_own_query, &brmctx->ip6_querier); } #endif static void br_multicast_gc_work(struct work_struct *work) { struct net_bridge *br = container_of(work, struct net_bridge, mcast_gc_work); HLIST_HEAD(deleted_head); spin_lock_bh(&br->multicast_lock); hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); br_multicast_gc(&deleted_head); } void br_multicast_ctx_init(struct net_bridge *br, struct net_bridge_vlan *vlan, struct net_bridge_mcast *brmctx) { brmctx->br = br; brmctx->vlan = vlan; brmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; brmctx->multicast_last_member_count = 2; brmctx->multicast_startup_query_count = 2; brmctx->multicast_last_member_interval = HZ; brmctx->multicast_query_response_interval = 10 * HZ; brmctx->multicast_startup_query_interval = 125 * HZ / 4; brmctx->multicast_query_interval = 125 * HZ; brmctx->multicast_querier_interval = 255 * HZ; brmctx->multicast_membership_interval = 260 * HZ; brmctx->ip4_querier.port_ifidx = 0; seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock); brmctx->multicast_igmp_version = 2; #if IS_ENABLED(CONFIG_IPV6) brmctx->multicast_mld_version = 1; brmctx->ip6_querier.port_ifidx = 0; seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock); #endif timer_setup(&brmctx->ip4_mc_router_timer, br_ip4_multicast_local_router_expired, 0); timer_setup(&brmctx->ip4_other_query.timer, br_ip4_multicast_querier_expired, 0); timer_setup(&brmctx->ip4_other_query.delay_timer, br_multicast_query_delay_expired, 0); timer_setup(&brmctx->ip4_own_query.timer, br_ip4_multicast_query_expired, 0); #if IS_ENABLED(CONFIG_IPV6) timer_setup(&brmctx->ip6_mc_router_timer, br_ip6_multicast_local_router_expired, 0); timer_setup(&brmctx->ip6_other_query.timer, br_ip6_multicast_querier_expired, 0); timer_setup(&brmctx->ip6_other_query.delay_timer, br_multicast_query_delay_expired, 0); timer_setup(&brmctx->ip6_own_query.timer, br_ip6_multicast_query_expired, 0); #endif } void br_multicast_ctx_deinit(struct net_bridge_mcast *brmctx) { __br_multicast_stop(brmctx); } void br_multicast_init(struct net_bridge *br) { br->hash_max = BR_MULTICAST_DEFAULT_HASH_MAX; br_multicast_ctx_init(br, NULL, &br->multicast_ctx); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, true); br_opt_toggle(br, BROPT_HAS_IPV6_ADDR, true); spin_lock_init(&br->multicast_lock); INIT_HLIST_HEAD(&br->mdb_list); INIT_HLIST_HEAD(&br->mcast_gc_list); INIT_WORK(&br->mcast_gc_work, br_multicast_gc_work); } static void br_ip4_multicast_join_snoopers(struct net_bridge *br) { struct in_device *in_dev = in_dev_get(br->dev); if (!in_dev) return; __ip_mc_inc_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP), GFP_ATOMIC); in_dev_put(in_dev); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_join_snoopers(struct net_bridge *br) { struct in6_addr addr; ipv6_addr_set(&addr, htonl(0xff020000), 0, 0, htonl(0x6a)); ipv6_dev_mc_inc(br->dev, &addr); } #else static inline void br_ip6_multicast_join_snoopers(struct net_bridge *br) { } #endif void br_multicast_join_snoopers(struct net_bridge *br) { br_ip4_multicast_join_snoopers(br); br_ip6_multicast_join_snoopers(br); } static void br_ip4_multicast_leave_snoopers(struct net_bridge *br) { struct in_device *in_dev = in_dev_get(br->dev); if (WARN_ON(!in_dev)) return; __ip_mc_dec_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP), GFP_ATOMIC); in_dev_put(in_dev); } #if IS_ENABLED(CONFIG_IPV6) static void br_ip6_multicast_leave_snoopers(struct net_bridge *br) { struct in6_addr addr; ipv6_addr_set(&addr, htonl(0xff020000), 0, 0, htonl(0x6a)); ipv6_dev_mc_dec(br->dev, &addr); } #else static inline void br_ip6_multicast_leave_snoopers(struct net_bridge *br) { } #endif void br_multicast_leave_snoopers(struct net_bridge *br) { br_ip4_multicast_leave_snoopers(br); br_ip6_multicast_leave_snoopers(br); } static void __br_multicast_open_query(struct net_bridge *br, struct bridge_mcast_own_query *query) { query->startup_sent = 0; if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) return; mod_timer(&query->timer, jiffies); } static void __br_multicast_open(struct net_bridge_mcast *brmctx) { __br_multicast_open_query(brmctx->br, &brmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) __br_multicast_open_query(brmctx->br, &brmctx->ip6_own_query); #endif } void br_multicast_open(struct net_bridge *br) { ASSERT_RTNL(); if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; vg = br_vlan_group(br); if (vg) { list_for_each_entry(vlan, &vg->vlan_list, vlist) { struct net_bridge_mcast *brmctx; brmctx = &vlan->br_mcast_ctx; if (br_vlan_is_brentry(vlan) && !br_multicast_ctx_vlan_disabled(brmctx)) __br_multicast_open(&vlan->br_mcast_ctx); } } } else { __br_multicast_open(&br->multicast_ctx); } } static void __br_multicast_stop(struct net_bridge_mcast *brmctx) { del_timer_sync(&brmctx->ip4_mc_router_timer); del_timer_sync(&brmctx->ip4_other_query.timer); del_timer_sync(&brmctx->ip4_other_query.delay_timer); del_timer_sync(&brmctx->ip4_own_query.timer); #if IS_ENABLED(CONFIG_IPV6) del_timer_sync(&brmctx->ip6_mc_router_timer); del_timer_sync(&brmctx->ip6_other_query.timer); del_timer_sync(&brmctx->ip6_other_query.delay_timer); del_timer_sync(&brmctx->ip6_own_query.timer); #endif } void br_multicast_toggle_one_vlan(struct net_bridge_vlan *vlan, bool on) { struct net_bridge *br; /* it's okay to check for the flag without the multicast lock because it * can only change under RTNL -> multicast_lock, we need the latter to * sync with timers and packets */ if (on == !!(vlan->priv_flags & BR_VLFLAG_MCAST_ENABLED)) return; if (br_vlan_is_master(vlan)) { br = vlan->br; if (!br_vlan_is_brentry(vlan) || (on && br_multicast_ctx_vlan_global_disabled(&vlan->br_mcast_ctx))) return; spin_lock_bh(&br->multicast_lock); vlan->priv_flags ^= BR_VLFLAG_MCAST_ENABLED; spin_unlock_bh(&br->multicast_lock); if (on) __br_multicast_open(&vlan->br_mcast_ctx); else __br_multicast_stop(&vlan->br_mcast_ctx); } else { struct net_bridge_mcast *brmctx; brmctx = br_multicast_port_ctx_get_global(&vlan->port_mcast_ctx); if (on && br_multicast_ctx_vlan_global_disabled(brmctx)) return; br = vlan->port->br; spin_lock_bh(&br->multicast_lock); vlan->priv_flags ^= BR_VLFLAG_MCAST_ENABLED; if (on) __br_multicast_enable_port_ctx(&vlan->port_mcast_ctx); else __br_multicast_disable_port_ctx(&vlan->port_mcast_ctx); spin_unlock_bh(&br->multicast_lock); } } static void br_multicast_toggle_vlan(struct net_bridge_vlan *vlan, bool on) { struct net_bridge_port *p; if (WARN_ON_ONCE(!br_vlan_is_master(vlan))) return; list_for_each_entry(p, &vlan->br->port_list, list) { struct net_bridge_vlan *vport; vport = br_vlan_find(nbp_vlan_group(p), vlan->vid); if (!vport) continue; br_multicast_toggle_one_vlan(vport, on); } if (br_vlan_is_brentry(vlan)) br_multicast_toggle_one_vlan(vlan, on); } int br_multicast_toggle_vlan_snooping(struct net_bridge *br, bool on, struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; struct net_bridge_port *p; if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED) == on) return 0; if (on && !br_opt_get(br, BROPT_VLAN_ENABLED)) { NL_SET_ERR_MSG_MOD(extack, "Cannot enable multicast vlan snooping with vlan filtering disabled"); return -EINVAL; } vg = br_vlan_group(br); if (!vg) return 0; br_opt_toggle(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED, on); /* disable/enable non-vlan mcast contexts based on vlan snooping */ if (on) __br_multicast_stop(&br->multicast_ctx); else __br_multicast_open(&br->multicast_ctx); list_for_each_entry(p, &br->port_list, list) { if (on) br_multicast_disable_port(p); else br_multicast_enable_port(p); } list_for_each_entry(vlan, &vg->vlan_list, vlist) br_multicast_toggle_vlan(vlan, on); return 0; } bool br_multicast_toggle_global_vlan(struct net_bridge_vlan *vlan, bool on) { ASSERT_RTNL(); /* BR_VLFLAG_GLOBAL_MCAST_ENABLED relies on eventual consistency and * requires only RTNL to change */ if (on == !!(vlan->priv_flags & BR_VLFLAG_GLOBAL_MCAST_ENABLED)) return false; vlan->priv_flags ^= BR_VLFLAG_GLOBAL_MCAST_ENABLED; br_multicast_toggle_vlan(vlan, on); return true; } void br_multicast_stop(struct net_bridge *br) { ASSERT_RTNL(); if (br_opt_get(br, BROPT_MCAST_VLAN_SNOOPING_ENABLED)) { struct net_bridge_vlan_group *vg; struct net_bridge_vlan *vlan; vg = br_vlan_group(br); if (vg) { list_for_each_entry(vlan, &vg->vlan_list, vlist) { struct net_bridge_mcast *brmctx; brmctx = &vlan->br_mcast_ctx; if (br_vlan_is_brentry(vlan) && !br_multicast_ctx_vlan_disabled(brmctx)) __br_multicast_stop(&vlan->br_mcast_ctx); } } } else { __br_multicast_stop(&br->multicast_ctx); } } void br_multicast_dev_del(struct net_bridge *br) { struct net_bridge_mdb_entry *mp; HLIST_HEAD(deleted_head); struct hlist_node *tmp; spin_lock_bh(&br->multicast_lock); hlist_for_each_entry_safe(mp, tmp, &br->mdb_list, mdb_node) br_multicast_del_mdb_entry(mp); hlist_move_list(&br->mcast_gc_list, &deleted_head); spin_unlock_bh(&br->multicast_lock); br_multicast_ctx_deinit(&br->multicast_ctx); br_multicast_gc(&deleted_head); cancel_work_sync(&br->mcast_gc_work); rcu_barrier(); } int br_multicast_set_router(struct net_bridge_mcast *brmctx, unsigned long val) { int err = -EINVAL; spin_lock_bh(&brmctx->br->multicast_lock); switch (val) { case MDB_RTR_TYPE_DISABLED: case MDB_RTR_TYPE_PERM: br_mc_router_state_change(brmctx->br, val == MDB_RTR_TYPE_PERM); del_timer(&brmctx->ip4_mc_router_timer); #if IS_ENABLED(CONFIG_IPV6) del_timer(&brmctx->ip6_mc_router_timer); #endif brmctx->multicast_router = val; err = 0; break; case MDB_RTR_TYPE_TEMP_QUERY: if (brmctx->multicast_router != MDB_RTR_TYPE_TEMP_QUERY) br_mc_router_state_change(brmctx->br, false); brmctx->multicast_router = val; err = 0; break; } spin_unlock_bh(&brmctx->br->multicast_lock); return err; } static void br_multicast_rport_del_notify(struct net_bridge_mcast_port *pmctx, bool deleted) { if (!deleted) return; /* For backwards compatibility for now, only notify if there is * no multicast router anymore for both IPv4 and IPv6. */ if (!hlist_unhashed(&pmctx->ip4_rlist)) return; #if IS_ENABLED(CONFIG_IPV6) if (!hlist_unhashed(&pmctx->ip6_rlist)) return; #endif br_rtr_notify(pmctx->port->br->dev, pmctx, RTM_DELMDB); br_port_mc_router_state_change(pmctx->port, false); /* don't allow timer refresh */ if (pmctx->multicast_router == MDB_RTR_TYPE_TEMP) pmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; } int br_multicast_set_port_router(struct net_bridge_mcast_port *pmctx, unsigned long val) { struct net_bridge_mcast *brmctx; unsigned long now = jiffies; int err = -EINVAL; bool del = false; brmctx = br_multicast_port_ctx_get_global(pmctx); spin_lock_bh(&brmctx->br->multicast_lock); if (pmctx->multicast_router == val) { /* Refresh the temp router port timer */ if (pmctx->multicast_router == MDB_RTR_TYPE_TEMP) { mod_timer(&pmctx->ip4_mc_router_timer, now + brmctx->multicast_querier_interval); #if IS_ENABLED(CONFIG_IPV6) mod_timer(&pmctx->ip6_mc_router_timer, now + brmctx->multicast_querier_interval); #endif } err = 0; goto unlock; } switch (val) { case MDB_RTR_TYPE_DISABLED: pmctx->multicast_router = MDB_RTR_TYPE_DISABLED; del |= br_ip4_multicast_rport_del(pmctx); del_timer(&pmctx->ip4_mc_router_timer); del |= br_ip6_multicast_rport_del(pmctx); #if IS_ENABLED(CONFIG_IPV6) del_timer(&pmctx->ip6_mc_router_timer); #endif br_multicast_rport_del_notify(pmctx, del); break; case MDB_RTR_TYPE_TEMP_QUERY: pmctx->multicast_router = MDB_RTR_TYPE_TEMP_QUERY; del |= br_ip4_multicast_rport_del(pmctx); del |= br_ip6_multicast_rport_del(pmctx); br_multicast_rport_del_notify(pmctx, del); break; case MDB_RTR_TYPE_PERM: pmctx->multicast_router = MDB_RTR_TYPE_PERM; del_timer(&pmctx->ip4_mc_router_timer); br_ip4_multicast_add_router(brmctx, pmctx); #if IS_ENABLED(CONFIG_IPV6) del_timer(&pmctx->ip6_mc_router_timer); #endif br_ip6_multicast_add_router(brmctx, pmctx); break; case MDB_RTR_TYPE_TEMP: pmctx->multicast_router = MDB_RTR_TYPE_TEMP; br_ip4_multicast_mark_router(brmctx, pmctx); br_ip6_multicast_mark_router(brmctx, pmctx); break; default: goto unlock; } err = 0; unlock: spin_unlock_bh(&brmctx->br->multicast_lock); return err; } int br_multicast_set_vlan_router(struct net_bridge_vlan *v, u8 mcast_router) { int err; if (br_vlan_is_master(v)) err = br_multicast_set_router(&v->br_mcast_ctx, mcast_router); else err = br_multicast_set_port_router(&v->port_mcast_ctx, mcast_router); return err; } static void br_multicast_start_querier(struct net_bridge_mcast *brmctx, struct bridge_mcast_own_query *query) { struct net_bridge_port *port; if (!br_multicast_ctx_matches_vlan_snooping(brmctx)) return; __br_multicast_open_query(brmctx->br, query); rcu_read_lock(); list_for_each_entry_rcu(port, &brmctx->br->port_list, list) { struct bridge_mcast_own_query *ip4_own_query; #if IS_ENABLED(CONFIG_IPV6) struct bridge_mcast_own_query *ip6_own_query; #endif if (br_multicast_port_ctx_state_stopped(&port->multicast_ctx)) continue; if (br_multicast_ctx_is_vlan(brmctx)) { struct net_bridge_vlan *vlan; vlan = br_vlan_find(nbp_vlan_group_rcu(port), brmctx->vlan->vid); if (!vlan || br_multicast_port_ctx_state_stopped(&vlan->port_mcast_ctx)) continue; ip4_own_query = &vlan->port_mcast_ctx.ip4_own_query; #if IS_ENABLED(CONFIG_IPV6) ip6_own_query = &vlan->port_mcast_ctx.ip6_own_query; #endif } else { ip4_own_query = &port->multicast_ctx.ip4_own_query; #if IS_ENABLED(CONFIG_IPV6) ip6_own_query = &port->multicast_ctx.ip6_own_query; #endif } if (query == &brmctx->ip4_own_query) br_multicast_enable(ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) else br_multicast_enable(ip6_own_query); #endif } rcu_read_unlock(); } int br_multicast_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { struct net_bridge_port *port; bool change_snoopers = false; int err = 0; spin_lock_bh(&br->multicast_lock); if (!!br_opt_get(br, BROPT_MULTICAST_ENABLED) == !!val) goto unlock; err = br_mc_disabled_update(br->dev, val, extack); if (err == -EOPNOTSUPP) err = 0; if (err) goto unlock; br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { change_snoopers = true; goto unlock; } if (!netif_running(br->dev)) goto unlock; br_multicast_open(br); list_for_each_entry(port, &br->port_list, list) __br_multicast_enable_port_ctx(&port->multicast_ctx); change_snoopers = true; unlock: spin_unlock_bh(&br->multicast_lock); /* br_multicast_join_snoopers has the potential to cause * an MLD Report/Leave to be delivered to br_multicast_rcv, * which would in turn call br_multicast_add_group, which would * attempt to acquire multicast_lock. This function should be * called after the lock has been released to avoid deadlocks on * multicast_lock. * * br_multicast_leave_snoopers does not have the problem since * br_multicast_rcv first checks BROPT_MULTICAST_ENABLED, and * returns without calling br_multicast_ipv4/6_rcv if it's not * enabled. Moved both functions out just for symmetry. */ if (change_snoopers) { if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) br_multicast_join_snoopers(br); else br_multicast_leave_snoopers(br); } return err; } bool br_multicast_enabled(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); return !!br_opt_get(br, BROPT_MULTICAST_ENABLED); } EXPORT_SYMBOL_GPL(br_multicast_enabled); bool br_multicast_router(const struct net_device *dev) { struct net_bridge *br = netdev_priv(dev); bool is_router; spin_lock_bh(&br->multicast_lock); is_router = br_multicast_is_router(&br->multicast_ctx, NULL); spin_unlock_bh(&br->multicast_lock); return is_router; } EXPORT_SYMBOL_GPL(br_multicast_router); int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val) { unsigned long max_delay; val = !!val; spin_lock_bh(&brmctx->br->multicast_lock); if (brmctx->multicast_querier == val) goto unlock; WRITE_ONCE(brmctx->multicast_querier, val); if (!val) goto unlock; max_delay = brmctx->multicast_query_response_interval; if (!timer_pending(&brmctx->ip4_other_query.timer)) mod_timer(&brmctx->ip4_other_query.delay_timer, jiffies + max_delay); br_multicast_start_querier(brmctx, &brmctx->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) if (!timer_pending(&brmctx->ip6_other_query.timer)) mod_timer(&brmctx->ip6_other_query.delay_timer, jiffies + max_delay); br_multicast_start_querier(brmctx, &brmctx->ip6_own_query); #endif unlock: spin_unlock_bh(&brmctx->br->multicast_lock); return 0; } int br_multicast_set_igmp_version(struct net_bridge_mcast *brmctx, unsigned long val) { /* Currently we support only version 2 and 3 */ switch (val) { case 2: case 3: break; default: return -EINVAL; } spin_lock_bh(&brmctx->br->multicast_lock); brmctx->multicast_igmp_version = val; spin_unlock_bh(&brmctx->br->multicast_lock); return 0; } #if IS_ENABLED(CONFIG_IPV6) int br_multicast_set_mld_version(struct net_bridge_mcast *brmctx, unsigned long val) { /* Currently we support version 1 and 2 */ switch (val) { case 1: case 2: break; default: return -EINVAL; } spin_lock_bh(&brmctx->br->multicast_lock); brmctx->multicast_mld_version = val; spin_unlock_bh(&brmctx->br->multicast_lock); return 0; } #endif void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx, unsigned long val) { unsigned long intvl_jiffies = clock_t_to_jiffies(val); if (intvl_jiffies < BR_MULTICAST_QUERY_INTVL_MIN) { br_info(brmctx->br, "trying to set multicast query interval below minimum, setting to %lu (%ums)\n", jiffies_to_clock_t(BR_MULTICAST_QUERY_INTVL_MIN), jiffies_to_msecs(BR_MULTICAST_QUERY_INTVL_MIN)); intvl_jiffies = BR_MULTICAST_QUERY_INTVL_MIN; } brmctx->multicast_query_interval = intvl_jiffies; } void br_multicast_set_startup_query_intvl(struct net_bridge_mcast *brmctx, unsigned long val) { unsigned long intvl_jiffies = clock_t_to_jiffies(val); if (intvl_jiffies < BR_MULTICAST_STARTUP_QUERY_INTVL_MIN) { br_info(brmctx->br, "trying to set multicast startup query interval below minimum, setting to %lu (%ums)\n", jiffies_to_clock_t(BR_MULTICAST_STARTUP_QUERY_INTVL_MIN), jiffies_to_msecs(BR_MULTICAST_STARTUP_QUERY_INTVL_MIN)); intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MIN; } brmctx->multicast_startup_query_interval = intvl_jiffies; } /** * br_multicast_list_adjacent - Returns snooped multicast addresses * @dev: The bridge port adjacent to which to retrieve addresses * @br_ip_list: The list to store found, snooped multicast IP addresses in * * Creates a list of IP addresses (struct br_ip_list) sensed by the multicast * snooping feature on all bridge ports of dev's bridge device, excluding * the addresses from dev itself. * * Returns the number of items added to br_ip_list. * * Notes: * - br_ip_list needs to be initialized by caller * - br_ip_list might contain duplicates in the end * (needs to be taken care of by caller) * - br_ip_list needs to be freed by caller */ int br_multicast_list_adjacent(struct net_device *dev, struct list_head *br_ip_list) { struct net_bridge *br; struct net_bridge_port *port; struct net_bridge_port_group *group; struct br_ip_list *entry; int count = 0; rcu_read_lock(); if (!br_ip_list || !netif_is_bridge_port(dev)) goto unlock; port = br_port_get_rcu(dev); if (!port || !port->br) goto unlock; br = port->br; list_for_each_entry_rcu(port, &br->port_list, list) { if (!port->dev || port->dev == dev) continue; hlist_for_each_entry_rcu(group, &port->mglist, mglist) { entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) goto unlock; entry->addr = group->key.addr; list_add(&entry->list, br_ip_list); count++; } } unlock: rcu_read_unlock(); return count; } EXPORT_SYMBOL_GPL(br_multicast_list_adjacent); /** * br_multicast_has_querier_anywhere - Checks for a querier on a bridge * @dev: The bridge port providing the bridge on which to check for a querier * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 * * Checks whether the given interface has a bridge on top and if so returns * true if a valid querier exists anywhere on the bridged link layer. * Otherwise returns false. */ bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto) { struct net_bridge *br; struct net_bridge_port *port; struct ethhdr eth; bool ret = false; rcu_read_lock(); if (!netif_is_bridge_port(dev)) goto unlock; port = br_port_get_rcu(dev); if (!port || !port->br) goto unlock; br = port->br; memset(ð, 0, sizeof(eth)); eth.h_proto = htons(proto); ret = br_multicast_querier_exists(&br->multicast_ctx, ð, NULL); unlock: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(br_multicast_has_querier_anywhere); /** * br_multicast_has_querier_adjacent - Checks for a querier behind a bridge port * @dev: The bridge port adjacent to which to check for a querier * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 * * Checks whether the given interface has a bridge on top and if so returns * true if a selected querier is behind one of the other ports of this * bridge. Otherwise returns false. */ bool br_multicast_has_querier_adjacent(struct net_device *dev, int proto) { struct net_bridge_mcast *brmctx; struct net_bridge *br; struct net_bridge_port *port; bool ret = false; int port_ifidx; rcu_read_lock(); if (!netif_is_bridge_port(dev)) goto unlock; port = br_port_get_rcu(dev); if (!port || !port->br) goto unlock; br = port->br; brmctx = &br->multicast_ctx; switch (proto) { case ETH_P_IP: port_ifidx = brmctx->ip4_querier.port_ifidx; if (!timer_pending(&brmctx->ip4_other_query.timer) || port_ifidx == port->dev->ifindex) goto unlock; break; #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: port_ifidx = brmctx->ip6_querier.port_ifidx; if (!timer_pending(&brmctx->ip6_other_query.timer) || port_ifidx == port->dev->ifindex) goto unlock; break; #endif default: goto unlock; } ret = true; unlock: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(br_multicast_has_querier_adjacent); /** * br_multicast_has_router_adjacent - Checks for a router behind a bridge port * @dev: The bridge port adjacent to which to check for a multicast router * @proto: The protocol family to check for: IGMP -> ETH_P_IP, MLD -> ETH_P_IPV6 * * Checks whether the given interface has a bridge on top and if so returns * true if a multicast router is behind one of the other ports of this * bridge. Otherwise returns false. */ bool br_multicast_has_router_adjacent(struct net_device *dev, int proto) { struct net_bridge_mcast_port *pmctx; struct net_bridge_mcast *brmctx; struct net_bridge_port *port; bool ret = false; rcu_read_lock(); port = br_port_get_check_rcu(dev); if (!port) goto unlock; brmctx = &port->br->multicast_ctx; switch (proto) { case ETH_P_IP: hlist_for_each_entry_rcu(pmctx, &brmctx->ip4_mc_router_list, ip4_rlist) { if (pmctx->port == port) continue; ret = true; goto unlock; } break; #if IS_ENABLED(CONFIG_IPV6) case ETH_P_IPV6: hlist_for_each_entry_rcu(pmctx, &brmctx->ip6_mc_router_list, ip6_rlist) { if (pmctx->port == port) continue; ret = true; goto unlock; } break; #endif default: /* when compiled without IPv6 support, be conservative and * always assume presence of an IPv6 multicast router */ ret = true; } unlock: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(br_multicast_has_router_adjacent); static void br_mcast_stats_add(struct bridge_mcast_stats __percpu *stats, const struct sk_buff *skb, u8 type, u8 dir) { struct bridge_mcast_stats *pstats = this_cpu_ptr(stats); __be16 proto = skb->protocol; unsigned int t_len; u64_stats_update_begin(&pstats->syncp); switch (proto) { case htons(ETH_P_IP): t_len = ntohs(ip_hdr(skb)->tot_len) - ip_hdrlen(skb); switch (type) { case IGMP_HOST_MEMBERSHIP_REPORT: pstats->mstats.igmp_v1reports[dir]++; break; case IGMPV2_HOST_MEMBERSHIP_REPORT: pstats->mstats.igmp_v2reports[dir]++; break; case IGMPV3_HOST_MEMBERSHIP_REPORT: pstats->mstats.igmp_v3reports[dir]++; break; case IGMP_HOST_MEMBERSHIP_QUERY: if (t_len != sizeof(struct igmphdr)) { pstats->mstats.igmp_v3queries[dir]++; } else { unsigned int offset = skb_transport_offset(skb); struct igmphdr *ih, _ihdr; ih = skb_header_pointer(skb, offset, sizeof(_ihdr), &_ihdr); if (!ih) break; if (!ih->code) pstats->mstats.igmp_v1queries[dir]++; else pstats->mstats.igmp_v2queries[dir]++; } break; case IGMP_HOST_LEAVE_MESSAGE: pstats->mstats.igmp_leaves[dir]++; break; } break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): t_len = ntohs(ipv6_hdr(skb)->payload_len) + sizeof(struct ipv6hdr); t_len -= skb_network_header_len(skb); switch (type) { case ICMPV6_MGM_REPORT: pstats->mstats.mld_v1reports[dir]++; break; case ICMPV6_MLD2_REPORT: pstats->mstats.mld_v2reports[dir]++; break; case ICMPV6_MGM_QUERY: if (t_len != sizeof(struct mld_msg)) pstats->mstats.mld_v2queries[dir]++; else pstats->mstats.mld_v1queries[dir]++; break; case ICMPV6_MGM_REDUCTION: pstats->mstats.mld_leaves[dir]++; break; } break; #endif /* CONFIG_IPV6 */ } u64_stats_update_end(&pstats->syncp); } void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p, const struct sk_buff *skb, u8 type, u8 dir) { struct bridge_mcast_stats __percpu *stats; /* if multicast_disabled is true then igmp type can't be set */ if (!type || !br_opt_get(br, BROPT_MULTICAST_STATS_ENABLED)) return; if (p) stats = p->mcast_stats; else stats = br->mcast_stats; if (WARN_ON(!stats)) return; br_mcast_stats_add(stats, skb, type, dir); } int br_multicast_init_stats(struct net_bridge *br) { br->mcast_stats = netdev_alloc_pcpu_stats(struct bridge_mcast_stats); if (!br->mcast_stats) return -ENOMEM; return 0; } void br_multicast_uninit_stats(struct net_bridge *br) { free_percpu(br->mcast_stats); } /* noinline for https://llvm.org/pr45802#c9 */ static noinline_for_stack void mcast_stats_add_dir(u64 *dst, u64 *src) { dst[BR_MCAST_DIR_RX] += src[BR_MCAST_DIR_RX]; dst[BR_MCAST_DIR_TX] += src[BR_MCAST_DIR_TX]; } void br_multicast_get_stats(const struct net_bridge *br, const struct net_bridge_port *p, struct br_mcast_stats *dest) { struct bridge_mcast_stats __percpu *stats; struct br_mcast_stats tdst; int i; memset(dest, 0, sizeof(*dest)); if (p) stats = p->mcast_stats; else stats = br->mcast_stats; if (WARN_ON(!stats)) return; memset(&tdst, 0, sizeof(tdst)); for_each_possible_cpu(i) { struct bridge_mcast_stats *cpu_stats = per_cpu_ptr(stats, i); struct br_mcast_stats temp; unsigned int start; do { start = u64_stats_fetch_begin(&cpu_stats->syncp); memcpy(&temp, &cpu_stats->mstats, sizeof(temp)); } while (u64_stats_fetch_retry(&cpu_stats->syncp, start)); mcast_stats_add_dir(tdst.igmp_v1queries, temp.igmp_v1queries); mcast_stats_add_dir(tdst.igmp_v2queries, temp.igmp_v2queries); mcast_stats_add_dir(tdst.igmp_v3queries, temp.igmp_v3queries); mcast_stats_add_dir(tdst.igmp_leaves, temp.igmp_leaves); mcast_stats_add_dir(tdst.igmp_v1reports, temp.igmp_v1reports); mcast_stats_add_dir(tdst.igmp_v2reports, temp.igmp_v2reports); mcast_stats_add_dir(tdst.igmp_v3reports, temp.igmp_v3reports); tdst.igmp_parse_errors += temp.igmp_parse_errors; mcast_stats_add_dir(tdst.mld_v1queries, temp.mld_v1queries); mcast_stats_add_dir(tdst.mld_v2queries, temp.mld_v2queries); mcast_stats_add_dir(tdst.mld_leaves, temp.mld_leaves); mcast_stats_add_dir(tdst.mld_v1reports, temp.mld_v1reports); mcast_stats_add_dir(tdst.mld_v2reports, temp.mld_v2reports); tdst.mld_parse_errors += temp.mld_parse_errors; } memcpy(dest, &tdst, sizeof(*dest)); } int br_mdb_hash_init(struct net_bridge *br) { int err; err = rhashtable_init(&br->sg_port_tbl, &br_sg_port_rht_params); if (err) return err; err = rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params); if (err) { rhashtable_destroy(&br->sg_port_tbl); return err; } return 0; } void br_mdb_hash_fini(struct net_bridge *br) { rhashtable_destroy(&br->sg_port_tbl); rhashtable_destroy(&br->mdb_hash_tbl); } |
| 5 6 2 6 1 5 2 2 2 5 5 9 2 7 6 1 6 5 7 3 3 2 3 3 1 1 3 3 3 8 8 2 1 5 4 1 2 2 1 1 4 2 2 1 1 11 12 2 10 9 2 5 5 5 1 4 3 3 3 2 1 1 5 4 4 1 1 3 1 1 1 2 20 20 1 2 3 1 2 1 1 7 1 1 4 1 2 2 1 1 2 1 1 3 1 1 4 1 1 1 1 16 15 4 1 3 3 1 1 1 2 1 1 4 5 5 1 4 3 1 5 5 5 1 4 2 2 6 6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth SCO sockets. */ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/sched/signal.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/sco.h> static bool disable_esco; static const struct proto_ops sco_sock_ops; static struct bt_sock_list sco_sk_list = { .lock = __RW_LOCK_UNLOCKED(sco_sk_list.lock) }; /* ---- SCO connections ---- */ struct sco_conn { struct hci_conn *hcon; spinlock_t lock; struct sock *sk; struct delayed_work timeout_work; unsigned int mtu; }; #define sco_conn_lock(c) spin_lock(&c->lock) #define sco_conn_unlock(c) spin_unlock(&c->lock) static void sco_sock_close(struct sock *sk); static void sco_sock_kill(struct sock *sk); /* ----- SCO socket info ----- */ #define sco_pi(sk) ((struct sco_pinfo *) sk) struct sco_pinfo { struct bt_sock bt; bdaddr_t src; bdaddr_t dst; __u32 flags; __u16 setting; struct bt_codec codec; struct sco_conn *conn; }; /* ---- SCO timers ---- */ #define SCO_CONN_TIMEOUT (HZ * 40) #define SCO_DISCONN_TIMEOUT (HZ * 2) static void sco_sock_timeout(struct work_struct *work) { struct sco_conn *conn = container_of(work, struct sco_conn, timeout_work.work); struct sock *sk; sco_conn_lock(conn); if (!conn->hcon) { sco_conn_unlock(conn); return; } sk = conn->sk; if (sk) sock_hold(sk); sco_conn_unlock(conn); if (!sk) return; BT_DBG("sock %p state %d", sk, sk->sk_state); lock_sock(sk); sk->sk_err = ETIMEDOUT; sk->sk_state_change(sk); release_sock(sk); sock_put(sk); } static void sco_sock_set_timer(struct sock *sk, long timeout) { if (!sco_pi(sk)->conn) return; BT_DBG("sock %p state %d timeout %ld", sk, sk->sk_state, timeout); cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); schedule_delayed_work(&sco_pi(sk)->conn->timeout_work, timeout); } static void sco_sock_clear_timer(struct sock *sk) { if (!sco_pi(sk)->conn) return; BT_DBG("sock %p state %d", sk, sk->sk_state); cancel_delayed_work(&sco_pi(sk)->conn->timeout_work); } /* ---- SCO connections ---- */ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) { struct sco_conn *conn = hcon->sco_data; if (conn) { if (!conn->hcon) conn->hcon = hcon; return conn; } conn = kzalloc(sizeof(struct sco_conn), GFP_KERNEL); if (!conn) return NULL; spin_lock_init(&conn->lock); INIT_DELAYED_WORK(&conn->timeout_work, sco_sock_timeout); hcon->sco_data = conn; conn->hcon = hcon; conn->mtu = hcon->mtu; if (hcon->mtu > 0) conn->mtu = hcon->mtu; else conn->mtu = 60; BT_DBG("hcon %p conn %p", hcon, conn); return conn; } /* Delete channel. * Must be called on the locked socket. */ static void sco_chan_del(struct sock *sk, int err) { struct sco_conn *conn; conn = sco_pi(sk)->conn; BT_DBG("sk %p, conn %p, err %d", sk, conn, err); if (conn) { sco_conn_lock(conn); conn->sk = NULL; sco_pi(sk)->conn = NULL; sco_conn_unlock(conn); if (conn->hcon) hci_conn_drop(conn->hcon); } sk->sk_state = BT_CLOSED; sk->sk_err = err; sk->sk_state_change(sk); sock_set_flag(sk, SOCK_ZAPPED); } static void sco_conn_del(struct hci_conn *hcon, int err) { struct sco_conn *conn = hcon->sco_data; struct sock *sk; if (!conn) return; BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); /* Kill socket */ sco_conn_lock(conn); sk = conn->sk; if (sk) sock_hold(sk); sco_conn_unlock(conn); if (sk) { lock_sock(sk); sco_sock_clear_timer(sk); sco_chan_del(sk, err); release_sock(sk); sock_put(sk); } /* Ensure no more work items will run before freeing conn. */ cancel_delayed_work_sync(&conn->timeout_work); hcon->sco_data = NULL; kfree(conn); } static void __sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) { BT_DBG("conn %p", conn); sco_pi(sk)->conn = conn; conn->sk = sk; if (parent) bt_accept_enqueue(parent, sk, true); } static int sco_chan_add(struct sco_conn *conn, struct sock *sk, struct sock *parent) { int err = 0; sco_conn_lock(conn); if (conn->sk) err = -EBUSY; else __sco_chan_add(conn, sk, parent); sco_conn_unlock(conn); return err; } static int sco_connect(struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; struct hci_dev *hdev; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) return -EHOSTUNREACH; hci_dev_lock(hdev); if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) { err = -EOPNOTSUPP; goto unlock; } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting, &sco_pi(sk)->codec, sk->sk_sndtimeo); if (IS_ERR(hcon)) { err = PTR_ERR(hcon); goto unlock; } conn = sco_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); err = -ENOMEM; goto unlock; } lock_sock(sk); err = sco_chan_add(conn, sk, NULL); if (err) { release_sock(sk); goto unlock; } /* Update source addr of the socket */ bacpy(&sco_pi(sk)->src, &hcon->src); if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; } else { sk->sk_state = BT_CONNECT; sco_sock_set_timer(sk, sk->sk_sndtimeo); } release_sock(sk); unlock: hci_dev_unlock(hdev); hci_dev_put(hdev); return err; } static int sco_send_frame(struct sock *sk, struct sk_buff *skb) { struct sco_conn *conn = sco_pi(sk)->conn; int len = skb->len; /* Check outgoing MTU */ if (len > conn->mtu) return -EINVAL; BT_DBG("sk %p len %d", sk, len); hci_send_sco(conn->hcon, skb); return len; } static void sco_recv_frame(struct sco_conn *conn, struct sk_buff *skb) { struct sock *sk; sco_conn_lock(conn); sk = conn->sk; sco_conn_unlock(conn); if (!sk) goto drop; BT_DBG("sk %p len %u", sk, skb->len); if (sk->sk_state != BT_CONNECTED) goto drop; if (!sock_queue_rcv_skb(sk, skb)) return; drop: kfree_skb(skb); } /* -------- Socket interface ---------- */ static struct sock *__sco_get_sock_listen_by_addr(bdaddr_t *ba) { struct sock *sk; sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (!bacmp(&sco_pi(sk)->src, ba)) return sk; } return NULL; } /* Find socket listening on source bdaddr. * Returns closest match. */ static struct sock *sco_get_sock_listen(bdaddr_t *src) { struct sock *sk = NULL, *sk1 = NULL; read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; /* Exact match. */ if (!bacmp(&sco_pi(sk)->src, src)) break; /* Closest match */ if (!bacmp(&sco_pi(sk)->src, BDADDR_ANY)) sk1 = sk; } read_unlock(&sco_sk_list.lock); return sk ? sk : sk1; } static void sco_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); } static void sco_sock_cleanup_listen(struct sock *parent) { struct sock *sk; BT_DBG("parent %p", parent); /* Close not yet accepted channels */ while ((sk = bt_accept_dequeue(parent, NULL))) { sco_sock_close(sk); sco_sock_kill(sk); } parent->sk_state = BT_CLOSED; sock_set_flag(parent, SOCK_ZAPPED); } /* Kill socket (only if zapped and orphan) * Must be called on unlocked socket. */ static void sco_sock_kill(struct sock *sk) { if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) return; BT_DBG("sk %p state %d", sk, sk->sk_state); /* Kill poor orphan */ bt_sock_unlink(&sco_sk_list, sk); sock_set_flag(sk, SOCK_DEAD); sock_put(sk); } static void __sco_sock_close(struct sock *sk) { BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket); switch (sk->sk_state) { case BT_LISTEN: sco_sock_cleanup_listen(sk); break; case BT_CONNECTED: case BT_CONFIG: if (sco_pi(sk)->conn->hcon) { sk->sk_state = BT_DISCONN; sco_sock_set_timer(sk, SCO_DISCONN_TIMEOUT); sco_conn_lock(sco_pi(sk)->conn); hci_conn_drop(sco_pi(sk)->conn->hcon); sco_pi(sk)->conn->hcon = NULL; sco_conn_unlock(sco_pi(sk)->conn); } else sco_chan_del(sk, ECONNRESET); break; case BT_CONNECT2: case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); break; default: sock_set_flag(sk, SOCK_ZAPPED); break; } } /* Must be called on unlocked socket. */ static void sco_sock_close(struct sock *sk) { lock_sock(sk); sco_sock_clear_timer(sk); __sco_sock_close(sk); release_sock(sk); } static void sco_sock_init(struct sock *sk, struct sock *parent) { BT_DBG("sk %p", sk); if (parent) { sk->sk_type = parent->sk_type; bt_sk(sk)->flags = bt_sk(parent)->flags; security_sk_clone(parent, sk); } } static struct proto sco_proto = { .name = "SCO", .owner = THIS_MODULE, .obj_size = sizeof(struct sco_pinfo) }; static struct sock *sco_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern) { struct sock *sk; sk = bt_sock_alloc(net, sock, &sco_proto, proto, prio, kern); if (!sk) return NULL; sk->sk_destruct = sco_sock_destruct; sk->sk_sndtimeo = SCO_CONN_TIMEOUT; sco_pi(sk)->setting = BT_VOICE_CVSD_16BIT; sco_pi(sk)->codec.id = BT_CODEC_CVSD; sco_pi(sk)->codec.cid = 0xffff; sco_pi(sk)->codec.vid = 0xffff; sco_pi(sk)->codec.data_path = 0x00; bt_sock_link(&sco_sk_list, sk); return sk; } static int sco_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; BT_DBG("sock %p", sock); sock->state = SS_UNCONNECTED; if (sock->type != SOCK_SEQPACKET) return -ESOCKTNOSUPPORT; sock->ops = &sco_sock_ops; sk = sco_sock_alloc(net, sock, protocol, GFP_ATOMIC, kern); if (!sk) return -ENOMEM; sco_sock_init(sk, NULL); return 0; } static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; int err = 0; if (!addr || addr_len < sizeof(struct sockaddr_sco) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; BT_DBG("sk %p %pMR", sk, &sa->sco_bdaddr); lock_sock(sk); if (sk->sk_state != BT_OPEN) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } bacpy(&sco_pi(sk)->src, &sa->sco_bdaddr); sk->sk_state = BT_BOUND; done: release_sock(sk); return err; } static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; int err; BT_DBG("sk %p", sk); if (alen < sizeof(struct sockaddr_sco) || addr->sa_family != AF_BLUETOOTH) return -EINVAL; if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) return -EBADFD; if (sk->sk_type != SOCK_SEQPACKET) err = -EINVAL; lock_sock(sk); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); release_sock(sk); err = sco_connect(sk); if (err) return err; lock_sock(sk); err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); release_sock(sk); return err; } static int sco_sock_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; bdaddr_t *src = &sco_pi(sk)->src; int err = 0; BT_DBG("sk %p backlog %d", sk, backlog); lock_sock(sk); if (sk->sk_state != BT_BOUND) { err = -EBADFD; goto done; } if (sk->sk_type != SOCK_SEQPACKET) { err = -EINVAL; goto done; } write_lock(&sco_sk_list.lock); if (__sco_get_sock_listen_by_addr(src)) { err = -EADDRINUSE; goto unlock; } sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; sk->sk_state = BT_LISTEN; unlock: write_unlock(&sco_sk_list.lock); done: release_sock(sk); return err; } static int sco_sock_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct sock *sk = sock->sk, *ch; long timeo; int err = 0; lock_sock(sk); timeo = sock_rcvtimeo(sk, arg->flags & O_NONBLOCK); BT_DBG("sk %p timeo %ld", sk, timeo); /* Wait for an incoming connection. (wake-one). */ add_wait_queue_exclusive(sk_sleep(sk), &wait); while (1) { if (sk->sk_state != BT_LISTEN) { err = -EBADFD; break; } ch = bt_accept_dequeue(sk, newsock); if (ch) break; if (!timeo) { err = -EAGAIN; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo); lock_sock(sk); } remove_wait_queue(sk_sleep(sk), &wait); if (err) goto done; newsock->state = SS_CONNECTED; BT_DBG("new socket %p", ch); done: release_sock(sk); return err; } static int sco_sock_getname(struct socket *sock, struct sockaddr *addr, int peer) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; BT_DBG("sock %p, sk %p", sock, sk); addr->sa_family = AF_BLUETOOTH; if (peer) bacpy(&sa->sco_bdaddr, &sco_pi(sk)->dst); else bacpy(&sa->sco_bdaddr, &sco_pi(sk)->src); return sizeof(struct sockaddr_sco); } static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct sk_buff *skb; int err; BT_DBG("sock %p, sk %p", sock, sk); err = sock_error(sk); if (err) return err; if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; skb = bt_skb_sendmsg(sk, msg, len, len, 0, 0); if (IS_ERR(skb)) return PTR_ERR(skb); lock_sock(sk); if (sk->sk_state == BT_CONNECTED) err = sco_send_frame(sk, skb); else err = -ENOTCONN; release_sock(sk); if (err < 0) kfree_skb(skb); return err; } static void sco_conn_defer_accept(struct hci_conn *conn, u16 setting) { struct hci_dev *hdev = conn->hdev; BT_DBG("conn %p", conn); conn->state = BT_CONFIG; if (!lmp_esco_capable(hdev)) { struct hci_cp_accept_conn_req cp; bacpy(&cp.bdaddr, &conn->dst); cp.role = 0x00; /* Ignored */ hci_send_cmd(hdev, HCI_OP_ACCEPT_CONN_REQ, sizeof(cp), &cp); } else { struct hci_cp_accept_sync_conn_req cp; bacpy(&cp.bdaddr, &conn->dst); cp.pkt_type = cpu_to_le16(conn->pkt_type); cp.tx_bandwidth = cpu_to_le32(0x00001f40); cp.rx_bandwidth = cpu_to_le32(0x00001f40); cp.content_format = cpu_to_le16(setting); switch (setting & SCO_AIRMODE_MASK) { case SCO_AIRMODE_TRANSP: if (conn->pkt_type & ESCO_2EV3) cp.max_latency = cpu_to_le16(0x0008); else cp.max_latency = cpu_to_le16(0x000D); cp.retrans_effort = 0x02; break; case SCO_AIRMODE_CVSD: cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; default: /* use CVSD settings as fallback */ cp.max_latency = cpu_to_le16(0xffff); cp.retrans_effort = 0xff; break; } hci_send_cmd(hdev, HCI_OP_ACCEPT_SYNC_CONN_REQ, sizeof(cp), &cp); } } static int sco_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sco_pinfo *pi = sco_pi(sk); lock_sock(sk); if (sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { sco_conn_defer_accept(pi->conn->hcon, pi->setting); sk->sk_state = BT_CONFIG; release_sock(sk); return 0; } release_sock(sk); return bt_sock_recvmsg(sock, msg, len, flags); } static int sco_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; int err = 0; struct bt_voice voice; u32 opt; struct bt_codecs *codecs; struct hci_dev *hdev; __u8 buffer[255]; BT_DBG("sk %p", sk); lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { err = -EINVAL; break; } err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); else clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); break; case BT_VOICE: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2) { err = -EINVAL; break; } voice.setting = sco_pi(sk)->setting; err = bt_copy_from_sockptr(&voice, sizeof(voice), optval, optlen); if (err) break; /* Explicitly check for these values */ if (voice.setting != BT_VOICE_TRANSPARENT && voice.setting != BT_VOICE_CVSD_16BIT) { err = -EINVAL; break; } sco_pi(sk)->setting = voice.setting; hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) { err = -EBADFD; break; } if (enhanced_sync_conn_capable(hdev) && voice.setting == BT_VOICE_TRANSPARENT) sco_pi(sk)->codec.id = BT_CODEC_TRANSPARENT; hci_dev_put(hdev); break; case BT_PKT_STATUS: err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); if (err) break; if (opt) set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); else clear_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags); break; case BT_CODEC: if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECT2) { err = -EINVAL; break; } hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) { err = -EBADFD; break; } if (!hci_dev_test_flag(hdev, HCI_OFFLOAD_CODECS_ENABLED)) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } if (!hdev->get_data_path_id) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } if (optlen < sizeof(struct bt_codecs) || optlen > sizeof(buffer)) { hci_dev_put(hdev); err = -EINVAL; break; } err = bt_copy_from_sockptr(buffer, optlen, optval, optlen); if (err) { hci_dev_put(hdev); break; } codecs = (void *)buffer; if (codecs->num_codecs > 1) { hci_dev_put(hdev); err = -EINVAL; break; } sco_pi(sk)->codec = codecs->codecs[0]; hci_dev_put(hdev); break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; struct sco_options opts; struct sco_conninfo cinfo; int err = 0; size_t len; BT_DBG("sk %p", sk); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); switch (optname) { case SCO_OPTIONS: if (sk->sk_state != BT_CONNECTED && !(sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))) { err = -ENOTCONN; break; } opts.mtu = sco_pi(sk)->conn->mtu; BT_DBG("mtu %u", opts.mtu); len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) err = -EFAULT; break; case SCO_CONNINFO: if (sk->sk_state != BT_CONNECTED && !(sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags))) { err = -ENOTCONN; break; } memset(&cinfo, 0, sizeof(cinfo)); cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle; memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3); len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *)&cinfo, len)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; int len, err = 0; struct bt_voice voice; u32 phys; int buf_len; struct codec_list *c; u8 num_codecs, i, __user *ptr; struct hci_dev *hdev; struct hci_codec_caps *caps; struct bt_codec codec; BT_DBG("sk %p", sk); if (level == SOL_SCO) return sco_sock_getsockopt_old(sock, optname, optval, optlen); if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); switch (optname) { case BT_DEFER_SETUP: if (sk->sk_state != BT_BOUND && sk->sk_state != BT_LISTEN) { err = -EINVAL; break; } if (put_user(test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags), (u32 __user *)optval)) err = -EFAULT; break; case BT_VOICE: voice.setting = sco_pi(sk)->setting; len = min_t(unsigned int, len, sizeof(voice)); if (copy_to_user(optval, (char *)&voice, len)) err = -EFAULT; break; case BT_PHY: if (sk->sk_state != BT_CONNECTED) { err = -ENOTCONN; break; } phys = hci_conn_get_phy(sco_pi(sk)->conn->hcon); if (put_user(phys, (u32 __user *) optval)) err = -EFAULT; break; case BT_PKT_STATUS: if (put_user(test_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags), (int __user *)optval)) err = -EFAULT; break; case BT_SNDMTU: case BT_RCVMTU: if (sk->sk_state != BT_CONNECTED) { err = -ENOTCONN; break; } if (put_user(sco_pi(sk)->conn->mtu, (u32 __user *)optval)) err = -EFAULT; break; case BT_CODEC: num_codecs = 0; buf_len = 0; hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); if (!hdev) { err = -EBADFD; break; } if (!hci_dev_test_flag(hdev, HCI_OFFLOAD_CODECS_ENABLED)) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } if (!hdev->get_data_path_id) { hci_dev_put(hdev); err = -EOPNOTSUPP; break; } release_sock(sk); /* find total buffer size required to copy codec + caps */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { if (c->transport != HCI_TRANSPORT_SCO_ESCO) continue; num_codecs++; for (i = 0, caps = c->caps; i < c->num_caps; i++) { buf_len += 1 + caps->len; caps = (void *)&caps->data[caps->len]; } buf_len += sizeof(struct bt_codec); } hci_dev_unlock(hdev); buf_len += sizeof(struct bt_codecs); if (buf_len > len) { hci_dev_put(hdev); return -ENOBUFS; } ptr = optval; if (put_user(num_codecs, ptr)) { hci_dev_put(hdev); return -EFAULT; } ptr += sizeof(num_codecs); /* Iterate all the codecs supported over SCO and populate * codec data */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { if (c->transport != HCI_TRANSPORT_SCO_ESCO) continue; codec.id = c->id; codec.cid = c->cid; codec.vid = c->vid; err = hdev->get_data_path_id(hdev, &codec.data_path); if (err < 0) break; codec.num_caps = c->num_caps; if (copy_to_user(ptr, &codec, sizeof(codec))) { err = -EFAULT; break; } ptr += sizeof(codec); /* find codec capabilities data length */ len = 0; for (i = 0, caps = c->caps; i < c->num_caps; i++) { len += 1 + caps->len; caps = (void *)&caps->data[caps->len]; } /* copy codec capabilities data */ if (len && copy_to_user(ptr, c->caps, len)) { err = -EFAULT; break; } ptr += len; } hci_dev_unlock(hdev); hci_dev_put(hdev); lock_sock(sk); if (!err && put_user(buf_len, optlen)) err = -EFAULT; break; default: err = -ENOPROTOOPT; break; } release_sock(sk); return err; } static int sco_sock_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p", sock, sk); if (!sk) return 0; sock_hold(sk); lock_sock(sk); if (!sk->sk_shutdown) { sk->sk_shutdown = SHUTDOWN_MASK; sco_sock_clear_timer(sk); __sco_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && !(current->flags & PF_EXITING)) err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); } release_sock(sk); sock_put(sk); return err; } static int sco_sock_release(struct socket *sock) { struct sock *sk = sock->sk; int err = 0; BT_DBG("sock %p, sk %p", sock, sk); if (!sk) return 0; sco_sock_close(sk); if (sock_flag(sk, SOCK_LINGER) && READ_ONCE(sk->sk_lingertime) && !(current->flags & PF_EXITING)) { lock_sock(sk); err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); release_sock(sk); } sock_orphan(sk); sco_sock_kill(sk); return err; } static void sco_conn_ready(struct sco_conn *conn) { struct sock *parent; struct sock *sk = conn->sk; BT_DBG("conn %p", conn); if (sk) { lock_sock(sk); sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; sk->sk_state_change(sk); release_sock(sk); } else { sco_conn_lock(conn); if (!conn->hcon) { sco_conn_unlock(conn); return; } parent = sco_get_sock_listen(&conn->hcon->src); if (!parent) { sco_conn_unlock(conn); return; } lock_sock(parent); sk = sco_sock_alloc(sock_net(parent), NULL, BTPROTO_SCO, GFP_ATOMIC, 0); if (!sk) { release_sock(parent); sco_conn_unlock(conn); return; } sco_sock_init(sk, parent); bacpy(&sco_pi(sk)->src, &conn->hcon->src); bacpy(&sco_pi(sk)->dst, &conn->hcon->dst); hci_conn_hold(conn->hcon); __sco_chan_add(conn, sk, parent); if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) sk->sk_state = BT_CONNECT2; else sk->sk_state = BT_CONNECTED; /* Wake up parent */ parent->sk_data_ready(parent); release_sock(parent); sco_conn_unlock(conn); } } /* ----- SCO interface with lower layer (HCI) ----- */ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { struct sock *sk; int lm = 0; BT_DBG("hdev %s, bdaddr %pMR", hdev->name, bdaddr); /* Find listening sockets */ read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { if (sk->sk_state != BT_LISTEN) continue; if (!bacmp(&sco_pi(sk)->src, &hdev->bdaddr) || !bacmp(&sco_pi(sk)->src, BDADDR_ANY)) { lm |= HCI_LM_ACCEPT; if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) *flags |= HCI_PROTO_DEFER; break; } } read_unlock(&sco_sk_list.lock); return lm; } static void sco_connect_cfm(struct hci_conn *hcon, __u8 status) { if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; BT_DBG("hcon %p bdaddr %pMR status %u", hcon, &hcon->dst, status); if (!status) { struct sco_conn *conn; conn = sco_conn_add(hcon); if (conn) sco_conn_ready(conn); } else sco_conn_del(hcon, bt_to_errno(status)); } static void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) { if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return; BT_DBG("hcon %p reason %d", hcon, reason); sco_conn_del(hcon, bt_to_errno(reason)); } void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) { struct sco_conn *conn = hcon->sco_data; if (!conn) goto drop; BT_DBG("conn %p len %u", conn, skb->len); if (skb->len) { sco_recv_frame(conn, skb); return; } drop: kfree_skb(skb); } static struct hci_cb sco_cb = { .name = "SCO", .connect_cfm = sco_connect_cfm, .disconn_cfm = sco_disconn_cfm, }; static int sco_debugfs_show(struct seq_file *f, void *p) { struct sock *sk; read_lock(&sco_sk_list.lock); sk_for_each(sk, &sco_sk_list.head) { seq_printf(f, "%pMR %pMR %d\n", &sco_pi(sk)->src, &sco_pi(sk)->dst, sk->sk_state); } read_unlock(&sco_sk_list.lock); return 0; } DEFINE_SHOW_ATTRIBUTE(sco_debugfs); static struct dentry *sco_debugfs; static const struct proto_ops sco_sock_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .release = sco_sock_release, .bind = sco_sock_bind, .connect = sco_sock_connect, .listen = sco_sock_listen, .accept = sco_sock_accept, .getname = sco_sock_getname, .sendmsg = sco_sock_sendmsg, .recvmsg = sco_sock_recvmsg, .poll = bt_sock_poll, .ioctl = bt_sock_ioctl, .gettstamp = sock_gettstamp, .mmap = sock_no_mmap, .socketpair = sock_no_socketpair, .shutdown = sco_sock_shutdown, .setsockopt = sco_sock_setsockopt, .getsockopt = sco_sock_getsockopt }; static const struct net_proto_family sco_sock_family_ops = { .family = PF_BLUETOOTH, .owner = THIS_MODULE, .create = sco_sock_create, }; int __init sco_init(void) { int err; BUILD_BUG_ON(sizeof(struct sockaddr_sco) > sizeof(struct sockaddr)); err = proto_register(&sco_proto, 0); if (err < 0) return err; err = bt_sock_register(BTPROTO_SCO, &sco_sock_family_ops); if (err < 0) { BT_ERR("SCO socket registration failed"); goto error; } err = bt_procfs_init(&init_net, "sco", &sco_sk_list, NULL); if (err < 0) { BT_ERR("Failed to create SCO proc file"); bt_sock_unregister(BTPROTO_SCO); goto error; } BT_INFO("SCO socket layer initialized"); hci_register_cb(&sco_cb); if (IS_ERR_OR_NULL(bt_debugfs)) return 0; sco_debugfs = debugfs_create_file("sco", 0444, bt_debugfs, NULL, &sco_debugfs_fops); return 0; error: proto_unregister(&sco_proto); return err; } void sco_exit(void) { bt_procfs_cleanup(&init_net, "sco"); debugfs_remove(sco_debugfs); hci_unregister_cb(&sco_cb); bt_sock_unregister(BTPROTO_SCO); proto_unregister(&sco_proto); } module_param(disable_esco, bool, 0644); MODULE_PARM_DESC(disable_esco, "Disable eSCO connection creation"); |
| 9 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic show_mem() implementation * * Copyright (C) 2008 Johannes Weiner <hannes@saeurebad.de> */ #include <linux/blkdev.h> #include <linux/cma.h> #include <linux/cpuset.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/swap.h> #include <linux/vmstat.h> #include "internal.h" #include "swap.h" atomic_long_t _totalram_pages __read_mostly; EXPORT_SYMBOL(_totalram_pages); unsigned long totalreserve_pages __read_mostly; unsigned long totalcma_pages __read_mostly; static inline void show_node(struct zone *zone) { if (IS_ENABLED(CONFIG_NUMA)) printk("Node %d ", zone_to_nid(zone)); } long si_mem_available(void) { long available; unsigned long pagecache; unsigned long wmark_low = 0; unsigned long reclaimable; struct zone *zone; for_each_zone(zone) wmark_low += low_wmark_pages(zone); /* * Estimate the amount of memory available for userspace allocations, * without causing swapping or OOM. */ available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages; /* * Not all the page cache can be freed, otherwise the system will * start swapping or thrashing. Assume at least half of the page * cache, or the low watermark worth of cache, needs to stay. */ pagecache = global_node_page_state(NR_ACTIVE_FILE) + global_node_page_state(NR_INACTIVE_FILE); pagecache -= min(pagecache / 2, wmark_low); available += pagecache; /* * Part of the reclaimable slab and other kernel memory consists of * items that are in use, and cannot be freed. Cap this estimate at the * low watermark. */ reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); reclaimable -= min(reclaimable / 2, wmark_low); available += reclaimable; if (available < 0) available = 0; return available; } EXPORT_SYMBOL_GPL(si_mem_available); void si_meminfo(struct sysinfo *val) { val->totalram = totalram_pages(); val->sharedram = global_node_page_state(NR_SHMEM); val->freeram = global_zone_page_state(NR_FREE_PAGES); val->bufferram = nr_blockdev_pages(); val->totalhigh = totalhigh_pages(); val->freehigh = nr_free_highpages(); val->mem_unit = PAGE_SIZE; } EXPORT_SYMBOL(si_meminfo); #ifdef CONFIG_NUMA void si_meminfo_node(struct sysinfo *val, int nid) { int zone_type; /* needs to be signed */ unsigned long managed_pages = 0; unsigned long managed_highpages = 0; unsigned long free_highpages = 0; pg_data_t *pgdat = NODE_DATA(nid); for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) managed_pages += zone_managed_pages(&pgdat->node_zones[zone_type]); val->totalram = managed_pages; val->sharedram = node_page_state(pgdat, NR_SHMEM); val->freeram = sum_zone_node_page_state(nid, NR_FREE_PAGES); #ifdef CONFIG_HIGHMEM for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) { struct zone *zone = &pgdat->node_zones[zone_type]; if (is_highmem(zone)) { managed_highpages += zone_managed_pages(zone); free_highpages += zone_page_state(zone, NR_FREE_PAGES); } } val->totalhigh = managed_highpages; val->freehigh = free_highpages; #else val->totalhigh = managed_highpages; val->freehigh = free_highpages; #endif val->mem_unit = PAGE_SIZE; } #endif /* * Determine whether the node should be displayed or not, depending on whether * SHOW_MEM_FILTER_NODES was passed to show_free_areas(). */ static bool show_mem_node_skip(unsigned int flags, int nid, nodemask_t *nodemask) { if (!(flags & SHOW_MEM_FILTER_NODES)) return false; /* * no node mask - aka implicit memory numa policy. Do not bother with * the synchronization - read_mems_allowed_begin - because we do not * have to be precise here. */ if (!nodemask) nodemask = &cpuset_current_mems_allowed; return !node_isset(nid, *nodemask); } static void show_migration_types(unsigned char type) { static const char types[MIGRATE_TYPES] = { [MIGRATE_UNMOVABLE] = 'U', [MIGRATE_MOVABLE] = 'M', [MIGRATE_RECLAIMABLE] = 'E', [MIGRATE_HIGHATOMIC] = 'H', #ifdef CONFIG_CMA [MIGRATE_CMA] = 'C', #endif #ifdef CONFIG_MEMORY_ISOLATION [MIGRATE_ISOLATE] = 'I', #endif }; char tmp[MIGRATE_TYPES + 1]; char *p = tmp; int i; for (i = 0; i < MIGRATE_TYPES; i++) { if (type & (1 << i)) *p++ = types[i]; } *p = '\0'; printk(KERN_CONT "(%s) ", tmp); } static bool node_has_managed_zones(pg_data_t *pgdat, int max_zone_idx) { int zone_idx; for (zone_idx = 0; zone_idx <= max_zone_idx; zone_idx++) if (zone_managed_pages(pgdat->node_zones + zone_idx)) return true; return false; } /* * Show free area list (used inside shift_scroll-lock stuff) * We also calculate the percentage fragmentation. We do this by counting the * memory on each free list with the exception of the first item on the list. * * Bits in @filter: * SHOW_MEM_FILTER_NODES: suppress nodes that are not allowed by current's * cpuset. */ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_zone_idx) { unsigned long free_pcp = 0; int cpu, nid; struct zone *zone; pg_data_t *pgdat; for_each_populated_zone(zone) { if (zone_idx(zone) > max_zone_idx) continue; if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; for_each_online_cpu(cpu) free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; } printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n" " active_file:%lu inactive_file:%lu isolated_file:%lu\n" " unevictable:%lu dirty:%lu writeback:%lu\n" " slab_reclaimable:%lu slab_unreclaimable:%lu\n" " mapped:%lu shmem:%lu pagetables:%lu\n" " sec_pagetables:%lu bounce:%lu\n" " kernel_misc_reclaimable:%lu\n" " free:%lu free_pcp:%lu free_cma:%lu\n", global_node_page_state(NR_ACTIVE_ANON), global_node_page_state(NR_INACTIVE_ANON), global_node_page_state(NR_ISOLATED_ANON), global_node_page_state(NR_ACTIVE_FILE), global_node_page_state(NR_INACTIVE_FILE), global_node_page_state(NR_ISOLATED_FILE), global_node_page_state(NR_UNEVICTABLE), global_node_page_state(NR_FILE_DIRTY), global_node_page_state(NR_WRITEBACK), global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B), global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B), global_node_page_state(NR_FILE_MAPPED), global_node_page_state(NR_SHMEM), global_node_page_state(NR_PAGETABLE), global_node_page_state(NR_SECONDARY_PAGETABLE), global_zone_page_state(NR_BOUNCE), global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE), global_zone_page_state(NR_FREE_PAGES), free_pcp, global_zone_page_state(NR_FREE_CMA_PAGES)); for_each_online_pgdat(pgdat) { if (show_mem_node_skip(filter, pgdat->node_id, nodemask)) continue; if (!node_has_managed_zones(pgdat, max_zone_idx)) continue; printk("Node %d" " active_anon:%lukB" " inactive_anon:%lukB" " active_file:%lukB" " inactive_file:%lukB" " unevictable:%lukB" " isolated(anon):%lukB" " isolated(file):%lukB" " mapped:%lukB" " dirty:%lukB" " writeback:%lukB" " shmem:%lukB" #ifdef CONFIG_TRANSPARENT_HUGEPAGE " shmem_thp:%lukB" " shmem_pmdmapped:%lukB" " anon_thp:%lukB" #endif " writeback_tmp:%lukB" " kernel_stack:%lukB" #ifdef CONFIG_SHADOW_CALL_STACK " shadow_call_stack:%lukB" #endif " pagetables:%lukB" " sec_pagetables:%lukB" " all_unreclaimable? %s" "\n", pgdat->node_id, K(node_page_state(pgdat, NR_ACTIVE_ANON)), K(node_page_state(pgdat, NR_INACTIVE_ANON)), K(node_page_state(pgdat, NR_ACTIVE_FILE)), K(node_page_state(pgdat, NR_INACTIVE_FILE)), K(node_page_state(pgdat, NR_UNEVICTABLE)), K(node_page_state(pgdat, NR_ISOLATED_ANON)), K(node_page_state(pgdat, NR_ISOLATED_FILE)), K(node_page_state(pgdat, NR_FILE_MAPPED)), K(node_page_state(pgdat, NR_FILE_DIRTY)), K(node_page_state(pgdat, NR_WRITEBACK)), K(node_page_state(pgdat, NR_SHMEM)), #ifdef CONFIG_TRANSPARENT_HUGEPAGE K(node_page_state(pgdat, NR_SHMEM_THPS)), K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)), K(node_page_state(pgdat, NR_ANON_THPS)), #endif K(node_page_state(pgdat, NR_WRITEBACK_TEMP)), node_page_state(pgdat, NR_KERNEL_STACK_KB), #ifdef CONFIG_SHADOW_CALL_STACK node_page_state(pgdat, NR_KERNEL_SCS_KB), #endif K(node_page_state(pgdat, NR_PAGETABLE)), K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)), pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ? "yes" : "no"); } for_each_populated_zone(zone) { int i; if (zone_idx(zone) > max_zone_idx) continue; if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; free_pcp = 0; for_each_online_cpu(cpu) free_pcp += per_cpu_ptr(zone->per_cpu_pageset, cpu)->count; show_node(zone); printk(KERN_CONT "%s" " free:%lukB" " boost:%lukB" " min:%lukB" " low:%lukB" " high:%lukB" " reserved_highatomic:%luKB" " active_anon:%lukB" " inactive_anon:%lukB" " active_file:%lukB" " inactive_file:%lukB" " unevictable:%lukB" " writepending:%lukB" " present:%lukB" " managed:%lukB" " mlocked:%lukB" " bounce:%lukB" " free_pcp:%lukB" " local_pcp:%ukB" " free_cma:%lukB" "\n", zone->name, K(zone_page_state(zone, NR_FREE_PAGES)), K(zone->watermark_boost), K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), K(zone->nr_reserved_highatomic), K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)), K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)), K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)), K(zone_page_state(zone, NR_ZONE_INACTIVE_FILE)), K(zone_page_state(zone, NR_ZONE_UNEVICTABLE)), K(zone_page_state(zone, NR_ZONE_WRITE_PENDING)), K(zone->present_pages), K(zone_managed_pages(zone)), K(zone_page_state(zone, NR_MLOCK)), K(zone_page_state(zone, NR_BOUNCE)), K(free_pcp), K(this_cpu_read(zone->per_cpu_pageset->count)), K(zone_page_state(zone, NR_FREE_CMA_PAGES))); printk("lowmem_reserve[]:"); for (i = 0; i < MAX_NR_ZONES; i++) printk(KERN_CONT " %ld", zone->lowmem_reserve[i]); printk(KERN_CONT "\n"); } for_each_populated_zone(zone) { unsigned int order; unsigned long nr[NR_PAGE_ORDERS], flags, total = 0; unsigned char types[NR_PAGE_ORDERS]; if (zone_idx(zone) > max_zone_idx) continue; if (show_mem_node_skip(filter, zone_to_nid(zone), nodemask)) continue; show_node(zone); printk(KERN_CONT "%s: ", zone->name); spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < NR_PAGE_ORDERS; order++) { struct free_area *area = &zone->free_area[order]; int type; nr[order] = area->nr_free; total += nr[order] << order; types[order] = 0; for (type = 0; type < MIGRATE_TYPES; type++) { if (!free_area_empty(area, type)) types[order] |= 1 << type; } } spin_unlock_irqrestore(&zone->lock, flags); for (order = 0; order < NR_PAGE_ORDERS; order++) { printk(KERN_CONT "%lu*%lukB ", nr[order], K(1UL) << order); if (nr[order]) show_migration_types(types[order]); } printk(KERN_CONT "= %lukB\n", K(total)); } for_each_online_node(nid) { if (show_mem_node_skip(filter, nid, nodemask)) continue; hugetlb_show_meminfo_node(nid); } printk("%ld total pagecache pages\n", global_node_page_state(NR_FILE_PAGES)); show_swap_cache_info(); } void __show_mem(unsigned int filter, nodemask_t *nodemask, int max_zone_idx) { unsigned long total = 0, reserved = 0, highmem = 0; struct zone *zone; printk("Mem-Info:\n"); show_free_areas(filter, nodemask, max_zone_idx); for_each_populated_zone(zone) { total += zone->present_pages; reserved += zone->present_pages - zone_managed_pages(zone); if (is_highmem(zone)) highmem += zone->present_pages; } printk("%lu pages RAM\n", total); printk("%lu pages HighMem/MovableOnly\n", highmem); printk("%lu pages reserved\n", reserved); #ifdef CONFIG_CMA printk("%lu pages cma reserved\n", totalcma_pages); #endif #ifdef CONFIG_MEMORY_FAILURE printk("%lu pages hwpoisoned\n", atomic_long_read(&num_poisoned_pages)); #endif #ifdef CONFIG_MEM_ALLOC_PROFILING { struct codetag_bytes tags[10]; size_t i, nr; nr = alloc_tag_top_users(tags, ARRAY_SIZE(tags), false); if (nr) { pr_notice("Memory allocations:\n"); for (i = 0; i < nr; i++) { struct codetag *ct = tags[i].ct; struct alloc_tag *tag = ct_to_alloc_tag(ct); struct alloc_tag_counters counter = alloc_tag_read(tag); /* Same as alloc_tag_to_text() but w/o intermediate buffer */ if (ct->modname) pr_notice("%12lli %8llu %s:%u [%s] func:%s\n", counter.bytes, counter.calls, ct->filename, ct->lineno, ct->modname, ct->function); else pr_notice("%12lli %8llu %s:%u func:%s\n", counter.bytes, counter.calls, ct->filename, ct->lineno, ct->function); } } } #endif } |
| 47 47 47 14 3 13 47 25 24 24 1 11 16 3 3 33 21 16 1 16 14 27 27 27 26 27 27 11 2 27 27 27 27 14 14 14 14 13 13 13 13 4 2 6 5 8 1 1 18 1 17 17 16 7 15 5 11 11 2 6 1 3 11 11 9 18 18 5 1 2 3 10 8 1 8 2 1 7 9 3 3 1 2 2 1 3 1 3 29 7 27 2 27 5 5 3 3 3 1 3 1 2 2 37 19 2 11 4 2 12 4 16 10 4 7 1 8 2 1 2 2 2 1 1 1 1 5 1 1 1 2 1 42 8 37 36 4 4 3 3 3 3 25 25 16 16 3 3 3 3 3 2 1 1 25 24 2 1 6 1 1 2 2 36 30 2 1 1 1 1 1 2 9 1 8 1 3 3 1 4 1 2 13 5 2 1 1 1 1 1 1 2 7 1 1 1 1 1 1 1 1 1 3 152 19 35 1 36 1 123 69 1 4 4 66 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 | // SPDX-License-Identifier: GPL-2.0-only /* * Functions to manage eBPF programs attached to cgroups * * Copyright (c) 2016 Daniel Mack */ #include <linux/kernel.h> #include <linux/atomic.h> #include <linux/cgroup.h> #include <linux/filter.h> #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/string.h> #include <linux/bpf.h> #include <linux/bpf-cgroup.h> #include <linux/bpf_lsm.h> #include <linux/bpf_verifier.h> #include <net/sock.h> #include <net/bpf_sk_storage.h> #include "../cgroup/cgroup-internal.h" DEFINE_STATIC_KEY_ARRAY_FALSE(cgroup_bpf_enabled_key, MAX_CGROUP_BPF_ATTACH_TYPE); EXPORT_SYMBOL(cgroup_bpf_enabled_key); /* __always_inline is necessary to prevent indirect call through run_prog * function pointer. */ static __always_inline int bpf_prog_run_array_cg(const struct cgroup_bpf *cgrp, enum cgroup_bpf_attach_type atype, const void *ctx, bpf_prog_run_fn run_prog, int retval, u32 *ret_flags) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_cg_run_ctx run_ctx; u32 func_ret; run_ctx.retval = retval; migrate_disable(); rcu_read_lock(); array = rcu_dereference(cgrp->effective[atype]); item = &array->items[0]; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); while ((prog = READ_ONCE(item->prog))) { run_ctx.prog_item = item; func_ret = run_prog(prog, ctx); if (ret_flags) { *(ret_flags) |= (func_ret >> 1); func_ret &= 1; } if (!func_ret && !IS_ERR_VALUE((long)run_ctx.retval)) run_ctx.retval = -EPERM; item++; } bpf_reset_run_ctx(old_run_ctx); rcu_read_unlock(); migrate_enable(); return run_ctx.retval; } unsigned int __cgroup_bpf_run_lsm_sock(const void *ctx, const struct bpf_insn *insn) { const struct bpf_prog *shim_prog; struct sock *sk; struct cgroup *cgrp; int ret = 0; u64 *args; args = (u64 *)ctx; sk = (void *)(unsigned long)args[0]; /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); if (likely(cgrp)) ret = bpf_prog_run_array_cg(&cgrp->bpf, shim_prog->aux->cgroup_atype, ctx, bpf_prog_run, 0, NULL); return ret; } unsigned int __cgroup_bpf_run_lsm_socket(const void *ctx, const struct bpf_insn *insn) { const struct bpf_prog *shim_prog; struct socket *sock; struct cgroup *cgrp; int ret = 0; u64 *args; args = (u64 *)ctx; sock = (void *)(unsigned long)args[0]; /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); cgrp = sock_cgroup_ptr(&sock->sk->sk_cgrp_data); if (likely(cgrp)) ret = bpf_prog_run_array_cg(&cgrp->bpf, shim_prog->aux->cgroup_atype, ctx, bpf_prog_run, 0, NULL); return ret; } unsigned int __cgroup_bpf_run_lsm_current(const void *ctx, const struct bpf_insn *insn) { const struct bpf_prog *shim_prog; struct cgroup *cgrp; int ret = 0; /*shim_prog = container_of(insn, struct bpf_prog, insnsi);*/ shim_prog = (const struct bpf_prog *)((void *)insn - offsetof(struct bpf_prog, insnsi)); /* We rely on trampoline's __bpf_prog_enter_lsm_cgroup to grab RCU read lock. */ cgrp = task_dfl_cgroup(current); if (likely(cgrp)) ret = bpf_prog_run_array_cg(&cgrp->bpf, shim_prog->aux->cgroup_atype, ctx, bpf_prog_run, 0, NULL); return ret; } #ifdef CONFIG_BPF_LSM struct cgroup_lsm_atype { u32 attach_btf_id; int refcnt; }; static struct cgroup_lsm_atype cgroup_lsm_atype[CGROUP_LSM_NUM]; static enum cgroup_bpf_attach_type bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id) { int i; lockdep_assert_held(&cgroup_mutex); if (attach_type != BPF_LSM_CGROUP) return to_cgroup_bpf_attach_type(attach_type); for (i = 0; i < ARRAY_SIZE(cgroup_lsm_atype); i++) if (cgroup_lsm_atype[i].attach_btf_id == attach_btf_id) return CGROUP_LSM_START + i; for (i = 0; i < ARRAY_SIZE(cgroup_lsm_atype); i++) if (cgroup_lsm_atype[i].attach_btf_id == 0) return CGROUP_LSM_START + i; return -E2BIG; } void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) { int i = cgroup_atype - CGROUP_LSM_START; lockdep_assert_held(&cgroup_mutex); WARN_ON_ONCE(cgroup_lsm_atype[i].attach_btf_id && cgroup_lsm_atype[i].attach_btf_id != attach_btf_id); cgroup_lsm_atype[i].attach_btf_id = attach_btf_id; cgroup_lsm_atype[i].refcnt++; } void bpf_cgroup_atype_put(int cgroup_atype) { int i = cgroup_atype - CGROUP_LSM_START; cgroup_lock(); if (--cgroup_lsm_atype[i].refcnt <= 0) cgroup_lsm_atype[i].attach_btf_id = 0; WARN_ON_ONCE(cgroup_lsm_atype[i].refcnt < 0); cgroup_unlock(); } #else static enum cgroup_bpf_attach_type bpf_cgroup_atype_find(enum bpf_attach_type attach_type, u32 attach_btf_id) { if (attach_type != BPF_LSM_CGROUP) return to_cgroup_bpf_attach_type(attach_type); return -EOPNOTSUPP; } #endif /* CONFIG_BPF_LSM */ void cgroup_bpf_offline(struct cgroup *cgrp) { cgroup_get(cgrp); percpu_ref_kill(&cgrp->bpf.refcnt); } static void bpf_cgroup_storages_free(struct bpf_cgroup_storage *storages[]) { enum bpf_cgroup_storage_type stype; for_each_cgroup_storage_type(stype) bpf_cgroup_storage_free(storages[stype]); } static int bpf_cgroup_storages_alloc(struct bpf_cgroup_storage *storages[], struct bpf_cgroup_storage *new_storages[], enum bpf_attach_type type, struct bpf_prog *prog, struct cgroup *cgrp) { enum bpf_cgroup_storage_type stype; struct bpf_cgroup_storage_key key; struct bpf_map *map; key.cgroup_inode_id = cgroup_id(cgrp); key.attach_type = type; for_each_cgroup_storage_type(stype) { map = prog->aux->cgroup_storage[stype]; if (!map) continue; storages[stype] = cgroup_storage_lookup((void *)map, &key, false); if (storages[stype]) continue; storages[stype] = bpf_cgroup_storage_alloc(prog, stype); if (IS_ERR(storages[stype])) { bpf_cgroup_storages_free(new_storages); return -ENOMEM; } new_storages[stype] = storages[stype]; } return 0; } static void bpf_cgroup_storages_assign(struct bpf_cgroup_storage *dst[], struct bpf_cgroup_storage *src[]) { enum bpf_cgroup_storage_type stype; for_each_cgroup_storage_type(stype) dst[stype] = src[stype]; } static void bpf_cgroup_storages_link(struct bpf_cgroup_storage *storages[], struct cgroup *cgrp, enum bpf_attach_type attach_type) { enum bpf_cgroup_storage_type stype; for_each_cgroup_storage_type(stype) bpf_cgroup_storage_link(storages[stype], cgrp, attach_type); } /* Called when bpf_cgroup_link is auto-detached from dying cgroup. * It drops cgroup and bpf_prog refcounts, and marks bpf_link as defunct. It * doesn't free link memory, which will eventually be done by bpf_link's * release() callback, when its last FD is closed. */ static void bpf_cgroup_link_auto_detach(struct bpf_cgroup_link *link) { cgroup_put(link->cgroup); link->cgroup = NULL; } /** * cgroup_bpf_release() - put references of all bpf programs and * release all cgroup bpf data * @work: work structure embedded into the cgroup to modify */ static void cgroup_bpf_release(struct work_struct *work) { struct cgroup *p, *cgrp = container_of(work, struct cgroup, bpf.release_work); struct bpf_prog_array *old_array; struct list_head *storages = &cgrp->bpf.storages; struct bpf_cgroup_storage *storage, *stmp; unsigned int atype; cgroup_lock(); for (atype = 0; atype < ARRAY_SIZE(cgrp->bpf.progs); atype++) { struct hlist_head *progs = &cgrp->bpf.progs[atype]; struct bpf_prog_list *pl; struct hlist_node *pltmp; hlist_for_each_entry_safe(pl, pltmp, progs, node) { hlist_del(&pl->node); if (pl->prog) { if (pl->prog->expected_attach_type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(pl->prog); bpf_prog_put(pl->prog); } if (pl->link) { if (pl->link->link.prog->expected_attach_type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(pl->link->link.prog); bpf_cgroup_link_auto_detach(pl->link); } kfree(pl); static_branch_dec(&cgroup_bpf_enabled_key[atype]); } old_array = rcu_dereference_protected( cgrp->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); bpf_prog_array_free(old_array); } list_for_each_entry_safe(storage, stmp, storages, list_cg) { bpf_cgroup_storage_unlink(storage); bpf_cgroup_storage_free(storage); } cgroup_unlock(); for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) cgroup_bpf_put(p); percpu_ref_exit(&cgrp->bpf.refcnt); cgroup_put(cgrp); } /** * cgroup_bpf_release_fn() - callback used to schedule releasing * of bpf cgroup data * @ref: percpu ref counter structure */ static void cgroup_bpf_release_fn(struct percpu_ref *ref) { struct cgroup *cgrp = container_of(ref, struct cgroup, bpf.refcnt); INIT_WORK(&cgrp->bpf.release_work, cgroup_bpf_release); queue_work(system_wq, &cgrp->bpf.release_work); } /* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through * link or direct prog. */ static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl) { if (pl->prog) return pl->prog; if (pl->link) return pl->link->link.prog; return NULL; } /* count number of elements in the list. * it's slow but the list cannot be long */ static u32 prog_list_length(struct hlist_head *head) { struct bpf_prog_list *pl; u32 cnt = 0; hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; cnt++; } return cnt; } /* if parent has non-overridable prog attached, * disallow attaching new programs to the descendent cgroup. * if parent has overridable or multi-prog, allow attaching */ static bool hierarchy_allows_attach(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype) { struct cgroup *p; p = cgroup_parent(cgrp); if (!p) return true; do { u32 flags = p->bpf.flags[atype]; u32 cnt; if (flags & BPF_F_ALLOW_MULTI) return true; cnt = prog_list_length(&p->bpf.progs[atype]); WARN_ON_ONCE(cnt > 1); if (cnt == 1) return !!(flags & BPF_F_ALLOW_OVERRIDE); p = cgroup_parent(p); } while (p); return true; } /* compute a chain of effective programs for a given cgroup: * start from the list of programs in this cgroup and add * all parent programs. * Note that parent's F_ALLOW_OVERRIDE-type program is yielding * to programs in this cgroup */ static int compute_effective_progs(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype, struct bpf_prog_array **array) { struct bpf_prog_array_item *item; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; int cnt = 0; /* count number of effective programs by walking parents */ do { if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) cnt += prog_list_length(&p->bpf.progs[atype]); p = cgroup_parent(p); } while (p); progs = bpf_prog_array_alloc(cnt, GFP_KERNEL); if (!progs) return -ENOMEM; /* populate the array with effective progs */ cnt = 0; p = cgrp; do { if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; hlist_for_each_entry(pl, &p->bpf.progs[atype], node) { if (!prog_list_prog(pl)) continue; item = &progs->items[cnt]; item->prog = prog_list_prog(pl); bpf_cgroup_storages_assign(item->cgroup_storage, pl->storage); cnt++; } } while ((p = cgroup_parent(p))); *array = progs; return 0; } static void activate_effective_progs(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype, struct bpf_prog_array *old_array) { old_array = rcu_replace_pointer(cgrp->bpf.effective[atype], old_array, lockdep_is_held(&cgroup_mutex)); /* free prog array after grace period, since __cgroup_bpf_run_*() * might be still walking the array */ bpf_prog_array_free(old_array); } /** * cgroup_bpf_inherit() - inherit effective programs from parent * @cgrp: the cgroup to modify */ int cgroup_bpf_inherit(struct cgroup *cgrp) { /* has to use marco instead of const int, since compiler thinks * that array below is variable length */ #define NR ARRAY_SIZE(cgrp->bpf.effective) struct bpf_prog_array *arrays[NR] = {}; struct cgroup *p; int ret, i; ret = percpu_ref_init(&cgrp->bpf.refcnt, cgroup_bpf_release_fn, 0, GFP_KERNEL); if (ret) return ret; for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) cgroup_bpf_get(p); for (i = 0; i < NR; i++) INIT_HLIST_HEAD(&cgrp->bpf.progs[i]); INIT_LIST_HEAD(&cgrp->bpf.storages); for (i = 0; i < NR; i++) if (compute_effective_progs(cgrp, i, &arrays[i])) goto cleanup; for (i = 0; i < NR; i++) activate_effective_progs(cgrp, i, arrays[i]); return 0; cleanup: for (i = 0; i < NR; i++) bpf_prog_array_free(arrays[i]); for (p = cgroup_parent(cgrp); p; p = cgroup_parent(p)) cgroup_bpf_put(p); percpu_ref_exit(&cgrp->bpf.refcnt); return -ENOMEM; } static int update_effective_progs(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype) { struct cgroup_subsys_state *css; int err; /* allocate and recompute effective prog arrays */ css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); if (percpu_ref_is_zero(&desc->bpf.refcnt)) continue; err = compute_effective_progs(desc, atype, &desc->bpf.inactive); if (err) goto cleanup; } /* all allocations were successful. Activate all prog arrays */ css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); if (percpu_ref_is_zero(&desc->bpf.refcnt)) { if (unlikely(desc->bpf.inactive)) { bpf_prog_array_free(desc->bpf.inactive); desc->bpf.inactive = NULL; } continue; } activate_effective_progs(desc, atype, desc->bpf.inactive); desc->bpf.inactive = NULL; } return 0; cleanup: /* oom while computing effective. Free all computed effective arrays * since they were not activated */ css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); bpf_prog_array_free(desc->bpf.inactive); desc->bpf.inactive = NULL; } return err; } #define BPF_CGROUP_MAX_PROGS 64 static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs, struct bpf_prog *prog, struct bpf_cgroup_link *link, struct bpf_prog *replace_prog, bool allow_multi) { struct bpf_prog_list *pl; /* single-attach case */ if (!allow_multi) { if (hlist_empty(progs)) return NULL; return hlist_entry(progs->first, typeof(*pl), node); } hlist_for_each_entry(pl, progs, node) { if (prog && pl->prog == prog && prog != replace_prog) /* disallow attaching the same prog twice */ return ERR_PTR(-EINVAL); if (link && pl->link == link) /* disallow attaching the same link twice */ return ERR_PTR(-EINVAL); } /* direct prog multi-attach w/ replacement case */ if (replace_prog) { hlist_for_each_entry(pl, progs, node) { if (pl->prog == replace_prog) /* a match found */ return pl; } /* prog to replace not found for cgroup */ return ERR_PTR(-ENOENT); } return NULL; } /** * __cgroup_bpf_attach() - Attach the program or the link to a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to attach * @link: A link to attach * @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set * @type: Type of attach operation * @flags: Option flags * * Exactly one of @prog or @link can be non-null. * Must be called with cgroup_mutex held. */ static int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_prog *replace_prog, struct bpf_cgroup_link *link, enum bpf_attach_type type, u32 flags) { u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)); struct bpf_prog *old_prog = NULL; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; struct bpf_prog *new_prog = prog ? : link->link.prog; enum cgroup_bpf_attach_type atype; struct bpf_prog_list *pl; struct hlist_head *progs; int err; if (((flags & BPF_F_ALLOW_OVERRIDE) && (flags & BPF_F_ALLOW_MULTI)) || ((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI))) /* invalid combination */ return -EINVAL; if (link && (prog || replace_prog)) /* only either link or prog/replace_prog can be specified */ return -EINVAL; if (!!replace_prog != !!(flags & BPF_F_REPLACE)) /* replace_prog implies BPF_F_REPLACE, and vice versa */ return -EINVAL; atype = bpf_cgroup_atype_find(type, new_prog->aux->attach_btf_id); if (atype < 0) return -EINVAL; progs = &cgrp->bpf.progs[atype]; if (!hierarchy_allows_attach(cgrp, atype)) return -EPERM; if (!hlist_empty(progs) && cgrp->bpf.flags[atype] != saved_flags) /* Disallow attaching non-overridable on top * of existing overridable in this cgroup. * Disallow attaching multi-prog if overridable or none */ return -EPERM; if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; pl = find_attach_entry(progs, prog, link, replace_prog, flags & BPF_F_ALLOW_MULTI); if (IS_ERR(pl)) return PTR_ERR(pl); if (bpf_cgroup_storages_alloc(storage, new_storage, type, prog ? : link->link.prog, cgrp)) return -ENOMEM; if (pl) { old_prog = pl->prog; } else { struct hlist_node *last = NULL; pl = kmalloc(sizeof(*pl), GFP_KERNEL); if (!pl) { bpf_cgroup_storages_free(new_storage); return -ENOMEM; } if (hlist_empty(progs)) hlist_add_head(&pl->node, progs); else hlist_for_each(last, progs) { if (last->next) continue; hlist_add_behind(&pl->node, last); break; } } pl->prog = prog; pl->link = link; bpf_cgroup_storages_assign(pl->storage, storage); cgrp->bpf.flags[atype] = saved_flags; if (type == BPF_LSM_CGROUP) { err = bpf_trampoline_link_cgroup_shim(new_prog, atype); if (err) goto cleanup; } err = update_effective_progs(cgrp, atype); if (err) goto cleanup_trampoline; if (old_prog) { if (type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(old_prog); bpf_prog_put(old_prog); } else { static_branch_inc(&cgroup_bpf_enabled_key[atype]); } bpf_cgroup_storages_link(new_storage, cgrp, type); return 0; cleanup_trampoline: if (type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(new_prog); cleanup: if (old_prog) { pl->prog = old_prog; pl->link = NULL; } bpf_cgroup_storages_free(new_storage); if (!old_prog) { hlist_del(&pl->node); kfree(pl); } return err; } static int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_prog *replace_prog, struct bpf_cgroup_link *link, enum bpf_attach_type type, u32 flags) { int ret; cgroup_lock(); ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags); cgroup_unlock(); return ret; } /* Swap updated BPF program for given link in effective program arrays across * all descendant cgroups. This function is guaranteed to succeed. */ static void replace_effective_prog(struct cgroup *cgrp, enum cgroup_bpf_attach_type atype, struct bpf_cgroup_link *link) { struct bpf_prog_array_item *item; struct cgroup_subsys_state *css; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct hlist_head *head; struct cgroup *cg; int pos; css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); if (percpu_ref_is_zero(&desc->bpf.refcnt)) continue; /* find position of link in effective progs array */ for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; head = &cg->bpf.progs[atype]; hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; if (pl->link == link) goto found; pos++; } } found: BUG_ON(!cg); progs = rcu_dereference_protected( desc->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); item = &progs->items[pos]; WRITE_ONCE(item->prog, link->link.prog); } } /** * __cgroup_bpf_replace() - Replace link's program and propagate the change * to descendants * @cgrp: The cgroup which descendants to traverse * @link: A link for which to replace BPF program * @new_prog: &struct bpf_prog for the target BPF program with its refcnt * incremented * * Must be called with cgroup_mutex held. */ static int __cgroup_bpf_replace(struct cgroup *cgrp, struct bpf_cgroup_link *link, struct bpf_prog *new_prog) { enum cgroup_bpf_attach_type atype; struct bpf_prog *old_prog; struct bpf_prog_list *pl; struct hlist_head *progs; bool found = false; atype = bpf_cgroup_atype_find(link->type, new_prog->aux->attach_btf_id); if (atype < 0) return -EINVAL; progs = &cgrp->bpf.progs[atype]; if (link->link.prog->type != new_prog->type) return -EINVAL; hlist_for_each_entry(pl, progs, node) { if (pl->link == link) { found = true; break; } } if (!found) return -ENOENT; old_prog = xchg(&link->link.prog, new_prog); replace_effective_prog(cgrp, atype, link); bpf_prog_put(old_prog); return 0; } static int cgroup_bpf_replace(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { struct bpf_cgroup_link *cg_link; int ret; cg_link = container_of(link, struct bpf_cgroup_link, link); cgroup_lock(); /* link might have been auto-released by dying cgroup, so fail */ if (!cg_link->cgroup) { ret = -ENOLINK; goto out_unlock; } if (old_prog && link->prog != old_prog) { ret = -EPERM; goto out_unlock; } ret = __cgroup_bpf_replace(cg_link->cgroup, cg_link, new_prog); out_unlock: cgroup_unlock(); return ret; } static struct bpf_prog_list *find_detach_entry(struct hlist_head *progs, struct bpf_prog *prog, struct bpf_cgroup_link *link, bool allow_multi) { struct bpf_prog_list *pl; if (!allow_multi) { if (hlist_empty(progs)) /* report error when trying to detach and nothing is attached */ return ERR_PTR(-ENOENT); /* to maintain backward compatibility NONE and OVERRIDE cgroups * allow detaching with invalid FD (prog==NULL) in legacy mode */ return hlist_entry(progs->first, typeof(*pl), node); } if (!prog && !link) /* to detach MULTI prog the user has to specify valid FD * of the program or link to be detached */ return ERR_PTR(-EINVAL); /* find the prog or link and detach it */ hlist_for_each_entry(pl, progs, node) { if (pl->prog == prog && pl->link == link) return pl; } return ERR_PTR(-ENOENT); } /** * purge_effective_progs() - After compute_effective_progs fails to alloc new * cgrp->bpf.inactive table we can recover by * recomputing the array in place. * * @cgrp: The cgroup which descendants to travers * @prog: A program to detach or NULL * @link: A link to detach or NULL * @atype: Type of detach operation */ static void purge_effective_progs(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_cgroup_link *link, enum cgroup_bpf_attach_type atype) { struct cgroup_subsys_state *css; struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct hlist_head *head; struct cgroup *cg; int pos; /* recompute effective prog array in place */ css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); if (percpu_ref_is_zero(&desc->bpf.refcnt)) continue; /* find position of link or prog in effective progs array */ for (pos = 0, cg = desc; cg; cg = cgroup_parent(cg)) { if (pos && !(cg->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; head = &cg->bpf.progs[atype]; hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; if (pl->prog == prog && pl->link == link) goto found; pos++; } } /* no link or prog match, skip the cgroup of this layer */ continue; found: progs = rcu_dereference_protected( desc->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); /* Remove the program from the array */ WARN_ONCE(bpf_prog_array_delete_safe_at(progs, pos), "Failed to purge a prog from array at index %d", pos); } } /** * __cgroup_bpf_detach() - Detach the program or link from a cgroup, and * propagate the change to descendants * @cgrp: The cgroup which descendants to traverse * @prog: A program to detach or NULL * @link: A link to detach or NULL * @type: Type of detach operation * * At most one of @prog or @link can be non-NULL. * Must be called with cgroup_mutex held. */ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, struct bpf_cgroup_link *link, enum bpf_attach_type type) { enum cgroup_bpf_attach_type atype; struct bpf_prog *old_prog; struct bpf_prog_list *pl; struct hlist_head *progs; u32 attach_btf_id = 0; u32 flags; if (prog) attach_btf_id = prog->aux->attach_btf_id; if (link) attach_btf_id = link->link.prog->aux->attach_btf_id; atype = bpf_cgroup_atype_find(type, attach_btf_id); if (atype < 0) return -EINVAL; progs = &cgrp->bpf.progs[atype]; flags = cgrp->bpf.flags[atype]; if (prog && link) /* only one of prog or link can be specified */ return -EINVAL; pl = find_detach_entry(progs, prog, link, flags & BPF_F_ALLOW_MULTI); if (IS_ERR(pl)) return PTR_ERR(pl); /* mark it deleted, so it's ignored while recomputing effective */ old_prog = pl->prog; pl->prog = NULL; pl->link = NULL; if (update_effective_progs(cgrp, atype)) { /* if update effective array failed replace the prog with a dummy prog*/ pl->prog = old_prog; pl->link = link; purge_effective_progs(cgrp, old_prog, link, atype); } /* now can actually delete it from this cgroup list */ hlist_del(&pl->node); kfree(pl); if (hlist_empty(progs)) /* last program was detached, reset flags to zero */ cgrp->bpf.flags[atype] = 0; if (old_prog) { if (type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(old_prog); bpf_prog_put(old_prog); } static_branch_dec(&cgroup_bpf_enabled_key[atype]); return 0; } static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type) { int ret; cgroup_lock(); ret = __cgroup_bpf_detach(cgrp, prog, NULL, type); cgroup_unlock(); return ret; } /* Must be called with cgroup_mutex held to avoid races. */ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr) { __u32 __user *prog_attach_flags = u64_to_user_ptr(attr->query.prog_attach_flags); bool effective_query = attr->query.query_flags & BPF_F_QUERY_EFFECTIVE; __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); enum bpf_attach_type type = attr->query.attach_type; enum cgroup_bpf_attach_type from_atype, to_atype; enum cgroup_bpf_attach_type atype; struct bpf_prog_array *effective; int cnt, ret = 0, i; int total_cnt = 0; u32 flags; if (effective_query && prog_attach_flags) return -EINVAL; if (type == BPF_LSM_CGROUP) { if (!effective_query && attr->query.prog_cnt && prog_ids && !prog_attach_flags) return -EINVAL; from_atype = CGROUP_LSM_START; to_atype = CGROUP_LSM_END; flags = 0; } else { from_atype = to_cgroup_bpf_attach_type(type); if (from_atype < 0) return -EINVAL; to_atype = from_atype; flags = cgrp->bpf.flags[from_atype]; } for (atype = from_atype; atype <= to_atype; atype++) { if (effective_query) { effective = rcu_dereference_protected(cgrp->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); total_cnt += bpf_prog_array_length(effective); } else { total_cnt += prog_list_length(&cgrp->bpf.progs[atype]); } } /* always output uattr->query.attach_flags as 0 during effective query */ flags = effective_query ? 0 : flags; if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) return -EFAULT; if (copy_to_user(&uattr->query.prog_cnt, &total_cnt, sizeof(total_cnt))) return -EFAULT; if (attr->query.prog_cnt == 0 || !prog_ids || !total_cnt) /* return early if user requested only program count + flags */ return 0; if (attr->query.prog_cnt < total_cnt) { total_cnt = attr->query.prog_cnt; ret = -ENOSPC; } for (atype = from_atype; atype <= to_atype && total_cnt; atype++) { if (effective_query) { effective = rcu_dereference_protected(cgrp->bpf.effective[atype], lockdep_is_held(&cgroup_mutex)); cnt = min_t(int, bpf_prog_array_length(effective), total_cnt); ret = bpf_prog_array_copy_to_user(effective, prog_ids, cnt); } else { struct hlist_head *progs; struct bpf_prog_list *pl; struct bpf_prog *prog; u32 id; progs = &cgrp->bpf.progs[atype]; cnt = min_t(int, prog_list_length(progs), total_cnt); i = 0; hlist_for_each_entry(pl, progs, node) { prog = prog_list_prog(pl); id = prog->aux->id; if (copy_to_user(prog_ids + i, &id, sizeof(id))) return -EFAULT; if (++i == cnt) break; } if (prog_attach_flags) { flags = cgrp->bpf.flags[atype]; for (i = 0; i < cnt; i++) if (copy_to_user(prog_attach_flags + i, &flags, sizeof(flags))) return -EFAULT; prog_attach_flags += cnt; } } prog_ids += cnt; total_cnt -= cnt; } return ret; } static int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr) { int ret; cgroup_lock(); ret = __cgroup_bpf_query(cgrp, attr, uattr); cgroup_unlock(); return ret; } int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog) { struct bpf_prog *replace_prog = NULL; struct cgroup *cgrp; int ret; cgrp = cgroup_get_from_fd(attr->target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); if ((attr->attach_flags & BPF_F_ALLOW_MULTI) && (attr->attach_flags & BPF_F_REPLACE)) { replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, ptype); if (IS_ERR(replace_prog)) { cgroup_put(cgrp); return PTR_ERR(replace_prog); } } ret = cgroup_bpf_attach(cgrp, prog, replace_prog, NULL, attr->attach_type, attr->attach_flags); if (replace_prog) bpf_prog_put(replace_prog); cgroup_put(cgrp); return ret; } int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { struct bpf_prog *prog; struct cgroup *cgrp; int ret; cgrp = cgroup_get_from_fd(attr->target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype); if (IS_ERR(prog)) prog = NULL; ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type); if (prog) bpf_prog_put(prog); cgroup_put(cgrp); return ret; } static void bpf_cgroup_link_release(struct bpf_link *link) { struct bpf_cgroup_link *cg_link = container_of(link, struct bpf_cgroup_link, link); struct cgroup *cg; /* link might have been auto-detached by dying cgroup already, * in that case our work is done here */ if (!cg_link->cgroup) return; cgroup_lock(); /* re-check cgroup under lock again */ if (!cg_link->cgroup) { cgroup_unlock(); return; } WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link, cg_link->type)); if (cg_link->type == BPF_LSM_CGROUP) bpf_trampoline_unlink_cgroup_shim(cg_link->link.prog); cg = cg_link->cgroup; cg_link->cgroup = NULL; cgroup_unlock(); cgroup_put(cg); } static void bpf_cgroup_link_dealloc(struct bpf_link *link) { struct bpf_cgroup_link *cg_link = container_of(link, struct bpf_cgroup_link, link); kfree(cg_link); } static int bpf_cgroup_link_detach(struct bpf_link *link) { bpf_cgroup_link_release(link); return 0; } static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_cgroup_link *cg_link = container_of(link, struct bpf_cgroup_link, link); u64 cg_id = 0; cgroup_lock(); if (cg_link->cgroup) cg_id = cgroup_id(cg_link->cgroup); cgroup_unlock(); seq_printf(seq, "cgroup_id:\t%llu\n" "attach_type:\t%d\n", cg_id, cg_link->type); } static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_cgroup_link *cg_link = container_of(link, struct bpf_cgroup_link, link); u64 cg_id = 0; cgroup_lock(); if (cg_link->cgroup) cg_id = cgroup_id(cg_link->cgroup); cgroup_unlock(); info->cgroup.cgroup_id = cg_id; info->cgroup.attach_type = cg_link->type; return 0; } static const struct bpf_link_ops bpf_cgroup_link_lops = { .release = bpf_cgroup_link_release, .dealloc = bpf_cgroup_link_dealloc, .detach = bpf_cgroup_link_detach, .update_prog = cgroup_bpf_replace, .show_fdinfo = bpf_cgroup_link_show_fdinfo, .fill_link_info = bpf_cgroup_link_fill_link_info, }; int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct bpf_link_primer link_primer; struct bpf_cgroup_link *link; struct cgroup *cgrp; int err; if (attr->link_create.flags) return -EINVAL; cgrp = cgroup_get_from_fd(attr->link_create.target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto out_put_cgroup; } bpf_link_init(&link->link, BPF_LINK_TYPE_CGROUP, &bpf_cgroup_link_lops, prog); link->cgroup = cgrp; link->type = attr->link_create.attach_type; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto out_put_cgroup; } err = cgroup_bpf_attach(cgrp, NULL, NULL, link, link->type, BPF_F_ALLOW_MULTI); if (err) { bpf_link_cleanup(&link_primer); goto out_put_cgroup; } return bpf_link_settle(&link_primer); out_put_cgroup: cgroup_put(cgrp); return err; } int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { struct cgroup *cgrp; int ret; cgrp = cgroup_get_from_fd(attr->query.target_fd); if (IS_ERR(cgrp)) return PTR_ERR(cgrp); ret = cgroup_bpf_query(cgrp, attr, uattr); cgroup_put(cgrp); return ret; } /** * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering * @sk: The socket sending or receiving traffic * @skb: The skb that is being sent or received * @atype: The type of program to be executed * * If no socket is passed, or the socket is not of type INET or INET6, * this function does nothing and returns 0. * * The program type passed in via @type must be suitable for network * filtering. No further check is performed to assert that. * * For egress packets, this function can return: * NET_XMIT_SUCCESS (0) - continue with packet output * NET_XMIT_DROP (1) - drop packet and notify TCP to call cwr * NET_XMIT_CN (2) - continue with packet output and notify TCP * to call cwr * -err - drop packet * * For ingress packets, this function will return -EPERM if any * attached program was found and if it returned != 1 during execution. * Otherwise 0 is returned. */ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum cgroup_bpf_attach_type atype) { unsigned int offset = -skb_network_offset(skb); struct sock *save_sk; void *saved_data_end; struct cgroup *cgrp; int ret; if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); save_sk = skb->sk; skb->sk = sk; __skb_push(skb, offset); /* compute pointers for the bpf prog */ bpf_compute_and_save_data_end(skb, &saved_data_end); if (atype == CGROUP_INET_EGRESS) { u32 flags = 0; bool cn; ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, skb, __bpf_prog_run_save_cb, 0, &flags); /* Return values of CGROUP EGRESS BPF programs are: * 0: drop packet * 1: keep packet * 2: drop packet and cn * 3: keep packet and cn * * The returned value is then converted to one of the NET_XMIT * or an error code that is then interpreted as drop packet * (and no cn): * 0: NET_XMIT_SUCCESS skb should be transmitted * 1: NET_XMIT_DROP skb should be dropped and cn * 2: NET_XMIT_CN skb should be transmitted and cn * 3: -err skb should be dropped */ cn = flags & BPF_RET_SET_CN; if (ret && !IS_ERR_VALUE((long)ret)) ret = -EFAULT; if (!ret) ret = (cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); else ret = (cn ? NET_XMIT_DROP : ret); } else { ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, skb, __bpf_prog_run_save_cb, 0, NULL); if (ret && !IS_ERR_VALUE((long)ret)) ret = -EFAULT; } bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); skb->sk = save_sk; return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb); /** * __cgroup_bpf_run_filter_sk() - Run a program on a sock * @sk: sock structure to manipulate * @atype: The type of program to be executed * * socket is passed is expected to be of type INET or INET6. * * The program type passed in via @type must be suitable for sock * filtering. No further check is performed to assert that. * * This function will return %-EPERM if any if an attached program was found * and if it returned != 1 during execution. In all other cases, 0 is returned. */ int __cgroup_bpf_run_filter_sk(struct sock *sk, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return bpf_prog_run_array_cg(&cgrp->bpf, atype, sk, bpf_prog_run, 0, NULL); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); /** * __cgroup_bpf_run_filter_sock_addr() - Run a program on a sock and * provided by user sockaddr * @sk: sock struct that will use sockaddr * @uaddr: sockaddr struct provided by user * @uaddrlen: Pointer to the size of the sockaddr struct provided by user. It is * read-only for AF_INET[6] uaddr but can be modified for AF_UNIX * uaddr. * @atype: The type of program to be executed * @t_ctx: Pointer to attach type specific context * @flags: Pointer to u32 which contains higher bits of BPF program * return value (OR'ed together). * * socket is expected to be of type INET, INET6 or UNIX. * * This function will return %-EPERM if an attached program is found and * returned value != 1 during execution. In all other cases, 0 is returned. */ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags) { struct bpf_sock_addr_kern ctx = { .sk = sk, .uaddr = uaddr, .t_ctx = t_ctx, }; struct sockaddr_storage unspec; struct cgroup *cgrp; int ret; /* Check socket family since not all sockets represent network * endpoint (e.g. AF_UNIX). */ if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6 && sk->sk_family != AF_UNIX) return 0; if (!ctx.uaddr) { memset(&unspec, 0, sizeof(unspec)); ctx.uaddr = (struct sockaddr *)&unspec; ctx.uaddrlen = 0; } else { ctx.uaddrlen = *uaddrlen; } cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0, flags); if (!ret && uaddr) *uaddrlen = ctx.uaddrlen; return ret; } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr); /** * __cgroup_bpf_run_filter_sock_ops() - Run a program on a sock * @sk: socket to get cgroup from * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains * sk with connection information (IP addresses, etc.) May not contain * cgroup info if it is a req sock. * @atype: The type of program to be executed * * socket passed is expected to be of type INET or INET6. * * The program type passed in via @type must be suitable for sock_ops * filtering. No further check is performed to assert that. * * This function will return %-EPERM if any if an attached program was found * and if it returned != 1 during execution. In all other cases, 0 is returned. */ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk, struct bpf_sock_ops_kern *sock_ops, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return bpf_prog_run_array_cg(&cgrp->bpf, atype, sock_ops, bpf_prog_run, 0, NULL); } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_ops); int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor, short access, enum cgroup_bpf_attach_type atype) { struct cgroup *cgrp; struct bpf_cgroup_dev_ctx ctx = { .access_type = (access << 16) | dev_type, .major = major, .minor = minor, }; int ret; rcu_read_lock(); cgrp = task_dfl_cgroup(current); ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0, NULL); rcu_read_unlock(); return ret; } BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags) { /* flags argument is not used now, * but provides an ability to extend the API. * verifier checks that its value is correct. */ enum bpf_cgroup_storage_type stype = cgroup_storage_type(map); struct bpf_cgroup_storage *storage; struct bpf_cg_run_ctx *ctx; void *ptr; /* get current cgroup storage from BPF run context */ ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); storage = ctx->prog_item->cgroup_storage[stype]; if (stype == BPF_CGROUP_STORAGE_SHARED) ptr = &READ_ONCE(storage->buf)->data[0]; else ptr = this_cpu_ptr(storage->percpu_buf); return (unsigned long)ptr; } const struct bpf_func_proto bpf_get_local_storage_proto = { .func = bpf_get_local_storage, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_ANYTHING, }; BPF_CALL_0(bpf_get_retval) { struct bpf_cg_run_ctx *ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); return ctx->retval; } const struct bpf_func_proto bpf_get_retval_proto = { .func = bpf_get_retval, .gpl_only = false, .ret_type = RET_INTEGER, }; BPF_CALL_1(bpf_set_retval, int, retval) { struct bpf_cg_run_ctx *ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx); ctx->retval = retval; return 0; } const struct bpf_func_proto bpf_set_retval_proto = { .func = bpf_set_retval, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, }; static const struct bpf_func_proto * cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; func_proto = cgroup_current_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: return bpf_base_func_proto(func_id, prog); } } static bool cgroup_dev_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (type == BPF_WRITE) return false; if (off < 0 || off + size > sizeof(struct bpf_cgroup_dev_ctx)) return false; /* The verifier guarantees that size > 0. */ if (off % size != 0) return false; switch (off) { case bpf_ctx_range(struct bpf_cgroup_dev_ctx, access_type): bpf_ctx_record_field_size(info, size_default); if (!bpf_ctx_narrow_access_ok(off, size, size_default)) return false; break; default: if (size != size_default) return false; } return true; } const struct bpf_prog_ops cg_dev_prog_ops = { }; const struct bpf_verifier_ops cg_dev_verifier_ops = { .get_func_proto = cgroup_dev_func_proto, .is_valid_access = cgroup_dev_is_valid_access, }; /** * __cgroup_bpf_run_filter_sysctl - Run a program on sysctl * * @head: sysctl table header * @table: sysctl table * @write: sysctl is being read (= 0) or written (= 1) * @buf: pointer to buffer (in and out) * @pcount: value-result argument: value is size of buffer pointed to by @buf, * result is size of @new_buf if program set new value, initial value * otherwise * @ppos: value-result argument: value is position at which read from or write * to sysctl is happening, result is new position if program overrode it, * initial value otherwise * @atype: type of program to be executed * * Program is run when sysctl is being accessed, either read or written, and * can allow or deny such access. * * This function will return %-EPERM if an attached program is found and * returned value != 1 during execution. In all other cases 0 is returned. */ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, struct ctl_table *table, int write, char **buf, size_t *pcount, loff_t *ppos, enum cgroup_bpf_attach_type atype) { struct bpf_sysctl_kern ctx = { .head = head, .table = table, .write = write, .ppos = ppos, .cur_val = NULL, .cur_len = PAGE_SIZE, .new_val = NULL, .new_len = 0, .new_updated = 0, }; struct cgroup *cgrp; loff_t pos = 0; int ret; ctx.cur_val = kmalloc_track_caller(ctx.cur_len, GFP_KERNEL); if (!ctx.cur_val || table->proc_handler(table, 0, ctx.cur_val, &ctx.cur_len, &pos)) { /* Let BPF program decide how to proceed. */ ctx.cur_len = 0; } if (write && *buf && *pcount) { /* BPF program should be able to override new value with a * buffer bigger than provided by user. */ ctx.new_val = kmalloc_track_caller(PAGE_SIZE, GFP_KERNEL); ctx.new_len = min_t(size_t, PAGE_SIZE, *pcount); if (ctx.new_val) { memcpy(ctx.new_val, *buf, ctx.new_len); } else { /* Let BPF program decide how to proceed. */ ctx.new_len = 0; } } rcu_read_lock(); cgrp = task_dfl_cgroup(current); ret = bpf_prog_run_array_cg(&cgrp->bpf, atype, &ctx, bpf_prog_run, 0, NULL); rcu_read_unlock(); kfree(ctx.cur_val); if (ret == 1 && ctx.new_updated) { kfree(*buf); *buf = ctx.new_val; *pcount = ctx.new_len; } else { kfree(ctx.new_val); } return ret; } #ifdef CONFIG_NET static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen, struct bpf_sockopt_buf *buf) { if (unlikely(max_optlen < 0)) return -EINVAL; if (unlikely(max_optlen > PAGE_SIZE)) { /* We don't expose optvals that are greater than PAGE_SIZE * to the BPF program. */ max_optlen = PAGE_SIZE; } if (max_optlen <= sizeof(buf->data)) { /* When the optval fits into BPF_SOCKOPT_KERN_BUF_SIZE * bytes avoid the cost of kzalloc. */ ctx->optval = buf->data; ctx->optval_end = ctx->optval + max_optlen; return max_optlen; } ctx->optval = kzalloc(max_optlen, GFP_USER); if (!ctx->optval) return -ENOMEM; ctx->optval_end = ctx->optval + max_optlen; return max_optlen; } static void sockopt_free_buf(struct bpf_sockopt_kern *ctx, struct bpf_sockopt_buf *buf) { if (ctx->optval == buf->data) return; kfree(ctx->optval); } static bool sockopt_buf_allocated(struct bpf_sockopt_kern *ctx, struct bpf_sockopt_buf *buf) { return ctx->optval != buf->data; } int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, int *optname, sockptr_t optval, int *optlen, char **kernel_optval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); struct bpf_sockopt_buf buf = {}; struct bpf_sockopt_kern ctx = { .sk = sk, .level = *level, .optname = *optname, }; int ret, max_optlen; /* Allocate a bit more than the initial user buffer for * BPF program. The canonical use case is overriding * TCP_CONGESTION(nv) to TCP_CONGESTION(cubic). */ max_optlen = max_t(int, 16, *optlen); max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) return max_optlen; ctx.optlen = *optlen; if (copy_from_sockptr(ctx.optval, optval, min(*optlen, max_optlen))) { ret = -EFAULT; goto out; } lock_sock(sk); ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_SETSOCKOPT, &ctx, bpf_prog_run, 0, NULL); release_sock(sk); if (ret) goto out; if (ctx.optlen == -1) { /* optlen set to -1, bypass kernel */ ret = 1; } else if (ctx.optlen > max_optlen || ctx.optlen < -1) { /* optlen is out of bounds */ if (*optlen > PAGE_SIZE && ctx.optlen >= 0) { pr_info_once("bpf setsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n", ctx.optlen, max_optlen); ret = 0; goto out; } ret = -EFAULT; } else { /* optlen within bounds, run kernel handler */ ret = 0; /* export any potential modifications */ *level = ctx.level; *optname = ctx.optname; /* optlen == 0 from BPF indicates that we should * use original userspace data. */ if (ctx.optlen != 0) { *optlen = ctx.optlen; /* We've used bpf_sockopt_kern->buf as an intermediary * storage, but the BPF program indicates that we need * to pass this data to the kernel setsockopt handler. * No way to export on-stack buf, have to allocate a * new buffer. */ if (!sockopt_buf_allocated(&ctx, &buf)) { void *p = kmalloc(ctx.optlen, GFP_USER); if (!p) { ret = -ENOMEM; goto out; } memcpy(p, ctx.optval, ctx.optlen); *kernel_optval = p; } else { *kernel_optval = ctx.optval; } /* export and don't free sockopt buf */ return 0; } } out: sockopt_free_buf(&ctx, &buf); return ret; } int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, int optname, sockptr_t optval, sockptr_t optlen, int max_optlen, int retval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); struct bpf_sockopt_buf buf = {}; struct bpf_sockopt_kern ctx = { .sk = sk, .level = level, .optname = optname, .current_task = current, }; int orig_optlen; int ret; orig_optlen = max_optlen; ctx.optlen = max_optlen; max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf); if (max_optlen < 0) return max_optlen; if (!retval) { /* If kernel getsockopt finished successfully, * copy whatever was returned to the user back * into our temporary buffer. Set optlen to the * one that kernel returned as well to let * BPF programs inspect the value. */ if (copy_from_sockptr(&ctx.optlen, optlen, sizeof(ctx.optlen))) { ret = -EFAULT; goto out; } if (ctx.optlen < 0) { ret = -EFAULT; goto out; } orig_optlen = ctx.optlen; if (copy_from_sockptr(ctx.optval, optval, min(ctx.optlen, max_optlen))) { ret = -EFAULT; goto out; } } lock_sock(sk); ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT, &ctx, bpf_prog_run, retval, NULL); release_sock(sk); if (ret < 0) goto out; if (!sockptr_is_null(optval) && (ctx.optlen > max_optlen || ctx.optlen < 0)) { if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) { pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n", ctx.optlen, max_optlen); ret = retval; goto out; } ret = -EFAULT; goto out; } if (ctx.optlen != 0) { if (!sockptr_is_null(optval) && copy_to_sockptr(optval, ctx.optval, ctx.optlen)) { ret = -EFAULT; goto out; } if (copy_to_sockptr(optlen, &ctx.optlen, sizeof(ctx.optlen))) { ret = -EFAULT; goto out; } } out: sockopt_free_buf(&ctx, &buf); return ret; } int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level, int optname, void *optval, int *optlen, int retval) { struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); struct bpf_sockopt_kern ctx = { .sk = sk, .level = level, .optname = optname, .optlen = *optlen, .optval = optval, .optval_end = optval + *optlen, .current_task = current, }; int ret; /* Note that __cgroup_bpf_run_filter_getsockopt doesn't copy * user data back into BPF buffer when reval != 0. This is * done as an optimization to avoid extra copy, assuming * kernel won't populate the data in case of an error. * Here we always pass the data and memset() should * be called if that data shouldn't be "exported". */ ret = bpf_prog_run_array_cg(&cgrp->bpf, CGROUP_GETSOCKOPT, &ctx, bpf_prog_run, retval, NULL); if (ret < 0) return ret; if (ctx.optlen > *optlen) return -EFAULT; /* BPF programs can shrink the buffer, export the modifications. */ if (ctx.optlen != 0) *optlen = ctx.optlen; return ret; } #endif static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp, size_t *lenp) { ssize_t tmp_ret = 0, ret; if (dir->header.parent) { tmp_ret = sysctl_cpy_dir(dir->header.parent, bufp, lenp); if (tmp_ret < 0) return tmp_ret; } ret = strscpy(*bufp, dir->header.ctl_table[0].procname, *lenp); if (ret < 0) return ret; *bufp += ret; *lenp -= ret; ret += tmp_ret; /* Avoid leading slash. */ if (!ret) return ret; tmp_ret = strscpy(*bufp, "/", *lenp); if (tmp_ret < 0) return tmp_ret; *bufp += tmp_ret; *lenp -= tmp_ret; return ret + tmp_ret; } BPF_CALL_4(bpf_sysctl_get_name, struct bpf_sysctl_kern *, ctx, char *, buf, size_t, buf_len, u64, flags) { ssize_t tmp_ret = 0, ret; if (!buf) return -EINVAL; if (!(flags & BPF_F_SYSCTL_BASE_NAME)) { if (!ctx->head) return -EINVAL; tmp_ret = sysctl_cpy_dir(ctx->head->parent, &buf, &buf_len); if (tmp_ret < 0) return tmp_ret; } ret = strscpy(buf, ctx->table->procname, buf_len); return ret < 0 ? ret : tmp_ret + ret; } static const struct bpf_func_proto bpf_sysctl_get_name_proto = { .func = bpf_sysctl_get_name, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_ANYTHING, }; static int copy_sysctl_value(char *dst, size_t dst_len, char *src, size_t src_len) { if (!dst) return -EINVAL; if (!dst_len) return -E2BIG; if (!src || !src_len) { memset(dst, 0, dst_len); return -EINVAL; } memcpy(dst, src, min(dst_len, src_len)); if (dst_len > src_len) { memset(dst + src_len, '\0', dst_len - src_len); return src_len; } dst[dst_len - 1] = '\0'; return -E2BIG; } BPF_CALL_3(bpf_sysctl_get_current_value, struct bpf_sysctl_kern *, ctx, char *, buf, size_t, buf_len) { return copy_sysctl_value(buf, buf_len, ctx->cur_val, ctx->cur_len); } static const struct bpf_func_proto bpf_sysctl_get_current_value_proto = { .func = bpf_sysctl_get_current_value, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, }; BPF_CALL_3(bpf_sysctl_get_new_value, struct bpf_sysctl_kern *, ctx, char *, buf, size_t, buf_len) { if (!ctx->write) { if (buf && buf_len) memset(buf, '\0', buf_len); return -EINVAL; } return copy_sysctl_value(buf, buf_len, ctx->new_val, ctx->new_len); } static const struct bpf_func_proto bpf_sysctl_get_new_value_proto = { .func = bpf_sysctl_get_new_value, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_UNINIT_MEM, .arg3_type = ARG_CONST_SIZE, }; BPF_CALL_3(bpf_sysctl_set_new_value, struct bpf_sysctl_kern *, ctx, const char *, buf, size_t, buf_len) { if (!ctx->write || !ctx->new_val || !ctx->new_len || !buf || !buf_len) return -EINVAL; if (buf_len > PAGE_SIZE - 1) return -E2BIG; memcpy(ctx->new_val, buf, buf_len); ctx->new_len = buf_len; ctx->new_updated = 1; return 0; } static const struct bpf_func_proto bpf_sysctl_set_new_value_proto = { .func = bpf_sysctl_set_new_value, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg3_type = ARG_CONST_SIZE, }; static const struct bpf_func_proto * sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; func_proto = cgroup_current_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { case BPF_FUNC_sysctl_get_name: return &bpf_sysctl_get_name_proto; case BPF_FUNC_sysctl_get_current_value: return &bpf_sysctl_get_current_value_proto; case BPF_FUNC_sysctl_get_new_value: return &bpf_sysctl_get_new_value_proto; case BPF_FUNC_sysctl_set_new_value: return &bpf_sysctl_set_new_value_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: return bpf_base_func_proto(func_id, prog); } } static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off + size > sizeof(struct bpf_sysctl) || off % size) return false; switch (off) { case bpf_ctx_range(struct bpf_sysctl, write): if (type != BPF_READ) return false; bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); case bpf_ctx_range(struct bpf_sysctl, file_pos): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); } else { return size == size_default; } default: return false; } } static u32 sysctl_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; u32 read_size; switch (si->off) { case offsetof(struct bpf_sysctl, write): *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sysctl_kern, write, sizeof_field(struct bpf_sysctl_kern, write), target_size)); break; case offsetof(struct bpf_sysctl, file_pos): /* ppos is a pointer so it should be accessed via indirect * loads and stores. Also for stores additional temporary * register is used since neither src_reg nor dst_reg can be * overridden. */ if (type == BPF_WRITE) { int treg = BPF_REG_9; if (si->src_reg == treg || si->dst_reg == treg) --treg; if (si->src_reg == treg || si->dst_reg == treg) --treg; *insn++ = BPF_STX_MEM( BPF_DW, si->dst_reg, treg, offsetof(struct bpf_sysctl_kern, tmp_reg)); *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, ppos)); *insn++ = BPF_RAW_INSN( BPF_CLASS(si->code) | BPF_MEM | BPF_SIZEOF(u32), treg, si->src_reg, bpf_ctx_narrow_access_offset( 0, sizeof(u32), sizeof(loff_t)), si->imm); *insn++ = BPF_LDX_MEM( BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sysctl_kern, tmp_reg)); } else { *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct bpf_sysctl_kern, ppos), si->dst_reg, si->src_reg, offsetof(struct bpf_sysctl_kern, ppos)); read_size = bpf_size_to_bytes(BPF_SIZE(si->code)); *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->dst_reg, bpf_ctx_narrow_access_offset( 0, read_size, sizeof(loff_t))); } *target_size = sizeof(u32); break; } return insn - insn_buf; } const struct bpf_verifier_ops cg_sysctl_verifier_ops = { .get_func_proto = sysctl_func_proto, .is_valid_access = sysctl_is_valid_access, .convert_ctx_access = sysctl_convert_ctx_access, }; const struct bpf_prog_ops cg_sysctl_prog_ops = { }; #ifdef CONFIG_NET BPF_CALL_1(bpf_get_netns_cookie_sockopt, struct bpf_sockopt_kern *, ctx) { const struct net *net = ctx ? sock_net(ctx->sk) : &init_net; return net->net_cookie; } static const struct bpf_func_proto bpf_get_netns_cookie_sockopt_proto = { .func = bpf_get_netns_cookie_sockopt, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX_OR_NULL, }; #endif static const struct bpf_func_proto * cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func_proto; func_proto = cgroup_common_func_proto(func_id, prog); if (func_proto) return func_proto; func_proto = cgroup_current_func_proto(func_id, prog); if (func_proto) return func_proto; switch (func_id) { #ifdef CONFIG_NET case BPF_FUNC_get_netns_cookie: return &bpf_get_netns_cookie_sockopt_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; case BPF_FUNC_setsockopt: if (prog->expected_attach_type == BPF_CGROUP_SETSOCKOPT) return &bpf_sk_setsockopt_proto; return NULL; case BPF_FUNC_getsockopt: if (prog->expected_attach_type == BPF_CGROUP_SETSOCKOPT) return &bpf_sk_getsockopt_proto; return NULL; #endif #ifdef CONFIG_INET case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: return bpf_base_func_proto(func_id, prog); } } static bool cg_sockopt_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { const int size_default = sizeof(__u32); if (off < 0 || off >= sizeof(struct bpf_sockopt)) return false; if (off % size != 0) return false; if (type == BPF_WRITE) { switch (off) { case offsetof(struct bpf_sockopt, retval): if (size != size_default) return false; return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT; case offsetof(struct bpf_sockopt, optname): fallthrough; case offsetof(struct bpf_sockopt, level): if (size != size_default) return false; return prog->expected_attach_type == BPF_CGROUP_SETSOCKOPT; case offsetof(struct bpf_sockopt, optlen): return size == size_default; default: return false; } } switch (off) { case offsetof(struct bpf_sockopt, sk): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_SOCKET; break; case offsetof(struct bpf_sockopt, optval): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET; break; case offsetof(struct bpf_sockopt, optval_end): if (size != sizeof(__u64)) return false; info->reg_type = PTR_TO_PACKET_END; break; case offsetof(struct bpf_sockopt, retval): if (size != size_default) return false; return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT; default: if (size != size_default) return false; break; } return true; } #define CG_SOCKOPT_READ_FIELD(F) \ BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F), \ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sockopt_kern, F)) #define CG_SOCKOPT_WRITE_FIELD(F) \ BPF_RAW_INSN((BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F) | \ BPF_MEM | BPF_CLASS(si->code)), \ si->dst_reg, si->src_reg, \ offsetof(struct bpf_sockopt_kern, F), \ si->imm) static u32 cg_sockopt_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { struct bpf_insn *insn = insn_buf; switch (si->off) { case offsetof(struct bpf_sockopt, sk): *insn++ = CG_SOCKOPT_READ_FIELD(sk); break; case offsetof(struct bpf_sockopt, level): if (type == BPF_WRITE) *insn++ = CG_SOCKOPT_WRITE_FIELD(level); else *insn++ = CG_SOCKOPT_READ_FIELD(level); break; case offsetof(struct bpf_sockopt, optname): if (type == BPF_WRITE) *insn++ = CG_SOCKOPT_WRITE_FIELD(optname); else *insn++ = CG_SOCKOPT_READ_FIELD(optname); break; case offsetof(struct bpf_sockopt, optlen): if (type == BPF_WRITE) *insn++ = CG_SOCKOPT_WRITE_FIELD(optlen); else *insn++ = CG_SOCKOPT_READ_FIELD(optlen); break; case offsetof(struct bpf_sockopt, retval): BUILD_BUG_ON(offsetof(struct bpf_cg_run_ctx, run_ctx) != 0); if (type == BPF_WRITE) { int treg = BPF_REG_9; if (si->src_reg == treg || si->dst_reg == treg) --treg; if (si->src_reg == treg || si->dst_reg == treg) --treg; *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, treg, offsetof(struct bpf_sockopt_kern, tmp_reg)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task), treg, si->dst_reg, offsetof(struct bpf_sockopt_kern, current_task)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), treg, treg, offsetof(struct task_struct, bpf_ctx)); *insn++ = BPF_RAW_INSN(BPF_CLASS(si->code) | BPF_MEM | BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), treg, si->src_reg, offsetof(struct bpf_cg_run_ctx, retval), si->imm); *insn++ = BPF_LDX_MEM(BPF_DW, treg, si->dst_reg, offsetof(struct bpf_sockopt_kern, tmp_reg)); } else { *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, current_task), si->dst_reg, si->src_reg, offsetof(struct bpf_sockopt_kern, current_task)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct task_struct, bpf_ctx), si->dst_reg, si->dst_reg, offsetof(struct task_struct, bpf_ctx)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_cg_run_ctx, retval), si->dst_reg, si->dst_reg, offsetof(struct bpf_cg_run_ctx, retval)); } break; case offsetof(struct bpf_sockopt, optval): *insn++ = CG_SOCKOPT_READ_FIELD(optval); break; case offsetof(struct bpf_sockopt, optval_end): *insn++ = CG_SOCKOPT_READ_FIELD(optval_end); break; } return insn - insn_buf; } static int cg_sockopt_get_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { /* Nothing to do for sockopt argument. The data is kzalloc'ated. */ return 0; } const struct bpf_verifier_ops cg_sockopt_verifier_ops = { .get_func_proto = cg_sockopt_func_proto, .is_valid_access = cg_sockopt_is_valid_access, .convert_ctx_access = cg_sockopt_convert_ctx_access, .gen_prologue = cg_sockopt_get_prologue, }; const struct bpf_prog_ops cg_sockopt_prog_ops = { }; /* Common helpers for cgroup hooks. */ const struct bpf_func_proto * cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; case BPF_FUNC_get_retval: switch (prog->expected_attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: return NULL; default: return &bpf_get_retval_proto; } case BPF_FUNC_set_retval: switch (prog->expected_attach_type) { case BPF_CGROUP_INET_INGRESS: case BPF_CGROUP_INET_EGRESS: case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_UDP4_RECVMSG: case BPF_CGROUP_UDP6_RECVMSG: case BPF_CGROUP_UNIX_RECVMSG: case BPF_CGROUP_INET4_GETPEERNAME: case BPF_CGROUP_INET6_GETPEERNAME: case BPF_CGROUP_UNIX_GETPEERNAME: case BPF_CGROUP_INET4_GETSOCKNAME: case BPF_CGROUP_INET6_GETSOCKNAME: case BPF_CGROUP_UNIX_GETSOCKNAME: return NULL; default: return &bpf_set_retval_proto; } default: return NULL; } } /* Common helpers for cgroup hooks with valid process context. */ const struct bpf_func_proto * cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_get_current_uid_gid: return &bpf_get_current_uid_gid_proto; case BPF_FUNC_get_current_comm: return &bpf_get_current_comm_proto; #ifdef CONFIG_CGROUP_NET_CLASSID case BPF_FUNC_get_cgroup_classid: return &bpf_get_cgroup_classid_curr_proto; #endif default: return NULL; } } |
| 74 76 69 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIMENS_H #define _LINUX_TIMENS_H #include <linux/sched.h> #include <linux/nsproxy.h> #include <linux/ns_common.h> #include <linux/err.h> #include <linux/time64.h> struct user_namespace; extern struct user_namespace init_user_ns; struct vm_area_struct; struct timens_offsets { struct timespec64 monotonic; struct timespec64 boottime; }; struct time_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; struct ns_common ns; struct timens_offsets offsets; struct page *vvar_page; /* If set prevents changing offsets after any task joined namespace. */ bool frozen_offsets; } __randomize_layout; extern struct time_namespace init_time_ns; #ifdef CONFIG_TIME_NS extern int vdso_join_timens(struct task_struct *task, struct time_namespace *ns); extern void timens_commit(struct task_struct *tsk, struct time_namespace *ns); static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { refcount_inc(&ns->ns.count); return ns; } struct time_namespace *copy_time_ns(unsigned long flags, struct user_namespace *user_ns, struct time_namespace *old_ns); void free_time_ns(struct time_namespace *ns); void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk); struct page *find_timens_vvar_page(struct vm_area_struct *vma); static inline void put_time_ns(struct time_namespace *ns) { if (refcount_dec_and_test(&ns->ns.count)) free_time_ns(ns); } void proc_timens_show_offsets(struct task_struct *p, struct seq_file *m); struct proc_timens_offset { int clockid; struct timespec64 val; }; int proc_timens_set_offset(struct file *file, struct task_struct *p, struct proc_timens_offset *offsets, int n); static inline void timens_add_monotonic(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_add(*ts, ns_offsets->monotonic); } static inline void timens_add_boottime(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_add(*ts, ns_offsets->boottime); } static inline u64 timens_add_boottime_ns(u64 nsec) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; return nsec + timespec64_to_ns(&ns_offsets->boottime); } static inline void timens_sub_boottime(struct timespec64 *ts) { struct timens_offsets *ns_offsets = ¤t->nsproxy->time_ns->offsets; *ts = timespec64_sub(*ts, ns_offsets->boottime); } ktime_t do_timens_ktime_to_host(clockid_t clockid, ktime_t tim, struct timens_offsets *offsets); static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) { struct time_namespace *ns = current->nsproxy->time_ns; if (likely(ns == &init_time_ns)) return tim; return do_timens_ktime_to_host(clockid, tim, &ns->offsets); } #else static inline int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) { return 0; } static inline void timens_commit(struct task_struct *tsk, struct time_namespace *ns) { } static inline struct time_namespace *get_time_ns(struct time_namespace *ns) { return NULL; } static inline void put_time_ns(struct time_namespace *ns) { } static inline struct time_namespace *copy_time_ns(unsigned long flags, struct user_namespace *user_ns, struct time_namespace *old_ns) { if (flags & CLONE_NEWTIME) return ERR_PTR(-EINVAL); return old_ns; } static inline void timens_on_fork(struct nsproxy *nsproxy, struct task_struct *tsk) { return; } static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) { return NULL; } static inline void timens_add_monotonic(struct timespec64 *ts) { } static inline void timens_add_boottime(struct timespec64 *ts) { } static inline u64 timens_add_boottime_ns(u64 nsec) { return nsec; } static inline void timens_sub_boottime(struct timespec64 *ts) { } static inline ktime_t timens_ktime_to_host(clockid_t clockid, ktime_t tim) { return tim; } #endif struct vdso_data *arch_get_vdso_data(void *vvar_page); #endif /* _LINUX_TIMENS_H */ |
| 11 6 1 5 2 1 4 62 55 7 7 5 62 61 1 8 2 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 6 6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SR-IPv6 implementation * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/slab.h> #include <linux/rhashtable.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/seg6.h> #include <net/genetlink.h> #include <linux/seg6.h> #include <linux/seg6_genl.h> #include <net/seg6_hmac.h> bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced) { unsigned int tlv_offset; int max_last_entry; int trailing; if (srh->type != IPV6_SRCRT_TYPE_4) return false; if (((srh->hdrlen + 1) << 3) != len) return false; if (!reduced && srh->segments_left > srh->first_segment) { return false; } else { max_last_entry = (srh->hdrlen / 2) - 1; if (srh->first_segment > max_last_entry) return false; if (srh->segments_left > srh->first_segment + 1) return false; } tlv_offset = sizeof(*srh) + ((srh->first_segment + 1) << 4); trailing = len - tlv_offset; if (trailing < 0) return false; while (trailing) { struct sr6_tlv *tlv; unsigned int tlv_len; if (trailing < sizeof(*tlv)) return false; tlv = (struct sr6_tlv *)((unsigned char *)srh + tlv_offset); tlv_len = sizeof(*tlv) + tlv->len; trailing -= tlv_len; if (trailing < 0) return false; tlv_offset += tlv_len; } return true; } struct ipv6_sr_hdr *seg6_get_srh(struct sk_buff *skb, int flags) { struct ipv6_sr_hdr *srh; int len, srhoff = 0; if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, &flags) < 0) return NULL; if (!pskb_may_pull(skb, srhoff + sizeof(*srh))) return NULL; srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); len = (srh->hdrlen + 1) << 3; if (!pskb_may_pull(skb, srhoff + len)) return NULL; /* note that pskb_may_pull may change pointers in header; * for this reason it is necessary to reload them when needed. */ srh = (struct ipv6_sr_hdr *)(skb->data + srhoff); if (!seg6_validate_srh(srh, len, true)) return NULL; return srh; } /* Determine if an ICMP invoking packet contains a segment routing * header. If it does, extract the offset to the true destination * address, which is in the first segment address. */ void seg6_icmp_srh(struct sk_buff *skb, struct inet6_skb_parm *opt) { __u16 network_header = skb->network_header; struct ipv6_sr_hdr *srh; /* Update network header to point to the invoking packet * inside the ICMP packet, so we can use the seg6_get_srh() * helper. */ skb_reset_network_header(skb); srh = seg6_get_srh(skb, 0); if (!srh) goto out; if (srh->type != IPV6_SRCRT_TYPE_4) goto out; opt->flags |= IP6SKB_SEG6; opt->srhoff = (unsigned char *)srh - skb->data; out: /* Restore the network header back to the ICMP packet */ skb->network_header = network_header; } static struct genl_family seg6_genl_family; static const struct nla_policy seg6_genl_policy[SEG6_ATTR_MAX + 1] = { [SEG6_ATTR_DST] = { .type = NLA_BINARY, .len = sizeof(struct in6_addr) }, [SEG6_ATTR_DSTLEN] = { .type = NLA_S32, }, [SEG6_ATTR_HMACKEYID] = { .type = NLA_U32, }, [SEG6_ATTR_SECRET] = { .type = NLA_BINARY, }, [SEG6_ATTR_SECRETLEN] = { .type = NLA_U8, }, [SEG6_ATTR_ALGID] = { .type = NLA_U8, }, [SEG6_ATTR_HMACINFO] = { .type = NLA_NESTED, }, }; #ifdef CONFIG_IPV6_SEG6_HMAC static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct seg6_pernet_data *sdata; struct seg6_hmac_info *hinfo; u32 hmackeyid; char *secret; int err = 0; u8 algid; u8 slen; sdata = seg6_pernet(net); if (!info->attrs[SEG6_ATTR_HMACKEYID] || !info->attrs[SEG6_ATTR_SECRETLEN] || !info->attrs[SEG6_ATTR_ALGID]) return -EINVAL; hmackeyid = nla_get_u32(info->attrs[SEG6_ATTR_HMACKEYID]); slen = nla_get_u8(info->attrs[SEG6_ATTR_SECRETLEN]); algid = nla_get_u8(info->attrs[SEG6_ATTR_ALGID]); if (hmackeyid == 0) return -EINVAL; if (slen > SEG6_HMAC_SECRET_LEN) return -EINVAL; mutex_lock(&sdata->lock); hinfo = seg6_hmac_info_lookup(net, hmackeyid); if (!slen) { err = seg6_hmac_info_del(net, hmackeyid); goto out_unlock; } if (!info->attrs[SEG6_ATTR_SECRET]) { err = -EINVAL; goto out_unlock; } if (slen > nla_len(info->attrs[SEG6_ATTR_SECRET])) { err = -EINVAL; goto out_unlock; } if (hinfo) { err = seg6_hmac_info_del(net, hmackeyid); if (err) goto out_unlock; } secret = (char *)nla_data(info->attrs[SEG6_ATTR_SECRET]); hinfo = kzalloc(sizeof(*hinfo), GFP_KERNEL); if (!hinfo) { err = -ENOMEM; goto out_unlock; } memcpy(hinfo->secret, secret, slen); hinfo->slen = slen; hinfo->alg_id = algid; hinfo->hmackeyid = hmackeyid; err = seg6_hmac_info_add(net, hmackeyid, hinfo); if (err) kfree(hinfo); out_unlock: mutex_unlock(&sdata->lock); return err; } #else static int seg6_genl_sethmac(struct sk_buff *skb, struct genl_info *info) { return -ENOTSUPP; } #endif static int seg6_genl_set_tunsrc(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct in6_addr *val, *t_old, *t_new; struct seg6_pernet_data *sdata; sdata = seg6_pernet(net); if (!info->attrs[SEG6_ATTR_DST]) return -EINVAL; val = nla_data(info->attrs[SEG6_ATTR_DST]); t_new = kmemdup(val, sizeof(*val), GFP_KERNEL); if (!t_new) return -ENOMEM; mutex_lock(&sdata->lock); t_old = sdata->tun_src; rcu_assign_pointer(sdata->tun_src, t_new); mutex_unlock(&sdata->lock); synchronize_net(); kfree(t_old); return 0; } static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct in6_addr *tun_src; struct sk_buff *msg; void *hdr; msg = genlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &seg6_genl_family, 0, SEG6_CMD_GET_TUNSRC); if (!hdr) goto free_msg; rcu_read_lock(); tun_src = rcu_dereference(seg6_pernet(net)->tun_src); if (nla_put(msg, SEG6_ATTR_DST, sizeof(struct in6_addr), tun_src)) goto nla_put_failure; rcu_read_unlock(); genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); nla_put_failure: rcu_read_unlock(); free_msg: nlmsg_free(msg); return -ENOMEM; } #ifdef CONFIG_IPV6_SEG6_HMAC static int __seg6_hmac_fill_info(struct seg6_hmac_info *hinfo, struct sk_buff *msg) { if (nla_put_u32(msg, SEG6_ATTR_HMACKEYID, hinfo->hmackeyid) || nla_put_u8(msg, SEG6_ATTR_SECRETLEN, hinfo->slen) || nla_put(msg, SEG6_ATTR_SECRET, hinfo->slen, hinfo->secret) || nla_put_u8(msg, SEG6_ATTR_ALGID, hinfo->alg_id)) return -1; return 0; } static int __seg6_genl_dumphmac_element(struct seg6_hmac_info *hinfo, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &seg6_genl_family, flags, cmd); if (!hdr) return -ENOMEM; if (__seg6_hmac_fill_info(hinfo, skb) < 0) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } static int seg6_genl_dumphmac_start(struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct seg6_pernet_data *sdata; struct rhashtable_iter *iter; sdata = seg6_pernet(net); iter = (struct rhashtable_iter *)cb->args[0]; if (!iter) { iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) return -ENOMEM; cb->args[0] = (long)iter; } rhashtable_walk_enter(&sdata->hmac_infos, iter); return 0; } static int seg6_genl_dumphmac_done(struct netlink_callback *cb) { struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; rhashtable_walk_exit(iter); kfree(iter); return 0; } static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) { struct rhashtable_iter *iter = (struct rhashtable_iter *)cb->args[0]; struct seg6_hmac_info *hinfo; int ret; rhashtable_walk_start(iter); for (;;) { hinfo = rhashtable_walk_next(iter); if (IS_ERR(hinfo)) { if (PTR_ERR(hinfo) == -EAGAIN) continue; ret = PTR_ERR(hinfo); goto done; } else if (!hinfo) { break; } ret = __seg6_genl_dumphmac_element(hinfo, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, SEG6_CMD_DUMPHMAC); if (ret) goto done; } ret = skb->len; done: rhashtable_walk_stop(iter); return ret; } #else static int seg6_genl_dumphmac_start(struct netlink_callback *cb) { return 0; } static int seg6_genl_dumphmac_done(struct netlink_callback *cb) { return 0; } static int seg6_genl_dumphmac(struct sk_buff *skb, struct netlink_callback *cb) { return -ENOTSUPP; } #endif static int __net_init seg6_net_init(struct net *net) { struct seg6_pernet_data *sdata; sdata = kzalloc(sizeof(*sdata), GFP_KERNEL); if (!sdata) return -ENOMEM; mutex_init(&sdata->lock); sdata->tun_src = kzalloc(sizeof(*sdata->tun_src), GFP_KERNEL); if (!sdata->tun_src) { kfree(sdata); return -ENOMEM; } net->ipv6.seg6_data = sdata; if (seg6_hmac_net_init(net)) { kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); return -ENOMEM; } return 0; } static void __net_exit seg6_net_exit(struct net *net) { struct seg6_pernet_data *sdata = seg6_pernet(net); seg6_hmac_net_exit(net); kfree(rcu_dereference_raw(sdata->tun_src)); kfree(sdata); } static struct pernet_operations ip6_segments_ops = { .init = seg6_net_init, .exit = seg6_net_exit, }; static const struct genl_ops seg6_genl_ops[] = { { .cmd = SEG6_CMD_SETHMAC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_sethmac, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_DUMPHMAC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .start = seg6_genl_dumphmac_start, .dumpit = seg6_genl_dumphmac, .done = seg6_genl_dumphmac_done, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_SET_TUNSRC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_set_tunsrc, .flags = GENL_ADMIN_PERM, }, { .cmd = SEG6_CMD_GET_TUNSRC, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = seg6_genl_get_tunsrc, .flags = GENL_ADMIN_PERM, }, }; static struct genl_family seg6_genl_family __ro_after_init = { .hdrsize = 0, .name = SEG6_GENL_NAME, .version = SEG6_GENL_VERSION, .maxattr = SEG6_ATTR_MAX, .policy = seg6_genl_policy, .netnsok = true, .parallel_ops = true, .ops = seg6_genl_ops, .n_ops = ARRAY_SIZE(seg6_genl_ops), .resv_start_op = SEG6_CMD_GET_TUNSRC + 1, .module = THIS_MODULE, }; int __init seg6_init(void) { int err; err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; err = genl_register_family(&seg6_genl_family); if (err) goto out_unregister_pernet; err = seg6_iptunnel_init(); if (err) goto out_unregister_genl; err = seg6_local_init(); if (err) goto out_unregister_iptun; err = seg6_hmac_init(); if (err) goto out_unregister_seg6; pr_info("Segment Routing with IPv6\n"); out: return err; out_unregister_seg6: seg6_local_exit(); out_unregister_iptun: seg6_iptunnel_exit(); out_unregister_genl: genl_unregister_family(&seg6_genl_family); out_unregister_pernet: unregister_pernet_subsys(&ip6_segments_ops); goto out; } void seg6_exit(void) { seg6_hmac_exit(); seg6_local_exit(); seg6_iptunnel_exit(); genl_unregister_family(&seg6_genl_family); unregister_pernet_subsys(&ip6_segments_ops); } |
| 5 5 3 1 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Spanning tree protocol; BPDU handling * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/netfilter_bridge.h> #include <linux/etherdevice.h> #include <linux/llc.h> #include <linux/slab.h> #include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> #include <net/stp.h> #include <asm/unaligned.h> #include "br_private.h" #include "br_private_stp.h" #define STP_HZ 256 #define LLC_RESERVE sizeof(struct llc_pdu_un) static int br_send_bpdu_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { return dev_queue_xmit(skb); } static void br_send_bpdu(struct net_bridge_port *p, const unsigned char *data, int length) { struct sk_buff *skb; skb = dev_alloc_skb(length+LLC_RESERVE); if (!skb) return; skb->dev = p->dev; skb->protocol = htons(ETH_P_802_2); skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, LLC_RESERVE); __skb_put_data(skb, data, length); llc_pdu_header_init(skb, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, LLC_SAP_BSPAN, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); llc_mac_hdr_init(skb, p->dev->dev_addr, p->br->group_addr); skb_reset_mac_header(skb); NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, dev_net(p->dev), NULL, skb, NULL, skb->dev, br_send_bpdu_finish); } static inline void br_set_ticks(unsigned char *dest, int j) { unsigned long ticks = (STP_HZ * j)/ HZ; put_unaligned_be16(ticks, dest); } static inline int br_get_ticks(const unsigned char *src) { unsigned long ticks = get_unaligned_be16(src); return DIV_ROUND_UP(ticks * HZ, STP_HZ); } /* called under bridge lock */ void br_send_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *bpdu) { unsigned char buf[35]; if (p->br->stp_enabled != BR_KERNEL_STP) return; buf[0] = 0; buf[1] = 0; buf[2] = 0; buf[3] = BPDU_TYPE_CONFIG; buf[4] = (bpdu->topology_change ? 0x01 : 0) | (bpdu->topology_change_ack ? 0x80 : 0); buf[5] = bpdu->root.prio[0]; buf[6] = bpdu->root.prio[1]; buf[7] = bpdu->root.addr[0]; buf[8] = bpdu->root.addr[1]; buf[9] = bpdu->root.addr[2]; buf[10] = bpdu->root.addr[3]; buf[11] = bpdu->root.addr[4]; buf[12] = bpdu->root.addr[5]; buf[13] = (bpdu->root_path_cost >> 24) & 0xFF; buf[14] = (bpdu->root_path_cost >> 16) & 0xFF; buf[15] = (bpdu->root_path_cost >> 8) & 0xFF; buf[16] = bpdu->root_path_cost & 0xFF; buf[17] = bpdu->bridge_id.prio[0]; buf[18] = bpdu->bridge_id.prio[1]; buf[19] = bpdu->bridge_id.addr[0]; buf[20] = bpdu->bridge_id.addr[1]; buf[21] = bpdu->bridge_id.addr[2]; buf[22] = bpdu->bridge_id.addr[3]; buf[23] = bpdu->bridge_id.addr[4]; buf[24] = bpdu->bridge_id.addr[5]; buf[25] = (bpdu->port_id >> 8) & 0xFF; buf[26] = bpdu->port_id & 0xFF; br_set_ticks(buf+27, bpdu->message_age); br_set_ticks(buf+29, bpdu->max_age); br_set_ticks(buf+31, bpdu->hello_time); br_set_ticks(buf+33, bpdu->forward_delay); br_send_bpdu(p, buf, 35); p->stp_xstats.tx_bpdu++; } /* called under bridge lock */ void br_send_tcn_bpdu(struct net_bridge_port *p) { unsigned char buf[4]; if (p->br->stp_enabled != BR_KERNEL_STP) return; buf[0] = 0; buf[1] = 0; buf[2] = 0; buf[3] = BPDU_TYPE_TCN; br_send_bpdu(p, buf, 4); p->stp_xstats.tx_tcn++; } /* * Called from llc. * * NO locks, but rcu_read_lock */ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { struct net_bridge_port *p; struct net_bridge *br; const unsigned char *buf; if (!pskb_may_pull(skb, 4)) goto err; /* compare of protocol id and version */ buf = skb->data; if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0) goto err; p = br_port_get_check_rcu(dev); if (!p) goto err; br = p->br; spin_lock(&br->lock); if (br->stp_enabled != BR_KERNEL_STP) goto out; if (!(br->dev->flags & IFF_UP)) goto out; if (p->state == BR_STATE_DISABLED) goto out; if (!ether_addr_equal(eth_hdr(skb)->h_dest, br->group_addr)) goto out; if (p->flags & BR_BPDU_GUARD) { br_notice(br, "BPDU received on blocked port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); br_stp_disable_port(p); goto out; } buf = skb_pull(skb, 3); if (buf[0] == BPDU_TYPE_CONFIG) { struct br_config_bpdu bpdu; if (!pskb_may_pull(skb, 32)) goto out; buf = skb->data; bpdu.topology_change = (buf[1] & 0x01) ? 1 : 0; bpdu.topology_change_ack = (buf[1] & 0x80) ? 1 : 0; bpdu.root.prio[0] = buf[2]; bpdu.root.prio[1] = buf[3]; bpdu.root.addr[0] = buf[4]; bpdu.root.addr[1] = buf[5]; bpdu.root.addr[2] = buf[6]; bpdu.root.addr[3] = buf[7]; bpdu.root.addr[4] = buf[8]; bpdu.root.addr[5] = buf[9]; bpdu.root_path_cost = (buf[10] << 24) | (buf[11] << 16) | (buf[12] << 8) | buf[13]; bpdu.bridge_id.prio[0] = buf[14]; bpdu.bridge_id.prio[1] = buf[15]; bpdu.bridge_id.addr[0] = buf[16]; bpdu.bridge_id.addr[1] = buf[17]; bpdu.bridge_id.addr[2] = buf[18]; bpdu.bridge_id.addr[3] = buf[19]; bpdu.bridge_id.addr[4] = buf[20]; bpdu.bridge_id.addr[5] = buf[21]; bpdu.port_id = (buf[22] << 8) | buf[23]; bpdu.message_age = br_get_ticks(buf+24); bpdu.max_age = br_get_ticks(buf+26); bpdu.hello_time = br_get_ticks(buf+28); bpdu.forward_delay = br_get_ticks(buf+30); if (bpdu.message_age > bpdu.max_age) { if (net_ratelimit()) br_notice(p->br, "port %u config from %pM" " (message_age %ul > max_age %ul)\n", p->port_no, eth_hdr(skb)->h_source, bpdu.message_age, bpdu.max_age); goto out; } br_received_config_bpdu(p, &bpdu); } else if (buf[0] == BPDU_TYPE_TCN) { br_received_tcn_bpdu(p); } out: spin_unlock(&br->lock); err: kfree_skb(skb); } |
| 1 1 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_TC_GACT_H #define __NET_TC_GACT_H #include <net/act_api.h> #include <linux/tc_act/tc_gact.h> struct tcf_gact { struct tc_action common; #ifdef CONFIG_GACT_PROB u16 tcfg_ptype; u16 tcfg_pval; int tcfg_paction; atomic_t packets; #endif }; #define to_gact(a) ((struct tcf_gact *)a) static inline bool __is_tcf_gact_act(const struct tc_action *a, int act, bool is_ext) { #ifdef CONFIG_NET_CLS_ACT struct tcf_gact *gact; if (a->ops && a->ops->id != TCA_ID_GACT) return false; gact = to_gact(a); if ((!is_ext && gact->tcf_action == act) || (is_ext && TC_ACT_EXT_CMP(gact->tcf_action, act))) return true; #endif return false; } static inline bool is_tcf_gact_ok(const struct tc_action *a) { return __is_tcf_gact_act(a, TC_ACT_OK, false); } static inline bool is_tcf_gact_shot(const struct tc_action *a) { return __is_tcf_gact_act(a, TC_ACT_SHOT, false); } static inline bool is_tcf_gact_trap(const struct tc_action *a) { return __is_tcf_gact_act(a, TC_ACT_TRAP, false); } static inline bool is_tcf_gact_goto_chain(const struct tc_action *a) { return __is_tcf_gact_act(a, TC_ACT_GOTO_CHAIN, true); } static inline u32 tcf_gact_goto_chain_index(const struct tc_action *a) { return READ_ONCE(a->tcfa_action) & TC_ACT_EXT_VAL_MASK; } static inline bool is_tcf_gact_continue(const struct tc_action *a) { return __is_tcf_gact_act(a, TC_ACT_UNSPEC, false); } static inline bool is_tcf_gact_reclassify(const struct tc_action *a) { return __is_tcf_gact_act(a, TC_ACT_RECLASSIFY, false); } static inline bool is_tcf_gact_pipe(const struct tc_action *a) { return __is_tcf_gact_act(a, TC_ACT_PIPE, false); } #endif /* __NET_TC_GACT_H */ |
| 2140 3 95 8 2048 130 8 1 60 69 69 590 588 12 1282 290 113 180 290 3 158 169 40 165 146 8 7 135 182 23 26 4 4 92 421 570 166 415 70 167 32 21 10321 10086 10326 10389 163 171 8 8 1 38 35 2 1 6 1 3 23 14 37 1 2 2 2 38 7 6 12 1 20 17 3 19 20 20 20 182 937 893 937 948 26 3 24 29 23 7 37 37 1 36 578 583 559 21 9 23 23 898 579 1 1 224 102 1273 1 101 70 165 52 5 15 20 19 1 1 5 2 1 4 897 6 6 139 141 1 136 3 2 19 422 426 2 1 1 38 22 2 9 9 479 1 1 477 2 472 3 478 475 3 90 390 94 3 11 202 83 161 1 243 244 243 84 161 244 38 1 1 1 2 11 13 37 536 533 9 1 536 535 539 112 119 2 112 118 119 111 1 71 27 3 5 1 1 78 29 115 2 106 103 70 42 1 516 517 2 1 517 484 514 34 3 2 32 33 38 24 2 12 10 22 24 557 1 6 145 1 419 524 554 186 1 4 169 2 170 184 2969 1 2948 2825 130 1 2819 2968 2960 38 2931 2949 1529 1527 122 1 1403 1510 1524 18 1517 1515 1521 89 4 89 87 93 93 2 9751 92 9141 718 9118 97 721 42 9776 9770 4 9851 9142 3 8867 167 167 3 327 9025 105 8964 245 21 8664 426 167 8787 164 8466 8466 46 9129 8461 1 69 8528 8264 8480 709 1 10 570 704 465 573 11 678 714 248 724 181 718 267 544 82 3 248 20 250 255 1 15 258 237 256 473 478 32 40 434 1 383 19 470 208 391 340 1 46 4 109 57 53 451 1 421 18 44 485 1 475 1 1 524 6 47 475 73 174 101 123 4 29 43 1 1 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET An implementation of the SOCKET network access protocol. * * Version: @(#)socket.c 1.1.93 18/02/95 * * Authors: Orest Zborowski, <obz@Kodak.COM> * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Fixes: * Anonymous : NOTSOCK/BADF cleanup. Error fix in * shutdown() * Alan Cox : verify_area() fixes * Alan Cox : Removed DDI * Jonathan Kamens : SOCK_DGRAM reconnect bug * Alan Cox : Moved a load of checks to the very * top level. * Alan Cox : Move address structures to/from user * mode above the protocol layers. * Rob Janssen : Allow 0 length sends. * Alan Cox : Asynchronous I/O support (cribbed from the * tty drivers). * Niibe Yutaka : Asynchronous I/O for writes (4.4BSD style) * Jeff Uphoff : Made max number of sockets command-line * configurable. * Matti Aarnio : Made the number of sockets dynamic, * to be allocated when needed, and mr. * Uphoff's max is used as max to be * allowed to allocate. * Linus : Argh. removed all the socket allocation * altogether: it's in the inode now. * Alan Cox : Made sock_alloc()/sock_release() public * for NetROM and future kernel nfsd type * stuff. * Alan Cox : sendmsg/recvmsg basics. * Tom Dyas : Export net symbols. * Marcin Dalecki : Fixed problems with CONFIG_NET="n". * Alan Cox : Added thread locking to sys_* calls * for sockets. May have errors at the * moment. * Kevin Buhr : Fixed the dumb errors in the above. * Andi Kleen : Some small cleanups, optimizations, * and fixed a copy_from_user() bug. * Tigran Aivazian : sys_send(args) calls sys_sendto(args, NULL, 0) * Tigran Aivazian : Made listen(2) backlog sanity checks * protocol-independent * * This module is effectively the top level interface to the BSD socket * paradigm. * * Based upon Swansea University Computer Society NET3.039 */ #include <linux/bpf-cgroup.h> #include <linux/ethtool.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/file.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/interrupt.h> #include <linux/thread_info.h> #include <linux/rcupdate.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/mutex.h> #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/ptp_classify.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/cache.h> #include <linux/module.h> #include <linux/highmem.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/compat.h> #include <linux/kmod.h> #include <linux/audit.h> #include <linux/wireless.h> #include <linux/nsproxy.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/nospec.h> #include <linux/indirect_call_wrapper.h> #include <linux/io_uring/net.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <net/compat.h> #include <net/wext.h> #include <net/cls_cgroup.h> #include <net/sock.h> #include <linux/netfilter.h> #include <linux/if_tun.h> #include <linux/ipv6_route.h> #include <linux/route.h> #include <linux/termios.h> #include <linux/sockios.h> #include <net/busy_poll.h> #include <linux/errqueue.h> #include <linux/ptp_clock_kernel.h> #include <trace/events/sock.h> #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; #endif static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to); static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from); static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait); static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); static void sock_splice_eof(struct file *file); #ifdef CONFIG_PROC_FS static void sock_show_fdinfo(struct seq_file *m, struct file *f) { struct socket *sock = f->private_data; const struct proto_ops *ops = READ_ONCE(sock->ops); if (ops->show_fdinfo) ops->show_fdinfo(m, sock); } #else #define sock_show_fdinfo NULL #endif /* * Socket files have a set of 'special' operations as well as the generic file ones. These don't appear * in the operation structures but are done directly via the socketcall() multiplexor. */ static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, .llseek = no_llseek, .read_iter = sock_read_iter, .write_iter = sock_write_iter, .poll = sock_poll, .unlocked_ioctl = sock_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = compat_sock_ioctl, #endif .uring_cmd = io_uring_cmd_sock, .mmap = sock_mmap, .release = sock_close, .fasync = sock_fasync, .splice_write = splice_to_socket, .splice_read = sock_splice_read, .splice_eof = sock_splice_eof, .show_fdinfo = sock_show_fdinfo, }; static const char * const pf_family_names[] = { [PF_UNSPEC] = "PF_UNSPEC", [PF_UNIX] = "PF_UNIX/PF_LOCAL", [PF_INET] = "PF_INET", [PF_AX25] = "PF_AX25", [PF_IPX] = "PF_IPX", [PF_APPLETALK] = "PF_APPLETALK", [PF_NETROM] = "PF_NETROM", [PF_BRIDGE] = "PF_BRIDGE", [PF_ATMPVC] = "PF_ATMPVC", [PF_X25] = "PF_X25", [PF_INET6] = "PF_INET6", [PF_ROSE] = "PF_ROSE", [PF_DECnet] = "PF_DECnet", [PF_NETBEUI] = "PF_NETBEUI", [PF_SECURITY] = "PF_SECURITY", [PF_KEY] = "PF_KEY", [PF_NETLINK] = "PF_NETLINK/PF_ROUTE", [PF_PACKET] = "PF_PACKET", [PF_ASH] = "PF_ASH", [PF_ECONET] = "PF_ECONET", [PF_ATMSVC] = "PF_ATMSVC", [PF_RDS] = "PF_RDS", [PF_SNA] = "PF_SNA", [PF_IRDA] = "PF_IRDA", [PF_PPPOX] = "PF_PPPOX", [PF_WANPIPE] = "PF_WANPIPE", [PF_LLC] = "PF_LLC", [PF_IB] = "PF_IB", [PF_MPLS] = "PF_MPLS", [PF_CAN] = "PF_CAN", [PF_TIPC] = "PF_TIPC", [PF_BLUETOOTH] = "PF_BLUETOOTH", [PF_IUCV] = "PF_IUCV", [PF_RXRPC] = "PF_RXRPC", [PF_ISDN] = "PF_ISDN", [PF_PHONET] = "PF_PHONET", [PF_IEEE802154] = "PF_IEEE802154", [PF_CAIF] = "PF_CAIF", [PF_ALG] = "PF_ALG", [PF_NFC] = "PF_NFC", [PF_VSOCK] = "PF_VSOCK", [PF_KCM] = "PF_KCM", [PF_QIPCRTR] = "PF_QIPCRTR", [PF_SMC] = "PF_SMC", [PF_XDP] = "PF_XDP", [PF_MCTP] = "PF_MCTP", }; /* * The protocol list. Each protocol is registered in here. */ static DEFINE_SPINLOCK(net_family_lock); static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly; /* * Support routines. * Move socket addresses back and forth across the kernel/user * divide and look after the messy bits. */ /** * move_addr_to_kernel - copy a socket address into kernel space * @uaddr: Address in user space * @kaddr: Address in kernel space * @ulen: Length in user space * * The address is copied into kernel space. If the provided address is * too long an error code of -EINVAL is returned. If the copy gives * invalid addresses -EFAULT is returned. On a success 0 is returned. */ int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr) { if (ulen < 0 || ulen > sizeof(struct sockaddr_storage)) return -EINVAL; if (ulen == 0) return 0; if (copy_from_user(kaddr, uaddr, ulen)) return -EFAULT; return audit_sockaddr(ulen, kaddr); } /** * move_addr_to_user - copy an address to user space * @kaddr: kernel space address * @klen: length of address in kernel * @uaddr: user space address * @ulen: pointer to user length field * * The value pointed to by ulen on entry is the buffer length available. * This is overwritten with the buffer space used. -EINVAL is returned * if an overlong buffer is specified or a negative buffer size. -EFAULT * is returned if either the buffer or the length field are not * accessible. * After copying the data up to the limit the user specifies, the true * length of the data is written over the length limit the user * specified. Zero is returned for a success. */ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen, void __user *uaddr, int __user *ulen) { int err; int len; BUG_ON(klen > sizeof(struct sockaddr_storage)); err = get_user(len, ulen); if (err) return err; if (len > klen) len = klen; if (len < 0) return -EINVAL; if (len) { if (audit_sockaddr(klen, kaddr)) return -ENOMEM; if (copy_to_user(uaddr, kaddr, len)) return -EFAULT; } /* * "fromlen shall refer to the value before truncation.." * 1003.1g */ return __put_user(klen, ulen); } static struct kmem_cache *sock_inode_cachep __ro_after_init; static struct inode *sock_alloc_inode(struct super_block *sb) { struct socket_alloc *ei; ei = alloc_inode_sb(sb, sock_inode_cachep, GFP_KERNEL); if (!ei) return NULL; init_waitqueue_head(&ei->socket.wq.wait); ei->socket.wq.fasync_list = NULL; ei->socket.wq.flags = 0; ei->socket.state = SS_UNCONNECTED; ei->socket.flags = 0; ei->socket.ops = NULL; ei->socket.sk = NULL; ei->socket.file = NULL; return &ei->vfs_inode; } static void sock_free_inode(struct inode *inode) { struct socket_alloc *ei; ei = container_of(inode, struct socket_alloc, vfs_inode); kmem_cache_free(sock_inode_cachep, ei); } static void init_once(void *foo) { struct socket_alloc *ei = (struct socket_alloc *)foo; inode_init_once(&ei->vfs_inode); } static void init_inodecache(void) { sock_inode_cachep = kmem_cache_create("sock_inode_cache", sizeof(struct socket_alloc), 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT), init_once); BUG_ON(sock_inode_cachep == NULL); } static const struct super_operations sockfs_ops = { .alloc_inode = sock_alloc_inode, .free_inode = sock_free_inode, .statfs = simple_statfs, }; /* * sockfs_dname() is called from d_path(). */ static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "socket:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations sockfs_dentry_operations = { .d_dname = sockfs_dname, }; static int sockfs_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *suffix, void *value, size_t size) { if (value) { if (dentry->d_name.len + 1 > size) return -ERANGE; memcpy(value, dentry->d_name.name, dentry->d_name.len + 1); } return dentry->d_name.len + 1; } #define XATTR_SOCKPROTONAME_SUFFIX "sockprotoname" #define XATTR_NAME_SOCKPROTONAME (XATTR_SYSTEM_PREFIX XATTR_SOCKPROTONAME_SUFFIX) #define XATTR_NAME_SOCKPROTONAME_LEN (sizeof(XATTR_NAME_SOCKPROTONAME)-1) static const struct xattr_handler sockfs_xattr_handler = { .name = XATTR_NAME_SOCKPROTONAME, .get = sockfs_xattr_get, }; static int sockfs_security_xattr_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) { /* Handled by LSM. */ return -EAGAIN; } static const struct xattr_handler sockfs_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, .set = sockfs_security_xattr_set, }; static const struct xattr_handler * const sockfs_xattr_handlers[] = { &sockfs_xattr_handler, &sockfs_security_xattr_handler, NULL }; static int sockfs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, SOCKFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &sockfs_ops; ctx->dops = &sockfs_dentry_operations; ctx->xattr = sockfs_xattr_handlers; return 0; } static struct vfsmount *sock_mnt __read_mostly; static struct file_system_type sock_fs_type = { .name = "sockfs", .init_fs_context = sockfs_init_fs_context, .kill_sb = kill_anon_super, }; /* * Obtains the first available file descriptor and sets it up for use. * * These functions create file structures and maps them to fd space * of the current process. On success it returns file descriptor * and file struct implicitly stored in sock->file. * Note that another thread may close file descriptor before we return * from this function. We use the fact that now we do not refer * to socket after mapping. If one day we will need it, this * function will increment ref. count on file by 1. * * In any case returned fd MAY BE not valid! * This race condition is unavoidable * with shared fd spaces, we cannot solve it inside kernel, * but we take care of internal coherence yet. */ /** * sock_alloc_file - Bind a &socket to a &file * @sock: socket * @flags: file status flags * @dname: protocol name * * Returns the &file bound with @sock, implicitly storing it * in sock->file. If dname is %NULL, sets to "". * * On failure @sock is released, and an ERR pointer is returned. * * This function uses GFP_KERNEL internally. */ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) { struct file *file; if (!dname) dname = sock->sk ? sock->sk->sk_prot_creator->name : ""; file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname, O_RDWR | (flags & O_NONBLOCK), &socket_file_ops); if (IS_ERR(file)) { sock_release(sock); return file; } file->f_mode |= FMODE_NOWAIT; sock->file = file; file->private_data = sock; stream_open(SOCK_INODE(sock), file); return file; } EXPORT_SYMBOL(sock_alloc_file); static int sock_map_fd(struct socket *sock, int flags) { struct file *newfile; int fd = get_unused_fd_flags(flags); if (unlikely(fd < 0)) { sock_release(sock); return fd; } newfile = sock_alloc_file(sock, flags, NULL); if (!IS_ERR(newfile)) { fd_install(fd, newfile); return fd; } put_unused_fd(fd); return PTR_ERR(newfile); } /** * sock_from_file - Return the &socket bounded to @file. * @file: file * * On failure returns %NULL. */ struct socket *sock_from_file(struct file *file) { if (file->f_op == &socket_file_ops) return file->private_data; /* set in sock_alloc_file */ return NULL; } EXPORT_SYMBOL(sock_from_file); /** * sockfd_lookup - Go from a file number to its socket slot * @fd: file handle * @err: pointer to an error code return * * The file handle passed in is locked and the socket it is bound * to is returned. If an error occurs the err pointer is overwritten * with a negative errno code and NULL is returned. The function checks * for both invalid handles and passing a handle which is not a socket. * * On a success the socket object pointer is returned. */ struct socket *sockfd_lookup(int fd, int *err) { struct file *file; struct socket *sock; file = fget(fd); if (!file) { *err = -EBADF; return NULL; } sock = sock_from_file(file); if (!sock) { *err = -ENOTSOCK; fput(file); } return sock; } EXPORT_SYMBOL(sockfd_lookup); static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) { struct fd f = fdget(fd); struct socket *sock; *err = -EBADF; if (f.file) { sock = sock_from_file(f.file); if (likely(sock)) { *fput_needed = f.flags & FDPUT_FPUT; return sock; } *err = -ENOTSOCK; fdput(f); } return NULL; } static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, size_t size) { ssize_t len; ssize_t used = 0; len = security_inode_listsecurity(d_inode(dentry), buffer, size); if (len < 0) return len; used += len; if (buffer) { if (size < used) return -ERANGE; buffer += len; } len = (XATTR_NAME_SOCKPROTONAME_LEN + 1); used += len; if (buffer) { if (size < used) return -ERANGE; memcpy(buffer, XATTR_NAME_SOCKPROTONAME, len); buffer += len; } return used; } static int sockfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { int err = simple_setattr(&nop_mnt_idmap, dentry, iattr); if (!err && (iattr->ia_valid & ATTR_UID)) { struct socket *sock = SOCKET_I(d_inode(dentry)); if (sock->sk) sock->sk->sk_uid = iattr->ia_uid; else err = -ENOENT; } return err; } static const struct inode_operations sockfs_inode_ops = { .listxattr = sockfs_listxattr, .setattr = sockfs_setattr, }; /** * sock_alloc - allocate a socket * * Allocate a new inode and socket object. The two are bound together * and initialised. The socket is then returned. If we are out of inodes * NULL is returned. This functions uses GFP_KERNEL internally. */ struct socket *sock_alloc(void) { struct inode *inode; struct socket *sock; inode = new_inode_pseudo(sock_mnt->mnt_sb); if (!inode) return NULL; sock = SOCKET_I(inode); inode->i_ino = get_next_ino(); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_op = &sockfs_inode_ops; return sock; } EXPORT_SYMBOL(sock_alloc); static void __sock_release(struct socket *sock, struct inode *inode) { const struct proto_ops *ops = READ_ONCE(sock->ops); if (ops) { struct module *owner = ops->owner; if (inode) inode_lock(inode); ops->release(sock); sock->sk = NULL; if (inode) inode_unlock(inode); sock->ops = NULL; module_put(owner); } if (sock->wq.fasync_list) pr_err("%s: fasync list not empty!\n", __func__); if (!sock->file) { iput(SOCK_INODE(sock)); return; } sock->file = NULL; } /** * sock_release - close a socket * @sock: socket to close * * The socket is released from the protocol stack if it has a release * callback, and the inode is then released if the socket is bound to * an inode not a file. */ void sock_release(struct socket *sock) { __sock_release(sock, NULL); } EXPORT_SYMBOL(sock_release); void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) { u8 flags = *tx_flags; if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) { flags |= SKBTX_HW_TSTAMP; /* PTP hardware clocks can provide a free running cycle counter * as a time base for virtual clocks. Tell driver to use the * free running cycle counter for timestamp if socket is bound * to virtual clock. */ if (tsflags & SOF_TIMESTAMPING_BIND_PHC) flags |= SKBTX_HW_TSTAMP_USE_CYCLES; } if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE) flags |= SKBTX_SW_TSTAMP; if (tsflags & SOF_TIMESTAMPING_TX_SCHED) flags |= SKBTX_SCHED_TSTAMP; *tx_flags = flags; } EXPORT_SYMBOL(__sock_tx_timestamp); INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *, size_t)); INDIRECT_CALLABLE_DECLARE(int inet6_sendmsg(struct socket *, struct msghdr *, size_t)); static noinline void call_trace_sock_send_length(struct sock *sk, int ret, int flags) { trace_sock_send_length(sk, ret, 0); } static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->sendmsg, inet6_sendmsg, inet_sendmsg, sock, msg, msg_data_left(msg)); BUG_ON(ret == -EIOCBQUEUED); if (trace_sock_send_length_enabled()) call_trace_sock_send_length(sock->sk, ret, 0); return ret; } static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) { int err = security_socket_sendmsg(sock, msg, msg_data_left(msg)); return err ?: sock_sendmsg_nosec(sock, msg); } /** * sock_sendmsg - send a message through @sock * @sock: socket * @msg: message to send * * Sends @msg through @sock, passing through LSM. * Returns the number of bytes sent, or an error code. */ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; struct sockaddr_storage address; int save_len = msg->msg_namelen; int ret; if (msg->msg_name) { memcpy(&address, msg->msg_name, msg->msg_namelen); msg->msg_name = &address; } ret = __sock_sendmsg(sock, msg); msg->msg_name = save_addr; msg->msg_namelen = save_len; return ret; } EXPORT_SYMBOL(sock_sendmsg); /** * kernel_sendmsg - send a message through @sock (kernel-space) * @sock: socket * @msg: message header * @vec: kernel vec * @num: vec array length * @size: total message data size * * Builds the message data with @vec and sends it through @sock. * Returns the number of bytes sent, or an error code. */ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { iov_iter_kvec(&msg->msg_iter, ITER_SOURCE, vec, num, size); return sock_sendmsg(sock, msg); } EXPORT_SYMBOL(kernel_sendmsg); /** * kernel_sendmsg_locked - send a message through @sock (kernel-space) * @sk: sock * @msg: message header * @vec: output s/g array * @num: output s/g array length * @size: total message data size * * Builds the message data with @vec and sends it through @sock. * Returns the number of bytes sent, or an error code. * Caller must hold @sk. */ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { struct socket *sock = sk->sk_socket; const struct proto_ops *ops = READ_ONCE(sock->ops); if (!ops->sendmsg_locked) return sock_no_sendmsg_locked(sk, msg, size); iov_iter_kvec(&msg->msg_iter, ITER_SOURCE, vec, num, size); return ops->sendmsg_locked(sk, msg, msg_data_left(msg)); } EXPORT_SYMBOL(kernel_sendmsg_locked); static bool skb_is_err_queue(const struct sk_buff *skb) { /* pkt_type of skbs enqueued on the error queue are set to * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do * in recvmsg, since skbs received on a local socket will never * have a pkt_type of PACKET_OUTGOING. */ return skb->pkt_type == PACKET_OUTGOING; } /* On transmit, software and hardware timestamps are returned independently. * As the two skb clones share the hardware timestamp, which may be updated * before the software timestamp is received, a hardware TX timestamp may be * returned only if there is no software TX timestamp. Ignore false software * timestamps, which may be made in the __sock_recv_timestamp() call when the * option SO_TIMESTAMP_OLD(NS) is enabled on the socket, even when the skb has a * hardware timestamp. */ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) { return skb->tstamp && !false_tstamp && skb_is_err_queue(skb); } static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index) { bool cycles = READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); struct net_device *orig_dev; ktime_t hwtstamp; rcu_read_lock(); orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); if (orig_dev) { *if_index = orig_dev->ifindex; hwtstamp = netdev_get_tstamp(orig_dev, shhwtstamps, cycles); } else { hwtstamp = shhwtstamps->hwtstamp; } rcu_read_unlock(); return hwtstamp; } static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb, int if_index) { struct scm_ts_pktinfo ts_pktinfo; struct net_device *orig_dev; if (!skb_mac_header_was_set(skb)) return; memset(&ts_pktinfo, 0, sizeof(ts_pktinfo)); if (!if_index) { rcu_read_lock(); orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); if (orig_dev) if_index = orig_dev->ifindex; rcu_read_unlock(); } ts_pktinfo.if_index = if_index; ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb); put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO, sizeof(ts_pktinfo), &ts_pktinfo); } /* * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP) */ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); struct scm_timestamping_internal tss; int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); int if_index; ktime_t hwtstamp; u32 tsflags; /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ if (need_software_tstamp && skb->tstamp == 0) { __net_timestamp(skb); false_tstamp = 1; } if (need_software_tstamp) { if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { struct __kernel_sock_timeval tv; skb_get_new_timestamp(skb, &tv); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(tv), &tv); } else { struct __kernel_old_timeval tv; skb_get_timestamp(skb, &tv); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } } else { if (new_tstamp) { struct __kernel_timespec ts; skb_get_new_timestampns(skb, &ts); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(ts), &ts); } else { struct __kernel_old_timespec ts; skb_get_timestampns(skb, &ts); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts), &ts); } } } memset(&tss, 0, sizeof(tss)); tsflags = READ_ONCE(sk->sk_tsflags); if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && !skb_is_swtx_tstamp(skb, false_tstamp)) { if_index = 0; if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) hwtstamp = get_timestamp(sk, skb, &if_index); else hwtstamp = shhwtstamps->hwtstamp; if (tsflags & SOF_TIMESTAMPING_BIND_PHC) hwtstamp = ptp_convert_timestamp(&hwtstamp, READ_ONCE(sk->sk_bind_phc)); if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) { empty = 0; if ((tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && !skb_is_err_queue(skb)) put_ts_pktinfo(msg, skb, if_index); } } if (!empty) { if (sock_flag(sk, SOCK_TSTAMP_NEW)) put_cmsg_scm_timestamping64(msg, &tss); else put_cmsg_scm_timestamping(msg, &tss); if (skb_is_err_queue(skb) && skb->len && SKB_EXT_ERR(skb)->opt_stats) put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS, skb->len, skb->data); } } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); #ifdef CONFIG_WIRELESS void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int ack; if (!sock_flag(sk, SOCK_WIFI_STATUS)) return; if (!skb->wifi_acked_valid) return; ack = skb->wifi_acked; put_cmsg(msg, SOL_SOCKET, SCM_WIFI_STATUS, sizeof(ack), &ack); } EXPORT_SYMBOL_GPL(__sock_recv_wifi_status); #endif static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && SOCK_SKB_CB(skb)->dropcount) put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL, sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount); } static void sock_recv_mark(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { if (sock_flag(sk, SOCK_RCVMARK) && skb) { /* We must use a bounce buffer for CONFIG_HARDENED_USERCOPY=y */ __u32 mark = skb->mark; put_cmsg(msg, SOL_SOCKET, SO_MARK, sizeof(__u32), &mark); } } void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { sock_recv_timestamp(msg, sk, skb); sock_recv_drops(msg, sk, skb); sock_recv_mark(msg, sk, skb); } EXPORT_SYMBOL_GPL(__sock_recv_cmsgs); INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *, size_t, int)); INDIRECT_CALLABLE_DECLARE(int inet6_recvmsg(struct socket *, struct msghdr *, size_t, int)); static noinline void call_trace_sock_recv_length(struct sock *sk, int ret, int flags) { trace_sock_recv_length(sk, ret, flags); } static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, int flags) { int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->recvmsg, inet6_recvmsg, inet_recvmsg, sock, msg, msg_data_left(msg), flags); if (trace_sock_recv_length_enabled()) call_trace_sock_recv_length(sock->sk, ret, flags); return ret; } /** * sock_recvmsg - receive a message from @sock * @sock: socket * @msg: message to receive * @flags: message flags * * Receives @msg from @sock, passing through LSM. Returns the total number * of bytes received, or an error. */ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags) { int err = security_socket_recvmsg(sock, msg, msg_data_left(msg), flags); return err ?: sock_recvmsg_nosec(sock, msg, flags); } EXPORT_SYMBOL(sock_recvmsg); /** * kernel_recvmsg - Receive a message from a socket (kernel space) * @sock: The socket to receive the message from * @msg: Received message * @vec: Input s/g array for message data * @num: Size of input s/g array * @size: Number of bytes to read * @flags: Message flags (MSG_DONTWAIT, etc...) * * On return the msg structure contains the scatter/gather array passed in the * vec argument. The array is modified so that it consists of the unfilled * portion of the original array. * * The returned value is the total number of bytes received, or an error. */ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { msg->msg_control_is_user = false; iov_iter_kvec(&msg->msg_iter, ITER_DEST, vec, num, size); return sock_recvmsg(sock, msg, flags); } EXPORT_SYMBOL(kernel_recvmsg); static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct socket *sock = file->private_data; const struct proto_ops *ops; ops = READ_ONCE(sock->ops); if (unlikely(!ops->splice_read)) return copy_splice_read(file, ppos, pipe, len, flags); return ops->splice_read(sock, ppos, pipe, len, flags); } static void sock_splice_eof(struct file *file) { struct socket *sock = file->private_data; const struct proto_ops *ops; ops = READ_ONCE(sock->ops); if (ops->splice_eof) ops->splice_eof(sock); } static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; struct msghdr msg = {.msg_iter = *to, .msg_iocb = iocb}; ssize_t res; if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (iocb->ki_pos != 0) return -ESPIPE; if (!iov_iter_count(to)) /* Match SYS5 behaviour */ return 0; res = sock_recvmsg(sock, &msg, msg.msg_flags); *to = msg.msg_iter; return res; } static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; struct msghdr msg = {.msg_iter = *from, .msg_iocb = iocb}; ssize_t res; if (iocb->ki_pos != 0) return -ESPIPE; if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } /* * Atomic setting of ioctl hooks to avoid race * with module unload. */ static DEFINE_MUTEX(br_ioctl_mutex); static int (*br_ioctl_hook)(struct net *net, struct net_bridge *br, unsigned int cmd, struct ifreq *ifr, void __user *uarg); void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br, unsigned int cmd, struct ifreq *ifr, void __user *uarg)) { mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; mutex_unlock(&br_ioctl_mutex); } EXPORT_SYMBOL(brioctl_set); int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd, struct ifreq *ifr, void __user *uarg) { int err = -ENOPKG; if (!br_ioctl_hook) request_module("bridge"); mutex_lock(&br_ioctl_mutex); if (br_ioctl_hook) err = br_ioctl_hook(net, br, cmd, ifr, uarg); mutex_unlock(&br_ioctl_mutex); return err; } static DEFINE_MUTEX(vlan_ioctl_mutex); static int (*vlan_ioctl_hook) (struct net *, void __user *arg); void vlan_ioctl_set(int (*hook) (struct net *, void __user *)) { mutex_lock(&vlan_ioctl_mutex); vlan_ioctl_hook = hook; mutex_unlock(&vlan_ioctl_mutex); } EXPORT_SYMBOL(vlan_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, unsigned int cmd, unsigned long arg) { const struct proto_ops *ops = READ_ONCE(sock->ops); struct ifreq ifr; bool need_copyout; int err; void __user *argp = (void __user *)arg; void __user *data; err = ops->ioctl(sock, cmd, arg); /* * If this ioctl is unknown try to hand it down * to the NIC driver. */ if (err != -ENOIOCTLCMD) return err; if (!is_socket_ioctl_cmd(cmd)) return -ENOTTY; if (get_user_ifreq(&ifr, &data, argp)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); if (!err && need_copyout) if (put_user_ifreq(&ifr, argp)) return -EFAULT; return err; } /* * With an ioctl, arg may well be a user mode pointer, but we don't know * what to do with it - that's up to the protocol still. */ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { const struct proto_ops *ops; struct socket *sock; struct sock *sk; void __user *argp = (void __user *)arg; int pid, err; struct net *net; sock = file->private_data; ops = READ_ONCE(sock->ops); sk = sock->sk; net = sock_net(sk); if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) { struct ifreq ifr; void __user *data; bool need_copyout; if (get_user_ifreq(&ifr, &data, argp)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); if (!err && need_copyout) if (put_user_ifreq(&ifr, argp)) return -EFAULT; } else #ifdef CONFIG_WEXT_CORE if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { err = wext_handle_ioctl(net, cmd, argp); } else #endif switch (cmd) { case FIOSETOWN: case SIOCSPGRP: err = -EFAULT; if (get_user(pid, (int __user *)argp)) break; err = f_setown(sock->file, pid, 1); break; case FIOGETOWN: case SIOCGPGRP: err = put_user(f_getown(sock->file), (int __user *)argp); break; case SIOCGIFBR: case SIOCSIFBR: case SIOCBRADDBR: case SIOCBRDELBR: err = br_ioctl_call(net, NULL, cmd, NULL, argp); break; case SIOCGIFVLAN: case SIOCSIFVLAN: err = -ENOPKG; if (!vlan_ioctl_hook) request_module("8021q"); mutex_lock(&vlan_ioctl_mutex); if (vlan_ioctl_hook) err = vlan_ioctl_hook(net, argp); mutex_unlock(&vlan_ioctl_mutex); break; case SIOCGSKNS: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = open_related_ns(&net->ns, get_net_ns); break; case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: if (!ops->gettstamp) { err = -ENOIOCTLCMD; break; } err = ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !IS_ENABLED(CONFIG_64BIT)); break; case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: if (!ops->gettstamp) { err = -ENOIOCTLCMD; break; } err = ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_NEW, false); break; case SIOCGIFCONF: err = dev_ifconf(net, argp); break; default: err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; } /** * sock_create_lite - creates a socket * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * Creates a new socket and assigns it to @res, passing through LSM. * The new socket initialization is not complete, see kernel_accept(). * Returns 0 or an error. On failure @res is set to %NULL. * This function internally uses GFP_KERNEL. */ int sock_create_lite(int family, int type, int protocol, struct socket **res) { int err; struct socket *sock = NULL; err = security_socket_create(family, type, protocol, 1); if (err) goto out; sock = sock_alloc(); if (!sock) { err = -ENOMEM; goto out; } sock->type = type; err = security_socket_post_create(sock, family, type, protocol, 1); if (err) goto out_release; out: *res = sock; return err; out_release: sock_release(sock); sock = NULL; goto out; } EXPORT_SYMBOL(sock_create_lite); /* No kernel lock held - perfect */ static __poll_t sock_poll(struct file *file, poll_table *wait) { struct socket *sock = file->private_data; const struct proto_ops *ops = READ_ONCE(sock->ops); __poll_t events = poll_requested_events(wait), flag = 0; if (!ops->poll) return 0; if (sk_can_busy_loop(sock->sk)) { /* poll once if requested by the syscall */ if (events & POLL_BUSY_LOOP) sk_busy_loop(sock->sk, 1); /* if this socket can poll_ll, tell the system call */ flag = POLL_BUSY_LOOP; } return ops->poll(file, sock, wait) | flag; } static int sock_mmap(struct file *file, struct vm_area_struct *vma) { struct socket *sock = file->private_data; return READ_ONCE(sock->ops)->mmap(file, sock, vma); } static int sock_close(struct inode *inode, struct file *filp) { __sock_release(SOCKET_I(inode), inode); return 0; } /* * Update the socket async list * * Fasync_list locking strategy. * * 1. fasync_list is modified only under process context socket lock * i.e. under semaphore. * 2. fasync_list is used under read_lock(&sk->sk_callback_lock) * or under socket lock */ static int sock_fasync(int fd, struct file *filp, int on) { struct socket *sock = filp->private_data; struct sock *sk = sock->sk; struct socket_wq *wq = &sock->wq; if (sk == NULL) return -EINVAL; lock_sock(sk); fasync_helper(fd, filp, on, &wq->fasync_list); if (!wq->fasync_list) sock_reset_flag(sk, SOCK_FASYNC); else sock_set_flag(sk, SOCK_FASYNC); release_sock(sk); return 0; } /* This function may be called only under rcu_lock */ int sock_wake_async(struct socket_wq *wq, int how, int band) { if (!wq || !wq->fasync_list) return -1; switch (how) { case SOCK_WAKE_WAITD: if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags)) break; goto call_kill; case SOCK_WAKE_SPACE: if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags)) break; fallthrough; case SOCK_WAKE_IO: call_kill: kill_fasync(&wq->fasync_list, SIGIO, band); break; case SOCK_WAKE_URG: kill_fasync(&wq->fasync_list, SIGURG, band); } return 0; } EXPORT_SYMBOL(sock_wake_async); /** * __sock_create - creates a socket * @net: net namespace * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * @kern: boolean for kernel space sockets * * Creates a new socket and assigns it to @res, passing through LSM. * Returns 0 or an error. On failure @res is set to %NULL. @kern must * be set to true if the socket resides in kernel space. * This function internally uses GFP_KERNEL. */ int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { int err; struct socket *sock; const struct net_proto_family *pf; /* * Check protocol is in range */ if (family < 0 || family >= NPROTO) return -EAFNOSUPPORT; if (type < 0 || type >= SOCK_MAX) return -EINVAL; /* Compatibility. This uglymoron is moved from INET layer to here to avoid deadlock in module load. */ if (family == PF_INET && type == SOCK_PACKET) { pr_info_once("%s uses obsolete (PF_INET,SOCK_PACKET)\n", current->comm); family = PF_PACKET; } err = security_socket_create(family, type, protocol, kern); if (err) return err; /* * Allocate the socket and allow the family to set things up. if * the protocol is 0, the family is instructed to select an appropriate * default. */ sock = sock_alloc(); if (!sock) { net_warn_ratelimited("socket: no more sockets\n"); return -ENFILE; /* Not exactly a match, but its the closest posix thing */ } sock->type = type; #ifdef CONFIG_MODULES /* Attempt to load a protocol module if the find failed. * * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user * requested real, full-featured networking support upon configuration. * Otherwise module support will break! */ if (rcu_access_pointer(net_families[family]) == NULL) request_module("net-pf-%d", family); #endif rcu_read_lock(); pf = rcu_dereference(net_families[family]); err = -EAFNOSUPPORT; if (!pf) goto out_release; /* * We will call the ->create function, that possibly is in a loadable * module, so we have to bump that loadable module refcnt first. */ if (!try_module_get(pf->owner)) goto out_release; /* Now protected by module ref count */ rcu_read_unlock(); err = pf->create(net, sock, protocol, kern); if (err < 0) goto out_module_put; /* * Now to bump the refcnt of the [loadable] module that owns this * socket at sock_release time we decrement its refcnt. */ if (!try_module_get(sock->ops->owner)) goto out_module_busy; /* * Now that we're done with the ->create function, the [loadable] * module can have its refcnt decremented */ module_put(pf->owner); err = security_socket_post_create(sock, family, type, protocol, kern); if (err) goto out_sock_release; *res = sock; return 0; out_module_busy: err = -EAFNOSUPPORT; out_module_put: sock->ops = NULL; module_put(pf->owner); out_sock_release: sock_release(sock); return err; out_release: rcu_read_unlock(); goto out_sock_release; } EXPORT_SYMBOL(__sock_create); /** * sock_create - creates a socket * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * A wrapper around __sock_create(). * Returns 0 or an error. This function internally uses GFP_KERNEL. */ int sock_create(int family, int type, int protocol, struct socket **res) { return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0); } EXPORT_SYMBOL(sock_create); /** * sock_create_kern - creates a socket (kernel space) * @net: net namespace * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * A wrapper around __sock_create(). * Returns 0 or an error. This function internally uses GFP_KERNEL. */ int sock_create_kern(struct net *net, int family, int type, int protocol, struct socket **res) { return __sock_create(net, family, type, protocol, res, 1); } EXPORT_SYMBOL(sock_create_kern); static struct socket *__sys_socket_create(int family, int type, int protocol) { struct socket *sock; int retval; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return ERR_PTR(-EINVAL); type &= SOCK_TYPE_MASK; retval = sock_create(family, type, protocol, &sock); if (retval < 0) return ERR_PTR(retval); return sock; } struct file *__sys_socket_file(int family, int type, int protocol) { struct socket *sock; int flags; sock = __sys_socket_create(family, type, protocol); if (IS_ERR(sock)) return ERR_CAST(sock); flags = type & ~SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_alloc_file(sock, flags, NULL); } /* A hook for bpf progs to attach to and update socket protocol. * * A static noinline declaration here could cause the compiler to * optimize away the function. A global noinline declaration will * keep the definition, but may optimize away the callsite. * Therefore, __weak is needed to ensure that the call is still * emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline int update_socket_protocol(int family, int type, int protocol) { return protocol; } __bpf_hook_end(); int __sys_socket(int family, int type, int protocol) { struct socket *sock; int flags; sock = __sys_socket_create(family, type, update_socket_protocol(family, type, protocol)); if (IS_ERR(sock)) return PTR_ERR(sock); flags = type & ~SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); } SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) { return __sys_socket(family, type, protocol); } /* * Create a pair of connected sockets. */ int __sys_socketpair(int family, int type, int protocol, int __user *usockvec) { struct socket *sock1, *sock2; int fd1, fd2, err; struct file *newfile1, *newfile2; int flags; flags = type & ~SOCK_TYPE_MASK; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; type &= SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; /* * reserve descriptors and make sure we won't fail * to return them to userland. */ fd1 = get_unused_fd_flags(flags); if (unlikely(fd1 < 0)) return fd1; fd2 = get_unused_fd_flags(flags); if (unlikely(fd2 < 0)) { put_unused_fd(fd1); return fd2; } err = put_user(fd1, &usockvec[0]); if (err) goto out; err = put_user(fd2, &usockvec[1]); if (err) goto out; /* * Obtain the first socket and check if the underlying protocol * supports the socketpair call. */ err = sock_create(family, type, protocol, &sock1); if (unlikely(err < 0)) goto out; err = sock_create(family, type, protocol, &sock2); if (unlikely(err < 0)) { sock_release(sock1); goto out; } err = security_socket_socketpair(sock1, sock2); if (unlikely(err)) { sock_release(sock2); sock_release(sock1); goto out; } err = READ_ONCE(sock1->ops)->socketpair(sock1, sock2); if (unlikely(err < 0)) { sock_release(sock2); sock_release(sock1); goto out; } newfile1 = sock_alloc_file(sock1, flags, NULL); if (IS_ERR(newfile1)) { err = PTR_ERR(newfile1); sock_release(sock2); goto out; } newfile2 = sock_alloc_file(sock2, flags, NULL); if (IS_ERR(newfile2)) { err = PTR_ERR(newfile2); fput(newfile1); goto out; } audit_fd_pair(fd1, fd2); fd_install(fd1, newfile1); fd_install(fd2, newfile2); return 0; out: put_unused_fd(fd2); put_unused_fd(fd1); return err; } SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, int __user *, usockvec) { return __sys_socketpair(family, type, protocol, usockvec); } int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, int addrlen) { int err; err = security_socket_bind(sock, (struct sockaddr *)address, addrlen); if (!err) err = READ_ONCE(sock->ops)->bind(sock, (struct sockaddr *)address, addrlen); return err; } /* * Bind a name to a socket. Nothing much to do here since it's * the protocol's responsibility to handle the local address. * * We move the socket address to kernel space before we call * the protocol layer (having also checked the address is ok). */ int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) { struct socket *sock; struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { err = move_addr_to_kernel(umyaddr, addrlen, &address); if (!err) err = __sys_bind_socket(sock, &address, addrlen); fput_light(sock->file, fput_needed); } return err; } SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) { return __sys_bind(fd, umyaddr, addrlen); } /* * Perform a listen. Basically, we allow the protocol to do anything * necessary for a listen, and if that works, we mark the socket as * ready for listening. */ int __sys_listen_socket(struct socket *sock, int backlog) { int somaxconn, err; somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); if ((unsigned int)backlog > somaxconn) backlog = somaxconn; err = security_socket_listen(sock, backlog); if (!err) err = READ_ONCE(sock->ops)->listen(sock, backlog); return err; } int __sys_listen(int fd, int backlog) { struct socket *sock; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { err = __sys_listen_socket(sock, backlog); fput_light(sock->file, fput_needed); } return err; } SYSCALL_DEFINE2(listen, int, fd, int, backlog) { return __sys_listen(fd, backlog); } struct file *do_accept(struct file *file, struct proto_accept_arg *arg, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; int err, len; struct sockaddr_storage address; const struct proto_ops *ops; sock = sock_from_file(file); if (!sock) return ERR_PTR(-ENOTSOCK); newsock = sock_alloc(); if (!newsock) return ERR_PTR(-ENFILE); ops = READ_ONCE(sock->ops); newsock->type = sock->type; newsock->ops = ops; /* * We don't need try_module_get here, as the listening socket (sock) * has the protocol module (sock->ops->owner) held. */ __module_get(ops->owner); newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); if (IS_ERR(newfile)) return newfile; err = security_socket_accept(sock, newsock); if (err) goto out_fd; arg->flags |= sock->file->f_flags; err = ops->accept(sock, newsock, arg); if (err < 0) goto out_fd; if (upeer_sockaddr) { len = ops->getname(newsock, (struct sockaddr *)&address, 2); if (len < 0) { err = -ECONNABORTED; goto out_fd; } err = move_addr_to_user(&address, len, upeer_sockaddr, upeer_addrlen); if (err < 0) goto out_fd; } /* File flags are not inherited via accept() unlike another OSes. */ return newfile; out_fd: fput(newfile); return ERR_PTR(err); } static int __sys_accept4_file(struct file *file, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { struct proto_accept_arg arg = { }; struct file *newfile; int newfd; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; newfd = get_unused_fd_flags(flags); if (unlikely(newfd < 0)) return newfd; newfile = do_accept(file, &arg, upeer_sockaddr, upeer_addrlen, flags); if (IS_ERR(newfile)) { put_unused_fd(newfd); return PTR_ERR(newfile); } fd_install(newfd, newfile); return newfd; } /* * For accept, we attempt to create a new socket, set up the link * with the client, wake up the client, then return the new * connected fd. We collect the address of the connector in kernel * space and move it to user at the very end. This is unclean because * we open the socket then return an error. * * 1003.1g adds the ability to recvmsg() to query connection pending * status to recvmsg. We need to add that support in a way thats * clean when we restructure accept also. */ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { int ret = -EBADF; struct fd f; f = fdget(fd); if (f.file) { ret = __sys_accept4_file(f.file, upeer_sockaddr, upeer_addrlen, flags); fdput(f); } return ret; } SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen, int, flags) { return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, flags); } SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen) { return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0); } /* * Attempt to connect to a socket with the server address. The address * is in user space so we verify it is OK and move it to kernel space. * * For 1003.1g we need to add clean support for a bind to AF_UNSPEC to * break bindings * * NOTE: 1003.1g draft 6.3 is broken with respect to AX.25/NetROM and * other SEQPACKET protocols that take time to connect() as it doesn't * include the -EINPROGRESS status for such sockets. */ int __sys_connect_file(struct file *file, struct sockaddr_storage *address, int addrlen, int file_flags) { struct socket *sock; int err; sock = sock_from_file(file); if (!sock) { err = -ENOTSOCK; goto out; } err = security_socket_connect(sock, (struct sockaddr *)address, addrlen); if (err) goto out; err = READ_ONCE(sock->ops)->connect(sock, (struct sockaddr *)address, addrlen, sock->file->f_flags | file_flags); out: return err; } int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) { int ret = -EBADF; struct fd f; f = fdget(fd); if (f.file) { struct sockaddr_storage address; ret = move_addr_to_kernel(uservaddr, addrlen, &address); if (!ret) ret = __sys_connect_file(f.file, &address, addrlen, 0); fdput(f); } return ret; } SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, int, addrlen) { return __sys_connect(fd, uservaddr, addrlen); } /* * Get the local address ('name') of a socket object. Move the obtained * name to user space. */ int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len) { struct socket *sock; struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = security_socket_getsockname(sock); if (err) goto out_put; err = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 0); if (err < 0) goto out_put; /* "err" is actually length in this case */ err = move_addr_to_user(&address, err, usockaddr, usockaddr_len); out_put: fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len) { return __sys_getsockname(fd, usockaddr, usockaddr_len); } /* * Get the remote address ('name') of a socket object. Move the obtained * name to user space. */ int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len) { struct socket *sock; struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { const struct proto_ops *ops = READ_ONCE(sock->ops); err = security_socket_getpeername(sock); if (err) { fput_light(sock->file, fput_needed); return err; } err = ops->getname(sock, (struct sockaddr *)&address, 1); if (err >= 0) /* "err" is actually length in this case */ err = move_addr_to_user(&address, err, usockaddr, usockaddr_len); fput_light(sock->file, fput_needed); } return err; } SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len) { return __sys_getpeername(fd, usockaddr, usockaddr_len); } /* * Send a datagram to a given address. We move the address into kernel * space and check the user space data area is readable before invoking * the protocol. */ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len) { struct socket *sock; struct sockaddr_storage address; int err; struct msghdr msg; int fput_needed; err = import_ubuf(ITER_SOURCE, buff, len, &msg.msg_iter); if (unlikely(err)) return err; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; msg.msg_name = NULL; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; msg.msg_ubuf = NULL; if (addr) { err = move_addr_to_kernel(addr, addr_len, &address); if (err < 0) goto out_put; msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = addr_len; } flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; err = __sock_sendmsg(sock, &msg); out_put: fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len) { return __sys_sendto(fd, buff, len, flags, addr, addr_len); } /* * Send a datagram down a socket. */ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, unsigned int, flags) { return __sys_sendto(fd, buff, len, flags, NULL, 0); } /* * Receive a frame from the socket and optionally record the address of the * sender. We verify the buffers are writable and if needed move the * sender address from kernel to user space. */ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, struct sockaddr __user *addr, int __user *addr_len) { struct sockaddr_storage address; struct msghdr msg = { /* Save some cycles and don't copy the address if not needed */ .msg_name = addr ? (struct sockaddr *)&address : NULL, }; struct socket *sock; int err, err2; int fput_needed; err = import_ubuf(ITER_DEST, ubuf, size, &msg.msg_iter); if (unlikely(err)) return err; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, flags); if (err >= 0 && addr != NULL) { err2 = move_addr_to_user(&address, msg.msg_namelen, addr, addr_len); if (err2 < 0) err = err2; } fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, unsigned int, flags, struct sockaddr __user *, addr, int __user *, addr_len) { return __sys_recvfrom(fd, ubuf, size, flags, addr, addr_len); } /* * Receive a datagram from a socket. */ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, unsigned int, flags) { return __sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } static bool sock_use_custom_sol_socket(const struct socket *sock) { return test_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags); } int do_sock_setsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, int optlen) { const struct proto_ops *ops; char *kernel_optval = NULL; int err; if (optlen < 0) return -EINVAL; err = security_socket_setsockopt(sock, level, optname); if (err) goto out_put; if (!compat) err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname, optval, &optlen, &kernel_optval); if (err < 0) goto out_put; if (err > 0) { err = 0; goto out_put; } if (kernel_optval) optval = KERNEL_SOCKPTR(kernel_optval); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET && !sock_use_custom_sol_socket(sock)) err = sock_setsockopt(sock, level, optname, optval, optlen); else if (unlikely(!ops->setsockopt)) err = -EOPNOTSUPP; else err = ops->setsockopt(sock, level, optname, optval, optlen); kfree(kernel_optval); out_put: return err; } EXPORT_SYMBOL(do_sock_setsockopt); /* Set a socket option. Because we don't know the option lengths we have * to pass the user mode parameter for the protocols to sort out. */ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, int optlen) { sockptr_t optval = USER_SOCKPTR(user_optval); bool compat = in_compat_syscall(); int err, fput_needed; struct socket *sock; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) return err; err = do_sock_setsockopt(sock, compat, level, optname, optval, optlen); fput_light(sock->file, fput_needed); return err; } SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, char __user *, optval, int, optlen) { return __sys_setsockopt(fd, level, optname, optval, optlen); } INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int optname)); int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen) { int max_optlen __maybe_unused = 0; const struct proto_ops *ops; int err; err = security_socket_getsockopt(sock, level, optname); if (err) return err; if (!compat) copy_from_sockptr(&max_optlen, optlen, sizeof(int)); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET) { err = sk_getsockopt(sock->sk, level, optname, optval, optlen); } else if (unlikely(!ops->getsockopt)) { err = -EOPNOTSUPP; } else { if (WARN_ONCE(optval.is_kernel || optlen.is_kernel, "Invalid argument type")) return -EOPNOTSUPP; err = ops->getsockopt(sock, level, optname, optval.user, optlen.user); } if (!compat) err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, optval, optlen, max_optlen, err); return err; } EXPORT_SYMBOL(do_sock_getsockopt); /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. */ int __sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) { int err, fput_needed; struct socket *sock; bool compat; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) return err; compat = in_compat_syscall(); err = do_sock_getsockopt(sock, compat, level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); fput_light(sock->file, fput_needed); return err; } SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, char __user *, optval, int __user *, optlen) { return __sys_getsockopt(fd, level, optname, optval, optlen); } /* * Shutdown a socket. */ int __sys_shutdown_sock(struct socket *sock, int how) { int err; err = security_socket_shutdown(sock, how); if (!err) err = READ_ONCE(sock->ops)->shutdown(sock, how); return err; } int __sys_shutdown(int fd, int how) { int err, fput_needed; struct socket *sock; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { err = __sys_shutdown_sock(sock, how); fput_light(sock->file, fput_needed); } return err; } SYSCALL_DEFINE2(shutdown, int, fd, int, how) { return __sys_shutdown(fd, how); } /* A couple of helpful macros for getting the address of the 32/64 bit * fields which are the same type (int / unsigned) on our platforms. */ #define COMPAT_MSG(msg, member) ((MSG_CMSG_COMPAT & flags) ? &msg##_compat->member : &msg->member) #define COMPAT_NAMELEN(msg) COMPAT_MSG(msg, msg_namelen) #define COMPAT_FLAGS(msg) COMPAT_MSG(msg, msg_flags) struct used_address { struct sockaddr_storage name; unsigned int name_len; }; int __copy_msghdr(struct msghdr *kmsg, struct user_msghdr *msg, struct sockaddr __user **save_addr) { ssize_t err; kmsg->msg_control_is_user = true; kmsg->msg_get_inq = 0; kmsg->msg_control_user = msg->msg_control; kmsg->msg_controllen = msg->msg_controllen; kmsg->msg_flags = msg->msg_flags; kmsg->msg_namelen = msg->msg_namelen; if (!msg->msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) return -EINVAL; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); if (save_addr) *save_addr = msg->msg_name; if (msg->msg_name && kmsg->msg_namelen) { if (!save_addr) { err = move_addr_to_kernel(msg->msg_name, kmsg->msg_namelen, kmsg->msg_name); if (err < 0) return err; } } else { kmsg->msg_name = NULL; kmsg->msg_namelen = 0; } if (msg->msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; kmsg->msg_ubuf = NULL; return 0; } static int copy_msghdr_from_user(struct msghdr *kmsg, struct user_msghdr __user *umsg, struct sockaddr __user **save_addr, struct iovec **iov) { struct user_msghdr msg; ssize_t err; if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; err = __copy_msghdr(kmsg, &msg, save_addr); if (err) return err; err = import_iovec(save_addr ? ITER_DEST : ITER_SOURCE, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); return err < 0 ? err : 0; } static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address, unsigned int allowed_msghdr_flags) { unsigned char ctl[sizeof(struct cmsghdr) + 20] __aligned(sizeof(__kernel_size_t)); /* 20 is size of ipv6_pktinfo */ unsigned char *ctl_buf = ctl; int ctl_len; ssize_t err; err = -ENOBUFS; if (msg_sys->msg_controllen > INT_MAX) goto out; flags |= (msg_sys->msg_flags & allowed_msghdr_flags); ctl_len = msg_sys->msg_controllen; if ((MSG_CMSG_COMPAT & flags) && ctl_len) { err = cmsghdr_from_user_compat_to_kern(msg_sys, sock->sk, ctl, sizeof(ctl)); if (err) goto out; ctl_buf = msg_sys->msg_control; ctl_len = msg_sys->msg_controllen; } else if (ctl_len) { BUILD_BUG_ON(sizeof(struct cmsghdr) != CMSG_ALIGN(sizeof(struct cmsghdr))); if (ctl_len > sizeof(ctl)) { ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL); if (ctl_buf == NULL) goto out; } err = -EFAULT; if (copy_from_user(ctl_buf, msg_sys->msg_control_user, ctl_len)) goto out_freectl; msg_sys->msg_control = ctl_buf; msg_sys->msg_control_is_user = false; } flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg_sys->msg_flags = flags; if (sock->file->f_flags & O_NONBLOCK) msg_sys->msg_flags |= MSG_DONTWAIT; /* * If this is sendmmsg() and current destination address is same as * previously succeeded address, omit asking LSM's decision. * used_address->name_len is initialized to UINT_MAX so that the first * destination address never matches. */ if (used_address && msg_sys->msg_name && used_address->name_len == msg_sys->msg_namelen && !memcmp(&used_address->name, msg_sys->msg_name, used_address->name_len)) { err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. */ if (used_address && err >= 0) { used_address->name_len = msg_sys->msg_namelen; if (msg_sys->msg_name) memcpy(&used_address->name, msg_sys->msg_name, used_address->name_len); } out_freectl: if (ctl_buf != ctl) sock_kfree_s(sock->sk, ctl_buf, ctl_len); out: return err; } static int sendmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct iovec **iov) { int err; if (flags & MSG_CMSG_COMPAT) { struct compat_msghdr __user *msg_compat; msg_compat = (struct compat_msghdr __user *) umsg; err = get_compat_msghdr(msg, msg_compat, NULL, iov); } else { err = copy_msghdr_from_user(msg, umsg, NULL, iov); } if (err < 0) return err; return 0; } static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address, unsigned int allowed_msghdr_flags) { struct sockaddr_storage address; struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; ssize_t err; msg_sys->msg_name = &address; err = sendmsg_copy_msghdr(msg_sys, msg, flags, &iov); if (err < 0) return err; err = ____sys_sendmsg(sock, msg_sys, flags, used_address, allowed_msghdr_flags); kfree(iov); return err; } /* * BSD sendmsg interface */ long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { return ____sys_sendmsg(sock, msg, flags, NULL, 0); } long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat) { int fput_needed, err; struct msghdr msg_sys; struct socket *sock; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0); fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { return __sys_sendmsg(fd, msg, flags, true); } /* * Linux sendmmsg interface */ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat) { int fput_needed, err, datagrams; struct socket *sock; struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct used_address used_address; unsigned int oflags = flags; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; if (vlen > UIO_MAXIOV) vlen = UIO_MAXIOV; datagrams = 0; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) return err; used_address.name_len = UINT_MAX; entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; err = 0; flags |= MSG_BATCH; while (datagrams < vlen) { if (datagrams == vlen - 1) flags = oflags; if (MSG_CMSG_COMPAT & flags) { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)compat_entry, &msg_sys, flags, &used_address, MSG_EOR); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)entry, &msg_sys, flags, &used_address, MSG_EOR); if (err < 0) break; err = put_user(err, &entry->msg_len); ++entry; } if (err) break; ++datagrams; if (msg_data_left(&msg_sys)) break; cond_resched(); } fput_light(sock->file, fput_needed); /* We only return an error if no datagrams were able to be sent */ if (datagrams != 0) return datagrams; return err; } SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags) { return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } static int recvmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct sockaddr __user **uaddr, struct iovec **iov) { ssize_t err; if (MSG_CMSG_COMPAT & flags) { struct compat_msghdr __user *msg_compat; msg_compat = (struct compat_msghdr __user *) umsg; err = get_compat_msghdr(msg, msg_compat, uaddr, iov); } else { err = copy_msghdr_from_user(msg, umsg, uaddr, iov); } if (err < 0) return err; return 0; } static int ____sys_recvmsg(struct socket *sock, struct msghdr *msg_sys, struct user_msghdr __user *msg, struct sockaddr __user *uaddr, unsigned int flags, int nosec) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *) msg; int __user *uaddr_len = COMPAT_NAMELEN(msg); struct sockaddr_storage addr; unsigned long cmsg_ptr; int len; ssize_t err; msg_sys->msg_name = &addr; cmsg_ptr = (unsigned long)msg_sys->msg_control; msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); /* We assume all kernel code knows the size of sockaddr_storage */ msg_sys->msg_namelen = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; if (unlikely(nosec)) err = sock_recvmsg_nosec(sock, msg_sys, flags); else err = sock_recvmsg(sock, msg_sys, flags); if (err < 0) goto out; len = err; if (uaddr != NULL) { err = move_addr_to_user(&addr, msg_sys->msg_namelen, uaddr, uaddr_len); if (err < 0) goto out; } err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT), COMPAT_FLAGS(msg)); if (err) goto out; if (MSG_CMSG_COMPAT & flags) err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg_compat->msg_controllen); else err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg->msg_controllen); if (err) goto out; err = len; out: return err; } static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, int nosec) { struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; /* user mode address pointers */ struct sockaddr __user *uaddr; ssize_t err; err = recvmsg_copy_msghdr(msg_sys, msg, flags, &uaddr, &iov); if (err < 0) return err; err = ____sys_recvmsg(sock, msg_sys, msg, uaddr, flags, nosec); kfree(iov); return err; } /* * BSD recvmsg interface */ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat) { int fput_needed, err; struct msghdr msg_sys; struct socket *sock; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = ___sys_recvmsg(sock, msg, &msg_sys, flags, 0); fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { return __sys_recvmsg(fd, msg, flags, true); } /* * Linux recvmmsg interface */ static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct timespec64 *timeout) { int fput_needed, err, datagrams; struct socket *sock; struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct timespec64 end_time; struct timespec64 timeout64; if (timeout && poll_select_set_timeout(&end_time, timeout->tv_sec, timeout->tv_nsec)) return -EINVAL; datagrams = 0; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) return err; if (likely(!(flags & MSG_ERRQUEUE))) { err = sock_error(sock->sk); if (err) { datagrams = err; goto out_put; } } entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; while (datagrams < vlen) { /* * No need to ask LSM for more than the first datagram. */ if (MSG_CMSG_COMPAT & flags) { err = ___sys_recvmsg(sock, (struct user_msghdr __user *)compat_entry, &msg_sys, flags & ~MSG_WAITFORONE, datagrams); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = ___sys_recvmsg(sock, (struct user_msghdr __user *)entry, &msg_sys, flags & ~MSG_WAITFORONE, datagrams); if (err < 0) break; err = put_user(err, &entry->msg_len); ++entry; } if (err) break; ++datagrams; /* MSG_WAITFORONE turns on MSG_DONTWAIT after one packet */ if (flags & MSG_WAITFORONE) flags |= MSG_DONTWAIT; if (timeout) { ktime_get_ts64(&timeout64); *timeout = timespec64_sub(end_time, timeout64); if (timeout->tv_sec < 0) { timeout->tv_sec = timeout->tv_nsec = 0; break; } /* Timeout, return less than vlen datagrams */ if (timeout->tv_nsec == 0 && timeout->tv_sec == 0) break; } /* Out of band data, return right away */ if (msg_sys.msg_flags & MSG_OOB) break; cond_resched(); } if (err == 0) goto out_put; if (datagrams == 0) { datagrams = err; goto out_put; } /* * We may return less entries than requested (vlen) if the * sock is non block and there aren't enough datagrams... */ if (err != -EAGAIN) { /* * ... or if recvmsg returns an error after we * received some datagrams, where we record the * error to return on the next call or if the * app asks about it using getsockopt(SO_ERROR). */ WRITE_ONCE(sock->sk->sk_err, -err); } out_put: fput_light(sock->file, fput_needed); return datagrams; } int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct __kernel_timespec __user *timeout, struct old_timespec32 __user *timeout32) { int datagrams; struct timespec64 timeout_sys; if (timeout && get_timespec64(&timeout_sys, timeout)) return -EFAULT; if (timeout32 && get_old_timespec32(&timeout_sys, timeout32)) return -EFAULT; if (!timeout && !timeout32) return do_recvmmsg(fd, mmsg, vlen, flags, NULL); datagrams = do_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys); if (datagrams <= 0) return datagrams; if (timeout && put_timespec64(&timeout_sys, timeout)) datagrams = -EFAULT; if (timeout32 && put_old_timespec32(&timeout_sys, timeout32)) datagrams = -EFAULT; return datagrams; } SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct __kernel_timespec __user *, timeout) { if (flags & MSG_CMSG_COMPAT) return -EINVAL; return __sys_recvmmsg(fd, mmsg, vlen, flags, timeout, NULL); } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE5(recvmmsg_time32, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct old_timespec32 __user *, timeout) { if (flags & MSG_CMSG_COMPAT) return -EINVAL; return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL, timeout); } #endif #ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) static const unsigned char nargs[21] = { AL(0), AL(3), AL(3), AL(3), AL(2), AL(3), AL(3), AL(3), AL(4), AL(4), AL(4), AL(6), AL(6), AL(2), AL(5), AL(5), AL(3), AL(3), AL(4), AL(5), AL(4) }; #undef AL /* * System call vectors. * * Argument checking cleaned up. Saved 20% in size. * This function doesn't need to set the kernel lock because * it is set by the callees. */ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) { unsigned long a[AUDITSC_ARGS]; unsigned long a0, a1; int err; unsigned int len; if (call < 1 || call > SYS_SENDMMSG) return -EINVAL; call = array_index_nospec(call, SYS_SENDMMSG + 1); len = nargs[call]; if (len > sizeof(a)) return -EINVAL; /* copy_from_user should be SMP safe. */ if (copy_from_user(a, args, len)) return -EFAULT; err = audit_socketcall(nargs[call] / sizeof(unsigned long), a); if (err) return err; a0 = a[0]; a1 = a[1]; switch (call) { case SYS_SOCKET: err = __sys_socket(a0, a1, a[2]); break; case SYS_BIND: err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_CONNECT: err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_LISTEN: err = __sys_listen(a0, a1); break; case SYS_ACCEPT: err = __sys_accept4(a0, (struct sockaddr __user *)a1, (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = __sys_getsockname(a0, (struct sockaddr __user *)a1, (int __user *)a[2]); break; case SYS_GETPEERNAME: err = __sys_getpeername(a0, (struct sockaddr __user *)a1, (int __user *)a[2]); break; case SYS_SOCKETPAIR: err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]); break; case SYS_SEND: err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], NULL, 0); break; case SYS_SENDTO: err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], (struct sockaddr __user *)a[4], a[5]); break; case SYS_RECV: err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], NULL, NULL); break; case SYS_RECVFROM: err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], (struct sockaddr __user *)a[4], (int __user *)a[5]); break; case SYS_SHUTDOWN: err = __sys_shutdown(a0, a1); break; case SYS_SETSOCKOPT: err = __sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]); break; case SYS_GETSOCKOPT: err = __sys_getsockopt(a0, a1, a[2], (char __user *)a[3], (int __user *)a[4]); break; case SYS_SENDMSG: err = __sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2], true); break; case SYS_SENDMMSG: err = __sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], true); break; case SYS_RECVMSG: err = __sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2], true); break; case SYS_RECVMMSG: if (IS_ENABLED(CONFIG_64BIT)) err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], (struct __kernel_timespec __user *)a[4], NULL); else err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], NULL, (struct old_timespec32 __user *)a[4]); break; case SYS_ACCEPT4: err = __sys_accept4(a0, (struct sockaddr __user *)a1, (int __user *)a[2], a[3]); break; default: err = -EINVAL; break; } return err; } #endif /* __ARCH_WANT_SYS_SOCKETCALL */ /** * sock_register - add a socket protocol handler * @ops: description of protocol * * This function is called by a protocol handler that wants to * advertise its address family, and have it linked into the * socket interface. The value ops->family corresponds to the * socket system call protocol family. */ int sock_register(const struct net_proto_family *ops) { int err; if (ops->family >= NPROTO) { pr_crit("protocol %d >= NPROTO(%d)\n", ops->family, NPROTO); return -ENOBUFS; } spin_lock(&net_family_lock); if (rcu_dereference_protected(net_families[ops->family], lockdep_is_held(&net_family_lock))) err = -EEXIST; else { rcu_assign_pointer(net_families[ops->family], ops); err = 0; } spin_unlock(&net_family_lock); pr_info("NET: Registered %s protocol family\n", pf_family_names[ops->family]); return err; } EXPORT_SYMBOL(sock_register); /** * sock_unregister - remove a protocol handler * @family: protocol family to remove * * This function is called by a protocol handler that wants to * remove its address family, and have it unlinked from the * new socket creation. * * If protocol handler is a module, then it can use module reference * counts to protect against new references. If protocol handler is not * a module then it needs to provide its own protection in * the ops->create routine. */ void sock_unregister(int family) { BUG_ON(family < 0 || family >= NPROTO); spin_lock(&net_family_lock); RCU_INIT_POINTER(net_families[family], NULL); spin_unlock(&net_family_lock); synchronize_rcu(); pr_info("NET: Unregistered %s protocol family\n", pf_family_names[family]); } EXPORT_SYMBOL(sock_unregister); bool sock_is_registered(int family) { return family < NPROTO && rcu_access_pointer(net_families[family]); } static int __init sock_init(void) { int err; /* * Initialize the network sysctl infrastructure. */ err = net_sysctl_init(); if (err) goto out; /* * Initialize skbuff SLAB cache */ skb_init(); /* * Initialize the protocols module. */ init_inodecache(); err = register_filesystem(&sock_fs_type); if (err) goto out; sock_mnt = kern_mount(&sock_fs_type); if (IS_ERR(sock_mnt)) { err = PTR_ERR(sock_mnt); goto out_mount; } /* The real protocol initialization is performed in later initcalls. */ #ifdef CONFIG_NETFILTER err = netfilter_init(); if (err) goto out; #endif ptp_classifier_init(); out: return err; out_mount: unregister_filesystem(&sock_fs_type); goto out; } core_initcall(sock_init); /* early initcall */ #ifdef CONFIG_PROC_FS void socket_seq_show(struct seq_file *seq) { seq_printf(seq, "sockets: used %d\n", sock_inuse_get(seq->private)); } #endif /* CONFIG_PROC_FS */ /* Handle the fact that while struct ifreq has the same *layout* on * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, * which are handled elsewhere, it still has different *size* due to * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, * resulting in struct ifreq being 32 and 40 bytes respectively). * As a result, if the struct happens to be at the end of a page and * the next page isn't readable/writable, we get a fault. To prevent * that, copy back and forth to the full size. */ int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg) { if (in_compat_syscall()) { struct compat_ifreq *ifr32 = (struct compat_ifreq *)ifr; memset(ifr, 0, sizeof(*ifr)); if (copy_from_user(ifr32, arg, sizeof(*ifr32))) return -EFAULT; if (ifrdata) *ifrdata = compat_ptr(ifr32->ifr_data); return 0; } if (copy_from_user(ifr, arg, sizeof(*ifr))) return -EFAULT; if (ifrdata) *ifrdata = ifr->ifr_data; return 0; } EXPORT_SYMBOL(get_user_ifreq); int put_user_ifreq(struct ifreq *ifr, void __user *arg) { size_t size = sizeof(*ifr); if (in_compat_syscall()) size = sizeof(struct compat_ifreq); if (copy_to_user(arg, ifr, size)) return -EFAULT; return 0; } EXPORT_SYMBOL(put_user_ifreq); #ifdef CONFIG_COMPAT static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) { compat_uptr_t uptr32; struct ifreq ifr; void __user *saved; int err; if (get_user_ifreq(&ifr, NULL, uifr32)) return -EFAULT; if (get_user(uptr32, &uifr32->ifr_settings.ifs_ifsu)) return -EFAULT; saved = ifr.ifr_settings.ifs_ifsu.raw_hdlc; ifr.ifr_settings.ifs_ifsu.raw_hdlc = compat_ptr(uptr32); err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL, NULL); if (!err) { ifr.ifr_settings.ifs_ifsu.raw_hdlc = saved; if (put_user_ifreq(&ifr, uifr32)) err = -EFAULT; } return err; } /* Handle ioctls that use ifreq::ifr_data and just need struct ifreq converted */ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct compat_ifreq __user *u_ifreq32) { struct ifreq ifreq; void __user *data; if (!is_socket_ioctl_cmd(cmd)) return -ENOTTY; if (get_user_ifreq(&ifreq, &data, u_ifreq32)) return -EFAULT; ifreq.ifr_data = data; return dev_ioctl(net, cmd, &ifreq, data, NULL); } static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; struct net *net = sock_net(sk); const struct proto_ops *ops; if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) return sock_ioctl(file, cmd, (unsigned long)argp); switch (cmd) { case SIOCWANDEV: return compat_siocwandev(net, argp); case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: ops = READ_ONCE(sock->ops); if (!ops->gettstamp) return -ENOIOCTLCMD; return ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !COMPAT_USE_64BIT_TIME); case SIOCETHTOOL: case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: case SIOCGHWTSTAMP: return compat_ifr_data_ioctl(net, cmd, argp); case FIOSETOWN: case SIOCSPGRP: case FIOGETOWN: case SIOCGPGRP: case SIOCBRADDBR: case SIOCBRDELBR: case SIOCGIFVLAN: case SIOCSIFVLAN: case SIOCGSKNS: case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: case SIOCGIFCONF: case SIOCSIFBR: case SIOCGIFBR: return sock_ioctl(file, cmd, arg); case SIOCGIFFLAGS: case SIOCSIFFLAGS: case SIOCGIFMAP: case SIOCSIFMAP: case SIOCGIFMETRIC: case SIOCSIFMETRIC: case SIOCGIFMTU: case SIOCSIFMTU: case SIOCGIFMEM: case SIOCSIFMEM: case SIOCGIFHWADDR: case SIOCSIFHWADDR: case SIOCADDMULTI: case SIOCDELMULTI: case SIOCGIFINDEX: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCSIFHWBROADCAST: case SIOCDIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCSIFPFLAGS: case SIOCGIFPFLAGS: case SIOCGIFTXQLEN: case SIOCSIFTXQLEN: case SIOCBRADDIF: case SIOCBRDELIF: case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: case SIOCSARP: case SIOCGARP: case SIOCDARP: case SIOCOUTQ: case SIOCOUTQNSD: case SIOCATMARK: return sock_do_ioctl(net, sock, cmd, arg); } return -ENOIOCTLCMD; } static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct socket *sock = file->private_data; const struct proto_ops *ops = READ_ONCE(sock->ops); int ret = -ENOIOCTLCMD; struct sock *sk; struct net *net; sk = sock->sk; net = sock_net(sk); if (ops->compat_ioctl) ret = ops->compat_ioctl(sock, cmd, arg); if (ret == -ENOIOCTLCMD && (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)) ret = compat_wext_handle_ioctl(net, cmd, arg); if (ret == -ENOIOCTLCMD) ret = compat_sock_ioctl_trans(file, sock, cmd, arg); return ret; } #endif /** * kernel_bind - bind an address to a socket (kernel space) * @sock: socket * @addr: address * @addrlen: length of address * * Returns 0 or an error. */ int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { struct sockaddr_storage address; memcpy(&address, addr, addrlen); return READ_ONCE(sock->ops)->bind(sock, (struct sockaddr *)&address, addrlen); } EXPORT_SYMBOL(kernel_bind); /** * kernel_listen - move socket to listening state (kernel space) * @sock: socket * @backlog: pending connections queue size * * Returns 0 or an error. */ int kernel_listen(struct socket *sock, int backlog) { return READ_ONCE(sock->ops)->listen(sock, backlog); } EXPORT_SYMBOL(kernel_listen); /** * kernel_accept - accept a connection (kernel space) * @sock: listening socket * @newsock: new connected socket * @flags: flags * * @flags must be SOCK_CLOEXEC, SOCK_NONBLOCK or 0. * If it fails, @newsock is guaranteed to be %NULL. * Returns 0 or an error. */ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) { struct sock *sk = sock->sk; const struct proto_ops *ops = READ_ONCE(sock->ops); struct proto_accept_arg arg = { .flags = flags, .kern = true, }; int err; err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol, newsock); if (err < 0) goto done; err = ops->accept(sock, *newsock, &arg); if (err < 0) { sock_release(*newsock); *newsock = NULL; goto done; } (*newsock)->ops = ops; __module_get(ops->owner); done: return err; } EXPORT_SYMBOL(kernel_accept); /** * kernel_connect - connect a socket (kernel space) * @sock: socket * @addr: address * @addrlen: address length * @flags: flags (O_NONBLOCK, ...) * * For datagram sockets, @addr is the address to which datagrams are sent * by default, and the only address from which datagrams are received. * For stream sockets, attempts to connect to @addr. * Returns 0 or an error code. */ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags) { struct sockaddr_storage address; memcpy(&address, addr, addrlen); return READ_ONCE(sock->ops)->connect(sock, (struct sockaddr *)&address, addrlen, flags); } EXPORT_SYMBOL(kernel_connect); /** * kernel_getsockname - get the address which the socket is bound (kernel space) * @sock: socket * @addr: address holder * * Fills the @addr pointer with the address which the socket is bound. * Returns the length of the address in bytes or an error code. */ int kernel_getsockname(struct socket *sock, struct sockaddr *addr) { return READ_ONCE(sock->ops)->getname(sock, addr, 0); } EXPORT_SYMBOL(kernel_getsockname); /** * kernel_getpeername - get the address which the socket is connected (kernel space) * @sock: socket * @addr: address holder * * Fills the @addr pointer with the address which the socket is connected. * Returns the length of the address in bytes or an error code. */ int kernel_getpeername(struct socket *sock, struct sockaddr *addr) { return READ_ONCE(sock->ops)->getname(sock, addr, 1); } EXPORT_SYMBOL(kernel_getpeername); /** * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket * @how: connection part * * Returns 0 or an error. */ int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) { return READ_ONCE(sock->ops)->shutdown(sock, how); } EXPORT_SYMBOL(kernel_sock_shutdown); /** * kernel_sock_ip_overhead - returns the IP overhead imposed by a socket * @sk: socket * * This routine returns the IP overhead imposed by a socket i.e. * the length of the underlying IP header, depending on whether * this is an IPv4 or IPv6 socket and the length from IP options turned * on at the socket. Assumes that the caller has a lock on the socket. */ u32 kernel_sock_ip_overhead(struct sock *sk) { struct inet_sock *inet; struct ip_options_rcu *opt; u32 overhead = 0; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *np; struct ipv6_txoptions *optv6 = NULL; #endif /* IS_ENABLED(CONFIG_IPV6) */ if (!sk) return overhead; switch (sk->sk_family) { case AF_INET: inet = inet_sk(sk); overhead += sizeof(struct iphdr); opt = rcu_dereference_protected(inet->inet_opt, sock_owned_by_user(sk)); if (opt) overhead += opt->opt.optlen; return overhead; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: np = inet6_sk(sk); overhead += sizeof(struct ipv6hdr); if (np) optv6 = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); if (optv6) overhead += (optv6->opt_flen + optv6->opt_nflen); return overhead; #endif /* IS_ENABLED(CONFIG_IPV6) */ default: /* Returns 0 overhead if the socket is not ipv4 or ipv6 */ return overhead; } } EXPORT_SYMBOL(kernel_sock_ip_overhead); |
| 116 117 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 | // SPDX-License-Identifier: GPL-2.0 /* * linux/mm/madvise.c * * Copyright (C) 1999 Linus Torvalds * Copyright (C) 2002 Christoph Hellwig */ #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/mempolicy.h> #include <linux/page-isolation.h> #include <linux/page_idle.h> #include <linux/userfaultfd_k.h> #include <linux/hugetlb.h> #include <linux/falloc.h> #include <linux/fadvise.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mm_inline.h> #include <linux/string.h> #include <linux/uio.h> #include <linux/ksm.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/mmu_notifier.h> #include <asm/tlb.h> #include "internal.h" #include "swap.h" struct madvise_walk_private { struct mmu_gather *tlb; bool pageout; }; /* * Any behaviour which results in changes to the vma->vm_flags needs to * take mmap_lock for writing. Others, which simply traverse vmas, need * to only take it for reading. */ static int madvise_need_mmap_write(int behavior) { switch (behavior) { case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_COLD: case MADV_PAGEOUT: case MADV_FREE: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: case MADV_COLLAPSE: return 0; default: /* be safe, default to 1. list exceptions explicitly */ return 1; } } #ifdef CONFIG_ANON_VMA_NAME struct anon_vma_name *anon_vma_name_alloc(const char *name) { struct anon_vma_name *anon_name; size_t count; /* Add 1 for NUL terminator at the end of the anon_name->name */ count = strlen(name) + 1; anon_name = kmalloc(struct_size(anon_name, name, count), GFP_KERNEL); if (anon_name) { kref_init(&anon_name->kref); memcpy(anon_name->name, name, count); } return anon_name; } void anon_vma_name_free(struct kref *kref) { struct anon_vma_name *anon_name = container_of(kref, struct anon_vma_name, kref); kfree(anon_name); } struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma) { mmap_assert_locked(vma->vm_mm); return vma->anon_name; } /* mmap_lock should be write-locked */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { struct anon_vma_name *orig_name = anon_vma_name(vma); if (!anon_name) { vma->anon_name = NULL; anon_vma_name_put(orig_name); return 0; } if (anon_vma_name_eq(orig_name, anon_name)) return 0; vma->anon_name = anon_vma_name_reuse(anon_name); anon_vma_name_put(orig_name); return 0; } #else /* CONFIG_ANON_VMA_NAME */ static int replace_anon_vma_name(struct vm_area_struct *vma, struct anon_vma_name *anon_name) { if (anon_name) return -EINVAL; return 0; } #endif /* CONFIG_ANON_VMA_NAME */ /* * Update the vm_flags on region of a vma, splitting it or merging it as * necessary. Must be called with mmap_lock held for writing; * Caller should ensure anon_name stability by raising its refcount even when * anon_name belongs to a valid vma because this function might free that vma. */ static int madvise_update_vma(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long new_flags, struct anon_vma_name *anon_name) { struct mm_struct *mm = vma->vm_mm; int error; VMA_ITERATOR(vmi, mm, start); if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name)) { *prev = vma; return 0; } vma = vma_modify_flags_name(&vmi, *prev, vma, start, end, new_flags, anon_name); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; /* vm_flags is protected by the mmap_lock held in write mode. */ vma_start_write(vma); vm_flags_reset(vma, new_flags); if (!vma->vm_file || vma_is_anon_shmem(vma)) { error = replace_anon_vma_name(vma, anon_name); if (error) return error; } return 0; } #ifdef CONFIG_SWAP static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->private; struct swap_iocb *splug = NULL; pte_t *ptep = NULL; spinlock_t *ptl; unsigned long addr; for (addr = start; addr < end; addr += PAGE_SIZE) { pte_t pte; swp_entry_t entry; struct folio *folio; if (!ptep++) { ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!ptep) break; } pte = ptep_get(ptep); if (!is_swap_pte(pte)) continue; entry = pte_to_swp_entry(pte); if (unlikely(non_swap_entry(entry))) continue; pte_unmap_unlock(ptep, ptl); ptep = NULL; folio = read_swap_cache_async(entry, GFP_HIGHUSER_MOVABLE, vma, addr, &splug); if (folio) folio_put(folio); } if (ptep) pte_unmap_unlock(ptep, ptl); swap_read_unplug(splug); cond_resched(); return 0; } static const struct mm_walk_ops swapin_walk_ops = { .pmd_entry = swapin_walk_pmd_entry, .walk_lock = PGWALK_RDLOCK, }; static void shmem_swapin_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct address_space *mapping) { XA_STATE(xas, &mapping->i_pages, linear_page_index(vma, start)); pgoff_t end_index = linear_page_index(vma, end) - 1; struct folio *folio; struct swap_iocb *splug = NULL; rcu_read_lock(); xas_for_each(&xas, folio, end_index) { unsigned long addr; swp_entry_t entry; if (!xa_is_value(folio)) continue; entry = radix_to_swp_entry(folio); /* There might be swapin error entries in shmem mapping. */ if (non_swap_entry(entry)) continue; addr = vma->vm_start + ((xas.xa_index - vma->vm_pgoff) << PAGE_SHIFT); xas_pause(&xas); rcu_read_unlock(); folio = read_swap_cache_async(entry, mapping_gfp_mask(mapping), vma, addr, &splug); if (folio) folio_put(folio); rcu_read_lock(); } rcu_read_unlock(); swap_read_unplug(splug); } #endif /* CONFIG_SWAP */ /* * Schedule all required I/O operations. Do not wait for completion. */ static long madvise_willneed(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct mm_struct *mm = vma->vm_mm; struct file *file = vma->vm_file; loff_t offset; *prev = vma; #ifdef CONFIG_SWAP if (!file) { walk_page_range(vma->vm_mm, start, end, &swapin_walk_ops, vma); lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } if (shmem_mapping(file->f_mapping)) { shmem_swapin_range(vma, start, end, file->f_mapping); lru_add_drain(); /* Push any new pages onto the LRU now */ return 0; } #else if (!file) return -EBADF; #endif if (IS_DAX(file_inode(file))) { /* no bad return value, but ignore advice */ return 0; } /* * Filesystem's fadvise may need to take various locks. We need to * explicitly grab a reference because the vma (and hence the * vma's reference to the file) can go away as soon as we drop * mmap_lock. */ *prev = NULL; /* tell sys_madvise we drop mmap_lock */ get_file(file); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); mmap_read_unlock(mm); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); mmap_read_lock(mm); return 0; } static inline bool can_do_file_pageout(struct vm_area_struct *vma) { if (!vma->vm_file) return false; /* * paging out pagecache only for non-anonymous mappings that correspond * to the files the calling process could (if tried) open for writing; * otherwise we'd be including shared non-exclusive mappings, which * opens a side channel. */ return inode_owner_or_capable(&nop_mnt_idmap, file_inode(vma->vm_file)) || file_permission(vma->vm_file, MAY_WRITE) == 0; } static inline int madvise_folio_pte_batch(unsigned long addr, unsigned long end, struct folio *folio, pte_t *ptep, pte_t pte, bool *any_young, bool *any_dirty) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; int max_nr = (end - addr) / PAGE_SIZE; return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL, any_young, any_dirty); } static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct madvise_walk_private *private = walk->private; struct mmu_gather *tlb = private->tlb; bool pageout = private->pageout; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; pte_t *start_pte, *pte, ptent; spinlock_t *ptl; struct folio *folio = NULL; LIST_HEAD(folio_list); bool pageout_anon_only_filter; unsigned int batch_count = 0; int nr; if (fatal_signal_pending(current)) return -EINTR; pageout_anon_only_filter = pageout && !vma_is_anonymous(vma) && !can_do_file_pageout(vma); #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(*pmd)) { pmd_t orig_pmd; unsigned long next = pmd_addr_end(addr, end); tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; orig_pmd = *pmd; if (is_huge_zero_pmd(orig_pmd)) goto huge_unlock; if (unlikely(!pmd_present(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(orig_pmd)); goto huge_unlock; } folio = pmd_folio(orig_pmd); /* Do not interfere with other mappings of this folio */ if (folio_likely_mapped_shared(folio)) goto huge_unlock; if (pageout_anon_only_filter && !folio_test_anon(folio)) goto huge_unlock; if (next - addr != HPAGE_PMD_SIZE) { int err; folio_get(folio); spin_unlock(ptl); folio_lock(folio); err = split_folio(folio); folio_unlock(folio); folio_put(folio); if (!err) goto regular_folio; return 0; } if (!pageout && pmd_young(orig_pmd)) { pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); set_pmd_at(mm, addr, pmd, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } folio_clear_referenced(folio); folio_test_clear_young(folio); if (folio_test_active(folio)) folio_set_workingset(folio); if (pageout) { if (folio_isolate_lru(folio)) { if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); } } else folio_deactivate(folio); huge_unlock: spin_unlock(ptl); if (pageout) reclaim_pages(&folio_list); return 0; } regular_folio: #endif tlb_change_page_size(tlb, PAGE_SIZE); restart: start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (!start_pte) return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) { nr = 1; ptent = ptep_get(pte); if (++batch_count == SWAP_CLUSTER_MAX) { batch_count = 0; if (need_resched()) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); cond_resched(); goto restart; } } if (pte_none(ptent)) continue; if (!pte_present(ptent)) continue; folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * If we encounter a large folio, only split it if it is not * fully mapped within the range we are operating on. Otherwise * leave it as is so that it can be swapped out whole. If we * fail to split a folio, leave it in place and advance to the * next pte in the range. */ if (folio_test_large(folio)) { bool any_young; nr = madvise_folio_pte_batch(addr, end, folio, pte, ptent, &any_young, NULL); if (any_young) ptent = pte_mkyoung(ptent); if (nr < folio_nr_pages(folio)) { int err; if (folio_likely_mapped_shared(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; if (!folio_trylock(folio)) continue; folio_get(folio); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) break; arch_enter_lazy_mmu_mode(); if (!err) nr = 0; continue; } } /* * Do not interfere with other mappings of this folio and * non-LRU folio. If we have a large folio at this point, we * know it is fully mapped so if its mapcount is the same as its * number of pages, it must be exclusive. */ if (!folio_test_lru(folio) || folio_mapcount(folio) != folio_nr_pages(folio)) continue; if (pageout_anon_only_filter && !folio_test_anon(folio)) continue; if (!pageout && pte_young(ptent)) { clear_young_dirty_ptes(vma, addr, pte, nr, CYDP_CLEAR_YOUNG); tlb_remove_tlb_entries(tlb, pte, nr, addr); } /* * We are deactivating a folio for accelerating reclaiming. * VM couldn't reclaim the folio unless we clear PG_young. * As a side effect, it makes confuse idle-page tracking * because they will miss recent referenced history. */ folio_clear_referenced(folio); folio_test_clear_young(folio); if (folio_test_active(folio)) folio_set_workingset(folio); if (pageout) { if (folio_isolate_lru(folio)) { if (folio_test_unevictable(folio)) folio_putback_lru(folio); else list_add(&folio->lru, &folio_list); } } else folio_deactivate(folio); } if (start_pte) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); } if (pageout) reclaim_pages(&folio_list); cond_resched(); return 0; } static const struct mm_walk_ops cold_walk_ops = { .pmd_entry = madvise_cold_or_pageout_pte_range, .walk_lock = PGWALK_RDLOCK, }; static void madvise_cold_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct madvise_walk_private walk_private = { .pageout = false, .tlb = tlb, }; tlb_start_vma(tlb, vma); walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); } static inline bool can_madv_lru_vma(struct vm_area_struct *vma) { return !(vma->vm_flags & (VM_LOCKED|VM_PFNMAP|VM_HUGETLB)); } static long madvise_cold(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) { struct mm_struct *mm = vma->vm_mm; struct mmu_gather tlb; *prev = vma; if (!can_madv_lru_vma(vma)) return -EINVAL; lru_add_drain(); tlb_gather_mmu(&tlb, mm); madvise_cold_page_range(&tlb, vma, start_addr, end_addr); tlb_finish_mmu(&tlb); return 0; } static void madvise_pageout_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct madvise_walk_private walk_private = { .pageout = true, .tlb = tlb, }; tlb_start_vma(tlb, vma); walk_page_range(vma->vm_mm, addr, end, &cold_walk_ops, &walk_private); tlb_end_vma(tlb, vma); } static long madvise_pageout(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start_addr, unsigned long end_addr) { struct mm_struct *mm = vma->vm_mm; struct mmu_gather tlb; *prev = vma; if (!can_madv_lru_vma(vma)) return -EINVAL; /* * If the VMA belongs to a private file mapping, there can be private * dirty pages which can be paged out if even this process is neither * owner nor write capable of the file. We allow private file mappings * further to pageout dirty anon pages. */ if (!vma_is_anonymous(vma) && (!can_do_file_pageout(vma) && (vma->vm_flags & VM_MAYSHARE))) return 0; lru_add_drain(); tlb_gather_mmu(&tlb, mm); madvise_pageout_page_range(&tlb, vma, start_addr, end_addr); tlb_finish_mmu(&tlb); return 0; } static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { const cydp_t cydp_flags = CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY; struct mmu_gather *tlb = walk->private; struct mm_struct *mm = tlb->mm; struct vm_area_struct *vma = walk->vma; spinlock_t *ptl; pte_t *start_pte, *pte, ptent; struct folio *folio; int nr_swap = 0; unsigned long next; int nr, max_nr; next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) if (madvise_free_huge_pmd(tlb, vma, pmd, addr, next)) return 0; tlb_change_page_size(tlb, PAGE_SIZE); start_pte = pte = pte_offset_map_lock(mm, pmd, addr, &ptl); if (!start_pte) return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); for (; addr != end; pte += nr, addr += PAGE_SIZE * nr) { nr = 1; ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * If the pte has swp_entry, just clear page table to * prevent swap-in which is more expensive rather than * (page allocation + zeroing). */ if (!pte_present(ptent)) { swp_entry_t entry; entry = pte_to_swp_entry(ptent); if (!non_swap_entry(entry)) { max_nr = (end - addr) / PAGE_SIZE; nr = swap_pte_batch(pte, max_nr, ptent); nr_swap -= nr; free_swap_and_cache_nr(entry, nr); clear_not_present_full_ptes(mm, addr, pte, nr, tlb->fullmm); } else if (is_hwpoison_entry(entry) || is_poisoned_swp_entry(entry)) { pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; /* * If we encounter a large folio, only split it if it is not * fully mapped within the range we are operating on. Otherwise * leave it as is so that it can be marked as lazyfree. If we * fail to split a folio, leave it in place and advance to the * next pte in the range. */ if (folio_test_large(folio)) { bool any_young, any_dirty; nr = madvise_folio_pte_batch(addr, end, folio, pte, ptent, &any_young, &any_dirty); if (nr < folio_nr_pages(folio)) { int err; if (folio_likely_mapped_shared(folio)) continue; if (!folio_trylock(folio)) continue; folio_get(folio); arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); start_pte = NULL; err = split_folio(folio); folio_unlock(folio); folio_put(folio); pte = pte_offset_map_lock(mm, pmd, addr, &ptl); start_pte = pte; if (!start_pte) break; arch_enter_lazy_mmu_mode(); if (!err) nr = 0; continue; } if (any_young) ptent = pte_mkyoung(ptent); if (any_dirty) ptent = pte_mkdirty(ptent); } if (folio_test_swapcache(folio) || folio_test_dirty(folio)) { if (!folio_trylock(folio)) continue; /* * If we have a large folio at this point, we know it is * fully mapped so if its mapcount is the same as its * number of pages, it must be exclusive. */ if (folio_mapcount(folio) != folio_nr_pages(folio)) { folio_unlock(folio); continue; } if (folio_test_swapcache(folio) && !folio_free_swap(folio)) { folio_unlock(folio); continue; } folio_clear_dirty(folio); folio_unlock(folio); } if (pte_young(ptent) || pte_dirty(ptent)) { clear_young_dirty_ptes(vma, addr, pte, nr, cydp_flags); tlb_remove_tlb_entries(tlb, pte, nr, addr); } folio_mark_lazyfree(folio); } if (nr_swap) add_mm_counter(mm, MM_SWAPENTS, nr_swap); if (start_pte) { arch_leave_lazy_mmu_mode(); pte_unmap_unlock(start_pte, ptl); } cond_resched(); return 0; } static const struct mm_walk_ops madvise_free_walk_ops = { .pmd_entry = madvise_free_pte_range, .walk_lock = PGWALK_RDLOCK, }; static int madvise_free_single_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr) { struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; struct mmu_gather tlb; /* MADV_FREE works for only anon vma at the moment */ if (!vma_is_anonymous(vma)) return -EINVAL; range.start = max(vma->vm_start, start_addr); if (range.start >= vma->vm_end) return -EINVAL; range.end = min(vma->vm_end, end_addr); if (range.end <= vma->vm_start) return -EINVAL; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, range.start, range.end); lru_add_drain(); tlb_gather_mmu(&tlb, mm); update_hiwater_rss(mm); mmu_notifier_invalidate_range_start(&range); tlb_start_vma(&tlb, vma); walk_page_range(vma->vm_mm, range.start, range.end, &madvise_free_walk_ops, &tlb); tlb_end_vma(&tlb, vma); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); return 0; } /* * Application no longer needs these pages. If the pages are dirty, * it's OK to just throw them away. The app will be more careful about * data it wants to keep. Be sure to free swap resources too. The * zap_page_range_single call sets things up for shrink_active_list to actually * free these pages later if no one else has touched them in the meantime, * although we could add these pages to a global reuse list for * shrink_active_list to pick up before reclaiming other pages. * * NB: This interface discards data rather than pushes it out to swap, * as some implementations do. This has performance implications for * applications like large transactional databases which want to discard * pages in anonymous maps after committing to backing store the data * that was kept in them. There is no reason to write this data out to * the swap area if the application is discarding it. * * An interface that causes the system to free clean pages and flush * dirty pages is already available as msync(MS_INVALIDATE). */ static long madvise_dontneed_single_vma(struct vm_area_struct *vma, unsigned long start, unsigned long end) { zap_page_range_single(vma, start, end - start, NULL); return 0; } static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma, unsigned long start, unsigned long *end, int behavior) { if (!is_vm_hugetlb_page(vma)) { unsigned int forbidden = VM_PFNMAP; if (behavior != MADV_DONTNEED_LOCKED) forbidden |= VM_LOCKED; return !(vma->vm_flags & forbidden); } if (behavior != MADV_DONTNEED && behavior != MADV_DONTNEED_LOCKED) return false; if (start & ~huge_page_mask(hstate_vma(vma))) return false; /* * Madvise callers expect the length to be rounded up to PAGE_SIZE * boundaries, and may be unaware that this VMA uses huge pages. * Avoid unexpected data loss by rounding down the number of * huge pages freed. */ *end = ALIGN_DOWN(*end, huge_page_size(hstate_vma(vma))); return true; } static long madvise_dontneed_free(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, int behavior) { struct mm_struct *mm = vma->vm_mm; *prev = vma; if (!madvise_dontneed_free_valid_vma(vma, start, &end, behavior)) return -EINVAL; if (start == end) return 0; if (!userfaultfd_remove(vma, start, end)) { *prev = NULL; /* mmap_lock has been dropped, prev is stale */ mmap_read_lock(mm); vma = vma_lookup(mm, start); if (!vma) return -ENOMEM; /* * Potential end adjustment for hugetlb vma is OK as * the check below keeps end within vma. */ if (!madvise_dontneed_free_valid_vma(vma, start, &end, behavior)) return -EINVAL; if (end > vma->vm_end) { /* * Don't fail if end > vma->vm_end. If the old * vma was split while the mmap_lock was * released the effect of the concurrent * operation may not cause madvise() to * have an undefined result. There may be an * adjacent next vma that we'll walk * next. userfaultfd_remove() will generate an * UFFD_EVENT_REMOVE repetition on the * end-vma->vm_end range, but the manager can * handle a repetition fine. */ end = vma->vm_end; } VM_WARN_ON(start >= end); } if (behavior == MADV_DONTNEED || behavior == MADV_DONTNEED_LOCKED) return madvise_dontneed_single_vma(vma, start, end); else if (behavior == MADV_FREE) return madvise_free_single_vma(vma, start, end); else return -EINVAL; } static long madvise_populate(struct mm_struct *mm, unsigned long start, unsigned long end, int behavior) { const bool write = behavior == MADV_POPULATE_WRITE; int locked = 1; long pages; while (start < end) { /* Populate (prefault) page tables readable/writable. */ pages = faultin_page_range(mm, start, end, write, &locked); if (!locked) { mmap_read_lock(mm); locked = 1; } if (pages < 0) { switch (pages) { case -EINTR: return -EINTR; case -EINVAL: /* Incompatible mappings / permissions. */ return -EINVAL; case -EHWPOISON: return -EHWPOISON; case -EFAULT: /* VM_FAULT_SIGBUS or VM_FAULT_SIGSEGV */ return -EFAULT; default: pr_warn_once("%s: unhandled return value: %ld\n", __func__, pages); fallthrough; case -ENOMEM: /* No VMA or out of memory. */ return -ENOMEM; } } start += pages * PAGE_SIZE; } return 0; } /* * Application wants to free up the pages and associated backing store. * This is effectively punching a hole into the middle of a file. */ static long madvise_remove(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { loff_t offset; int error; struct file *f; struct mm_struct *mm = vma->vm_mm; *prev = NULL; /* tell sys_madvise we drop mmap_lock */ if (vma->vm_flags & VM_LOCKED) return -EINVAL; f = vma->vm_file; if (!f || !f->f_mapping || !f->f_mapping->host) { return -EINVAL; } if (!vma_is_shared_maywrite(vma)) return -EACCES; offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); /* * Filesystem's fallocate may need to take i_rwsem. We need to * explicitly grab a reference because the vma (and hence the * vma's reference to the file) can go away as soon as we drop * mmap_lock. */ get_file(f); if (userfaultfd_remove(vma, start, end)) { /* mmap_lock was not released by userfaultfd_remove() */ mmap_read_unlock(mm); } error = vfs_fallocate(f, FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE, offset, end - start); fput(f); mmap_read_lock(mm); return error; } /* * Apply an madvise behavior to a region of a vma. madvise_update_vma * will handle splitting a vm area into separate areas, each area with its own * behavior. */ static int madvise_vma_behavior(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long behavior) { int error; struct anon_vma_name *anon_name; unsigned long new_flags = vma->vm_flags; switch (behavior) { case MADV_REMOVE: return madvise_remove(vma, prev, start, end); case MADV_WILLNEED: return madvise_willneed(vma, prev, start, end); case MADV_COLD: return madvise_cold(vma, prev, start, end); case MADV_PAGEOUT: return madvise_pageout(vma, prev, start, end); case MADV_FREE: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: return madvise_dontneed_free(vma, prev, start, end, behavior); case MADV_NORMAL: new_flags = new_flags & ~VM_RAND_READ & ~VM_SEQ_READ; break; case MADV_SEQUENTIAL: new_flags = (new_flags & ~VM_RAND_READ) | VM_SEQ_READ; break; case MADV_RANDOM: new_flags = (new_flags & ~VM_SEQ_READ) | VM_RAND_READ; break; case MADV_DONTFORK: new_flags |= VM_DONTCOPY; break; case MADV_DOFORK: if (vma->vm_flags & VM_IO) return -EINVAL; new_flags &= ~VM_DONTCOPY; break; case MADV_WIPEONFORK: /* MADV_WIPEONFORK is only supported on anonymous memory. */ if (vma->vm_file || vma->vm_flags & VM_SHARED) return -EINVAL; new_flags |= VM_WIPEONFORK; break; case MADV_KEEPONFORK: if (vma->vm_flags & VM_DROPPABLE) return -EINVAL; new_flags &= ~VM_WIPEONFORK; break; case MADV_DONTDUMP: new_flags |= VM_DONTDUMP; break; case MADV_DODUMP: if ((!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) || (vma->vm_flags & VM_DROPPABLE)) return -EINVAL; new_flags &= ~VM_DONTDUMP; break; case MADV_MERGEABLE: case MADV_UNMERGEABLE: error = ksm_madvise(vma, start, end, behavior, &new_flags); if (error) goto out; break; case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: error = hugepage_madvise(vma, &new_flags, behavior); if (error) goto out; break; case MADV_COLLAPSE: return madvise_collapse(vma, prev, start, end); } anon_name = anon_vma_name(vma); anon_vma_name_get(anon_name); error = madvise_update_vma(vma, prev, start, end, new_flags, anon_name); anon_vma_name_put(anon_name); out: /* * madvise() returns EAGAIN if kernel resources, such as * slab, are temporarily unavailable. */ if (error == -ENOMEM) error = -EAGAIN; return error; } #ifdef CONFIG_MEMORY_FAILURE /* * Error injection support for memory error handling. */ static int madvise_inject_error(int behavior, unsigned long start, unsigned long end) { unsigned long size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; for (; start < end; start += size) { unsigned long pfn; struct page *page; int ret; ret = get_user_pages_fast(start, 1, 0, &page); if (ret != 1) return ret; pfn = page_to_pfn(page); /* * When soft offlining hugepages, after migrating the page * we dissolve it, therefore in the second loop "page" will * no longer be a compound page. */ size = page_size(compound_head(page)); if (behavior == MADV_SOFT_OFFLINE) { pr_info("Soft offlining pfn %#lx at process virtual address %#lx\n", pfn, start); ret = soft_offline_page(pfn, MF_COUNT_INCREASED); } else { pr_info("Injecting memory failure for pfn %#lx at process virtual address %#lx\n", pfn, start); ret = memory_failure(pfn, MF_ACTION_REQUIRED | MF_COUNT_INCREASED | MF_SW_SIMULATED); if (ret == -EOPNOTSUPP) ret = 0; } if (ret) return ret; } return 0; } #endif static bool madvise_behavior_valid(int behavior) { switch (behavior) { case MADV_DOFORK: case MADV_DONTFORK: case MADV_NORMAL: case MADV_SEQUENTIAL: case MADV_RANDOM: case MADV_REMOVE: case MADV_WILLNEED: case MADV_DONTNEED: case MADV_DONTNEED_LOCKED: case MADV_FREE: case MADV_COLD: case MADV_PAGEOUT: case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: #ifdef CONFIG_KSM case MADV_MERGEABLE: case MADV_UNMERGEABLE: #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: case MADV_COLLAPSE: #endif case MADV_DONTDUMP: case MADV_DODUMP: case MADV_WIPEONFORK: case MADV_KEEPONFORK: #ifdef CONFIG_MEMORY_FAILURE case MADV_SOFT_OFFLINE: case MADV_HWPOISON: #endif return true; default: return false; } } static bool process_madvise_behavior_valid(int behavior) { switch (behavior) { case MADV_COLD: case MADV_PAGEOUT: case MADV_WILLNEED: case MADV_COLLAPSE: return true; default: return false; } } /* * Walk the vmas in range [start,end), and call the visit function on each one. * The visit function will get start and end parameters that cover the overlap * between the current vma and the original range. Any unmapped regions in the * original range will result in this function returning -ENOMEM while still * calling the visit function on all of the existing vmas in the range. * Must be called with the mmap_lock held for reading or writing. */ static int madvise_walk_vmas(struct mm_struct *mm, unsigned long start, unsigned long end, unsigned long arg, int (*visit)(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long arg)) { struct vm_area_struct *vma; struct vm_area_struct *prev; unsigned long tmp; int unmapped_error = 0; /* * If the interval [start,end) covers some unmapped address * ranges, just ignore them, but return -ENOMEM at the end. * - different from the way of handling in mlock etc. */ vma = find_vma_prev(mm, start, &prev); if (vma && start > vma->vm_start) prev = vma; for (;;) { int error; /* Still start < end. */ if (!vma) return -ENOMEM; /* Here start < (end|vma->vm_end). */ if (start < vma->vm_start) { unmapped_error = -ENOMEM; start = vma->vm_start; if (start >= end) break; } /* Here vma->vm_start <= start < (end|vma->vm_end) */ tmp = vma->vm_end; if (end < tmp) tmp = end; /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ error = visit(vma, &prev, start, tmp, arg); if (error) return error; start = tmp; if (prev && start < prev->vm_end) start = prev->vm_end; if (start >= end) break; if (prev) vma = find_vma(mm, prev->vm_end); else /* madvise_remove dropped mmap_lock */ vma = find_vma(mm, start); } return unmapped_error; } #ifdef CONFIG_ANON_VMA_NAME static int madvise_vma_anon_name(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, unsigned long anon_name) { int error; /* Only anonymous mappings can be named */ if (vma->vm_file && !vma_is_anon_shmem(vma)) return -EBADF; error = madvise_update_vma(vma, prev, start, end, vma->vm_flags, (struct anon_vma_name *)anon_name); /* * madvise() returns EAGAIN if kernel resources, such as * slab, are temporarily unavailable. */ if (error == -ENOMEM) error = -EAGAIN; return error; } int madvise_set_anon_name(struct mm_struct *mm, unsigned long start, unsigned long len_in, struct anon_vma_name *anon_name) { unsigned long end; unsigned long len; if (start & ~PAGE_MASK) return -EINVAL; len = (len_in + ~PAGE_MASK) & PAGE_MASK; /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return -EINVAL; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; return madvise_walk_vmas(mm, start, end, (unsigned long)anon_name, madvise_vma_anon_name); } #endif /* CONFIG_ANON_VMA_NAME */ /* * The madvise(2) system call. * * Applications can use madvise() to advise the kernel how it should * handle paging I/O in this VM area. The idea is to help the kernel * use appropriate read-ahead and caching techniques. The information * provided is advisory only, and can be safely disregarded by the * kernel without affecting the correct operation of the application. * * behavior values: * MADV_NORMAL - the default behavior is to read clusters. This * results in some read-ahead and read-behind. * MADV_RANDOM - the system should read the minimum amount of data * on any access, since it is unlikely that the appli- * cation will need more than what it asks for. * MADV_SEQUENTIAL - pages in the given range will probably be accessed * once, so they can be aggressively read ahead, and * can be freed soon after they are accessed. * MADV_WILLNEED - the application is notifying the system to read * some pages ahead. * MADV_DONTNEED - the application is finished with the given range, * so the kernel can free resources associated with it. * MADV_FREE - the application marks pages in the given range as lazy free, * where actual purges are postponed until memory pressure happens. * MADV_REMOVE - the application wants to free up the given range of * pages and associated backing store. * MADV_DONTFORK - omit this area from child's address space when forking: * typically, to avoid COWing pages pinned by get_user_pages(). * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking. * MADV_WIPEONFORK - present the child process with zero-filled memory in this * range after a fork. * MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK * MADV_HWPOISON - trigger memory error handler as if the given memory range * were corrupted by unrecoverable hardware memory failure. * MADV_SOFT_OFFLINE - try to soft-offline the given range of memory. * MADV_MERGEABLE - the application recommends that KSM try to merge pages in * this area with pages of identical content from other such areas. * MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others. * MADV_HUGEPAGE - the application wants to back the given range by transparent * huge pages in the future. Existing pages might be coalesced and * new pages might be allocated as THP. * MADV_NOHUGEPAGE - mark the given range as not worth being backed by * transparent huge pages so the existing pages will not be * coalesced into THP and new pages will not be allocated as THP. * MADV_COLLAPSE - synchronously coalesce pages into new THP. * MADV_DONTDUMP - the application wants to prevent pages in the given range * from being included in its core dump. * MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump. * MADV_COLD - the application is not expected to use this memory soon, * deactivate pages in this range so that they can be reclaimed * easily if memory pressure happens. * MADV_PAGEOUT - the application is not expected to use this memory soon, * page out the pages in this range immediately. * MADV_POPULATE_READ - populate (prefault) page tables readable by * triggering read faults if required * MADV_POPULATE_WRITE - populate (prefault) page tables writable by * triggering write faults if required * * return values: * zero - success * -EINVAL - start + len < 0, start is not page-aligned, * "behavior" is not a valid value, or application * is attempting to release locked or shared pages, * or the specified address range includes file, Huge TLB, * MAP_SHARED or VMPFNMAP range. * -ENOMEM - addresses in the specified range are not currently * mapped, or are outside the AS of the process. * -EIO - an I/O error occurred while paging in data. * -EBADF - map exists, but area maps something that isn't a file. * -EAGAIN - a kernel resource was temporarily unavailable. * -EPERM - memory is sealed. */ int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior) { unsigned long end; int error; int write; size_t len; struct blk_plug plug; if (!madvise_behavior_valid(behavior)) return -EINVAL; if (!PAGE_ALIGNED(start)) return -EINVAL; len = PAGE_ALIGN(len_in); /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) return -EINVAL; end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; #ifdef CONFIG_MEMORY_FAILURE if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE) return madvise_inject_error(behavior, start, start + len_in); #endif write = madvise_need_mmap_write(behavior); if (write) { if (mmap_write_lock_killable(mm)) return -EINTR; } else { mmap_read_lock(mm); } start = untagged_addr_remote(mm, start); end = start + len; /* * Check if the address range is sealed for do_madvise(). * can_modify_mm_madv assumes we have acquired the lock on MM. */ if (unlikely(!can_modify_mm_madv(mm, start, end, behavior))) { error = -EPERM; goto out; } blk_start_plug(&plug); switch (behavior) { case MADV_POPULATE_READ: case MADV_POPULATE_WRITE: error = madvise_populate(mm, start, end, behavior); break; default: error = madvise_walk_vmas(mm, start, end, behavior, madvise_vma_behavior); break; } blk_finish_plug(&plug); out: if (write) mmap_write_unlock(mm); else mmap_read_unlock(mm); return error; } SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) { return do_madvise(current->mm, start, len_in, behavior); } SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec, size_t, vlen, int, behavior, unsigned int, flags) { ssize_t ret; struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; struct task_struct *task; struct mm_struct *mm; size_t total_len; unsigned int f_flags; if (flags != 0) { ret = -EINVAL; goto out; } ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) goto out; task = pidfd_get_task(pidfd, &f_flags); if (IS_ERR(task)) { ret = PTR_ERR(task); goto free_iov; } if (!process_madvise_behavior_valid(behavior)) { ret = -EINVAL; goto release_task; } /* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS); if (IS_ERR_OR_NULL(mm)) { ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; goto release_task; } /* * Require CAP_SYS_NICE for influencing process performance. Note that * only non-destructive hints are currently supported. */ if (!capable(CAP_SYS_NICE)) { ret = -EPERM; goto release_mm; } total_len = iov_iter_count(&iter); while (iov_iter_count(&iter)) { ret = do_madvise(mm, (unsigned long)iter_iov_addr(&iter), iter_iov_len(&iter), behavior); if (ret < 0) break; iov_iter_advance(&iter, iter_iov_len(&iter)); } ret = (total_len - iov_iter_count(&iter)) ? : ret; release_mm: mmput(mm); release_task: put_task_struct(task); free_iov: kfree(iov); out: return ret; } |
| 4 3 1 1 1 | 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 | #include <linux/errno.h> #include <linux/ip.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/types.h> #include <net/checksum.h> #include <net/ip.h> #include <net/ip6_fib.h> #include <net/lwtunnel.h> #include <net/protocol.h> #include <uapi/linux/ila.h> #include "ila.h" void ila_init_saved_csum(struct ila_params *p) { if (!p->locator_match.v64) return; p->csum_diff = compute_csum_diff8( (__be32 *)&p->locator, (__be32 *)&p->locator_match); } static __wsum get_csum_diff_iaddr(struct ila_addr *iaddr, struct ila_params *p) { if (p->locator_match.v64) return p->csum_diff; else return compute_csum_diff8((__be32 *)&p->locator, (__be32 *)&iaddr->loc); } static __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) { return get_csum_diff_iaddr(ila_a2i(&ip6h->daddr), p); } static void ila_csum_do_neutral_fmt(struct ila_addr *iaddr, struct ila_params *p) { __sum16 *adjust = (__force __sum16 *)&iaddr->ident.v16[3]; __wsum diff, fval; diff = get_csum_diff_iaddr(iaddr, p); fval = (__force __wsum)(ila_csum_neutral_set(iaddr->ident) ? CSUM_NEUTRAL_FLAG : ~CSUM_NEUTRAL_FLAG); diff = csum_add(diff, fval); *adjust = ~csum_fold(csum_add(diff, csum_unfold(*adjust))); /* Flip the csum-neutral bit. Either we are doing a SIR->ILA * translation with ILA_CSUM_NEUTRAL_MAP as the csum_method * and the C-bit is not set, or we are doing an ILA-SIR * tranlsation and the C-bit is set. */ iaddr->ident.csum_neutral ^= 1; } static void ila_csum_do_neutral_nofmt(struct ila_addr *iaddr, struct ila_params *p) { __sum16 *adjust = (__force __sum16 *)&iaddr->ident.v16[3]; __wsum diff; diff = get_csum_diff_iaddr(iaddr, p); *adjust = ~csum_fold(csum_add(diff, csum_unfold(*adjust))); } static void ila_csum_adjust_transport(struct sk_buff *skb, struct ila_params *p) { size_t nhoff = sizeof(struct ipv6hdr); struct ipv6hdr *ip6h = ipv6_hdr(skb); __wsum diff; switch (ip6h->nexthdr) { case NEXTHDR_TCP: if (likely(pskb_may_pull(skb, nhoff + sizeof(struct tcphdr)))) { struct tcphdr *th = (struct tcphdr *) (skb_network_header(skb) + nhoff); diff = get_csum_diff(ip6h, p); inet_proto_csum_replace_by_diff(&th->check, skb, diff, true); } break; case NEXTHDR_UDP: if (likely(pskb_may_pull(skb, nhoff + sizeof(struct udphdr)))) { struct udphdr *uh = (struct udphdr *) (skb_network_header(skb) + nhoff); if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { diff = get_csum_diff(ip6h, p); inet_proto_csum_replace_by_diff(&uh->check, skb, diff, true); if (!uh->check) uh->check = CSUM_MANGLED_0; } } break; case NEXTHDR_ICMP: if (likely(pskb_may_pull(skb, nhoff + sizeof(struct icmp6hdr)))) { struct icmp6hdr *ih = (struct icmp6hdr *) (skb_network_header(skb) + nhoff); diff = get_csum_diff(ip6h, p); inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb, diff, true); } break; } } void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p, bool sir2ila) { struct ipv6hdr *ip6h = ipv6_hdr(skb); struct ila_addr *iaddr = ila_a2i(&ip6h->daddr); switch (p->csum_mode) { case ILA_CSUM_ADJUST_TRANSPORT: ila_csum_adjust_transport(skb, p); break; case ILA_CSUM_NEUTRAL_MAP: if (sir2ila) { if (WARN_ON(ila_csum_neutral_set(iaddr->ident))) { /* Checksum flag should never be * set in a formatted SIR address. */ break; } } else if (!ila_csum_neutral_set(iaddr->ident)) { /* ILA to SIR translation and C-bit isn't * set so we're good. */ break; } ila_csum_do_neutral_fmt(iaddr, p); break; case ILA_CSUM_NEUTRAL_MAP_AUTO: ila_csum_do_neutral_nofmt(iaddr, p); break; case ILA_CSUM_NO_ACTION: break; } /* Now change destination address */ iaddr->loc = p->locator; } |
| 4 4 1 1 4 4 4 4 1 1 5 1 5 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'tty_io.c' gives an orthogonal feeling to tty's, be they consoles * or rs-channels. It also implements echoing, cooked mode etc. * * Kill-line thanks to John T Kohl, who also corrected VMIN = VTIME = 0. * * Modified by Theodore Ts'o, 9/14/92, to dynamically allocate the * tty_struct and tty_queue structures. Previously there was an array * of 256 tty_struct's which was statically allocated, and the * tty_queue structures were allocated at boot time. Both are now * dynamically allocated only when the tty is open. * * Also restructured routines so that there is more of a separation * between the high-level tty routines (tty_io.c and tty_ioctl.c) and * the low-level tty routines (serial.c, pty.c, console.c). This * makes for cleaner and more compact code. -TYT, 9/17/92 * * Modified by Fred N. van Kempen, 01/29/93, to add line disciplines * which can be dynamically activated and de-activated by the line * discipline handling modules (like SLIP). * * NOTE: pay no attention to the line discipline code (yet); its * interface is still subject to change in this version... * -- TYT, 1/31/92 * * Added functionality to the OPOST tty handling. No delays, but all * other bits should be there. * -- Nick Holloway <alfie@dcs.warwick.ac.uk>, 27th May 1993. * * Rewrote canonical mode and added more termios flags. * -- julian@uhunix.uhcc.hawaii.edu (J. Cowley), 13Jan94 * * Reorganized FASYNC support so mouse code can share it. * -- ctm@ardi.com, 9Sep95 * * New TIOCLINUX variants added. * -- mj@k332.feld.cvut.cz, 19-Nov-95 * * Restrict vt switching via ioctl() * -- grif@cs.ucr.edu, 5-Dec-95 * * Move console and virtual terminal code to more appropriate files, * implement CONFIG_VT and generalize console device interface. * -- Marko Kohtala <Marko.Kohtala@hut.fi>, March 97 * * Rewrote tty_init_dev and tty_release_dev to eliminate races. * -- Bill Hawes <whawes@star.net>, June 97 * * Added devfs support. * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 13-Jan-1998 * * Added support for a Unix98-style ptmx device. * -- C. Scott Ananian <cananian@alumni.princeton.edu>, 14-Jan-1998 * * Reduced memory usage for older ARM systems * -- Russell King <rmk@arm.linux.org.uk> * * Move do_SAK() into process context. Less stack use in devfs functions. * alloc_tty_struct() always uses kmalloc() * -- Andrew Morton <andrewm@uow.edu.eu> 17Mar01 */ #include <linux/types.h> #include <linux/major.h> #include <linux/errno.h> #include <linux/signal.h> #include <linux/fcntl.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/interrupt.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/tty_flip.h> #include <linux/devpts_fs.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/console.h> #include <linux/timer.h> #include <linux/ctype.h> #include <linux/kd.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/ppp-ioctl.h> #include <linux/proc_fs.h> #include <linux/init.h> #include <linux/module.h> #include <linux/device.h> #include <linux/wait.h> #include <linux/bitops.h> #include <linux/delay.h> #include <linux/seq_file.h> #include <linux/serial.h> #include <linux/ratelimit.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <linux/termios_internal.h> #include <linux/fs.h> #include <linux/kbd_kern.h> #include <linux/vt_kern.h> #include <linux/selection.h> #include <linux/kmod.h> #include <linux/nsproxy.h> #include "tty.h" #undef TTY_DEBUG_HANGUP #ifdef TTY_DEBUG_HANGUP # define tty_debug_hangup(tty, f, args...) tty_debug(tty, f, ##args) #else # define tty_debug_hangup(tty, f, args...) do { } while (0) #endif #define TTY_PARANOIA_CHECK 1 #define CHECK_TTY_COUNT 1 struct ktermios tty_std_termios = { /* for the benefit of tty drivers */ .c_iflag = ICRNL | IXON, .c_oflag = OPOST | ONLCR, .c_cflag = B38400 | CS8 | CREAD | HUPCL, .c_lflag = ISIG | ICANON | ECHO | ECHOE | ECHOK | ECHOCTL | ECHOKE | IEXTEN, .c_cc = INIT_C_CC, .c_ispeed = 38400, .c_ospeed = 38400, /* .c_line = N_TTY, */ }; EXPORT_SYMBOL(tty_std_termios); /* This list gets poked at by procfs and various bits of boot up code. This * could do with some rationalisation such as pulling the tty proc function * into this file. */ LIST_HEAD(tty_drivers); /* linked list of tty drivers */ /* Mutex to protect creating and releasing a tty */ DEFINE_MUTEX(tty_mutex); static ssize_t tty_read(struct kiocb *, struct iov_iter *); static ssize_t tty_write(struct kiocb *, struct iov_iter *); static __poll_t tty_poll(struct file *, poll_table *); static int tty_open(struct inode *, struct file *); #ifdef CONFIG_COMPAT static long tty_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #else #define tty_compat_ioctl NULL #endif static int __tty_fasync(int fd, struct file *filp, int on); static int tty_fasync(int fd, struct file *filp, int on); static void release_tty(struct tty_struct *tty, int idx); /** * free_tty_struct - free a disused tty * @tty: tty struct to free * * Free the write buffers, tty queue and tty memory itself. * * Locking: none. Must be called after tty is definitely unused */ static void free_tty_struct(struct tty_struct *tty) { tty_ldisc_deinit(tty); put_device(tty->dev); kvfree(tty->write_buf); kfree(tty); } static inline struct tty_struct *file_tty(struct file *file) { return ((struct tty_file_private *)file->private_data)->tty; } int tty_alloc_file(struct file *file) { struct tty_file_private *priv; priv = kmalloc(sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; file->private_data = priv; return 0; } /* Associate a new file with the tty structure */ void tty_add_file(struct tty_struct *tty, struct file *file) { struct tty_file_private *priv = file->private_data; priv->tty = tty; priv->file = file; spin_lock(&tty->files_lock); list_add(&priv->list, &tty->tty_files); spin_unlock(&tty->files_lock); } /** * tty_free_file - free file->private_data * @file: to free private_data of * * This shall be used only for fail path handling when tty_add_file was not * called yet. */ void tty_free_file(struct file *file) { struct tty_file_private *priv = file->private_data; file->private_data = NULL; kfree(priv); } /* Delete file from its tty */ static void tty_del_file(struct file *file) { struct tty_file_private *priv = file->private_data; struct tty_struct *tty = priv->tty; spin_lock(&tty->files_lock); list_del(&priv->list); spin_unlock(&tty->files_lock); tty_free_file(file); } /** * tty_name - return tty naming * @tty: tty structure * * Convert a tty structure into a name. The name reflects the kernel naming * policy and if udev is in use may not reflect user space * * Locking: none */ const char *tty_name(const struct tty_struct *tty) { if (!tty) /* Hmm. NULL pointer. That's fun. */ return "NULL tty"; return tty->name; } EXPORT_SYMBOL(tty_name); const char *tty_driver_name(const struct tty_struct *tty) { if (!tty || !tty->driver) return ""; return tty->driver->name; } static int tty_paranoia_check(struct tty_struct *tty, struct inode *inode, const char *routine) { #ifdef TTY_PARANOIA_CHECK if (!tty) { pr_warn("(%d:%d): %s: NULL tty\n", imajor(inode), iminor(inode), routine); return 1; } #endif return 0; } /* Caller must hold tty_lock */ static void check_tty_count(struct tty_struct *tty, const char *routine) { #ifdef CHECK_TTY_COUNT struct list_head *p; int count = 0, kopen_count = 0; spin_lock(&tty->files_lock); list_for_each(p, &tty->tty_files) { count++; } spin_unlock(&tty->files_lock); if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_SLAVE && tty->link && tty->link->count) count++; if (tty_port_kopened(tty->port)) kopen_count++; if (tty->count != (count + kopen_count)) { tty_warn(tty, "%s: tty->count(%d) != (#fd's(%d) + #kopen's(%d))\n", routine, tty->count, count, kopen_count); } #endif } /** * get_tty_driver - find device of a tty * @device: device identifier * @index: returns the index of the tty * * This routine returns a tty driver structure, given a device number and also * passes back the index number. * * Locking: caller must hold tty_mutex */ static struct tty_driver *get_tty_driver(dev_t device, int *index) { struct tty_driver *p; list_for_each_entry(p, &tty_drivers, tty_drivers) { dev_t base = MKDEV(p->major, p->minor_start); if (device < base || device >= base + p->num) continue; *index = device - base; return tty_driver_kref_get(p); } return NULL; } /** * tty_dev_name_to_number - return dev_t for device name * @name: user space name of device under /dev * @number: pointer to dev_t that this function will populate * * This function converts device names like ttyS0 or ttyUSB1 into dev_t like * (4, 64) or (188, 1). If no corresponding driver is registered then the * function returns -%ENODEV. * * Locking: this acquires tty_mutex to protect the tty_drivers list from * being modified while we are traversing it, and makes sure to * release it before exiting. */ int tty_dev_name_to_number(const char *name, dev_t *number) { struct tty_driver *p; int ret; int index, prefix_length = 0; const char *str; for (str = name; *str && !isdigit(*str); str++) ; if (!*str) return -EINVAL; ret = kstrtoint(str, 10, &index); if (ret) return ret; prefix_length = str - name; mutex_lock(&tty_mutex); list_for_each_entry(p, &tty_drivers, tty_drivers) if (prefix_length == strlen(p->name) && strncmp(name, p->name, prefix_length) == 0) { if (index < p->num) { *number = MKDEV(p->major, p->minor_start + index); goto out; } } /* if here then driver wasn't found */ ret = -ENODEV; out: mutex_unlock(&tty_mutex); return ret; } EXPORT_SYMBOL_GPL(tty_dev_name_to_number); #ifdef CONFIG_CONSOLE_POLL /** * tty_find_polling_driver - find device of a polled tty * @name: name string to match * @line: pointer to resulting tty line nr * * This routine returns a tty driver structure, given a name and the condition * that the tty driver is capable of polled operation. */ struct tty_driver *tty_find_polling_driver(char *name, int *line) { struct tty_driver *p, *res = NULL; int tty_line = 0; int len; char *str, *stp; for (str = name; *str; str++) if ((*str >= '0' && *str <= '9') || *str == ',') break; if (!*str) return NULL; len = str - name; tty_line = simple_strtoul(str, &str, 10); mutex_lock(&tty_mutex); /* Search through the tty devices to look for a match */ list_for_each_entry(p, &tty_drivers, tty_drivers) { if (!len || strncmp(name, p->name, len) != 0) continue; stp = str; if (*stp == ',') stp++; if (*stp == '\0') stp = NULL; if (tty_line >= 0 && tty_line < p->num && p->ops && p->ops->poll_init && !p->ops->poll_init(p, tty_line, stp)) { res = tty_driver_kref_get(p); *line = tty_line; break; } } mutex_unlock(&tty_mutex); return res; } EXPORT_SYMBOL_GPL(tty_find_polling_driver); #endif static ssize_t hung_up_tty_read(struct kiocb *iocb, struct iov_iter *to) { return 0; } static ssize_t hung_up_tty_write(struct kiocb *iocb, struct iov_iter *from) { return -EIO; } /* No kernel lock held - none needed ;) */ static __poll_t hung_up_tty_poll(struct file *filp, poll_table *wait) { return EPOLLIN | EPOLLOUT | EPOLLERR | EPOLLHUP | EPOLLRDNORM | EPOLLWRNORM; } static long hung_up_tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return cmd == TIOCSPGRP ? -ENOTTY : -EIO; } static long hung_up_tty_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return cmd == TIOCSPGRP ? -ENOTTY : -EIO; } static int hung_up_tty_fasync(int fd, struct file *file, int on) { return -ENOTTY; } static void tty_show_fdinfo(struct seq_file *m, struct file *file) { struct tty_struct *tty = file_tty(file); if (tty && tty->ops && tty->ops->show_fdinfo) tty->ops->show_fdinfo(tty, m); } static const struct file_operations tty_fops = { .llseek = no_llseek, .read_iter = tty_read, .write_iter = tty_write, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, .poll = tty_poll, .unlocked_ioctl = tty_ioctl, .compat_ioctl = tty_compat_ioctl, .open = tty_open, .release = tty_release, .fasync = tty_fasync, .show_fdinfo = tty_show_fdinfo, }; static const struct file_operations console_fops = { .llseek = no_llseek, .read_iter = tty_read, .write_iter = redirected_tty_write, .splice_read = copy_splice_read, .splice_write = iter_file_splice_write, .poll = tty_poll, .unlocked_ioctl = tty_ioctl, .compat_ioctl = tty_compat_ioctl, .open = tty_open, .release = tty_release, .fasync = tty_fasync, }; static const struct file_operations hung_up_tty_fops = { .llseek = no_llseek, .read_iter = hung_up_tty_read, .write_iter = hung_up_tty_write, .poll = hung_up_tty_poll, .unlocked_ioctl = hung_up_tty_ioctl, .compat_ioctl = hung_up_tty_compat_ioctl, .release = tty_release, .fasync = hung_up_tty_fasync, }; static DEFINE_SPINLOCK(redirect_lock); static struct file *redirect; /** * tty_wakeup - request more data * @tty: terminal * * Internal and external helper for wakeups of tty. This function informs the * line discipline if present that the driver is ready to receive more output * data. */ void tty_wakeup(struct tty_struct *tty) { struct tty_ldisc *ld; if (test_bit(TTY_DO_WRITE_WAKEUP, &tty->flags)) { ld = tty_ldisc_ref(tty); if (ld) { if (ld->ops->write_wakeup) ld->ops->write_wakeup(tty); tty_ldisc_deref(ld); } } wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT); } EXPORT_SYMBOL_GPL(tty_wakeup); /** * tty_release_redirect - Release a redirect on a pty if present * @tty: tty device * * This is available to the pty code so if the master closes, if the slave is a * redirect it can release the redirect. */ static struct file *tty_release_redirect(struct tty_struct *tty) { struct file *f = NULL; spin_lock(&redirect_lock); if (redirect && file_tty(redirect) == tty) { f = redirect; redirect = NULL; } spin_unlock(&redirect_lock); return f; } /** * __tty_hangup - actual handler for hangup events * @tty: tty device * @exit_session: if non-zero, signal all foreground group processes * * This can be called by a "kworker" kernel thread. That is process synchronous * but doesn't hold any locks, so we need to make sure we have the appropriate * locks for what we're doing. * * The hangup event clears any pending redirections onto the hung up device. It * ensures future writes will error and it does the needed line discipline * hangup and signal delivery. The tty object itself remains intact. * * Locking: * * BTM * * * redirect lock for undoing redirection * * file list lock for manipulating list of ttys * * tty_ldiscs_lock from called functions * * termios_rwsem resetting termios data * * tasklist_lock to walk task list for hangup event * * * ->siglock to protect ->signal/->sighand * */ static void __tty_hangup(struct tty_struct *tty, int exit_session) { struct file *cons_filp = NULL; struct file *filp, *f; struct tty_file_private *priv; int closecount = 0, n; int refs; if (!tty) return; f = tty_release_redirect(tty); tty_lock(tty); if (test_bit(TTY_HUPPED, &tty->flags)) { tty_unlock(tty); return; } /* * Some console devices aren't actually hung up for technical and * historical reasons, which can lead to indefinite interruptible * sleep in n_tty_read(). The following explicitly tells * n_tty_read() to abort readers. */ set_bit(TTY_HUPPING, &tty->flags); /* inuse_filps is protected by the single tty lock, * this really needs to change if we want to flush the * workqueue with the lock held. */ check_tty_count(tty, "tty_hangup"); spin_lock(&tty->files_lock); /* This breaks for file handles being sent over AF_UNIX sockets ? */ list_for_each_entry(priv, &tty->tty_files, list) { filp = priv->file; if (filp->f_op->write_iter == redirected_tty_write) cons_filp = filp; if (filp->f_op->write_iter != tty_write) continue; closecount++; __tty_fasync(-1, filp, 0); /* can't block */ filp->f_op = &hung_up_tty_fops; } spin_unlock(&tty->files_lock); refs = tty_signal_session_leader(tty, exit_session); /* Account for the p->signal references we killed */ while (refs--) tty_kref_put(tty); tty_ldisc_hangup(tty, cons_filp != NULL); spin_lock_irq(&tty->ctrl.lock); clear_bit(TTY_THROTTLED, &tty->flags); clear_bit(TTY_DO_WRITE_WAKEUP, &tty->flags); put_pid(tty->ctrl.session); put_pid(tty->ctrl.pgrp); tty->ctrl.session = NULL; tty->ctrl.pgrp = NULL; tty->ctrl.pktstatus = 0; spin_unlock_irq(&tty->ctrl.lock); /* * If one of the devices matches a console pointer, we * cannot just call hangup() because that will cause * tty->count and state->count to go out of sync. * So we just call close() the right number of times. */ if (cons_filp) { if (tty->ops->close) for (n = 0; n < closecount; n++) tty->ops->close(tty, cons_filp); } else if (tty->ops->hangup) tty->ops->hangup(tty); /* * We don't want to have driver/ldisc interactions beyond the ones * we did here. The driver layer expects no calls after ->hangup() * from the ldisc side, which is now guaranteed. */ set_bit(TTY_HUPPED, &tty->flags); clear_bit(TTY_HUPPING, &tty->flags); tty_unlock(tty); if (f) fput(f); } static void do_tty_hangup(struct work_struct *work) { struct tty_struct *tty = container_of(work, struct tty_struct, hangup_work); __tty_hangup(tty, 0); } /** * tty_hangup - trigger a hangup event * @tty: tty to hangup * * A carrier loss (virtual or otherwise) has occurred on @tty. Schedule a * hangup sequence to run after this event. */ void tty_hangup(struct tty_struct *tty) { tty_debug_hangup(tty, "hangup\n"); schedule_work(&tty->hangup_work); } EXPORT_SYMBOL(tty_hangup); /** * tty_vhangup - process vhangup * @tty: tty to hangup * * The user has asked via system call for the terminal to be hung up. We do * this synchronously so that when the syscall returns the process is complete. * That guarantee is necessary for security reasons. */ void tty_vhangup(struct tty_struct *tty) { tty_debug_hangup(tty, "vhangup\n"); __tty_hangup(tty, 0); } EXPORT_SYMBOL(tty_vhangup); /** * tty_vhangup_self - process vhangup for own ctty * * Perform a vhangup on the current controlling tty */ void tty_vhangup_self(void) { struct tty_struct *tty; tty = get_current_tty(); if (tty) { tty_vhangup(tty); tty_kref_put(tty); } } /** * tty_vhangup_session - hangup session leader exit * @tty: tty to hangup * * The session leader is exiting and hanging up its controlling terminal. * Every process in the foreground process group is signalled %SIGHUP. * * We do this synchronously so that when the syscall returns the process is * complete. That guarantee is necessary for security reasons. */ void tty_vhangup_session(struct tty_struct *tty) { tty_debug_hangup(tty, "session hangup\n"); __tty_hangup(tty, 1); } /** * tty_hung_up_p - was tty hung up * @filp: file pointer of tty * * Return: true if the tty has been subject to a vhangup or a carrier loss */ int tty_hung_up_p(struct file *filp) { return (filp && filp->f_op == &hung_up_tty_fops); } EXPORT_SYMBOL(tty_hung_up_p); void __stop_tty(struct tty_struct *tty) { if (tty->flow.stopped) return; tty->flow.stopped = true; if (tty->ops->stop) tty->ops->stop(tty); } /** * stop_tty - propagate flow control * @tty: tty to stop * * Perform flow control to the driver. May be called on an already stopped * device and will not re-call the &tty_driver->stop() method. * * This functionality is used by both the line disciplines for halting incoming * flow and by the driver. It may therefore be called from any context, may be * under the tty %atomic_write_lock but not always. * * Locking: * flow.lock */ void stop_tty(struct tty_struct *tty) { unsigned long flags; spin_lock_irqsave(&tty->flow.lock, flags); __stop_tty(tty); spin_unlock_irqrestore(&tty->flow.lock, flags); } EXPORT_SYMBOL(stop_tty); void __start_tty(struct tty_struct *tty) { if (!tty->flow.stopped || tty->flow.tco_stopped) return; tty->flow.stopped = false; if (tty->ops->start) tty->ops->start(tty); tty_wakeup(tty); } /** * start_tty - propagate flow control * @tty: tty to start * * Start a tty that has been stopped if at all possible. If @tty was previously * stopped and is now being started, the &tty_driver->start() method is invoked * and the line discipline woken. * * Locking: * flow.lock */ void start_tty(struct tty_struct *tty) { unsigned long flags; spin_lock_irqsave(&tty->flow.lock, flags); __start_tty(tty); spin_unlock_irqrestore(&tty->flow.lock, flags); } EXPORT_SYMBOL(start_tty); static void tty_update_time(struct tty_struct *tty, bool mtime) { time64_t sec = ktime_get_real_seconds(); struct tty_file_private *priv; spin_lock(&tty->files_lock); list_for_each_entry(priv, &tty->tty_files, list) { struct inode *inode = file_inode(priv->file); struct timespec64 time = mtime ? inode_get_mtime(inode) : inode_get_atime(inode); /* * We only care if the two values differ in anything other than the * lower three bits (i.e every 8 seconds). If so, then we can update * the time of the tty device, otherwise it could be construded as a * security leak to let userspace know the exact timing of the tty. */ if ((sec ^ time.tv_sec) & ~7) { if (mtime) inode_set_mtime(inode, sec, 0); else inode_set_atime(inode, sec, 0); } } spin_unlock(&tty->files_lock); } /* * Iterate on the ldisc ->read() function until we've gotten all * the data the ldisc has for us. * * The "cookie" is something that the ldisc read function can fill * in to let us know that there is more data to be had. * * We promise to continue to call the ldisc until it stops returning * data or clears the cookie. The cookie may be something that the * ldisc maintains state for and needs to free. */ static ssize_t iterate_tty_read(struct tty_ldisc *ld, struct tty_struct *tty, struct file *file, struct iov_iter *to) { void *cookie = NULL; unsigned long offset = 0; ssize_t retval = 0; size_t copied, count = iov_iter_count(to); u8 kernel_buf[64]; do { ssize_t size = min(count, sizeof(kernel_buf)); size = ld->ops->read(tty, file, kernel_buf, size, &cookie, offset); if (!size) break; if (size < 0) { /* Did we have an earlier error (ie -EFAULT)? */ if (retval) break; retval = size; /* * -EOVERFLOW means we didn't have enough space * for a whole packet, and we shouldn't return * a partial result. */ if (retval == -EOVERFLOW) offset = 0; break; } copied = copy_to_iter(kernel_buf, size, to); offset += copied; count -= copied; /* * If the user copy failed, we still need to do another ->read() * call if we had a cookie to let the ldisc clear up. * * But make sure size is zeroed. */ if (unlikely(copied != size)) { count = 0; retval = -EFAULT; } } while (cookie); /* We always clear tty buffer in case they contained passwords */ memzero_explicit(kernel_buf, sizeof(kernel_buf)); return offset ? offset : retval; } /** * tty_read - read method for tty device files * @iocb: kernel I/O control block * @to: destination for the data read * * Perform the read system call function on this terminal device. Checks * for hung up devices before calling the line discipline method. * * Locking: * Locks the line discipline internally while needed. Multiple read calls * may be outstanding in parallel. */ static ssize_t tty_read(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct tty_struct *tty = file_tty(file); struct tty_ldisc *ld; ssize_t ret; if (tty_paranoia_check(tty, inode, "tty_read")) return -EIO; if (!tty || tty_io_error(tty)) return -EIO; /* We want to wait for the line discipline to sort out in this * situation. */ ld = tty_ldisc_ref_wait(tty); if (!ld) return hung_up_tty_read(iocb, to); ret = -EIO; if (ld->ops->read) ret = iterate_tty_read(ld, tty, file, to); tty_ldisc_deref(ld); if (ret > 0) tty_update_time(tty, false); return ret; } void tty_write_unlock(struct tty_struct *tty) { mutex_unlock(&tty->atomic_write_lock); wake_up_interruptible_poll(&tty->write_wait, EPOLLOUT); } int tty_write_lock(struct tty_struct *tty, bool ndelay) { if (!mutex_trylock(&tty->atomic_write_lock)) { if (ndelay) return -EAGAIN; if (mutex_lock_interruptible(&tty->atomic_write_lock)) return -ERESTARTSYS; } return 0; } /* * Split writes up in sane blocksizes to avoid * denial-of-service type attacks */ static ssize_t iterate_tty_write(struct tty_ldisc *ld, struct tty_struct *tty, struct file *file, struct iov_iter *from) { size_t chunk, count = iov_iter_count(from); ssize_t ret, written = 0; ret = tty_write_lock(tty, file->f_flags & O_NDELAY); if (ret < 0) return ret; /* * We chunk up writes into a temporary buffer. This * simplifies low-level drivers immensely, since they * don't have locking issues and user mode accesses. * * But if TTY_NO_WRITE_SPLIT is set, we should use a * big chunk-size.. * * The default chunk-size is 2kB, because the NTTY * layer has problems with bigger chunks. It will * claim to be able to handle more characters than * it actually does. */ chunk = 2048; if (test_bit(TTY_NO_WRITE_SPLIT, &tty->flags)) chunk = 65536; if (count < chunk) chunk = count; /* write_buf/write_cnt is protected by the atomic_write_lock mutex */ if (tty->write_cnt < chunk) { u8 *buf_chunk; if (chunk < 1024) chunk = 1024; buf_chunk = kvmalloc(chunk, GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!buf_chunk) { ret = -ENOMEM; goto out; } kvfree(tty->write_buf); tty->write_cnt = chunk; tty->write_buf = buf_chunk; } /* Do the write .. */ for (;;) { size_t size = min(chunk, count); ret = -EFAULT; if (copy_from_iter(tty->write_buf, size, from) != size) break; ret = ld->ops->write(tty, file, tty->write_buf, size); if (ret <= 0) break; written += ret; if (ret > size) break; /* FIXME! Have Al check this! */ if (ret != size) iov_iter_revert(from, size-ret); count -= ret; if (!count) break; ret = -ERESTARTSYS; if (signal_pending(current)) break; cond_resched(); } if (written) { tty_update_time(tty, true); ret = written; } out: tty_write_unlock(tty); return ret; } #ifdef CONFIG_PRINT_QUOTA_WARNING /** * tty_write_message - write a message to a certain tty, not just the console. * @tty: the destination tty_struct * @msg: the message to write * * This is used for messages that need to be redirected to a specific tty. We * don't put it into the syslog queue right now maybe in the future if really * needed. * * We must still hold the BTM and test the CLOSING flag for the moment. * * This function is DEPRECATED, do not use in new code. */ void tty_write_message(struct tty_struct *tty, char *msg) { if (tty) { mutex_lock(&tty->atomic_write_lock); tty_lock(tty); if (tty->ops->write && tty->count > 0) tty->ops->write(tty, msg, strlen(msg)); tty_unlock(tty); tty_write_unlock(tty); } } #endif static ssize_t file_tty_write(struct file *file, struct kiocb *iocb, struct iov_iter *from) { struct tty_struct *tty = file_tty(file); struct tty_ldisc *ld; ssize_t ret; if (tty_paranoia_check(tty, file_inode(file), "tty_write")) return -EIO; if (!tty || !tty->ops->write || tty_io_error(tty)) return -EIO; /* Short term debug to catch buggy drivers */ if (tty->ops->write_room == NULL) tty_err(tty, "missing write_room method\n"); ld = tty_ldisc_ref_wait(tty); if (!ld) return hung_up_tty_write(iocb, from); if (!ld->ops->write) ret = -EIO; else ret = iterate_tty_write(ld, tty, file, from); tty_ldisc_deref(ld); return ret; } /** * tty_write - write method for tty device file * @iocb: kernel I/O control block * @from: iov_iter with data to write * * Write data to a tty device via the line discipline. * * Locking: * Locks the line discipline as required * Writes to the tty driver are serialized by the atomic_write_lock * and are then processed in chunks to the device. The line * discipline write method will not be invoked in parallel for * each device. */ static ssize_t tty_write(struct kiocb *iocb, struct iov_iter *from) { return file_tty_write(iocb->ki_filp, iocb, from); } ssize_t redirected_tty_write(struct kiocb *iocb, struct iov_iter *iter) { struct file *p = NULL; spin_lock(&redirect_lock); if (redirect) p = get_file(redirect); spin_unlock(&redirect_lock); /* * We know the redirected tty is just another tty, we can * call file_tty_write() directly with that file pointer. */ if (p) { ssize_t res; res = file_tty_write(p, iocb, iter); fput(p); return res; } return tty_write(iocb, iter); } /** * tty_send_xchar - send priority character * @tty: the tty to send to * @ch: xchar to send * * Send a high priority character to the tty even if stopped. * * Locking: none for xchar method, write ordering for write method. */ int tty_send_xchar(struct tty_struct *tty, u8 ch) { bool was_stopped = tty->flow.stopped; if (tty->ops->send_xchar) { down_read(&tty->termios_rwsem); tty->ops->send_xchar(tty, ch); up_read(&tty->termios_rwsem); return 0; } if (tty_write_lock(tty, false) < 0) return -ERESTARTSYS; down_read(&tty->termios_rwsem); if (was_stopped) start_tty(tty); tty->ops->write(tty, &ch, 1); if (was_stopped) stop_tty(tty); up_read(&tty->termios_rwsem); tty_write_unlock(tty); return 0; } /** * pty_line_name - generate name for a pty * @driver: the tty driver in use * @index: the minor number * @p: output buffer of at least 6 bytes * * Generate a name from a @driver reference and write it to the output buffer * @p. * * Locking: None */ static void pty_line_name(struct tty_driver *driver, int index, char *p) { static const char ptychar[] = "pqrstuvwxyzabcde"; int i = index + driver->name_base; /* ->name is initialized to "ttyp", but "tty" is expected */ sprintf(p, "%s%c%x", driver->subtype == PTY_TYPE_SLAVE ? "tty" : driver->name, ptychar[i >> 4 & 0xf], i & 0xf); } /** * tty_line_name - generate name for a tty * @driver: the tty driver in use * @index: the minor number * @p: output buffer of at least 7 bytes * * Generate a name from a @driver reference and write it to the output buffer * @p. * * Locking: None */ static ssize_t tty_line_name(struct tty_driver *driver, int index, char *p) { if (driver->flags & TTY_DRIVER_UNNUMBERED_NODE) return sprintf(p, "%s", driver->name); else return sprintf(p, "%s%d", driver->name, index + driver->name_base); } /** * tty_driver_lookup_tty() - find an existing tty, if any * @driver: the driver for the tty * @file: file object * @idx: the minor number * * Return: the tty, if found. If not found, return %NULL or ERR_PTR() if the * driver lookup() method returns an error. * * Locking: tty_mutex must be held. If the tty is found, bump the tty kref. */ static struct tty_struct *tty_driver_lookup_tty(struct tty_driver *driver, struct file *file, int idx) { struct tty_struct *tty; if (driver->ops->lookup) { if (!file) tty = ERR_PTR(-EIO); else tty = driver->ops->lookup(driver, file, idx); } else { if (idx >= driver->num) return ERR_PTR(-EINVAL); tty = driver->ttys[idx]; } if (!IS_ERR(tty)) tty_kref_get(tty); return tty; } /** * tty_init_termios - helper for termios setup * @tty: the tty to set up * * Initialise the termios structure for this tty. This runs under the * %tty_mutex currently so we can be relaxed about ordering. */ void tty_init_termios(struct tty_struct *tty) { struct ktermios *tp; int idx = tty->index; if (tty->driver->flags & TTY_DRIVER_RESET_TERMIOS) tty->termios = tty->driver->init_termios; else { /* Check for lazy saved data */ tp = tty->driver->termios[idx]; if (tp != NULL) { tty->termios = *tp; tty->termios.c_line = tty->driver->init_termios.c_line; } else tty->termios = tty->driver->init_termios; } /* Compatibility until drivers always set this */ tty->termios.c_ispeed = tty_termios_input_baud_rate(&tty->termios); tty->termios.c_ospeed = tty_termios_baud_rate(&tty->termios); } EXPORT_SYMBOL_GPL(tty_init_termios); /** * tty_standard_install - usual tty->ops->install * @driver: the driver for the tty * @tty: the tty * * If the @driver overrides @tty->ops->install, it still can call this function * to perform the standard install operations. */ int tty_standard_install(struct tty_driver *driver, struct tty_struct *tty) { tty_init_termios(tty); tty_driver_kref_get(driver); tty->count++; driver->ttys[tty->index] = tty; return 0; } EXPORT_SYMBOL_GPL(tty_standard_install); /** * tty_driver_install_tty() - install a tty entry in the driver * @driver: the driver for the tty * @tty: the tty * * Install a tty object into the driver tables. The @tty->index field will be * set by the time this is called. This method is responsible for ensuring any * need additional structures are allocated and configured. * * Locking: tty_mutex for now */ static int tty_driver_install_tty(struct tty_driver *driver, struct tty_struct *tty) { return driver->ops->install ? driver->ops->install(driver, tty) : tty_standard_install(driver, tty); } /** * tty_driver_remove_tty() - remove a tty from the driver tables * @driver: the driver for the tty * @tty: tty to remove * * Remove a tty object from the driver tables. The tty->index field will be set * by the time this is called. * * Locking: tty_mutex for now */ static void tty_driver_remove_tty(struct tty_driver *driver, struct tty_struct *tty) { if (driver->ops->remove) driver->ops->remove(driver, tty); else driver->ttys[tty->index] = NULL; } /** * tty_reopen() - fast re-open of an open tty * @tty: the tty to open * * Re-opens on master ptys are not allowed and return -%EIO. * * Locking: Caller must hold tty_lock * Return: 0 on success, -errno on error. */ static int tty_reopen(struct tty_struct *tty) { struct tty_driver *driver = tty->driver; struct tty_ldisc *ld; int retval = 0; if (driver->type == TTY_DRIVER_TYPE_PTY && driver->subtype == PTY_TYPE_MASTER) return -EIO; if (!tty->count) return -EAGAIN; if (test_bit(TTY_EXCLUSIVE, &tty->flags) && !capable(CAP_SYS_ADMIN)) return -EBUSY; ld = tty_ldisc_ref_wait(tty); if (ld) { tty_ldisc_deref(ld); } else { retval = tty_ldisc_lock(tty, 5 * HZ); if (retval) return retval; if (!tty->ldisc) retval = tty_ldisc_reinit(tty, tty->termios.c_line); tty_ldisc_unlock(tty); } if (retval == 0) tty->count++; return retval; } /** * tty_init_dev - initialise a tty device * @driver: tty driver we are opening a device on * @idx: device index * * Prepare a tty device. This may not be a "new" clean device but could also be * an active device. The pty drivers require special handling because of this. * * Locking: * The function is called under the tty_mutex, which protects us from the * tty struct or driver itself going away. * * On exit the tty device has the line discipline attached and a reference * count of 1. If a pair was created for pty/tty use and the other was a pty * master then it too has a reference count of 1. * * WSH 06/09/97: Rewritten to remove races and properly clean up after a failed * open. The new code protects the open with a mutex, so it's really quite * straightforward. The mutex locking can probably be relaxed for the (most * common) case of reopening a tty. * * Return: new tty structure */ struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx) { struct tty_struct *tty; int retval; /* * First time open is complex, especially for PTY devices. * This code guarantees that either everything succeeds and the * TTY is ready for operation, or else the table slots are vacated * and the allocated memory released. (Except that the termios * may be retained.) */ if (!try_module_get(driver->owner)) return ERR_PTR(-ENODEV); tty = alloc_tty_struct(driver, idx); if (!tty) { retval = -ENOMEM; goto err_module_put; } tty_lock(tty); retval = tty_driver_install_tty(driver, tty); if (retval < 0) goto err_free_tty; if (!tty->port) tty->port = driver->ports[idx]; if (WARN_RATELIMIT(!tty->port, "%s: %s driver does not set tty->port. This would crash the kernel. Fix the driver!\n", __func__, tty->driver->name)) { retval = -EINVAL; goto err_release_lock; } retval = tty_ldisc_lock(tty, 5 * HZ); if (retval) goto err_release_lock; tty->port->itty = tty; /* * Structures all installed ... call the ldisc open routines. * If we fail here just call release_tty to clean up. No need * to decrement the use counts, as release_tty doesn't care. */ retval = tty_ldisc_setup(tty, tty->link); if (retval) goto err_release_tty; tty_ldisc_unlock(tty); /* Return the tty locked so that it cannot vanish under the caller */ return tty; err_free_tty: tty_unlock(tty); free_tty_struct(tty); err_module_put: module_put(driver->owner); return ERR_PTR(retval); /* call the tty release_tty routine to clean out this slot */ err_release_tty: tty_ldisc_unlock(tty); tty_info_ratelimited(tty, "ldisc open failed (%d), clearing slot %d\n", retval, idx); err_release_lock: tty_unlock(tty); release_tty(tty, idx); return ERR_PTR(retval); } /** * tty_save_termios() - save tty termios data in driver table * @tty: tty whose termios data to save * * Locking: Caller guarantees serialisation with tty_init_termios(). */ void tty_save_termios(struct tty_struct *tty) { struct ktermios *tp; int idx = tty->index; /* If the port is going to reset then it has no termios to save */ if (tty->driver->flags & TTY_DRIVER_RESET_TERMIOS) return; /* Stash the termios data */ tp = tty->driver->termios[idx]; if (tp == NULL) { tp = kmalloc(sizeof(*tp), GFP_KERNEL); if (tp == NULL) return; tty->driver->termios[idx] = tp; } *tp = tty->termios; } EXPORT_SYMBOL_GPL(tty_save_termios); /** * tty_flush_works - flush all works of a tty/pty pair * @tty: tty device to flush works for (or either end of a pty pair) * * Sync flush all works belonging to @tty (and the 'other' tty). */ static void tty_flush_works(struct tty_struct *tty) { flush_work(&tty->SAK_work); flush_work(&tty->hangup_work); if (tty->link) { flush_work(&tty->link->SAK_work); flush_work(&tty->link->hangup_work); } } /** * release_one_tty - release tty structure memory * @work: work of tty we are obliterating * * Releases memory associated with a tty structure, and clears out the * driver table slots. This function is called when a device is no longer * in use. It also gets called when setup of a device fails. * * Locking: * takes the file list lock internally when working on the list of ttys * that the driver keeps. * * This method gets called from a work queue so that the driver private * cleanup ops can sleep (needed for USB at least) */ static void release_one_tty(struct work_struct *work) { struct tty_struct *tty = container_of(work, struct tty_struct, hangup_work); struct tty_driver *driver = tty->driver; struct module *owner = driver->owner; if (tty->ops->cleanup) tty->ops->cleanup(tty); tty_driver_kref_put(driver); module_put(owner); spin_lock(&tty->files_lock); list_del_init(&tty->tty_files); spin_unlock(&tty->files_lock); put_pid(tty->ctrl.pgrp); put_pid(tty->ctrl.session); free_tty_struct(tty); } static void queue_release_one_tty(struct kref *kref) { struct tty_struct *tty = container_of(kref, struct tty_struct, kref); /* The hangup queue is now free so we can reuse it rather than * waste a chunk of memory for each port. */ INIT_WORK(&tty->hangup_work, release_one_tty); schedule_work(&tty->hangup_work); } /** * tty_kref_put - release a tty kref * @tty: tty device * * Release a reference to the @tty device and if need be let the kref layer * destruct the object for us. */ void tty_kref_put(struct tty_struct *tty) { if (tty) kref_put(&tty->kref, queue_release_one_tty); } EXPORT_SYMBOL(tty_kref_put); /** * release_tty - release tty structure memory * @tty: tty device release * @idx: index of the tty device release * * Release both @tty and a possible linked partner (think pty pair), * and decrement the refcount of the backing module. * * Locking: * tty_mutex * takes the file list lock internally when working on the list of ttys * that the driver keeps. */ static void release_tty(struct tty_struct *tty, int idx) { /* This should always be true but check for the moment */ WARN_ON(tty->index != idx); WARN_ON(!mutex_is_locked(&tty_mutex)); if (tty->ops->shutdown) tty->ops->shutdown(tty); tty_save_termios(tty); tty_driver_remove_tty(tty->driver, tty); if (tty->port) tty->port->itty = NULL; if (tty->link) tty->link->port->itty = NULL; if (tty->port) tty_buffer_cancel_work(tty->port); if (tty->link) tty_buffer_cancel_work(tty->link->port); tty_kref_put(tty->link); tty_kref_put(tty); } /** * tty_release_checks - check a tty before real release * @tty: tty to check * @idx: index of the tty * * Performs some paranoid checking before true release of the @tty. This is a * no-op unless %TTY_PARANOIA_CHECK is defined. */ static int tty_release_checks(struct tty_struct *tty, int idx) { #ifdef TTY_PARANOIA_CHECK if (idx < 0 || idx >= tty->driver->num) { tty_debug(tty, "bad idx %d\n", idx); return -1; } /* not much to check for devpts */ if (tty->driver->flags & TTY_DRIVER_DEVPTS_MEM) return 0; if (tty != tty->driver->ttys[idx]) { tty_debug(tty, "bad driver table[%d] = %p\n", idx, tty->driver->ttys[idx]); return -1; } if (tty->driver->other) { struct tty_struct *o_tty = tty->link; if (o_tty != tty->driver->other->ttys[idx]) { tty_debug(tty, "bad other table[%d] = %p\n", idx, tty->driver->other->ttys[idx]); return -1; } if (o_tty->link != tty) { tty_debug(tty, "bad link = %p\n", o_tty->link); return -1; } } #endif return 0; } /** * tty_kclose - closes tty opened by tty_kopen * @tty: tty device * * Performs the final steps to release and free a tty device. It is the same as * tty_release_struct() except that it also resets %TTY_PORT_KOPENED flag on * @tty->port. */ void tty_kclose(struct tty_struct *tty) { /* * Ask the line discipline code to release its structures */ tty_ldisc_release(tty); /* Wait for pending work before tty destruction commences */ tty_flush_works(tty); tty_debug_hangup(tty, "freeing structure\n"); /* * The release_tty function takes care of the details of clearing * the slots and preserving the termios structure. */ mutex_lock(&tty_mutex); tty_port_set_kopened(tty->port, 0); release_tty(tty, tty->index); mutex_unlock(&tty_mutex); } EXPORT_SYMBOL_GPL(tty_kclose); /** * tty_release_struct - release a tty struct * @tty: tty device * @idx: index of the tty * * Performs the final steps to release and free a tty device. It is roughly the * reverse of tty_init_dev(). */ void tty_release_struct(struct tty_struct *tty, int idx) { /* * Ask the line discipline code to release its structures */ tty_ldisc_release(tty); /* Wait for pending work before tty destruction commmences */ tty_flush_works(tty); tty_debug_hangup(tty, "freeing structure\n"); /* * The release_tty function takes care of the details of clearing * the slots and preserving the termios structure. */ mutex_lock(&tty_mutex); release_tty(tty, idx); mutex_unlock(&tty_mutex); } EXPORT_SYMBOL_GPL(tty_release_struct); /** * tty_release - vfs callback for close * @inode: inode of tty * @filp: file pointer for handle to tty * * Called the last time each file handle is closed that references this tty. * There may however be several such references. * * Locking: * Takes BKL. See tty_release_dev(). * * Even releasing the tty structures is a tricky business. We have to be very * careful that the structures are all released at the same time, as interrupts * might otherwise get the wrong pointers. * * WSH 09/09/97: rewritten to avoid some nasty race conditions that could * lead to double frees or releasing memory still in use. */ int tty_release(struct inode *inode, struct file *filp) { struct tty_struct *tty = file_tty(filp); struct tty_struct *o_tty = NULL; int do_sleep, final; int idx; long timeout = 0; int once = 1; if (tty_paranoia_check(tty, inode, __func__)) return 0; tty_lock(tty); check_tty_count(tty, __func__); __tty_fasync(-1, filp, 0); idx = tty->index; if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER) o_tty = tty->link; if (tty_release_checks(tty, idx)) { tty_unlock(tty); return 0; } tty_debug_hangup(tty, "releasing (count=%d)\n", tty->count); if (tty->ops->close) tty->ops->close(tty, filp); /* If tty is pty master, lock the slave pty (stable lock order) */ tty_lock_slave(o_tty); /* * Sanity check: if tty->count is going to zero, there shouldn't be * any waiters on tty->read_wait or tty->write_wait. We test the * wait queues and kick everyone out _before_ actually starting to * close. This ensures that we won't block while releasing the tty * structure. * * The test for the o_tty closing is necessary, since the master and * slave sides may close in any order. If the slave side closes out * first, its count will be one, since the master side holds an open. * Thus this test wouldn't be triggered at the time the slave closed, * so we do it now. */ while (1) { do_sleep = 0; if (tty->count <= 1) { if (waitqueue_active(&tty->read_wait)) { wake_up_poll(&tty->read_wait, EPOLLIN); do_sleep++; } if (waitqueue_active(&tty->write_wait)) { wake_up_poll(&tty->write_wait, EPOLLOUT); do_sleep++; } } if (o_tty && o_tty->count <= 1) { if (waitqueue_active(&o_tty->read_wait)) { wake_up_poll(&o_tty->read_wait, EPOLLIN); do_sleep++; } if (waitqueue_active(&o_tty->write_wait)) { wake_up_poll(&o_tty->write_wait, EPOLLOUT); do_sleep++; } } if (!do_sleep) break; if (once) { once = 0; tty_warn(tty, "read/write wait queue active!\n"); } schedule_timeout_killable(timeout); if (timeout < 120 * HZ) timeout = 2 * timeout + 1; else timeout = MAX_SCHEDULE_TIMEOUT; } if (o_tty) { if (--o_tty->count < 0) { tty_warn(tty, "bad slave count (%d)\n", o_tty->count); o_tty->count = 0; } } if (--tty->count < 0) { tty_warn(tty, "bad tty->count (%d)\n", tty->count); tty->count = 0; } /* * We've decremented tty->count, so we need to remove this file * descriptor off the tty->tty_files list; this serves two * purposes: * - check_tty_count sees the correct number of file descriptors * associated with this tty. * - do_tty_hangup no longer sees this file descriptor as * something that needs to be handled for hangups. */ tty_del_file(filp); /* * Perform some housekeeping before deciding whether to return. * * If _either_ side is closing, make sure there aren't any * processes that still think tty or o_tty is their controlling * tty. */ if (!tty->count) { read_lock(&tasklist_lock); session_clear_tty(tty->ctrl.session); if (o_tty) session_clear_tty(o_tty->ctrl.session); read_unlock(&tasklist_lock); } /* check whether both sides are closing ... */ final = !tty->count && !(o_tty && o_tty->count); tty_unlock_slave(o_tty); tty_unlock(tty); /* At this point, the tty->count == 0 should ensure a dead tty * cannot be re-opened by a racing opener. */ if (!final) return 0; tty_debug_hangup(tty, "final close\n"); tty_release_struct(tty, idx); return 0; } /** * tty_open_current_tty - get locked tty of current task * @device: device number * @filp: file pointer to tty * @return: locked tty of the current task iff @device is /dev/tty * * Performs a re-open of the current task's controlling tty. * * We cannot return driver and index like for the other nodes because devpts * will not work then. It expects inodes to be from devpts FS. */ static struct tty_struct *tty_open_current_tty(dev_t device, struct file *filp) { struct tty_struct *tty; int retval; if (device != MKDEV(TTYAUX_MAJOR, 0)) return NULL; tty = get_current_tty(); if (!tty) return ERR_PTR(-ENXIO); filp->f_flags |= O_NONBLOCK; /* Don't let /dev/tty block */ /* noctty = 1; */ tty_lock(tty); tty_kref_put(tty); /* safe to drop the kref now */ retval = tty_reopen(tty); if (retval < 0) { tty_unlock(tty); tty = ERR_PTR(retval); } return tty; } /** * tty_lookup_driver - lookup a tty driver for a given device file * @device: device number * @filp: file pointer to tty * @index: index for the device in the @return driver * * If returned value is not erroneous, the caller is responsible to decrement * the refcount by tty_driver_kref_put(). * * Locking: %tty_mutex protects get_tty_driver() * * Return: driver for this inode (with increased refcount) */ static struct tty_driver *tty_lookup_driver(dev_t device, struct file *filp, int *index) { struct tty_driver *driver = NULL; switch (device) { #ifdef CONFIG_VT case MKDEV(TTY_MAJOR, 0): { extern struct tty_driver *console_driver; driver = tty_driver_kref_get(console_driver); *index = fg_console; break; } #endif case MKDEV(TTYAUX_MAJOR, 1): { struct tty_driver *console_driver = console_device(index); if (console_driver) { driver = tty_driver_kref_get(console_driver); if (driver && filp) { /* Don't let /dev/console block */ filp->f_flags |= O_NONBLOCK; break; } } if (driver) tty_driver_kref_put(driver); return ERR_PTR(-ENODEV); } default: driver = get_tty_driver(device, index); if (!driver) return ERR_PTR(-ENODEV); break; } return driver; } static struct tty_struct *tty_kopen(dev_t device, int shared) { struct tty_struct *tty; struct tty_driver *driver; int index = -1; mutex_lock(&tty_mutex); driver = tty_lookup_driver(device, NULL, &index); if (IS_ERR(driver)) { mutex_unlock(&tty_mutex); return ERR_CAST(driver); } /* check whether we're reopening an existing tty */ tty = tty_driver_lookup_tty(driver, NULL, index); if (IS_ERR(tty) || shared) goto out; if (tty) { /* drop kref from tty_driver_lookup_tty() */ tty_kref_put(tty); tty = ERR_PTR(-EBUSY); } else { /* tty_init_dev returns tty with the tty_lock held */ tty = tty_init_dev(driver, index); if (IS_ERR(tty)) goto out; tty_port_set_kopened(tty->port, 1); } out: mutex_unlock(&tty_mutex); tty_driver_kref_put(driver); return tty; } /** * tty_kopen_exclusive - open a tty device for kernel * @device: dev_t of device to open * * Opens tty exclusively for kernel. Performs the driver lookup, makes sure * it's not already opened and performs the first-time tty initialization. * * Claims the global %tty_mutex to serialize: * * concurrent first-time tty initialization * * concurrent tty driver removal w/ lookup * * concurrent tty removal from driver table * * Return: the locked initialized &tty_struct */ struct tty_struct *tty_kopen_exclusive(dev_t device) { return tty_kopen(device, 0); } EXPORT_SYMBOL_GPL(tty_kopen_exclusive); /** * tty_kopen_shared - open a tty device for shared in-kernel use * @device: dev_t of device to open * * Opens an already existing tty for in-kernel use. Compared to * tty_kopen_exclusive() above it doesn't ensure to be the only user. * * Locking: identical to tty_kopen() above. */ struct tty_struct *tty_kopen_shared(dev_t device) { return tty_kopen(device, 1); } EXPORT_SYMBOL_GPL(tty_kopen_shared); /** * tty_open_by_driver - open a tty device * @device: dev_t of device to open * @filp: file pointer to tty * * Performs the driver lookup, checks for a reopen, or otherwise performs the * first-time tty initialization. * * * Claims the global tty_mutex to serialize: * * concurrent first-time tty initialization * * concurrent tty driver removal w/ lookup * * concurrent tty removal from driver table * * Return: the locked initialized or re-opened &tty_struct */ static struct tty_struct *tty_open_by_driver(dev_t device, struct file *filp) { struct tty_struct *tty; struct tty_driver *driver = NULL; int index = -1; int retval; mutex_lock(&tty_mutex); driver = tty_lookup_driver(device, filp, &index); if (IS_ERR(driver)) { mutex_unlock(&tty_mutex); return ERR_CAST(driver); } /* check whether we're reopening an existing tty */ tty = tty_driver_lookup_tty(driver, filp, index); if (IS_ERR(tty)) { mutex_unlock(&tty_mutex); goto out; } if (tty) { if (tty_port_kopened(tty->port)) { tty_kref_put(tty); mutex_unlock(&tty_mutex); tty = ERR_PTR(-EBUSY); goto out; } mutex_unlock(&tty_mutex); retval = tty_lock_interruptible(tty); tty_kref_put(tty); /* drop kref from tty_driver_lookup_tty() */ if (retval) { if (retval == -EINTR) retval = -ERESTARTSYS; tty = ERR_PTR(retval); goto out; } retval = tty_reopen(tty); if (retval < 0) { tty_unlock(tty); tty = ERR_PTR(retval); } } else { /* Returns with the tty_lock held for now */ tty = tty_init_dev(driver, index); mutex_unlock(&tty_mutex); } out: tty_driver_kref_put(driver); return tty; } /** * tty_open - open a tty device * @inode: inode of device file * @filp: file pointer to tty * * tty_open() and tty_release() keep up the tty count that contains the number * of opens done on a tty. We cannot use the inode-count, as different inodes * might point to the same tty. * * Open-counting is needed for pty masters, as well as for keeping track of * serial lines: DTR is dropped when the last close happens. * (This is not done solely through tty->count, now. - Ted 1/27/92) * * The termios state of a pty is reset on the first open so that settings don't * persist across reuse. * * Locking: * * %tty_mutex protects tty, tty_lookup_driver() and tty_init_dev(). * * @tty->count should protect the rest. * * ->siglock protects ->signal/->sighand * * Note: the tty_unlock/lock cases without a ref are only safe due to %tty_mutex */ static int tty_open(struct inode *inode, struct file *filp) { struct tty_struct *tty; int noctty, retval; dev_t device = inode->i_rdev; unsigned saved_flags = filp->f_flags; nonseekable_open(inode, filp); retry_open: retval = tty_alloc_file(filp); if (retval) return -ENOMEM; tty = tty_open_current_tty(device, filp); if (!tty) tty = tty_open_by_driver(device, filp); if (IS_ERR(tty)) { tty_free_file(filp); retval = PTR_ERR(tty); if (retval != -EAGAIN || signal_pending(current)) return retval; schedule(); goto retry_open; } tty_add_file(tty, filp); check_tty_count(tty, __func__); tty_debug_hangup(tty, "opening (count=%d)\n", tty->count); if (tty->ops->open) retval = tty->ops->open(tty, filp); else retval = -ENODEV; filp->f_flags = saved_flags; if (retval) { tty_debug_hangup(tty, "open error %d, releasing\n", retval); tty_unlock(tty); /* need to call tty_release without BTM */ tty_release(inode, filp); if (retval != -ERESTARTSYS) return retval; if (signal_pending(current)) return retval; schedule(); /* * Need to reset f_op in case a hangup happened. */ if (tty_hung_up_p(filp)) filp->f_op = &tty_fops; goto retry_open; } clear_bit(TTY_HUPPED, &tty->flags); noctty = (filp->f_flags & O_NOCTTY) || (IS_ENABLED(CONFIG_VT) && device == MKDEV(TTY_MAJOR, 0)) || device == MKDEV(TTYAUX_MAJOR, 1) || (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER); if (!noctty) tty_open_proc_set_tty(filp, tty); tty_unlock(tty); return 0; } /** * tty_poll - check tty status * @filp: file being polled * @wait: poll wait structures to update * * Call the line discipline polling method to obtain the poll status of the * device. * * Locking: locks called line discipline but ldisc poll method may be * re-entered freely by other callers. */ static __poll_t tty_poll(struct file *filp, poll_table *wait) { struct tty_struct *tty = file_tty(filp); struct tty_ldisc *ld; __poll_t ret = 0; if (tty_paranoia_check(tty, file_inode(filp), "tty_poll")) return 0; ld = tty_ldisc_ref_wait(tty); if (!ld) return hung_up_tty_poll(filp, wait); if (ld->ops->poll) ret = ld->ops->poll(tty, filp, wait); tty_ldisc_deref(ld); return ret; } static int __tty_fasync(int fd, struct file *filp, int on) { struct tty_struct *tty = file_tty(filp); unsigned long flags; int retval = 0; if (tty_paranoia_check(tty, file_inode(filp), "tty_fasync")) goto out; retval = fasync_helper(fd, filp, on, &tty->fasync); if (retval <= 0) goto out; if (on) { enum pid_type type; struct pid *pid; spin_lock_irqsave(&tty->ctrl.lock, flags); if (tty->ctrl.pgrp) { pid = tty->ctrl.pgrp; type = PIDTYPE_PGID; } else { pid = task_pid(current); type = PIDTYPE_TGID; } get_pid(pid); spin_unlock_irqrestore(&tty->ctrl.lock, flags); __f_setown(filp, pid, type, 0); put_pid(pid); retval = 0; } out: return retval; } static int tty_fasync(int fd, struct file *filp, int on) { struct tty_struct *tty = file_tty(filp); int retval = -ENOTTY; tty_lock(tty); if (!tty_hung_up_p(filp)) retval = __tty_fasync(fd, filp, on); tty_unlock(tty); return retval; } static bool tty_legacy_tiocsti __read_mostly = IS_ENABLED(CONFIG_LEGACY_TIOCSTI); /** * tiocsti - fake input character * @tty: tty to fake input into * @p: pointer to character * * Fake input to a tty device. Does the necessary locking and input management. * * FIXME: does not honour flow control ?? * * Locking: * * Called functions take tty_ldiscs_lock * * current->signal->tty check is safe without locks */ static int tiocsti(struct tty_struct *tty, u8 __user *p) { struct tty_ldisc *ld; u8 ch; if (!tty_legacy_tiocsti && !capable(CAP_SYS_ADMIN)) return -EIO; if ((current->signal->tty != tty) && !capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(ch, p)) return -EFAULT; tty_audit_tiocsti(tty, ch); ld = tty_ldisc_ref_wait(tty); if (!ld) return -EIO; tty_buffer_lock_exclusive(tty->port); if (ld->ops->receive_buf) ld->ops->receive_buf(tty, &ch, NULL, 1); tty_buffer_unlock_exclusive(tty->port); tty_ldisc_deref(ld); return 0; } /** * tiocgwinsz - implement window query ioctl * @tty: tty * @arg: user buffer for result * * Copies the kernel idea of the window size into the user buffer. * * Locking: @tty->winsize_mutex is taken to ensure the winsize data is * consistent. */ static int tiocgwinsz(struct tty_struct *tty, struct winsize __user *arg) { int err; mutex_lock(&tty->winsize_mutex); err = copy_to_user(arg, &tty->winsize, sizeof(*arg)); mutex_unlock(&tty->winsize_mutex); return err ? -EFAULT : 0; } /** * tty_do_resize - resize event * @tty: tty being resized * @ws: new dimensions * * Update the termios variables and send the necessary signals to peform a * terminal resize correctly. */ int tty_do_resize(struct tty_struct *tty, struct winsize *ws) { struct pid *pgrp; /* Lock the tty */ mutex_lock(&tty->winsize_mutex); if (!memcmp(ws, &tty->winsize, sizeof(*ws))) goto done; /* Signal the foreground process group */ pgrp = tty_get_pgrp(tty); if (pgrp) kill_pgrp(pgrp, SIGWINCH, 1); put_pid(pgrp); tty->winsize = *ws; done: mutex_unlock(&tty->winsize_mutex); return 0; } EXPORT_SYMBOL(tty_do_resize); /** * tiocswinsz - implement window size set ioctl * @tty: tty side of tty * @arg: user buffer for result * * Copies the user idea of the window size to the kernel. Traditionally this is * just advisory information but for the Linux console it actually has driver * level meaning and triggers a VC resize. * * Locking: * Driver dependent. The default do_resize method takes the tty termios * mutex and ctrl.lock. The console takes its own lock then calls into the * default method. */ static int tiocswinsz(struct tty_struct *tty, struct winsize __user *arg) { struct winsize tmp_ws; if (copy_from_user(&tmp_ws, arg, sizeof(*arg))) return -EFAULT; if (tty->ops->resize) return tty->ops->resize(tty, &tmp_ws); else return tty_do_resize(tty, &tmp_ws); } /** * tioccons - allow admin to move logical console * @file: the file to become console * * Allow the administrator to move the redirected console device. * * Locking: uses redirect_lock to guard the redirect information */ static int tioccons(struct file *file) { if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (file->f_op->write_iter == redirected_tty_write) { struct file *f; spin_lock(&redirect_lock); f = redirect; redirect = NULL; spin_unlock(&redirect_lock); if (f) fput(f); return 0; } if (file->f_op->write_iter != tty_write) return -ENOTTY; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; spin_lock(&redirect_lock); if (redirect) { spin_unlock(&redirect_lock); return -EBUSY; } redirect = get_file(file); spin_unlock(&redirect_lock); return 0; } /** * tiocsetd - set line discipline * @tty: tty device * @p: pointer to user data * * Set the line discipline according to user request. * * Locking: see tty_set_ldisc(), this function is just a helper */ static int tiocsetd(struct tty_struct *tty, int __user *p) { int disc; int ret; if (get_user(disc, p)) return -EFAULT; ret = tty_set_ldisc(tty, disc); return ret; } /** * tiocgetd - get line discipline * @tty: tty device * @p: pointer to user data * * Retrieves the line discipline id directly from the ldisc. * * Locking: waits for ldisc reference (in case the line discipline is changing * or the @tty is being hungup) */ static int tiocgetd(struct tty_struct *tty, int __user *p) { struct tty_ldisc *ld; int ret; ld = tty_ldisc_ref_wait(tty); if (!ld) return -EIO; ret = put_user(ld->ops->num, p); tty_ldisc_deref(ld); return ret; } /** * send_break - performed time break * @tty: device to break on * @duration: timeout in mS * * Perform a timed break on hardware that lacks its own driver level timed * break functionality. * * Locking: * @tty->atomic_write_lock serializes */ static int send_break(struct tty_struct *tty, unsigned int duration) { int retval; if (tty->ops->break_ctl == NULL) return 0; if (tty->driver->flags & TTY_DRIVER_HARDWARE_BREAK) return tty->ops->break_ctl(tty, duration); /* Do the work ourselves */ if (tty_write_lock(tty, false) < 0) return -EINTR; retval = tty->ops->break_ctl(tty, -1); if (!retval) { msleep_interruptible(duration); retval = tty->ops->break_ctl(tty, 0); } else if (retval == -EOPNOTSUPP) { /* some drivers can tell only dynamically */ retval = 0; } tty_write_unlock(tty); if (signal_pending(current)) retval = -EINTR; return retval; } /** * tty_get_tiocm - get tiocm status register * @tty: tty device * * Obtain the modem status bits from the tty driver if the feature * is supported. */ int tty_get_tiocm(struct tty_struct *tty) { int retval = -ENOTTY; if (tty->ops->tiocmget) retval = tty->ops->tiocmget(tty); return retval; } EXPORT_SYMBOL_GPL(tty_get_tiocm); /** * tty_tiocmget - get modem status * @tty: tty device * @p: pointer to result * * Obtain the modem status bits from the tty driver if the feature is * supported. Return -%ENOTTY if it is not available. * * Locking: none (up to the driver) */ static int tty_tiocmget(struct tty_struct *tty, int __user *p) { int retval; retval = tty_get_tiocm(tty); if (retval >= 0) retval = put_user(retval, p); return retval; } /** * tty_tiocmset - set modem status * @tty: tty device * @cmd: command - clear bits, set bits or set all * @p: pointer to desired bits * * Set the modem status bits from the tty driver if the feature * is supported. Return -%ENOTTY if it is not available. * * Locking: none (up to the driver) */ static int tty_tiocmset(struct tty_struct *tty, unsigned int cmd, unsigned __user *p) { int retval; unsigned int set, clear, val; if (tty->ops->tiocmset == NULL) return -ENOTTY; retval = get_user(val, p); if (retval) return retval; set = clear = 0; switch (cmd) { case TIOCMBIS: set = val; break; case TIOCMBIC: clear = val; break; case TIOCMSET: set = val; clear = ~val; break; } set &= TIOCM_DTR|TIOCM_RTS|TIOCM_OUT1|TIOCM_OUT2|TIOCM_LOOP; clear &= TIOCM_DTR|TIOCM_RTS|TIOCM_OUT1|TIOCM_OUT2|TIOCM_LOOP; return tty->ops->tiocmset(tty, set, clear); } /** * tty_get_icount - get tty statistics * @tty: tty device * @icount: output parameter * * Gets a copy of the @tty's icount statistics. * * Locking: none (up to the driver) */ int tty_get_icount(struct tty_struct *tty, struct serial_icounter_struct *icount) { memset(icount, 0, sizeof(*icount)); if (tty->ops->get_icount) return tty->ops->get_icount(tty, icount); else return -ENOTTY; } EXPORT_SYMBOL_GPL(tty_get_icount); static int tty_tiocgicount(struct tty_struct *tty, void __user *arg) { struct serial_icounter_struct icount; int retval; retval = tty_get_icount(tty, &icount); if (retval != 0) return retval; if (copy_to_user(arg, &icount, sizeof(icount))) return -EFAULT; return 0; } static int tty_set_serial(struct tty_struct *tty, struct serial_struct *ss) { char comm[TASK_COMM_LEN]; int flags; flags = ss->flags & ASYNC_DEPRECATED; if (flags) pr_warn_ratelimited("%s: '%s' is using deprecated serial flags (with no effect): %.8x\n", __func__, get_task_comm(comm, current), flags); if (!tty->ops->set_serial) return -ENOTTY; return tty->ops->set_serial(tty, ss); } static int tty_tiocsserial(struct tty_struct *tty, struct serial_struct __user *ss) { struct serial_struct v; if (copy_from_user(&v, ss, sizeof(*ss))) return -EFAULT; return tty_set_serial(tty, &v); } static int tty_tiocgserial(struct tty_struct *tty, struct serial_struct __user *ss) { struct serial_struct v; int err; memset(&v, 0, sizeof(v)); if (!tty->ops->get_serial) return -ENOTTY; err = tty->ops->get_serial(tty, &v); if (!err && copy_to_user(ss, &v, sizeof(v))) err = -EFAULT; return err; } /* * if pty, return the slave side (real_tty) * otherwise, return self */ static struct tty_struct *tty_pair_get_tty(struct tty_struct *tty) { if (tty->driver->type == TTY_DRIVER_TYPE_PTY && tty->driver->subtype == PTY_TYPE_MASTER) tty = tty->link; return tty; } /* * Split this up, as gcc can choke on it otherwise.. */ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct tty_struct *tty = file_tty(file); struct tty_struct *real_tty; void __user *p = (void __user *)arg; int retval; struct tty_ldisc *ld; if (tty_paranoia_check(tty, file_inode(file), "tty_ioctl")) return -EINVAL; real_tty = tty_pair_get_tty(tty); /* * Factor out some common prep work */ switch (cmd) { case TIOCSETD: case TIOCSBRK: case TIOCCBRK: case TCSBRK: case TCSBRKP: retval = tty_check_change(tty); if (retval) return retval; if (cmd != TIOCCBRK) { tty_wait_until_sent(tty, 0); if (signal_pending(current)) return -EINTR; } break; } /* * Now do the stuff. */ switch (cmd) { case TIOCSTI: return tiocsti(tty, p); case TIOCGWINSZ: return tiocgwinsz(real_tty, p); case TIOCSWINSZ: return tiocswinsz(real_tty, p); case TIOCCONS: return real_tty != tty ? -EINVAL : tioccons(file); case TIOCEXCL: set_bit(TTY_EXCLUSIVE, &tty->flags); return 0; case TIOCNXCL: clear_bit(TTY_EXCLUSIVE, &tty->flags); return 0; case TIOCGEXCL: { int excl = test_bit(TTY_EXCLUSIVE, &tty->flags); return put_user(excl, (int __user *)p); } case TIOCGETD: return tiocgetd(tty, p); case TIOCSETD: return tiocsetd(tty, p); case TIOCVHANGUP: if (!capable(CAP_SYS_ADMIN)) return -EPERM; tty_vhangup(tty); return 0; case TIOCGDEV: { unsigned int ret = new_encode_dev(tty_devnum(real_tty)); return put_user(ret, (unsigned int __user *)p); } /* * Break handling */ case TIOCSBRK: /* Turn break on, unconditionally */ if (tty->ops->break_ctl) return tty->ops->break_ctl(tty, -1); return 0; case TIOCCBRK: /* Turn break off, unconditionally */ if (tty->ops->break_ctl) return tty->ops->break_ctl(tty, 0); return 0; case TCSBRK: /* SVID version: non-zero arg --> no break */ /* non-zero arg means wait for all output data * to be sent (performed above) but don't send break. * This is used by the tcdrain() termios function. */ if (!arg) return send_break(tty, 250); return 0; case TCSBRKP: /* support for POSIX tcsendbreak() */ return send_break(tty, arg ? arg*100 : 250); case TIOCMGET: return tty_tiocmget(tty, p); case TIOCMSET: case TIOCMBIC: case TIOCMBIS: return tty_tiocmset(tty, cmd, p); case TIOCGICOUNT: return tty_tiocgicount(tty, p); case TCFLSH: switch (arg) { case TCIFLUSH: case TCIOFLUSH: /* flush tty buffer and allow ldisc to process ioctl */ tty_buffer_flush(tty, NULL); break; } break; case TIOCSSERIAL: return tty_tiocsserial(tty, p); case TIOCGSERIAL: return tty_tiocgserial(tty, p); case TIOCGPTPEER: /* Special because the struct file is needed */ return ptm_open_peer(file, tty, (int)arg); default: retval = tty_jobctrl_ioctl(tty, real_tty, file, cmd, arg); if (retval != -ENOIOCTLCMD) return retval; } if (tty->ops->ioctl) { retval = tty->ops->ioctl(tty, cmd, arg); if (retval != -ENOIOCTLCMD) return retval; } ld = tty_ldisc_ref_wait(tty); if (!ld) return hung_up_tty_ioctl(file, cmd, arg); retval = -EINVAL; if (ld->ops->ioctl) { retval = ld->ops->ioctl(tty, cmd, arg); if (retval == -ENOIOCTLCMD) retval = -ENOTTY; } tty_ldisc_deref(ld); return retval; } #ifdef CONFIG_COMPAT struct serial_struct32 { compat_int_t type; compat_int_t line; compat_uint_t port; compat_int_t irq; compat_int_t flags; compat_int_t xmit_fifo_size; compat_int_t custom_divisor; compat_int_t baud_base; unsigned short close_delay; char io_type; char reserved_char; compat_int_t hub6; unsigned short closing_wait; /* time to wait before closing */ unsigned short closing_wait2; /* no longer used... */ compat_uint_t iomem_base; unsigned short iomem_reg_shift; unsigned int port_high; /* compat_ulong_t iomap_base FIXME */ compat_int_t reserved; }; static int compat_tty_tiocsserial(struct tty_struct *tty, struct serial_struct32 __user *ss) { struct serial_struct32 v32; struct serial_struct v; if (copy_from_user(&v32, ss, sizeof(*ss))) return -EFAULT; memcpy(&v, &v32, offsetof(struct serial_struct32, iomem_base)); v.iomem_base = compat_ptr(v32.iomem_base); v.iomem_reg_shift = v32.iomem_reg_shift; v.port_high = v32.port_high; v.iomap_base = 0; return tty_set_serial(tty, &v); } static int compat_tty_tiocgserial(struct tty_struct *tty, struct serial_struct32 __user *ss) { struct serial_struct32 v32; struct serial_struct v; int err; memset(&v, 0, sizeof(v)); memset(&v32, 0, sizeof(v32)); if (!tty->ops->get_serial) return -ENOTTY; err = tty->ops->get_serial(tty, &v); if (!err) { memcpy(&v32, &v, offsetof(struct serial_struct32, iomem_base)); v32.iomem_base = (unsigned long)v.iomem_base >> 32 ? 0xfffffff : ptr_to_compat(v.iomem_base); v32.iomem_reg_shift = v.iomem_reg_shift; v32.port_high = v.port_high; if (copy_to_user(ss, &v32, sizeof(v32))) err = -EFAULT; } return err; } static long tty_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct tty_struct *tty = file_tty(file); struct tty_ldisc *ld; int retval = -ENOIOCTLCMD; switch (cmd) { case TIOCOUTQ: case TIOCSTI: case TIOCGWINSZ: case TIOCSWINSZ: case TIOCGEXCL: case TIOCGETD: case TIOCSETD: case TIOCGDEV: case TIOCMGET: case TIOCMSET: case TIOCMBIC: case TIOCMBIS: case TIOCGICOUNT: case TIOCGPGRP: case TIOCSPGRP: case TIOCGSID: case TIOCSERGETLSR: case TIOCGRS485: case TIOCSRS485: #ifdef TIOCGETP case TIOCGETP: case TIOCSETP: case TIOCSETN: #endif #ifdef TIOCGETC case TIOCGETC: case TIOCSETC: #endif #ifdef TIOCGLTC case TIOCGLTC: case TIOCSLTC: #endif case TCSETSF: case TCSETSW: case TCSETS: case TCGETS: #ifdef TCGETS2 case TCGETS2: case TCSETSF2: case TCSETSW2: case TCSETS2: #endif case TCGETA: case TCSETAF: case TCSETAW: case TCSETA: case TIOCGLCKTRMIOS: case TIOCSLCKTRMIOS: #ifdef TCGETX case TCGETX: case TCSETX: case TCSETXW: case TCSETXF: #endif case TIOCGSOFTCAR: case TIOCSSOFTCAR: case PPPIOCGCHAN: case PPPIOCGUNIT: return tty_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); case TIOCCONS: case TIOCEXCL: case TIOCNXCL: case TIOCVHANGUP: case TIOCSBRK: case TIOCCBRK: case TCSBRK: case TCSBRKP: case TCFLSH: case TIOCGPTPEER: case TIOCNOTTY: case TIOCSCTTY: case TCXONC: case TIOCMIWAIT: case TIOCSERCONFIG: return tty_ioctl(file, cmd, arg); } if (tty_paranoia_check(tty, file_inode(file), "tty_ioctl")) return -EINVAL; switch (cmd) { case TIOCSSERIAL: return compat_tty_tiocsserial(tty, compat_ptr(arg)); case TIOCGSERIAL: return compat_tty_tiocgserial(tty, compat_ptr(arg)); } if (tty->ops->compat_ioctl) { retval = tty->ops->compat_ioctl(tty, cmd, arg); if (retval != -ENOIOCTLCMD) return retval; } ld = tty_ldisc_ref_wait(tty); if (!ld) return hung_up_tty_compat_ioctl(file, cmd, arg); if (ld->ops->compat_ioctl) retval = ld->ops->compat_ioctl(tty, cmd, arg); if (retval == -ENOIOCTLCMD && ld->ops->ioctl) retval = ld->ops->ioctl(tty, (unsigned long)compat_ptr(cmd), arg); tty_ldisc_deref(ld); return retval; } #endif static int this_tty(const void *t, struct file *file, unsigned fd) { if (likely(file->f_op->read_iter != tty_read)) return 0; return file_tty(file) != t ? 0 : fd + 1; } /* * This implements the "Secure Attention Key" --- the idea is to * prevent trojan horses by killing all processes associated with this * tty when the user hits the "Secure Attention Key". Required for * super-paranoid applications --- see the Orange Book for more details. * * This code could be nicer; ideally it should send a HUP, wait a few * seconds, then send a INT, and then a KILL signal. But you then * have to coordinate with the init process, since all processes associated * with the current tty must be dead before the new getty is allowed * to spawn. * * Now, if it would be correct ;-/ The current code has a nasty hole - * it doesn't catch files in flight. We may send the descriptor to ourselves * via AF_UNIX socket, close it and later fetch from socket. FIXME. * * Nasty bug: do_SAK is being called in interrupt context. This can * deadlock. We punt it up to process context. AKPM - 16Mar2001 */ void __do_SAK(struct tty_struct *tty) { struct task_struct *g, *p; struct pid *session; int i; unsigned long flags; spin_lock_irqsave(&tty->ctrl.lock, flags); session = get_pid(tty->ctrl.session); spin_unlock_irqrestore(&tty->ctrl.lock, flags); tty_ldisc_flush(tty); tty_driver_flush_buffer(tty); read_lock(&tasklist_lock); /* Kill the entire session */ do_each_pid_task(session, PIDTYPE_SID, p) { tty_notice(tty, "SAK: killed process %d (%s): by session\n", task_pid_nr(p), p->comm); group_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_SID); } while_each_pid_task(session, PIDTYPE_SID, p); /* Now kill any processes that happen to have the tty open */ for_each_process_thread(g, p) { if (p->signal->tty == tty) { tty_notice(tty, "SAK: killed process %d (%s): by controlling tty\n", task_pid_nr(p), p->comm); group_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_SID); continue; } task_lock(p); i = iterate_fd(p->files, 0, this_tty, tty); if (i != 0) { tty_notice(tty, "SAK: killed process %d (%s): by fd#%d\n", task_pid_nr(p), p->comm, i - 1); group_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_SID); } task_unlock(p); } read_unlock(&tasklist_lock); put_pid(session); } static void do_SAK_work(struct work_struct *work) { struct tty_struct *tty = container_of(work, struct tty_struct, SAK_work); __do_SAK(tty); } /* * The tq handling here is a little racy - tty->SAK_work may already be queued. * Fortunately we don't need to worry, because if ->SAK_work is already queued, * the values which we write to it will be identical to the values which it * already has. --akpm */ void do_SAK(struct tty_struct *tty) { if (!tty) return; schedule_work(&tty->SAK_work); } EXPORT_SYMBOL(do_SAK); /* Must put_device() after it's unused! */ static struct device *tty_get_device(struct tty_struct *tty) { dev_t devt = tty_devnum(tty); return class_find_device_by_devt(&tty_class, devt); } /** * alloc_tty_struct - allocate a new tty * @driver: driver which will handle the returned tty * @idx: minor of the tty * * This subroutine allocates and initializes a tty structure. * * Locking: none - @tty in question is not exposed at this point */ struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx) { struct tty_struct *tty; tty = kzalloc(sizeof(*tty), GFP_KERNEL_ACCOUNT); if (!tty) return NULL; kref_init(&tty->kref); if (tty_ldisc_init(tty)) { kfree(tty); return NULL; } tty->ctrl.session = NULL; tty->ctrl.pgrp = NULL; mutex_init(&tty->legacy_mutex); mutex_init(&tty->throttle_mutex); init_rwsem(&tty->termios_rwsem); mutex_init(&tty->winsize_mutex); init_ldsem(&tty->ldisc_sem); init_waitqueue_head(&tty->write_wait); init_waitqueue_head(&tty->read_wait); INIT_WORK(&tty->hangup_work, do_tty_hangup); mutex_init(&tty->atomic_write_lock); spin_lock_init(&tty->ctrl.lock); spin_lock_init(&tty->flow.lock); spin_lock_init(&tty->files_lock); INIT_LIST_HEAD(&tty->tty_files); INIT_WORK(&tty->SAK_work, do_SAK_work); tty->driver = driver; tty->ops = driver->ops; tty->index = idx; tty_line_name(driver, idx, tty->name); tty->dev = tty_get_device(tty); return tty; } /** * tty_put_char - write one character to a tty * @tty: tty * @ch: character to write * * Write one byte to the @tty using the provided @tty->ops->put_char() method * if present. * * Note: the specific put_char operation in the driver layer may go * away soon. Don't call it directly, use this method * * Return: the number of characters successfully output. */ int tty_put_char(struct tty_struct *tty, u8 ch) { if (tty->ops->put_char) return tty->ops->put_char(tty, ch); return tty->ops->write(tty, &ch, 1); } EXPORT_SYMBOL_GPL(tty_put_char); static int tty_cdev_add(struct tty_driver *driver, dev_t dev, unsigned int index, unsigned int count) { int err; /* init here, since reused cdevs cause crashes */ driver->cdevs[index] = cdev_alloc(); if (!driver->cdevs[index]) return -ENOMEM; driver->cdevs[index]->ops = &tty_fops; driver->cdevs[index]->owner = driver->owner; err = cdev_add(driver->cdevs[index], dev, count); if (err) kobject_put(&driver->cdevs[index]->kobj); return err; } /** * tty_register_device - register a tty device * @driver: the tty driver that describes the tty device * @index: the index in the tty driver for this tty device * @device: a struct device that is associated with this tty device. * This field is optional, if there is no known struct device * for this tty device it can be set to NULL safely. * * This call is required to be made to register an individual tty device * if the tty driver's flags have the %TTY_DRIVER_DYNAMIC_DEV bit set. If * that bit is not set, this function should not be called by a tty * driver. * * Locking: ?? * * Return: A pointer to the struct device for this tty device (or * ERR_PTR(-EFOO) on error). */ struct device *tty_register_device(struct tty_driver *driver, unsigned index, struct device *device) { return tty_register_device_attr(driver, index, device, NULL, NULL); } EXPORT_SYMBOL(tty_register_device); static void tty_device_create_release(struct device *dev) { dev_dbg(dev, "releasing...\n"); kfree(dev); } /** * tty_register_device_attr - register a tty device * @driver: the tty driver that describes the tty device * @index: the index in the tty driver for this tty device * @device: a struct device that is associated with this tty device. * This field is optional, if there is no known struct device * for this tty device it can be set to %NULL safely. * @drvdata: Driver data to be set to device. * @attr_grp: Attribute group to be set on device. * * This call is required to be made to register an individual tty device if the * tty driver's flags have the %TTY_DRIVER_DYNAMIC_DEV bit set. If that bit is * not set, this function should not be called by a tty driver. * * Locking: ?? * * Return: A pointer to the struct device for this tty device (or * ERR_PTR(-EFOO) on error). */ struct device *tty_register_device_attr(struct tty_driver *driver, unsigned index, struct device *device, void *drvdata, const struct attribute_group **attr_grp) { char name[64]; dev_t devt = MKDEV(driver->major, driver->minor_start) + index; struct ktermios *tp; struct device *dev; int retval; if (index >= driver->num) { pr_err("%s: Attempt to register invalid tty line number (%d)\n", driver->name, index); return ERR_PTR(-EINVAL); } if (driver->type == TTY_DRIVER_TYPE_PTY) pty_line_name(driver, index, name); else tty_line_name(driver, index, name); dev = kzalloc(sizeof(*dev), GFP_KERNEL); if (!dev) return ERR_PTR(-ENOMEM); dev->devt = devt; dev->class = &tty_class; dev->parent = device; dev->release = tty_device_create_release; dev_set_name(dev, "%s", name); dev->groups = attr_grp; dev_set_drvdata(dev, drvdata); dev_set_uevent_suppress(dev, 1); retval = device_register(dev); if (retval) goto err_put; if (!(driver->flags & TTY_DRIVER_DYNAMIC_ALLOC)) { /* * Free any saved termios data so that the termios state is * reset when reusing a minor number. */ tp = driver->termios[index]; if (tp) { driver->termios[index] = NULL; kfree(tp); } retval = tty_cdev_add(driver, devt, index, 1); if (retval) goto err_del; } dev_set_uevent_suppress(dev, 0); kobject_uevent(&dev->kobj, KOBJ_ADD); return dev; err_del: device_del(dev); err_put: put_device(dev); return ERR_PTR(retval); } EXPORT_SYMBOL_GPL(tty_register_device_attr); /** * tty_unregister_device - unregister a tty device * @driver: the tty driver that describes the tty device * @index: the index in the tty driver for this tty device * * If a tty device is registered with a call to tty_register_device() then * this function must be called when the tty device is gone. * * Locking: ?? */ void tty_unregister_device(struct tty_driver *driver, unsigned index) { device_destroy(&tty_class, MKDEV(driver->major, driver->minor_start) + index); if (!(driver->flags & TTY_DRIVER_DYNAMIC_ALLOC)) { cdev_del(driver->cdevs[index]); driver->cdevs[index] = NULL; } } EXPORT_SYMBOL(tty_unregister_device); /** * __tty_alloc_driver - allocate tty driver * @lines: count of lines this driver can handle at most * @owner: module which is responsible for this driver * @flags: some of %TTY_DRIVER_ flags, will be set in driver->flags * * This should not be called directly, some of the provided macros should be * used instead. Use IS_ERR() and friends on @retval. */ struct tty_driver *__tty_alloc_driver(unsigned int lines, struct module *owner, unsigned long flags) { struct tty_driver *driver; unsigned int cdevs = 1; int err; if (!lines || (flags & TTY_DRIVER_UNNUMBERED_NODE && lines > 1)) return ERR_PTR(-EINVAL); driver = kzalloc(sizeof(*driver), GFP_KERNEL); if (!driver) return ERR_PTR(-ENOMEM); kref_init(&driver->kref); driver->num = lines; driver->owner = owner; driver->flags = flags; if (!(flags & TTY_DRIVER_DEVPTS_MEM)) { driver->ttys = kcalloc(lines, sizeof(*driver->ttys), GFP_KERNEL); driver->termios = kcalloc(lines, sizeof(*driver->termios), GFP_KERNEL); if (!driver->ttys || !driver->termios) { err = -ENOMEM; goto err_free_all; } } if (!(flags & TTY_DRIVER_DYNAMIC_ALLOC)) { driver->ports = kcalloc(lines, sizeof(*driver->ports), GFP_KERNEL); if (!driver->ports) { err = -ENOMEM; goto err_free_all; } cdevs = lines; } driver->cdevs = kcalloc(cdevs, sizeof(*driver->cdevs), GFP_KERNEL); if (!driver->cdevs) { err = -ENOMEM; goto err_free_all; } return driver; err_free_all: kfree(driver->ports); kfree(driver->ttys); kfree(driver->termios); kfree(driver->cdevs); kfree(driver); return ERR_PTR(err); } EXPORT_SYMBOL(__tty_alloc_driver); static void destruct_tty_driver(struct kref *kref) { struct tty_driver *driver = container_of(kref, struct tty_driver, kref); int i; struct ktermios *tp; if (driver->flags & TTY_DRIVER_INSTALLED) { for (i = 0; i < driver->num; i++) { tp = driver->termios[i]; if (tp) { driver->termios[i] = NULL; kfree(tp); } if (!(driver->flags & TTY_DRIVER_DYNAMIC_DEV)) tty_unregister_device(driver, i); } proc_tty_unregister_driver(driver); if (driver->flags & TTY_DRIVER_DYNAMIC_ALLOC) cdev_del(driver->cdevs[0]); } kfree(driver->cdevs); kfree(driver->ports); kfree(driver->termios); kfree(driver->ttys); kfree(driver); } /** * tty_driver_kref_put - drop a reference to a tty driver * @driver: driver of which to drop the reference * * The final put will destroy and free up the driver. */ void tty_driver_kref_put(struct tty_driver *driver) { kref_put(&driver->kref, destruct_tty_driver); } EXPORT_SYMBOL(tty_driver_kref_put); /** * tty_register_driver - register a tty driver * @driver: driver to register * * Called by a tty driver to register itself. */ int tty_register_driver(struct tty_driver *driver) { int error; int i; dev_t dev; struct device *d; if (!driver->major) { error = alloc_chrdev_region(&dev, driver->minor_start, driver->num, driver->name); if (!error) { driver->major = MAJOR(dev); driver->minor_start = MINOR(dev); } } else { dev = MKDEV(driver->major, driver->minor_start); error = register_chrdev_region(dev, driver->num, driver->name); } if (error < 0) goto err; if (driver->flags & TTY_DRIVER_DYNAMIC_ALLOC) { error = tty_cdev_add(driver, dev, 0, driver->num); if (error) goto err_unreg_char; } mutex_lock(&tty_mutex); list_add(&driver->tty_drivers, &tty_drivers); mutex_unlock(&tty_mutex); if (!(driver->flags & TTY_DRIVER_DYNAMIC_DEV)) { for (i = 0; i < driver->num; i++) { d = tty_register_device(driver, i, NULL); if (IS_ERR(d)) { error = PTR_ERR(d); goto err_unreg_devs; } } } proc_tty_register_driver(driver); driver->flags |= TTY_DRIVER_INSTALLED; return 0; err_unreg_devs: for (i--; i >= 0; i--) tty_unregister_device(driver, i); mutex_lock(&tty_mutex); list_del(&driver->tty_drivers); mutex_unlock(&tty_mutex); err_unreg_char: unregister_chrdev_region(dev, driver->num); err: return error; } EXPORT_SYMBOL(tty_register_driver); /** * tty_unregister_driver - unregister a tty driver * @driver: driver to unregister * * Called by a tty driver to unregister itself. */ void tty_unregister_driver(struct tty_driver *driver) { unregister_chrdev_region(MKDEV(driver->major, driver->minor_start), driver->num); mutex_lock(&tty_mutex); list_del(&driver->tty_drivers); mutex_unlock(&tty_mutex); } EXPORT_SYMBOL(tty_unregister_driver); dev_t tty_devnum(struct tty_struct *tty) { return MKDEV(tty->driver->major, tty->driver->minor_start) + tty->index; } EXPORT_SYMBOL(tty_devnum); void tty_default_fops(struct file_operations *fops) { *fops = tty_fops; } static char *tty_devnode(const struct device *dev, umode_t *mode) { if (!mode) return NULL; if (dev->devt == MKDEV(TTYAUX_MAJOR, 0) || dev->devt == MKDEV(TTYAUX_MAJOR, 2)) *mode = 0666; return NULL; } const struct class tty_class = { .name = "tty", .devnode = tty_devnode, }; static int __init tty_class_init(void) { return class_register(&tty_class); } postcore_initcall(tty_class_init); /* 3/2004 jmc: why do these devices exist? */ static struct cdev tty_cdev, console_cdev; static ssize_t show_cons_active(struct device *dev, struct device_attribute *attr, char *buf) { struct console *cs[16]; int i = 0; struct console *c; ssize_t count = 0; /* * Hold the console_list_lock to guarantee that no consoles are * unregistered until all console processing is complete. * This also allows safe traversal of the console list and * race-free reading of @flags. */ console_list_lock(); for_each_console(c) { if (!c->device) continue; if (!c->write) continue; if ((c->flags & CON_ENABLED) == 0) continue; cs[i++] = c; if (i >= ARRAY_SIZE(cs)) break; } /* * Take console_lock to serialize device() callback with * other console operations. For example, fg_console is * modified under console_lock when switching vt. */ console_lock(); while (i--) { int index = cs[i]->index; struct tty_driver *drv = cs[i]->device(cs[i], &index); /* don't resolve tty0 as some programs depend on it */ if (drv && (cs[i]->index > 0 || drv->major != TTY_MAJOR)) count += tty_line_name(drv, index, buf + count); else count += sprintf(buf + count, "%s%d", cs[i]->name, cs[i]->index); count += sprintf(buf + count, "%c", i ? ' ':'\n'); } console_unlock(); console_list_unlock(); return count; } static DEVICE_ATTR(active, S_IRUGO, show_cons_active, NULL); static struct attribute *cons_dev_attrs[] = { &dev_attr_active.attr, NULL }; ATTRIBUTE_GROUPS(cons_dev); static struct device *consdev; void console_sysfs_notify(void) { if (consdev) sysfs_notify(&consdev->kobj, NULL, "active"); } static struct ctl_table tty_table[] = { { .procname = "legacy_tiocsti", .data = &tty_legacy_tiocsti, .maxlen = sizeof(tty_legacy_tiocsti), .mode = 0644, .proc_handler = proc_dobool, }, { .procname = "ldisc_autoload", .data = &tty_ldisc_autoload, .maxlen = sizeof(tty_ldisc_autoload), .mode = 0644, .proc_handler = proc_dointvec, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; /* * Ok, now we can initialize the rest of the tty devices and can count * on memory allocations, interrupts etc.. */ int __init tty_init(void) { register_sysctl_init("dev/tty", tty_table); cdev_init(&tty_cdev, &tty_fops); if (cdev_add(&tty_cdev, MKDEV(TTYAUX_MAJOR, 0), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 0), 1, "/dev/tty") < 0) panic("Couldn't register /dev/tty driver\n"); device_create(&tty_class, NULL, MKDEV(TTYAUX_MAJOR, 0), NULL, "tty"); cdev_init(&console_cdev, &console_fops); if (cdev_add(&console_cdev, MKDEV(TTYAUX_MAJOR, 1), 1) || register_chrdev_region(MKDEV(TTYAUX_MAJOR, 1), 1, "/dev/console") < 0) panic("Couldn't register /dev/console driver\n"); consdev = device_create_with_groups(&tty_class, NULL, MKDEV(TTYAUX_MAJOR, 1), NULL, cons_dev_groups, "console"); if (IS_ERR(consdev)) consdev = NULL; #ifdef CONFIG_VT vty_init(&console_fops); #endif return 0; } |
| 8 8 8 8 8 8 8 7 8 8 8 3 3 674 672 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/percpu-vm.c - vmalloc area based chunk allocation * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * Chunks are mapped into vmalloc areas and populated page by page. * This is the default chunk allocator. */ #include "internal.h" static struct page *pcpu_chunk_page(struct pcpu_chunk *chunk, unsigned int cpu, int page_idx) { /* must not be used on pre-mapped chunk */ WARN_ON(chunk->immutable); return vmalloc_to_page((void *)pcpu_chunk_addr(chunk, cpu, page_idx)); } /** * pcpu_get_pages - get temp pages array * * Returns pointer to array of pointers to struct page which can be indexed * with pcpu_page_idx(). Note that there is only one array and accesses * should be serialized by pcpu_alloc_mutex. * * RETURNS: * Pointer to temp pages array on success. */ static struct page **pcpu_get_pages(void) { static struct page **pages; size_t pages_size = pcpu_nr_units * pcpu_unit_pages * sizeof(pages[0]); lockdep_assert_held(&pcpu_alloc_mutex); if (!pages) pages = pcpu_mem_zalloc(pages_size, GFP_KERNEL); return pages; } /** * pcpu_free_pages - free pages which were allocated for @chunk * @chunk: chunk pages were allocated for * @pages: array of pages to be freed, indexed by pcpu_page_idx() * @page_start: page index of the first page to be freed * @page_end: page index of the last page to be freed + 1 * * Free pages [@page_start and @page_end) in @pages for all units. * The pages were allocated for @chunk. */ static void pcpu_free_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page = pages[pcpu_page_idx(cpu, i)]; if (page) __free_page(page); } } } /** * pcpu_alloc_pages - allocates pages for @chunk * @chunk: target chunk * @pages: array to put the allocated pages into, indexed by pcpu_page_idx() * @page_start: page index of the first page to be allocated * @page_end: page index of the last page to be allocated + 1 * @gfp: allocation flags passed to the underlying allocator * * Allocate pages [@page_start,@page_end) into @pages for all units. * The allocation is for @chunk. Percpu core doesn't care about the * content of @pages and will pass it verbatim to pcpu_map_pages(). */ static int pcpu_alloc_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end, gfp_t gfp) { unsigned int cpu, tcpu; int i; gfp |= __GFP_HIGHMEM; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page **pagep = &pages[pcpu_page_idx(cpu, i)]; *pagep = alloc_pages_node(cpu_to_node(cpu), gfp, 0); if (!*pagep) goto err; } } return 0; err: while (--i >= page_start) __free_page(pages[pcpu_page_idx(cpu, i)]); for_each_possible_cpu(tcpu) { if (tcpu == cpu) break; for (i = page_start; i < page_end; i++) __free_page(pages[pcpu_page_idx(tcpu, i)]); } return -ENOMEM; } /** * pcpu_pre_unmap_flush - flush cache prior to unmapping * @chunk: chunk the regions to be flushed belongs to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages in [@page_start,@page_end) of @chunk are about to be * unmapped. Flush cache. As each flushing trial can be very * expensive, issue flush on the whole region at once rather than * doing it for each cpu. This could be an overkill but is more * scalable. */ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vunmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static void __pcpu_unmap_pages(unsigned long addr, int nr_pages) { vunmap_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT)); } /** * pcpu_unmap_pages - unmap pages out of a pcpu_chunk * @chunk: chunk of interest * @pages: pages array which can be used to pass information to free * @page_start: page index of the first page to unmap * @page_end: page index of the last page to unmap + 1 * * For each cpu, unmap pages [@page_start,@page_end) out of @chunk. * Corresponding elements in @pages were cleared by the caller and can * be used to carry information to pcpu_free_pages() which will be * called after all unmaps are finished. The caller should call * proper pre/post flush functions. */ static void pcpu_unmap_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu; int i; for_each_possible_cpu(cpu) { for (i = page_start; i < page_end; i++) { struct page *page; page = pcpu_chunk_page(chunk, cpu, i); WARN_ON(!page); pages[pcpu_page_idx(cpu, i)] = page; } __pcpu_unmap_pages(pcpu_chunk_addr(chunk, cpu, page_start), page_end - page_start); } } /** * pcpu_post_unmap_tlb_flush - flush TLB after unmapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been unmapped. Flush * TLB for the regions. This can be skipped if the area is to be * returned to vmalloc as vmalloc will handle TLB flushing lazily. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_tlb_kernel_range( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } static int __pcpu_map_pages(unsigned long addr, struct page **pages, int nr_pages) { return vmap_pages_range_noflush(addr, addr + (nr_pages << PAGE_SHIFT), PAGE_KERNEL, pages, PAGE_SHIFT); } /** * pcpu_map_pages - map pages into a pcpu_chunk * @chunk: chunk of interest * @pages: pages array containing pages to be mapped * @page_start: page index of the first page to map * @page_end: page index of the last page to map + 1 * * For each cpu, map pages [@page_start,@page_end) into @chunk. The * caller is responsible for calling pcpu_post_map_flush() after all * mappings are complete. * * This function is responsible for setting up whatever is necessary for * reverse lookup (addr -> chunk). */ static int pcpu_map_pages(struct pcpu_chunk *chunk, struct page **pages, int page_start, int page_end) { unsigned int cpu, tcpu; int i, err; for_each_possible_cpu(cpu) { err = __pcpu_map_pages(pcpu_chunk_addr(chunk, cpu, page_start), &pages[pcpu_page_idx(cpu, page_start)], page_end - page_start); if (err < 0) goto err; for (i = page_start; i < page_end; i++) pcpu_set_page_chunk(pages[pcpu_page_idx(cpu, i)], chunk); } return 0; err: for_each_possible_cpu(tcpu) { __pcpu_unmap_pages(pcpu_chunk_addr(chunk, tcpu, page_start), page_end - page_start); if (tcpu == cpu) break; } pcpu_post_unmap_tlb_flush(chunk, page_start, page_end); return err; } /** * pcpu_post_map_flush - flush cache after mapping * @chunk: pcpu_chunk the regions to be flushed belong to * @page_start: page index of the first page to be flushed * @page_end: page index of the last page to be flushed + 1 * * Pages [@page_start,@page_end) of @chunk have been mapped. Flush * cache. * * As with pcpu_pre_unmap_flush(), TLB flushing also is done at once * for the whole region. */ static void pcpu_post_map_flush(struct pcpu_chunk *chunk, int page_start, int page_end) { flush_cache_vmap( pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start), pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end)); } /** * pcpu_populate_chunk - populate and map an area of a pcpu_chunk * @chunk: chunk of interest * @page_start: the start page * @page_end: the end page * @gfp: allocation flags passed to the underlying memory allocator * * For each cpu, populate and map pages [@page_start,@page_end) into * @chunk. * * CONTEXT: * pcpu_alloc_mutex, does GFP_KERNEL allocation. */ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end, gfp_t gfp) { struct page **pages; pages = pcpu_get_pages(); if (!pages) return -ENOMEM; if (pcpu_alloc_pages(chunk, pages, page_start, page_end, gfp)) return -ENOMEM; if (pcpu_map_pages(chunk, pages, page_start, page_end)) { pcpu_free_pages(chunk, pages, page_start, page_end); return -ENOMEM; } pcpu_post_map_flush(chunk, page_start, page_end); return 0; } /** * pcpu_depopulate_chunk - depopulate and unmap an area of a pcpu_chunk * @chunk: chunk to depopulate * @page_start: the start page * @page_end: the end page * * For each cpu, depopulate and unmap pages [@page_start,@page_end) * from @chunk. * * Caller is required to call pcpu_post_unmap_tlb_flush() if not returning the * region back to vmalloc() which will lazily flush the tlb. * * CONTEXT: * pcpu_alloc_mutex. */ static void pcpu_depopulate_chunk(struct pcpu_chunk *chunk, int page_start, int page_end) { struct page **pages; /* * If control reaches here, there must have been at least one * successful population attempt so the temp pages array must * be available now. */ pages = pcpu_get_pages(); BUG_ON(!pages); /* unmap and free */ pcpu_pre_unmap_flush(chunk, page_start, page_end); pcpu_unmap_pages(chunk, pages, page_start, page_end); pcpu_free_pages(chunk, pages, page_start, page_end); } static struct pcpu_chunk *pcpu_create_chunk(gfp_t gfp) { struct pcpu_chunk *chunk; struct vm_struct **vms; chunk = pcpu_alloc_chunk(gfp); if (!chunk) return NULL; vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, pcpu_nr_groups, pcpu_atom_size); if (!vms) { pcpu_free_chunk(chunk); return NULL; } chunk->data = vms; chunk->base_addr = vms[0]->addr - pcpu_group_offsets[0]; pcpu_stats_chunk_alloc(); trace_percpu_create_chunk(chunk->base_addr); return chunk; } static void pcpu_destroy_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; pcpu_stats_chunk_dealloc(); trace_percpu_destroy_chunk(chunk->base_addr); if (chunk->data) pcpu_free_vm_areas(chunk->data, pcpu_nr_groups); pcpu_free_chunk(chunk); } static struct page *pcpu_addr_to_page(void *addr) { return vmalloc_to_page(addr); } static int __init pcpu_verify_alloc_info(const struct pcpu_alloc_info *ai) { /* no extra restriction */ return 0; } /** * pcpu_should_reclaim_chunk - determine if a chunk should go into reclaim * @chunk: chunk of interest * * This is the entry point for percpu reclaim. If a chunk qualifies, it is then * isolated and managed in separate lists at the back of pcpu_slot: sidelined * and to_depopulate respectively. The to_depopulate list holds chunks slated * for depopulation. They no longer contribute to pcpu_nr_empty_pop_pages once * they are on this list. Once depopulated, they are moved onto the sidelined * list which enables them to be pulled back in for allocation if no other chunk * can suffice the allocation. */ static bool pcpu_should_reclaim_chunk(struct pcpu_chunk *chunk) { /* do not reclaim either the first chunk or reserved chunk */ if (chunk == pcpu_first_chunk || chunk == pcpu_reserved_chunk) return false; /* * If it is isolated, it may be on the sidelined list so move it back to * the to_depopulate list. If we hit at least 1/4 pages empty pages AND * there is no system-wide shortage of empty pages aside from this * chunk, move it to the to_depopulate list. */ return ((chunk->isolated && chunk->nr_empty_pop_pages) || (pcpu_nr_empty_pop_pages > (PCPU_EMPTY_POP_PAGES_HIGH + chunk->nr_empty_pop_pages) && chunk->nr_empty_pop_pages >= chunk->nr_pages / 4)); } |
| 3 2 1004 23 24 24 24 24 992 794 794 313 7 21 23 6 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_INETDEVICE_H #define _LINUX_INETDEVICE_H #ifdef __KERNEL__ #include <linux/bitmap.h> #include <linux/if.h> #include <linux/ip.h> #include <linux/netdevice.h> #include <linux/rcupdate.h> #include <linux/timer.h> #include <linux/sysctl.h> #include <linux/rtnetlink.h> #include <linux/refcount.h> struct ipv4_devconf { void *sysctl; int data[IPV4_DEVCONF_MAX]; DECLARE_BITMAP(state, IPV4_DEVCONF_MAX); }; #define MC_HASH_SZ_LOG 9 struct in_device { struct net_device *dev; netdevice_tracker dev_tracker; refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ struct ip_mc_list __rcu *mc_list; /* IP multicast filter chain */ struct ip_mc_list __rcu * __rcu *mc_hash; int mc_count; /* Number of installed mcasts */ spinlock_t mc_tomb_lock; struct ip_mc_list *mc_tomb; unsigned long mr_v1_seen; unsigned long mr_v2_seen; unsigned long mr_maxdelay; unsigned long mr_qi; /* Query Interval */ unsigned long mr_qri; /* Query Response Interval */ unsigned char mr_qrv; /* Query Robustness Variable */ unsigned char mr_gq_running; u32 mr_ifc_count; struct timer_list mr_gq_timer; /* general query timer */ struct timer_list mr_ifc_timer; /* interface change timer */ struct neigh_parms *arp_parms; struct ipv4_devconf cnf; struct rcu_head rcu_head; }; #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1]) #define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr)) #define IPV4_DEVCONF_ALL(net, attr) \ IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr) #define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr)) static inline int ipv4_devconf_get(const struct in_device *in_dev, int index) { index--; return READ_ONCE(in_dev->cnf.data[index]); } static inline void ipv4_devconf_set(struct in_device *in_dev, int index, int val) { index--; set_bit(index, in_dev->cnf.state); WRITE_ONCE(in_dev->cnf.data[index], val); } static inline void ipv4_devconf_setall(struct in_device *in_dev) { bitmap_fill(in_dev->cnf.state, IPV4_DEVCONF_MAX); } #define IN_DEV_CONF_GET(in_dev, attr) \ ipv4_devconf_get((in_dev), IPV4_DEVCONF_ ## attr) #define IN_DEV_CONF_SET(in_dev, attr, val) \ ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val)) #define IN_DEV_ANDCONF(in_dev, attr) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_NET_ORCONF(in_dev, net, attr) \ (IPV4_DEVCONF_ALL_RO(net, attr) || \ IN_DEV_CONF_GET((in_dev), attr)) #define IN_DEV_ORCONF(in_dev, attr) \ IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr) #define IN_DEV_MAXCONF(in_dev, attr) \ (max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \ IN_DEV_CONF_GET((in_dev), attr))) #define IN_DEV_FORWARD(in_dev) IN_DEV_CONF_GET((in_dev), FORWARDING) #define IN_DEV_MFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), MC_FORWARDING) #define IN_DEV_BFORWARD(in_dev) IN_DEV_ANDCONF((in_dev), BC_FORWARDING) #define IN_DEV_RPFILTER(in_dev) IN_DEV_MAXCONF((in_dev), RP_FILTER) #define IN_DEV_SRC_VMARK(in_dev) IN_DEV_ORCONF((in_dev), SRC_VMARK) #define IN_DEV_SOURCE_ROUTE(in_dev) IN_DEV_ANDCONF((in_dev), \ ACCEPT_SOURCE_ROUTE) #define IN_DEV_ACCEPT_LOCAL(in_dev) IN_DEV_ORCONF((in_dev), ACCEPT_LOCAL) #define IN_DEV_BOOTP_RELAY(in_dev) IN_DEV_ANDCONF((in_dev), BOOTP_RELAY) #define IN_DEV_LOG_MARTIANS(in_dev) IN_DEV_ORCONF((in_dev), LOG_MARTIANS) #define IN_DEV_PROXY_ARP(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP) #define IN_DEV_PROXY_ARP_PVLAN(in_dev) IN_DEV_ORCONF((in_dev), PROXY_ARP_PVLAN) #define IN_DEV_SHARED_MEDIA(in_dev) IN_DEV_ORCONF((in_dev), SHARED_MEDIA) #define IN_DEV_TX_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), SEND_REDIRECTS) #define IN_DEV_SEC_REDIRECTS(in_dev) IN_DEV_ORCONF((in_dev), \ SECURE_REDIRECTS) #define IN_DEV_IDTAG(in_dev) IN_DEV_CONF_GET(in_dev, TAG) #define IN_DEV_MEDIUM_ID(in_dev) IN_DEV_CONF_GET(in_dev, MEDIUM_ID) #define IN_DEV_PROMOTE_SECONDARIES(in_dev) \ IN_DEV_ORCONF((in_dev), \ PROMOTE_SECONDARIES) #define IN_DEV_ROUTE_LOCALNET(in_dev) IN_DEV_ORCONF(in_dev, ROUTE_LOCALNET) #define IN_DEV_NET_ROUTE_LOCALNET(in_dev, net) \ IN_DEV_NET_ORCONF(in_dev, net, ROUTE_LOCALNET) #define IN_DEV_RX_REDIRECTS(in_dev) \ ((IN_DEV_FORWARD(in_dev) && \ IN_DEV_ANDCONF((in_dev), ACCEPT_REDIRECTS)) \ || (!IN_DEV_FORWARD(in_dev) && \ IN_DEV_ORCONF((in_dev), ACCEPT_REDIRECTS))) #define IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) \ IN_DEV_ORCONF((in_dev), IGNORE_ROUTES_WITH_LINKDOWN) #define IN_DEV_ARPFILTER(in_dev) IN_DEV_ORCONF((in_dev), ARPFILTER) #define IN_DEV_ARP_ACCEPT(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ACCEPT) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) #define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node hash; struct in_ifaddr __rcu *ifa_next; struct in_device *ifa_dev; struct rcu_head rcu_head; __be32 ifa_local; __be32 ifa_address; __be32 ifa_mask; __u32 ifa_rt_priority; __be32 ifa_broadcast; unsigned char ifa_scope; unsigned char ifa_prefixlen; unsigned char ifa_proto; __u32 ifa_flags; char ifa_label[IFNAMSIZ]; /* In seconds, relative to tstamp. Expiry is at tstamp + HZ * lft. */ __u32 ifa_valid_lft; __u32 ifa_preferred_lft; unsigned long ifa_cstamp; /* created timestamp */ unsigned long ifa_tstamp; /* updated timestamp */ }; struct in_validator_info { __be32 ivi_addr; struct in_device *ivi_dev; struct netlink_ext_ack *extack; }; int register_inetaddr_notifier(struct notifier_block *nb); int unregister_inetaddr_notifier(struct notifier_block *nb); int register_inetaddr_validator_notifier(struct notifier_block *nb); int unregister_inetaddr_validator_notifier(struct notifier_block *nb); void inet_netconf_notify_devconf(struct net *net, int event, int type, int ifindex, struct ipv4_devconf *devconf); struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref); static inline struct net_device *ip_dev_find(struct net *net, __be32 addr) { return __ip_dev_find(net, addr, true); } int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b); int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *); #ifdef CONFIG_INET int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size); #else static inline int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { return 0; } #endif void devinet_init(void); struct in_device *inetdev_by_index(struct net *, int); __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope); __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst, __be32 local, int scope); struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask); struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr); static inline bool inet_ifa_match(__be32 addr, const struct in_ifaddr *ifa) { return !((addr^ifa->ifa_address)&ifa->ifa_mask); } /* * Check if a mask is acceptable. */ static __inline__ bool bad_mask(__be32 mask, __be32 addr) { __u32 hmask; if (addr & (mask = ~mask)) return true; hmask = ntohl(mask); if (hmask & (hmask+1)) return true; return false; } #define in_dev_for_each_ifa_rtnl(ifa, in_dev) \ for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa; \ ifa = rtnl_dereference(ifa->ifa_next)) #define in_dev_for_each_ifa_rcu(ifa, in_dev) \ for (ifa = rcu_dereference((in_dev)->ifa_list); ifa; \ ifa = rcu_dereference(ifa->ifa_next)) static inline struct in_device *__in_dev_get_rcu(const struct net_device *dev) { return rcu_dereference(dev->ip_ptr); } static inline struct in_device *in_dev_get(const struct net_device *dev) { struct in_device *in_dev; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) refcount_inc(&in_dev->refcnt); rcu_read_unlock(); return in_dev; } static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev) { return rtnl_dereference(dev->ip_ptr); } /* called with rcu_read_lock or rtnl held */ static inline bool ip_ignore_linkdown(const struct net_device *dev) { struct in_device *in_dev; bool rc = false; in_dev = rcu_dereference_rtnl(dev->ip_ptr); if (in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rc = true; return rc; } static inline struct neigh_parms *__in_dev_arp_parms_get_rcu(const struct net_device *dev) { struct in_device *in_dev = __in_dev_get_rcu(dev); return in_dev ? in_dev->arp_parms : NULL; } void in_dev_finish_destroy(struct in_device *idev); static inline void in_dev_put(struct in_device *idev) { if (refcount_dec_and_test(&idev->refcnt)) in_dev_finish_destroy(idev); } #define __in_dev_put(idev) refcount_dec(&(idev)->refcnt) #define in_dev_hold(idev) refcount_inc(&(idev)->refcnt) #endif /* __KERNEL__ */ static __inline__ __be32 inet_make_mask(int logmask) { if (logmask) return htonl(~((1U<<(32-logmask))-1)); return 0; } static __inline__ int inet_mask_len(__be32 mask) { __u32 hmask = ntohl(mask); if (!hmask) return 0; return 32 - ffz(~hmask); } #endif /* _LINUX_INETDEVICE_H */ |
| 27 17 14 14 14 14 14 14 14 4 10 10 10 10 14 14 14 14 14 4 14 14 14 14 13 15 15 15 15 14 15 14 14 14 11 4 15 3 3 4 4 4 4 4 1 1 1 2 2 2 3 3 3 3 3 3 3 3 3 3 2 3 3 3 662 665 669 2 1 1 1 1 3 153 153 81 87 150 25 4 3 1 3 25 3 3 3 3 3 3 13 33 20 20 20 20 20 20 20 20 10 10 10 10 10 20 18 10 10 13 13 13 13 4 13 47 48 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 529 463 70 591 586 527 533 528 528 530 6 6 530 27 513 589 588 72 530 528 531 528 531 529 412 529 588 18 18 6 17 17 11 12 17 2 17 17 1 15 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/filemap.c * * Copyright (C) 1994-1999 Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */ #include <linux/export.h> #include <linux/compiler.h> #include <linux/dax.h> #include <linux/fs.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/capability.h> #include <linux/kernel_stat.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/syscalls.h> #include <linux/mman.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/error-injection.h> #include <linux/hash.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/pagevec.h> #include <linux/security.h> #include <linux/cpuset.h> #include <linux/hugetlb.h> #include <linux/memcontrol.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> #include <linux/ramfs.h> #include <linux/page_idle.h> #include <linux/migrate.h> #include <linux/pipe_fs_i.h> #include <linux/splice.h> #include <linux/rcupdate_wait.h> #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include "internal.h" #define CREATE_TRACE_POINTS #include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */ #include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> #include "swap.h" /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995 Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * * ->i_mmap_rwsem (truncate_pagecache) * ->private_lock (__free_pte->block_dirty_folio) * ->swap_lock (exclusive_swap_page, others) * ->i_pages lock * * ->i_rwsem * ->invalidate_lock (acquired by fs in truncate path) * ->i_mmap_rwsem (truncate->unmap_mapping_range) * * ->mmap_lock * ->i_mmap_rwsem * ->page_table_lock or pte_lock (various, mainly in memory.c) * ->i_pages lock (arch-dependent flush_dcache_mmap_lock) * * ->mmap_lock * ->invalidate_lock (filemap_fault) * ->lock_page (filemap_fault, access_process_vm) * * ->i_rwsem (generic_perform_write) * ->mmap_lock (fault_in_readable->do_page_fault) * * bdi->wb.list_lock * sb_lock (fs/fs-writeback.c) * ->i_pages lock (__sync_single_inode) * * ->i_mmap_rwsem * ->anon_vma.lock (vma_merge) * * ->anon_vma.lock * ->page_table_lock or pte_lock (anon_vma_prepare and various) * * ->page_table_lock or pte_lock * ->swap_lock (try_to_unmap_one) * ->private_lock (try_to_unmap_one) * ->i_pages lock (try_to_unmap_one) * ->lruvec->lru_lock (follow_page->mark_page_accessed) * ->lruvec->lru_lock (check_pte_range->isolate_lru_page) * ->private_lock (folio_remove_rmap_pte->set_page_dirty) * ->i_pages lock (folio_remove_rmap_pte->set_page_dirty) * bdi.wb->list_lock (folio_remove_rmap_pte->set_page_dirty) * ->inode->i_lock (folio_remove_rmap_pte->set_page_dirty) * ->memcg->move_lock (folio_remove_rmap_pte->folio_memcg_lock) * bdi.wb->list_lock (zap_pte_range->set_page_dirty) * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->block_dirty_folio) */ static void mapping_set_update(struct xa_state *xas, struct address_space *mapping) { if (dax_mapping(mapping) || shmem_mapping(mapping)) return; xas_set_update(xas, workingset_update_node); xas_set_lru(xas, &shadow_nodes); } static void page_cache_delete(struct address_space *mapping, struct folio *folio, void *shadow) { XA_STATE(xas, &mapping->i_pages, folio->index); long nr = 1; mapping_set_update(&xas, mapping); xas_set_order(&xas, folio->index, folio_order(folio)); nr = folio_nr_pages(folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); xas_store(&xas, shadow); xas_init_marks(&xas); folio->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ mapping->nrpages -= nr; } static void filemap_unaccount_folio(struct address_space *mapping, struct folio *folio) { long nr; VM_BUG_ON_FOLIO(folio_mapped(folio), folio); if (!IS_ENABLED(CONFIG_DEBUG_VM) && unlikely(folio_mapped(folio))) { pr_alert("BUG: Bad page cache in process %s pfn:%05lx\n", current->comm, folio_pfn(folio)); dump_page(&folio->page, "still mapped when deleted"); dump_stack(); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); if (mapping_exiting(mapping) && !folio_test_large(folio)) { int mapcount = folio_mapcount(folio); if (folio_ref_count(folio) >= mapcount + 2) { /* * All vmas have already been torn down, so it's * a good bet that actually the page is unmapped * and we'd rather not leak it: if we're wrong, * another bad page check should catch it later. */ atomic_set(&folio->_mapcount, -1); folio_ref_sub(folio, mapcount); } } } /* hugetlb folios do not participate in page cache accounting. */ if (folio_test_hugetlb(folio)) return; nr = folio_nr_pages(folio); __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr); if (folio_test_swapbacked(folio)) { __lruvec_stat_mod_folio(folio, NR_SHMEM, -nr); if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else if (folio_test_pmd_mappable(folio)) { __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } /* * At this point folio must be either written or cleaned by * truncate. Dirty folio here signals a bug and loss of * unwritten data - on ordinary filesystems. * * But it's harmless on in-memory filesystems like tmpfs; and can * occur when a driver which did get_user_pages() sets page dirty * before putting it, while the inode is being finally evicted. * * Below fixes dirty accounting after removing the folio entirely * but leaves the dirty flag set: it has no effect for truncated * folio and anyway will be cleared before returning folio to * buddy allocator. */ if (WARN_ON_ONCE(folio_test_dirty(folio) && mapping_can_writeback(mapping))) folio_account_cleaned(folio, inode_to_wb(mapping->host)); } /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe. The caller must hold the i_pages lock. */ void __filemap_remove_folio(struct folio *folio, void *shadow) { struct address_space *mapping = folio->mapping; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); page_cache_delete(mapping, folio, shadow); } void filemap_free_folio(struct address_space *mapping, struct folio *folio) { void (*free_folio)(struct folio *); int refs = 1; free_folio = mapping->a_ops->free_folio; if (free_folio) free_folio(folio); if (folio_test_large(folio)) refs = folio_nr_pages(folio); folio_put_refs(folio, refs); } /** * filemap_remove_folio - Remove folio from page cache. * @folio: The folio. * * This must be called only on folios that are locked and have been * verified to be in the page cache. It will never put the folio into * the free list because the caller has a reference on the page. */ void filemap_remove_folio(struct folio *folio) { struct address_space *mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); __filemap_remove_folio(folio, NULL); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); filemap_free_folio(mapping, folio); } /* * page_cache_delete_batch - delete several folios from page cache * @mapping: the mapping to which folios belong * @fbatch: batch of folios to delete * * The function walks over mapping->i_pages and removes folios passed in * @fbatch from the mapping. The function expects @fbatch to be sorted * by page index and is optimised for it to be dense. * It tolerates holes in @fbatch (mapping entries at those indices are not * modified). * * The function expects the i_pages lock to be held. */ static void page_cache_delete_batch(struct address_space *mapping, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, fbatch->folios[0]->index); long total_pages = 0; int i = 0; struct folio *folio; mapping_set_update(&xas, mapping); xas_for_each(&xas, folio, ULONG_MAX) { if (i >= folio_batch_count(fbatch)) break; /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(folio)) continue; /* * A page got inserted in our range? Skip it. We have our * pages locked so they are protected from being removed. * If we see a page whose index is higher than ours, it * means our page has been removed, which shouldn't be * possible because we're holding the PageLock. */ if (folio != fbatch->folios[i]) { VM_BUG_ON_FOLIO(folio->index > fbatch->folios[i]->index, folio); continue; } WARN_ON_ONCE(!folio_test_locked(folio)); folio->mapping = NULL; /* Leave folio->index set: truncation lookup relies on it */ i++; xas_store(&xas, NULL); total_pages += folio_nr_pages(folio); } mapping->nrpages -= total_pages; } void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch) { int i; if (!folio_batch_count(fbatch)) return; spin_lock(&mapping->host->i_lock); xa_lock_irq(&mapping->i_pages); for (i = 0; i < folio_batch_count(fbatch); i++) { struct folio *folio = fbatch->folios[i]; trace_mm_filemap_delete_from_page_cache(folio); filemap_unaccount_folio(mapping, folio); } page_cache_delete_batch(mapping, fbatch); xa_unlock_irq(&mapping->i_pages); if (mapping_shrinkable(mapping)) inode_add_lru(mapping->host); spin_unlock(&mapping->host->i_lock); for (i = 0; i < folio_batch_count(fbatch); i++) filemap_free_folio(mapping, fbatch->folios[i]); } int filemap_check_errors(struct address_space *mapping) { int ret = 0; /* Check for outstanding write errors */ if (test_bit(AS_ENOSPC, &mapping->flags) && test_and_clear_bit(AS_ENOSPC, &mapping->flags)) ret = -ENOSPC; if (test_bit(AS_EIO, &mapping->flags) && test_and_clear_bit(AS_EIO, &mapping->flags)) ret = -EIO; return ret; } EXPORT_SYMBOL(filemap_check_errors); static int filemap_check_and_keep_errors(struct address_space *mapping) { /* Check for outstanding write errors */ if (test_bit(AS_EIO, &mapping->flags)) return -EIO; if (test_bit(AS_ENOSPC, &mapping->flags)) return -ENOSPC; return 0; } /** * filemap_fdatawrite_wbc - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @wbc: the writeback_control controlling the writeout * * Call writepages on the mapping using the provided wbc to control the * writeout. * * Return: %0 on success, negative error code otherwise. */ int filemap_fdatawrite_wbc(struct address_space *mapping, struct writeback_control *wbc) { int ret; if (!mapping_can_writeback(mapping) || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) return 0; wbc_attach_fdatawrite_inode(wbc, mapping->host); ret = do_writepages(mapping, wbc); wbc_detach_inode(wbc); return ret; } EXPORT_SYMBOL(filemap_fdatawrite_wbc); /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as * opposed to a regular memory cleansing writeback. The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. * * Return: %0 on success, negative error code otherwise. */ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end, int sync_mode) { struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; return filemap_fdatawrite_wbc(mapping, &wbc); } static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end) { return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } EXPORT_SYMBOL(filemap_fdatawrite_range); /** * filemap_flush - mostly a non-blocking flush * @mapping: target address_space * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. * * Return: %0 on success, negative error code otherwise. */ int filemap_flush(struct address_space *mapping) { return __filemap_fdatawrite(mapping, WB_SYNC_NONE); } EXPORT_SYMBOL(filemap_flush); /** * filemap_range_has_page - check if a page exists in range. * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. * * Return: %true if at least one page exists in the specified range, * %false otherwise. */ bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { struct folio *folio; XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; rcu_read_lock(); for (;;) { folio = xas_find(&xas, max); if (xas_retry(&xas, folio)) continue; /* Shadow entries don't count */ if (xa_is_value(folio)) continue; /* * We don't need to try to pin this page; we're about to * release the RCU lock anyway. It is enough to know that * there was a page here recently. */ break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL(filemap_range_has_page); static void __filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { pgoff_t index = start_byte >> PAGE_SHIFT; pgoff_t end = end_byte >> PAGE_SHIFT; struct folio_batch fbatch; unsigned nr_folios; folio_batch_init(&fbatch); while (index <= end) { unsigned i; nr_folios = filemap_get_folios_tag(mapping, &index, end, PAGECACHE_TAG_WRITEBACK, &fbatch); if (!nr_folios) break; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; folio_wait_writeback(folio); folio_clear_error(folio); } folio_batch_release(&fbatch); cond_resched(); } } /** * filemap_fdatawait_range - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. Check error status of * the address space and return it. * * Since the error status of the address space is cleared by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space. */ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait_range_keep_errors - wait for writeback to complete * @mapping: address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space in the * given range and wait for all of them. Unlike filemap_fdatawait_range(), * this function does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) */ int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { __filemap_fdatawait_range(mapping, start_byte, end_byte); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_range_keep_errors); /** * file_fdatawait_range - wait for writeback to complete * @file: file pointing to address space structure to wait for * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the address space that file * refers to, in the given range and wait for all of them. Check error * status of the address space vs. the file->f_wb_err cursor and return it. * * Since the error status of the file is advanced by this function, * callers are responsible for checking the return value and handling and/or * reporting the error. * * Return: error status of the address space vs. the file->f_wb_err cursor. */ int file_fdatawait_range(struct file *file, loff_t start_byte, loff_t end_byte) { struct address_space *mapping = file->f_mapping; __filemap_fdatawait_range(mapping, start_byte, end_byte); return file_check_and_advance_wb_err(file); } EXPORT_SYMBOL(file_fdatawait_range); /** * filemap_fdatawait_keep_errors - wait for writeback without clearing errors * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. Unlike filemap_fdatawait(), this function * does not clear error status of the address space. * * Use this function if callers don't handle errors themselves. Expected * call sites are system-wide / filesystem-wide data flushers: e.g. sync(2), * fsfreeze(8) * * Return: error status of the address space. */ int filemap_fdatawait_keep_errors(struct address_space *mapping) { __filemap_fdatawait_range(mapping, 0, LLONG_MAX); return filemap_check_and_keep_errors(mapping); } EXPORT_SYMBOL(filemap_fdatawait_keep_errors); /* Returns true if writeback might be needed or already in progress. */ static bool mapping_needs_writeback(struct address_space *mapping) { return mapping->nrpages; } bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); pgoff_t max = end_byte >> PAGE_SHIFT; struct folio *folio; if (end_byte < start_byte) return false; rcu_read_lock(); xas_for_each(&xas, folio, max) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) continue; if (folio_test_dirty(folio) || folio_test_locked(folio) || folio_test_writeback(folio)) break; } rcu_read_unlock(); return folio != NULL; } EXPORT_SYMBOL_GPL(filemap_range_has_writeback); /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping: the address_space for the pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * Return: error status of the address space. */ int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend) { int err = 0, err2; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* * Even if the above returned error, the pages may be * written partially (e.g. -ENOSPC), so we wait for it. * But the -EIO is special case, it may indicate the worst * thing (e.g. bug) happened, so we avoid waiting for it. */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = filemap_check_errors(mapping); if (!err) err = err2; return err; } EXPORT_SYMBOL(filemap_write_and_wait_range); void __filemap_set_wb_err(struct address_space *mapping, int err) { errseq_t eseq = errseq_set(&mapping->wb_err, err); trace_filemap_set_wb_err(mapping, eseq); } EXPORT_SYMBOL(__filemap_set_wb_err); /** * file_check_and_advance_wb_err - report wb error (if any) that was previously * and advance wb_err to current one * @file: struct file on which the error is being reported * * When userland calls fsync (or something like nfsd does the equivalent), we * want to report any writeback errors that occurred since the last fsync (or * since the file was opened if there haven't been any). * * Grab the wb_err from the mapping. If it matches what we have in the file, * then just quickly return 0. The file is all caught up. * * If it doesn't match, then take the mapping value, set the "seen" flag in * it and try to swap it into place. If it works, or another task beat us * to it with the new value, then update the f_wb_err and return the error * portion. The error at this point must be reported via proper channels * (a'la fsync, or NFS COMMIT operation, etc.). * * While we handle mapping->wb_err with atomic operations, the f_wb_err * value is protected by the f_lock since we must ensure that it reflects * the latest value swapped in for this file descriptor. * * Return: %0 on success, negative error code otherwise. */ int file_check_and_advance_wb_err(struct file *file) { int err = 0; errseq_t old = READ_ONCE(file->f_wb_err); struct address_space *mapping = file->f_mapping; /* Locklessly handle the common case where nothing has changed */ if (errseq_check(&mapping->wb_err, old)) { /* Something changed, must use slow path */ spin_lock(&file->f_lock); old = file->f_wb_err; err = errseq_check_and_advance(&mapping->wb_err, &file->f_wb_err); trace_file_check_and_advance_wb_err(file, old); spin_unlock(&file->f_lock); } /* * We're mostly using this function as a drop in replacement for * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect * that the legacy code would have had on these flags. */ clear_bit(AS_EIO, &mapping->flags); clear_bit(AS_ENOSPC, &mapping->flags); return err; } EXPORT_SYMBOL(file_check_and_advance_wb_err); /** * file_write_and_wait_range - write out & wait on a file range * @file: file pointing to address_space with pages * @lstart: offset in bytes where the range starts * @lend: offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that @lend is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). * * After writing out and waiting on the data, we check and advance the * f_wb_err cursor to the latest value, and return any errors detected there. * * Return: %0 on success, negative error code otherwise. */ int file_write_and_wait_range(struct file *file, loff_t lstart, loff_t lend) { int err = 0, err2; struct address_space *mapping = file->f_mapping; if (lend < lstart) return 0; if (mapping_needs_writeback(mapping)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ if (err != -EIO) __filemap_fdatawait_range(mapping, lstart, lend); } err2 = file_check_and_advance_wb_err(file); if (!err) err = err2; return err; } EXPORT_SYMBOL(file_write_and_wait_range); /** * replace_page_cache_folio - replace a pagecache folio with a new one * @old: folio to be replaced * @new: folio to replace with * * This function replaces a folio in the pagecache with a new one. On * success it acquires the pagecache reference for the new folio and * drops it for the old folio. Both the old and new folios must be * locked. This function does not add the new folio to the LRU, the * caller must do that. * * The remove + add is atomic. This function cannot fail. */ void replace_page_cache_folio(struct folio *old, struct folio *new) { struct address_space *mapping = old->mapping; void (*free_folio)(struct folio *) = mapping->a_ops->free_folio; pgoff_t offset = old->index; XA_STATE(xas, &mapping->i_pages, offset); VM_BUG_ON_FOLIO(!folio_test_locked(old), old); VM_BUG_ON_FOLIO(!folio_test_locked(new), new); VM_BUG_ON_FOLIO(new->mapping, new); folio_get(new); new->mapping = mapping; new->index = offset; mem_cgroup_replace_folio(old, new); xas_lock_irq(&xas); xas_store(&xas, new); old->mapping = NULL; /* hugetlb pages do not participate in page cache accounting. */ if (!folio_test_hugetlb(old)) __lruvec_stat_sub_folio(old, NR_FILE_PAGES); if (!folio_test_hugetlb(new)) __lruvec_stat_add_folio(new, NR_FILE_PAGES); if (folio_test_swapbacked(old)) __lruvec_stat_sub_folio(old, NR_SHMEM); if (folio_test_swapbacked(new)) __lruvec_stat_add_folio(new, NR_SHMEM); xas_unlock_irq(&xas); if (free_folio) free_folio(old); folio_put(old); } EXPORT_SYMBOL_GPL(replace_page_cache_folio); noinline int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp) { XA_STATE(xas, &mapping->i_pages, index); void *alloced_shadow = NULL; int alloced_order = 0; bool huge; long nr; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio); mapping_set_update(&xas, mapping); VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio); xas_set_order(&xas, index, folio_order(folio)); huge = folio_test_hugetlb(folio); nr = folio_nr_pages(folio); gfp &= GFP_RECLAIM_MASK; folio_ref_add(folio, nr); folio->mapping = mapping; folio->index = xas.xa_index; for (;;) { int order = -1, split_order = 0; void *entry, *old = NULL; xas_lock_irq(&xas); xas_for_each_conflict(&xas, entry) { old = entry; if (!xa_is_value(entry)) { xas_set_err(&xas, -EEXIST); goto unlock; } /* * If a larger entry exists, * it will be the first and only entry iterated. */ if (order == -1) order = xas_get_order(&xas); } /* entry may have changed before we re-acquire the lock */ if (alloced_order && (old != alloced_shadow || order != alloced_order)) { xas_destroy(&xas); alloced_order = 0; } if (old) { if (order > 0 && order > folio_order(folio)) { /* How to handle large swap entries? */ BUG_ON(shmem_mapping(mapping)); if (!alloced_order) { split_order = order; goto unlock; } xas_split(&xas, old, order); xas_reset(&xas); } if (shadowp) *shadowp = old; } xas_store(&xas, folio); if (xas_error(&xas)) goto unlock; mapping->nrpages += nr; /* hugetlb pages do not participate in page cache accounting */ if (!huge) { __lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr); if (folio_test_pmd_mappable(folio)) __lruvec_stat_mod_folio(folio, NR_FILE_THPS, nr); } unlock: xas_unlock_irq(&xas); /* split needed, alloc here and retry. */ if (split_order) { xas_split_alloc(&xas, old, split_order, gfp); if (xas_error(&xas)) goto error; alloced_shadow = old; alloced_order = split_order; xas_reset(&xas); continue; } if (!xas_nomem(&xas, gfp)) break; } if (xas_error(&xas)) goto error; trace_mm_filemap_add_to_page_cache(folio); return 0; error: folio->mapping = NULL; /* Leave page->index set: truncation relies upon it */ folio_put_refs(folio, nr); return xas_error(&xas); } ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp) { void *shadow = NULL; int ret; ret = mem_cgroup_charge(folio, NULL, gfp); if (ret) return ret; __folio_set_locked(folio); ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow); if (unlikely(ret)) { mem_cgroup_uncharge(folio); __folio_clear_locked(folio); } else { /* * The folio might have been evicted from cache only * recently, in which case it should be activated like * any other repeatedly accessed folio. * The exception is folios getting rewritten; evicting other * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ WARN_ON_ONCE(folio_test_active(folio)); if (!(gfp & __GFP_WRITE) && shadow) workingset_refault(folio, shadow); folio_add_lru(folio); } return ret; } EXPORT_SYMBOL_GPL(filemap_add_folio); #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order) { int n; struct folio *folio; if (cpuset_do_page_mem_spread()) { unsigned int cpuset_mems_cookie; do { cpuset_mems_cookie = read_mems_allowed_begin(); n = cpuset_mem_spread_node(); folio = __folio_alloc_node_noprof(gfp, order, n); } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie)); return folio; } return folio_alloc_noprof(gfp, order); } EXPORT_SYMBOL(filemap_alloc_folio_noprof); #endif /* * filemap_invalidate_lock_two - lock invalidate_lock for two mappings * * Lock exclusively invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to lock * @mapping2: the second mapping to lock */ void filemap_invalidate_lock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1 > mapping2) swap(mapping1, mapping2); if (mapping1) down_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) down_write_nested(&mapping2->invalidate_lock, 1); } EXPORT_SYMBOL(filemap_invalidate_lock_two); /* * filemap_invalidate_unlock_two - unlock invalidate_lock for two mappings * * Unlock exclusive invalidate_lock of any passed mapping that is not NULL. * * @mapping1: the first mapping to unlock * @mapping2: the second mapping to unlock */ void filemap_invalidate_unlock_two(struct address_space *mapping1, struct address_space *mapping2) { if (mapping1) up_write(&mapping1->invalidate_lock); if (mapping2 && mapping1 != mapping2) up_write(&mapping2->invalidate_lock); } EXPORT_SYMBOL(filemap_invalidate_unlock_two); /* * In order to wait for pages to become available there must be * waitqueues associated with pages. By using a hash table of * waitqueues where the bucket discipline is to maintain all * waiters on the same queue and wake all when any of the pages * become available, and for the woken contexts to check to be * sure the appropriate page became available, this saves space * at a cost of "thundering herd" phenomena during rare hash * collisions. */ #define PAGE_WAIT_TABLE_BITS 8 #define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS) static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned; static wait_queue_head_t *folio_waitqueue(struct folio *folio) { return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)]; } void __init pagecache_init(void) { int i; for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++) init_waitqueue_head(&folio_wait_table[i]); page_writeback_init(); } /* * The page wait code treats the "wait->flags" somewhat unusually, because * we have multiple different kinds of waits, not just the usual "exclusive" * one. * * We have: * * (a) no special bits set: * * We're just waiting for the bit to be released, and when a waker * calls the wakeup function, we set WQ_FLAG_WOKEN and wake it up, * and remove it from the wait queue. * * Simple and straightforward. * * (b) WQ_FLAG_EXCLUSIVE: * * The waiter is waiting to get the lock, and only one waiter should * be woken up to avoid any thundering herd behavior. We'll set the * WQ_FLAG_WOKEN bit, wake it up, and remove it from the wait queue. * * This is the traditional exclusive wait. * * (c) WQ_FLAG_EXCLUSIVE | WQ_FLAG_CUSTOM: * * The waiter is waiting to get the bit, and additionally wants the * lock to be transferred to it for fair lock behavior. If the lock * cannot be taken, we stop walking the wait queue without waking * the waiter. * * This is the "fair lock handoff" case, and in addition to setting * WQ_FLAG_WOKEN, we set WQ_FLAG_DONE to let the waiter easily see * that it now has the lock. */ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync, void *arg) { unsigned int flags; struct wait_page_key *key = arg; struct wait_page_queue *wait_page = container_of(wait, struct wait_page_queue, wait); if (!wake_page_match(wait_page, key)) return 0; /* * If it's a lock handoff wait, we get the bit for it, and * stop walking (and do not wake it up) if we can't. */ flags = wait->flags; if (flags & WQ_FLAG_EXCLUSIVE) { if (test_bit(key->bit_nr, &key->folio->flags)) return -1; if (flags & WQ_FLAG_CUSTOM) { if (test_and_set_bit(key->bit_nr, &key->folio->flags)) return -1; flags |= WQ_FLAG_DONE; } } /* * We are holding the wait-queue lock, but the waiter that * is waiting for this will be checking the flags without * any locking. * * So update the flags atomically, and wake up the waiter * afterwards to avoid any races. This store-release pairs * with the load-acquire in folio_wait_bit_common(). */ smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN); wake_up_state(wait->private, mode); /* * Ok, we have successfully done what we're waiting for, * and we can unconditionally remove the wait entry. * * Note that this pairs with the "finish_wait()" in the * waiter, and has to be the absolute last thing we do. * After this list_del_init(&wait->entry) the wait entry * might be de-allocated and the process might even have * exited. */ list_del_init_careful(&wait->entry); return (flags & WQ_FLAG_EXCLUSIVE) != 0; } static void folio_wake_bit(struct folio *folio, int bit_nr) { wait_queue_head_t *q = folio_waitqueue(folio); struct wait_page_key key; unsigned long flags; key.folio = folio; key.bit_nr = bit_nr; key.page_match = 0; spin_lock_irqsave(&q->lock, flags); __wake_up_locked_key(q, TASK_NORMAL, &key); /* * It's possible to miss clearing waiters here, when we woke our page * waiters, but the hashed waitqueue has waiters for other pages on it. * That's okay, it's a rare case. The next waker will clear it. * * Note that, depending on the page pool (buddy, hugetlb, ZONE_DEVICE, * other), the flag may be cleared in the course of freeing the page; * but that is not required for correctness. */ if (!waitqueue_active(q) || !key.page_match) folio_clear_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } /* * A choice of three behaviors for folio_wait_bit_common(): */ enum behavior { EXCLUSIVE, /* Hold ref to page and take the bit when woken, like * __folio_lock() waiting on then setting PG_locked. */ SHARED, /* Hold ref to page and check the bit when woken, like * folio_wait_writeback() waiting on PG_writeback. */ DROP, /* Drop ref to page before wait, no check when woken, * like folio_put_wait_locked() on PG_locked. */ }; /* * Attempt to check (or get) the folio flag, and mark us done * if successful. */ static inline bool folio_trylock_flag(struct folio *folio, int bit_nr, struct wait_queue_entry *wait) { if (wait->flags & WQ_FLAG_EXCLUSIVE) { if (test_and_set_bit(bit_nr, &folio->flags)) return false; } else if (test_bit(bit_nr, &folio->flags)) return false; wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE; return true; } /* How many times do we accept lock stealing from under a waiter? */ int sysctl_page_lock_unfairness = 5; static inline int folio_wait_bit_common(struct folio *folio, int bit_nr, int state, enum behavior behavior) { wait_queue_head_t *q = folio_waitqueue(folio); int unfairness = sysctl_page_lock_unfairness; struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; if (bit_nr == PG_locked && !folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = bit_nr; repeat: wait->flags = 0; if (behavior == EXCLUSIVE) { wait->flags = WQ_FLAG_EXCLUSIVE; if (--unfairness < 0) wait->flags |= WQ_FLAG_CUSTOM; } /* * Do one last check whether we can get the * page bit synchronously. * * Do the folio_set_waiters() marking before that * to let any waker we _just_ missed know they * need to wake us up (otherwise they'll never * even go to the slow case that looks at the * page queue), and add ourselves to the wait * queue if we need to sleep. * * This part needs to be done under the queue * lock to avoid races. */ spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, bit_nr, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * From now on, all the logic will be based on * the WQ_FLAG_WOKEN and WQ_FLAG_DONE flag, to * see whether the page bit testing has already * been done by the wake function. * * We can drop our reference to the folio. */ if (behavior == DROP) folio_put(folio); /* * Note that until the "finish_wait()", or until * we see the WQ_FLAG_WOKEN flag, we need to * be very careful with the 'wait->flags', because * we may race with a waker that sets them. */ for (;;) { unsigned int flags; set_current_state(state); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(state, current)) break; io_schedule(); continue; } /* If we were non-exclusive, we're done */ if (behavior != EXCLUSIVE) break; /* If the waker got the lock for us, we're done */ if (flags & WQ_FLAG_DONE) break; /* * Otherwise, if we're getting the lock, we need to * try to get it ourselves. * * And if that fails, we'll have to retry this all. */ if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0)))) goto repeat; wait->flags |= WQ_FLAG_DONE; break; } /* * If a signal happened, this 'finish_wait()' may remove the last * waiter from the wait-queues, but the folio waiters bit will remain * set. That's ok. The next wakeup will take care of it, and trying * to do it here would be difficult and prone to races. */ finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } /* * NOTE! The wait->flags weren't stable until we've done the * 'finish_wait()', and we could have exited the loop above due * to a signal, and had a wakeup event happen after the signal * test but before the 'finish_wait()'. * * So only after the finish_wait() can we reliably determine * if we got woken up or not, so we can now figure out the final * return value based on that state without races. * * Also note that WQ_FLAG_WOKEN is sufficient for a non-exclusive * waiter, but an exclusive one requires WQ_FLAG_DONE. */ if (behavior == EXCLUSIVE) return wait->flags & WQ_FLAG_DONE ? 0 : -EINTR; return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR; } #ifdef CONFIG_MIGRATION /** * migration_entry_wait_on_locked - Wait for a migration entry to be removed * @entry: migration swap entry. * @ptl: already locked ptl. This function will drop the lock. * * Wait for a migration entry referencing the given page to be removed. This is * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except * this can be called without taking a reference on the page. Instead this * should be called while holding the ptl for the migration entry referencing * the page. * * Returns after unlocking the ptl. * * This follows the same logic as folio_wait_bit_common() so see the comments * there. */ void migration_entry_wait_on_locked(swp_entry_t entry, spinlock_t *ptl) __releases(ptl) { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; unsigned long pflags; bool in_thrashing; wait_queue_head_t *q; struct folio *folio = pfn_swap_entry_folio(entry); q = folio_waitqueue(folio); if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) { delayacct_thrashing_start(&in_thrashing); psi_memstall_enter(&pflags); thrashing = true; } init_wait(wait); wait->func = wake_page_function; wait_page.folio = folio; wait_page.bit_nr = PG_locked; wait->flags = 0; spin_lock_irq(&q->lock); folio_set_waiters(folio); if (!folio_trylock_flag(folio, PG_locked, wait)) __add_wait_queue_entry_tail(q, wait); spin_unlock_irq(&q->lock); /* * If a migration entry exists for the page the migration path must hold * a valid reference to the page, and it must take the ptl to remove the * migration entry. So the page is valid until the ptl is dropped. */ spin_unlock(ptl); for (;;) { unsigned int flags; set_current_state(TASK_UNINTERRUPTIBLE); /* Loop until we've been woken or interrupted */ flags = smp_load_acquire(&wait->flags); if (!(flags & WQ_FLAG_WOKEN)) { if (signal_pending_state(TASK_UNINTERRUPTIBLE, current)) break; io_schedule(); continue; } break; } finish_wait(q, wait); if (thrashing) { delayacct_thrashing_end(&in_thrashing); psi_memstall_leave(&pflags); } } #endif void folio_wait_bit(struct folio *folio, int bit_nr) { folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit); int folio_wait_bit_killable(struct folio *folio, int bit_nr) { return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED); } EXPORT_SYMBOL(folio_wait_bit_killable); /** * folio_put_wait_locked - Drop a reference and wait for it to be unlocked * @folio: The folio to wait for. * @state: The sleep state (TASK_KILLABLE, TASK_UNINTERRUPTIBLE, etc). * * The caller should hold a reference on @folio. They expect the page to * become unlocked relatively soon, but do not wish to hold up migration * (for example) by holding the reference while waiting for the folio to * come unlocked. After this function returns, the caller should not * dereference @folio. * * Return: 0 if the folio was unlocked or -EINTR if interrupted by a signal. */ static int folio_put_wait_locked(struct folio *folio, int state) { return folio_wait_bit_common(folio, PG_locked, state, DROP); } /** * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue * @folio: Folio defining the wait queue of interest * @waiter: Waiter to add to the queue * * Add an arbitrary @waiter to the wait queue for the nominated @folio. */ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter) { wait_queue_head_t *q = folio_waitqueue(folio); unsigned long flags; spin_lock_irqsave(&q->lock, flags); __add_wait_queue_entry_tail(q, waiter); folio_set_waiters(folio); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(folio_add_wait_queue); /** * folio_unlock - Unlock a locked folio. * @folio: The folio. * * Unlocks the folio and wakes up any thread sleeping on the page lock. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_unlock(struct folio *folio) { /* Bit 7 allows x86 to check the byte's sign bit */ BUILD_BUG_ON(PG_waiters != 7); BUILD_BUG_ON(PG_locked > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (folio_xor_flags_has_waiters(folio, 1 << PG_locked)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_unlock); /** * folio_end_read - End read on a folio. * @folio: The folio. * @success: True if all reads completed successfully. * * When all reads against a folio have completed, filesystems should * call this function to let the pagecache know that no more reads * are outstanding. This will unlock the folio and wake up any thread * sleeping on the lock. The folio will also be marked uptodate if all * reads succeeded. * * Context: May be called from interrupt or process context. May not be * called from NMI context. */ void folio_end_read(struct folio *folio, bool success) { unsigned long mask = 1 << PG_locked; /* Must be in bottom byte for x86 to work */ BUILD_BUG_ON(PG_uptodate > 7); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio); if (likely(success)) mask |= 1 << PG_uptodate; if (folio_xor_flags_has_waiters(folio, mask)) folio_wake_bit(folio, PG_locked); } EXPORT_SYMBOL(folio_end_read); /** * folio_end_private_2 - Clear PG_private_2 and wake any waiters. * @folio: The folio. * * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for * it. The folio reference held for PG_private_2 being set is released. * * This is, for example, used when a netfs folio is being written to a local * disk cache, thereby allowing writes to the cache for the same folio to be * serialised. */ void folio_end_private_2(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio); clear_bit_unlock(PG_private_2, folio_flags(folio, 0)); folio_wake_bit(folio, PG_private_2); folio_put(folio); } EXPORT_SYMBOL(folio_end_private_2); /** * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio. */ void folio_wait_private_2(struct folio *folio) { while (folio_test_private_2(folio)) folio_wait_bit(folio, PG_private_2); } EXPORT_SYMBOL(folio_wait_private_2); /** * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio. * @folio: The folio to wait on. * * Wait for PG_private_2 to be cleared on a folio or until a fatal signal is * received by the calling task. * * Return: * - 0 if successful. * - -EINTR if a fatal signal was encountered. */ int folio_wait_private_2_killable(struct folio *folio) { int ret = 0; while (folio_test_private_2(folio)) { ret = folio_wait_bit_killable(folio, PG_private_2); if (ret < 0) break; } return ret; } EXPORT_SYMBOL(folio_wait_private_2_killable); /** * folio_end_writeback - End writeback against a folio. * @folio: The folio. * * The folio must actually be under writeback. * * Context: May be called from process or interrupt context. */ void folio_end_writeback(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio); /* * folio_test_clear_reclaim() could be used here but it is an * atomic operation and overkill in this particular case. Failing * to shuffle a folio marked for immediate reclaim is too mild * a gain to justify taking an atomic operation penalty at the * end of every folio writeback. */ if (folio_test_reclaim(folio)) { folio_clear_reclaim(folio); folio_rotate_reclaimable(folio); } /* * Writeback does not hold a folio reference of its own, relying * on truncation to wait for the clearing of PG_writeback. * But here we must make sure that the folio is not freed and * reused before the folio_wake_bit(). */ folio_get(folio); if (__folio_end_writeback(folio)) folio_wake_bit(folio, PG_writeback); acct_reclaim_writeback(folio); folio_put(folio); } EXPORT_SYMBOL(folio_end_writeback); /** * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it. * @folio: The folio to lock */ void __folio_lock(struct folio *folio) { folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE, EXCLUSIVE); } EXPORT_SYMBOL(__folio_lock); int __folio_lock_killable(struct folio *folio) { return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE, EXCLUSIVE); } EXPORT_SYMBOL_GPL(__folio_lock_killable); static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait) { struct wait_queue_head *q = folio_waitqueue(folio); int ret; wait->folio = folio; wait->bit_nr = PG_locked; spin_lock_irq(&q->lock); __add_wait_queue_entry_tail(q, &wait->wait); folio_set_waiters(folio); ret = !folio_trylock(folio); /* * If we were successful now, we know we're still on the * waitqueue as we're still under the lock. This means it's * safe to remove and return success, we know the callback * isn't going to trigger. */ if (!ret) __remove_wait_queue(q, &wait->wait); else ret = -EIOCBQUEUED; spin_unlock_irq(&q->lock); return ret; } /* * Return values: * 0 - folio is locked. * non-zero - folio is not locked. * mmap_lock or per-VMA lock has been released (mmap_read_unlock() or * vma_end_read()), unless flags had both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_RETRY_NOWAIT set, in which case the lock is still held. * * If neither ALLOW_RETRY nor KILLABLE are set, will always return 0 * with the folio locked and the mmap_lock/per-VMA lock is left unperturbed. */ vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { unsigned int flags = vmf->flags; if (fault_flag_allow_retry_first(flags)) { /* * CAUTION! In this case, mmap_lock/per-VMA lock is not * released even though returning VM_FAULT_RETRY. */ if (flags & FAULT_FLAG_RETRY_NOWAIT) return VM_FAULT_RETRY; release_fault_lock(vmf); if (flags & FAULT_FLAG_KILLABLE) folio_wait_locked_killable(folio); else folio_wait_locked(folio); return VM_FAULT_RETRY; } if (flags & FAULT_FLAG_KILLABLE) { bool ret; ret = __folio_lock_killable(folio); if (ret) { release_fault_lock(vmf); return VM_FAULT_RETRY; } } else { __folio_lock(folio); } return 0; } /** * page_cache_next_miss() - Find the next gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the * gap with the lowest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 5, then subsequently a gap is * created at index 10, page_cache_next_miss covering both indices may * return 10 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'return - index >= max_scan' will be true). * In the rare case of index wrap-around, 0 will be returned. */ pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_next(&xas); if (!entry || xa_is_value(entry)) return xas.xa_index; if (xas.xa_index == 0) return 0; } return index + max_scan; } EXPORT_SYMBOL(page_cache_next_miss); /** * page_cache_prev_miss() - Find the previous gap in the page cache. * @mapping: Mapping. * @index: Index. * @max_scan: Maximum range to search. * * Search the range [max(index - max_scan + 1, 0), index] for the * gap with the highest index. * * This function may be called under the rcu_read_lock. However, this will * not atomically search a snapshot of the cache at a single point in time. * For example, if a gap is created at index 10, then subsequently a gap is * created at index 5, page_cache_prev_miss() covering both indices may * return 5 if called under the rcu_read_lock. * * Return: The index of the gap if found, otherwise an index outside the * range specified (in which case 'index - return >= max_scan' will be true). * In the rare case of wrap-around, ULONG_MAX will be returned. */ pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { XA_STATE(xas, &mapping->i_pages, index); while (max_scan--) { void *entry = xas_prev(&xas); if (!entry || xa_is_value(entry)) break; if (xas.xa_index == ULONG_MAX) break; } return xas.xa_index; } EXPORT_SYMBOL(page_cache_prev_miss); /* * Lockless page cache protocol: * On the lookup side: * 1. Load the folio from i_pages * 2. Increment the refcount if it's not zero * 3. If the folio is not found by xas_reload(), put the refcount and retry * * On the removal side: * A. Freeze the page (by zeroing the refcount if nobody else has a reference) * B. Remove the page from i_pages * C. Return the page to the page allocator * * This means that any page may have its reference count temporarily * increased by a speculative page cache (or GUP-fast) lookup as it can * be allocated by another user before the RCU grace period expires. * Because the refcount temporarily acquired here may end up being the * last refcount on the page, any page allocation must be freeable by * folio_put(). */ /* * filemap_get_entry - Get a page cache entry. * @mapping: the address_space to search * @index: The page cache index. * * Looks up the page cache entry at @mapping & @index. If it is a folio, * it is returned with an increased refcount. If it is a shadow entry * of a previously evicted folio, or a swap entry from shmem/tmpfs, * it is returned without further action. * * Return: The folio, swap or shadow entry, %NULL if nothing is found. */ void *filemap_get_entry(struct address_space *mapping, pgoff_t index) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); repeat: xas_reset(&xas); folio = xas_load(&xas); if (xas_retry(&xas, folio)) goto repeat; /* * A shadow entry of a recently evicted page, or a swap entry from * shmem/tmpfs. Return it without attempting to raise page count. */ if (!folio || xa_is_value(folio)) goto out; if (!folio_try_get(folio)) goto repeat; if (unlikely(folio != xas_reload(&xas))) { folio_put(folio); goto repeat; } out: rcu_read_unlock(); return folio; } /** * __filemap_get_folio - Find and get a reference to a folio. * @mapping: The address_space to search. * @index: The page index. * @fgp_flags: %FGP flags modify how the folio is returned. * @gfp: Memory allocation flags to use if %FGP_CREAT is specified. * * Looks up the page cache entry at @mapping & @index. * * If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even * if the %GFP flags specified for %FGP_CREAT are atomic. * * If this function returns a folio, it is returned with an increased refcount. * * Return: The found folio or an ERR_PTR() otherwise. */ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp) { struct folio *folio; repeat: folio = filemap_get_entry(mapping, index); if (xa_is_value(folio)) folio = NULL; if (!folio) goto no_page; if (fgp_flags & FGP_LOCK) { if (fgp_flags & FGP_NOWAIT) { if (!folio_trylock(folio)) { folio_put(folio); return ERR_PTR(-EAGAIN); } } else { folio_lock(folio); } /* Has the page been truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto repeat; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); } if (fgp_flags & FGP_ACCESSED) folio_mark_accessed(folio); else if (fgp_flags & FGP_WRITE) { /* Clear idle flag for buffer write */ if (folio_test_idle(folio)) folio_clear_idle(folio); } if (fgp_flags & FGP_STABLE) folio_wait_stable(folio); no_page: if (!folio && (fgp_flags & FGP_CREAT)) { unsigned order = FGF_GET_ORDER(fgp_flags); int err; if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping)) gfp |= __GFP_WRITE; if (fgp_flags & FGP_NOFS) gfp &= ~__GFP_FS; if (fgp_flags & FGP_NOWAIT) { gfp &= ~GFP_KERNEL; gfp |= GFP_NOWAIT | __GFP_NOWARN; } if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP)))) fgp_flags |= FGP_LOCK; if (!mapping_large_folio_support(mapping)) order = 0; if (order > MAX_PAGECACHE_ORDER) order = MAX_PAGECACHE_ORDER; /* If we're not aligned, allocate a smaller folio */ if (index & ((1UL << order) - 1)) order = __ffs(index); do { gfp_t alloc_gfp = gfp; err = -ENOMEM; if (order > 0) alloc_gfp |= __GFP_NORETRY | __GFP_NOWARN; folio = filemap_alloc_folio(alloc_gfp, order); if (!folio) continue; /* Init accessed so avoid atomic mark_page_accessed later */ if (fgp_flags & FGP_ACCESSED) __folio_set_referenced(folio); err = filemap_add_folio(mapping, folio, index, gfp); if (!err) break; folio_put(folio); folio = NULL; } while (order-- > 0); if (err == -EEXIST) goto repeat; if (err) return ERR_PTR(err); /* * filemap_add_folio locks the page, and for mmap * we expect an unlocked page. */ if (folio && (fgp_flags & FGP_FOR_MMAP)) folio_unlock(folio); } if (!folio) return ERR_PTR(-ENOENT); return folio; } EXPORT_SYMBOL(__filemap_get_folio); static inline struct folio *find_get_entry(struct xa_state *xas, pgoff_t max, xa_mark_t mark) { struct folio *folio; retry: if (mark == XA_PRESENT) folio = xas_find(xas, max); else folio = xas_find_marked(xas, max, mark); if (xas_retry(xas, folio)) goto retry; /* * A shadow entry of a recently evicted page, a swap * entry from shmem/tmpfs or a DAX entry. Return it * without attempting to raise page count. */ if (!folio || xa_is_value(folio)) return folio; if (!folio_try_get(folio)) goto reset; if (unlikely(folio != xas_reload(xas))) { folio_put(folio); goto reset; } return folio; reset: xas_reset(xas); goto retry; } /** * find_get_entries - gang pagecache lookup * @mapping: The address_space to search * @start: The starting page cache index * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices corresponding to the entries in @entries * * find_get_entries() will search for and return a batch of entries in * the mapping. The entries are placed in @fbatch. find_get_entries() * takes a reference on any actual folios it returns. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries or large folios. * * Any shadow entries of evicted folios, or swap entries from * shmem/tmpfs, are included in the returned array. * * Return: The number of entries which were found. */ unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) { indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; } rcu_read_unlock(); if (folio_batch_count(fbatch)) { unsigned long nr = 1; int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; if (!xa_is_value(folio)) nr = folio_nr_pages(folio); *start = indices[idx] + nr; } return folio_batch_count(fbatch); } /** * find_lock_entries - Find a batch of pagecache entries. * @mapping: The address_space to search. * @start: The starting page cache index. * @end: The final page index (inclusive). * @fbatch: Where the resulting entries are placed. * @indices: The cache indices of the entries in @fbatch. * * find_lock_entries() will return a batch of entries from @mapping. * Swap, shadow and DAX entries are included. Folios are returned * locked and with an incremented refcount. Folios which are locked * by somebody else or under writeback are skipped. Folios which are * partially outside the range are not returned. * * The entries have ascending indexes. The indices may not be consecutive * due to not-present entries, large folios, folios which could not be * locked or folios under writeback. * * Return: The number of entries which were found. */ unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, XA_PRESENT))) { if (!xa_is_value(folio)) { if (folio->index < *start) goto put; if (folio_next_index(folio) - 1 > end) goto put; if (!folio_trylock(folio)) goto put; if (folio->mapping != mapping || folio_test_writeback(folio)) goto unlock; VM_BUG_ON_FOLIO(!folio_contains(folio, xas.xa_index), folio); } indices[fbatch->nr] = xas.xa_index; if (!folio_batch_add(fbatch, folio)) break; continue; unlock: folio_unlock(folio); put: folio_put(folio); } rcu_read_unlock(); if (folio_batch_count(fbatch)) { unsigned long nr = 1; int idx = folio_batch_count(fbatch) - 1; folio = fbatch->folios[idx]; if (!xa_is_value(folio)) nr = folio_nr_pages(folio); *start = indices[idx] + nr; } return folio_batch_count(fbatch); } /** * filemap_get_folios - Get a batch of folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill. * * Search for and return a batch of folios in the mapping starting at * index @start and up to index @end (inclusive). The folios are returned * in @fbatch with an elevated reference count. * * Return: The number of folios which were found. * We also update @start to index the next folio for the traversal. */ unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { return filemap_get_folios_tag(mapping, start, end, XA_PRESENT, fbatch); } EXPORT_SYMBOL(filemap_get_folios); /** * filemap_get_folios_contig - Get a batch of contiguous folios * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @fbatch: The batch to fill * * filemap_get_folios_contig() works exactly like filemap_get_folios(), * except the returned folios are guaranteed to be contiguous. This may * not return all contiguous folios if the batch gets filled up. * * Return: The number of folios found. * Also update @start to be positioned for traversal of the next folio. */ unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); unsigned long nr; struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio && xas.xa_index <= end; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; /* * If the entry has been swapped out, we can stop looking. * No current caller is looking for DAX entries. */ if (xa_is_value(folio)) goto update_start; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) { nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } update_start: nr = folio_batch_count(fbatch); if (nr) { folio = fbatch->folios[nr - 1]; *start = folio_next_index(folio); } out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_contig); /** * filemap_get_folios_tag - Get a batch of folios matching @tag * @mapping: The address_space to search * @start: The starting page index * @end: The final page index (inclusive) * @tag: The tag index * @fbatch: The batch to fill * * The first folio may start before @start; if it does, it will contain * @start. The final folio may extend beyond @end; if it does, it will * contain @end. The folios have ascending indices. There may be gaps * between the folios if there are indices which have no folio in the * page cache. If folios are added to or removed from the page cache * while this is running, they may or may not be found by this call. * Only returns folios that are tagged with @tag. * * Return: The number of folios found. * Also update @start to index the next folio for traversal. */ unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, *start); struct folio *folio; rcu_read_lock(); while ((folio = find_get_entry(&xas, end, tag)) != NULL) { /* * Shadow entries should never be tagged, but this iteration * is lockless so there is a window for page reclaim to evict * a page we saw tagged. Skip over it. */ if (xa_is_value(folio)) continue; if (!folio_batch_add(fbatch, folio)) { unsigned long nr = folio_nr_pages(folio); *start = folio->index + nr; goto out; } } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This * breaks the iteration when there is a page at index -1 but that is * already broke anyway. */ if (end == (pgoff_t)-1) *start = (pgoff_t)-1; else *start = end + 1; out: rcu_read_unlock(); return folio_batch_count(fbatch); } EXPORT_SYMBOL(filemap_get_folios_tag); /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: * * ---R__________________________________________B__________ * ^ reading here ^ bad block(assume 4k) * * read(R) => miss => readahead(R...B) => media error => frustrating retries * => failing the whole request => read(R) => read(R+1) => * readahead(R+1...B+1) => bang => read(R+2) => read(R+3) => * readahead(R+3...B+2) => bang => read(R+3) => read(R+4) => * readahead(R+4...B+3) => bang => read(R+4) => read(R+5) => ...... * * It is going insane. Fix it by quickly scaling down the readahead size. */ static void shrink_readahead_size_eio(struct file_ra_state *ra) { ra->ra_pages /= 4; } /* * filemap_get_read_batch - Get a batch of folios for read * * Get a batch of folios which represent a contiguous range of bytes in * the file. No exceptional entries will be returned. If @index is in * the middle of a folio, the entire folio will be returned. The last * folio in the batch may have the readahead flag set or the uptodate flag * clear so that the caller can take the appropriate action. */ static void filemap_get_read_batch(struct address_space *mapping, pgoff_t index, pgoff_t max, struct folio_batch *fbatch) { XA_STATE(xas, &mapping->i_pages, index); struct folio *folio; rcu_read_lock(); for (folio = xas_load(&xas); folio; folio = xas_next(&xas)) { if (xas_retry(&xas, folio)) continue; if (xas.xa_index > max || xa_is_value(folio)) break; if (xa_is_sibling(folio)) break; if (!folio_try_get(folio)) goto retry; if (unlikely(folio != xas_reload(&xas))) goto put_folio; if (!folio_batch_add(fbatch, folio)) break; if (!folio_test_uptodate(folio)) break; if (folio_test_readahead(folio)) break; xas_advance(&xas, folio_next_index(folio) - 1); continue; put_folio: folio_put(folio); retry: xas_reset(&xas); } rcu_read_unlock(); } static int filemap_read_folio(struct file *file, filler_t filler, struct folio *folio) { bool workingset = folio_test_workingset(folio); unsigned long pflags; int error; /* * A previous I/O error may have been due to temporary failures, * eg. multipath errors. PG_error will be set again if read_folio * fails. */ folio_clear_error(folio); /* Start the actual read. The read will unlock the page. */ if (unlikely(workingset)) psi_memstall_enter(&pflags); error = filler(file, folio); if (unlikely(workingset)) psi_memstall_leave(&pflags); if (error) return error; error = folio_wait_locked_killable(folio); if (error) return error; if (folio_test_uptodate(folio)) return 0; if (file) shrink_readahead_size_eio(&file->f_ra); return -EIO; } static bool filemap_range_uptodate(struct address_space *mapping, loff_t pos, size_t count, struct folio *folio, bool need_uptodate) { if (folio_test_uptodate(folio)) return true; /* pipes can't handle partially uptodate pages */ if (need_uptodate) return false; if (!mapping->a_ops->is_partially_uptodate) return false; if (mapping->host->i_blkbits >= folio_shift(folio)) return false; if (folio_pos(folio) > pos) { count -= folio_pos(folio) - pos; pos = 0; } else { pos -= folio_pos(folio); } return mapping->a_ops->is_partially_uptodate(folio, pos, count); } static int filemap_update_page(struct kiocb *iocb, struct address_space *mapping, size_t count, struct folio *folio, bool need_uptodate) { int error; if (iocb->ki_flags & IOCB_NOWAIT) { if (!filemap_invalidate_trylock_shared(mapping)) return -EAGAIN; } else { filemap_invalidate_lock_shared(mapping); } if (!folio_trylock(folio)) { error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO)) goto unlock_mapping; if (!(iocb->ki_flags & IOCB_WAITQ)) { filemap_invalidate_unlock_shared(mapping); /* * This is where we usually end up waiting for a * previously submitted readahead to finish. */ folio_put_wait_locked(folio, TASK_KILLABLE); return AOP_TRUNCATED_PAGE; } error = __folio_lock_async(folio, iocb->ki_waitq); if (error) goto unlock_mapping; } error = AOP_TRUNCATED_PAGE; if (!folio->mapping) goto unlock; error = 0; if (filemap_range_uptodate(mapping, iocb->ki_pos, count, folio, need_uptodate)) goto unlock; error = -EAGAIN; if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ)) goto unlock; error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio, folio); goto unlock_mapping; unlock: folio_unlock(folio); unlock_mapping: filemap_invalidate_unlock_shared(mapping); if (error == AOP_TRUNCATED_PAGE) folio_put(folio); return error; } static int filemap_create_folio(struct file *file, struct address_space *mapping, pgoff_t index, struct folio_batch *fbatch) { struct folio *folio; int error; folio = filemap_alloc_folio(mapping_gfp_mask(mapping), 0); if (!folio) return -ENOMEM; /* * Protect against truncate / hole punch. Grabbing invalidate_lock * here assures we cannot instantiate and bring uptodate new * pagecache folios after evicting page cache during truncate * and before actually freeing blocks. Note that we could * release invalidate_lock after inserting the folio into * the page cache as the locked folio would then be enough to * synchronize with hole punching. But there are code paths * such as filemap_update_page() filling in partially uptodate * pages or ->readahead() that need to hold invalidate_lock * while mapping blocks for IO so let's hold the lock here as * well to keep locking rules simple. */ filemap_invalidate_lock_shared(mapping); error = filemap_add_folio(mapping, folio, index, mapping_gfp_constraint(mapping, GFP_KERNEL)); if (error == -EEXIST) error = AOP_TRUNCATED_PAGE; if (error) goto error; error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (error) goto error; filemap_invalidate_unlock_shared(mapping); folio_batch_add(fbatch, folio); return 0; error: filemap_invalidate_unlock_shared(mapping); folio_put(folio); return error; } static int filemap_readahead(struct kiocb *iocb, struct file *file, struct address_space *mapping, struct folio *folio, pgoff_t last_index) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, folio->index); if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; page_cache_async_ra(&ractl, folio, last_index - folio->index); return 0; } static int filemap_get_pages(struct kiocb *iocb, size_t count, struct folio_batch *fbatch, bool need_uptodate) { struct file *filp = iocb->ki_filp; struct address_space *mapping = filp->f_mapping; struct file_ra_state *ra = &filp->f_ra; pgoff_t index = iocb->ki_pos >> PAGE_SHIFT; pgoff_t last_index; struct folio *folio; int err = 0; /* "last_index" is the index of the page beyond the end of the read */ last_index = DIV_ROUND_UP(iocb->ki_pos + count, PAGE_SIZE); retry: if (fatal_signal_pending(current)) return -EINTR; filemap_get_read_batch(mapping, index, last_index - 1, fbatch); if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & IOCB_NOIO) return -EAGAIN; page_cache_sync_readahead(mapping, ra, filp, index, last_index - index); filemap_get_read_batch(mapping, index, last_index - 1, fbatch); } if (!folio_batch_count(fbatch)) { if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_WAITQ)) return -EAGAIN; err = filemap_create_folio(filp, mapping, iocb->ki_pos >> PAGE_SHIFT, fbatch); if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } folio = fbatch->folios[folio_batch_count(fbatch) - 1]; if (folio_test_readahead(folio)) { err = filemap_readahead(iocb, filp, mapping, folio, last_index); if (err) goto err; } if (!folio_test_uptodate(folio)) { if ((iocb->ki_flags & IOCB_WAITQ) && folio_batch_count(fbatch) > 1) iocb->ki_flags |= IOCB_NOWAIT; err = filemap_update_page(iocb, mapping, count, folio, need_uptodate); if (err) goto err; } return 0; err: if (err < 0) folio_put(folio); if (likely(--fbatch->nr)) return 0; if (err == AOP_TRUNCATED_PAGE) goto retry; return err; } static inline bool pos_same_folio(loff_t pos1, loff_t pos2, struct folio *folio) { unsigned int shift = folio_shift(folio); return (pos1 >> shift == pos2 >> shift); } /** * filemap_read - Read data from the page cache. * @iocb: The iocb to read. * @iter: Destination for the data. * @already_read: Number of bytes already read by the caller. * * Copies data from the page cache. If the data is not currently present, * uses the readahead and read_folio address_space operations to fetch it. * * Return: Total number of bytes copied, including those already read by * the caller. If an error happens before any bytes are copied, returns * a negative error number. */ ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *iter, ssize_t already_read) { struct file *filp = iocb->ki_filp; struct file_ra_state *ra = &filp->f_ra; struct address_space *mapping = filp->f_mapping; struct inode *inode = mapping->host; struct folio_batch fbatch; int i, error = 0; bool writably_mapped; loff_t isize, end_offset; loff_t last_pos = ra->prev_pos; if (unlikely(iocb->ki_pos >= inode->i_sb->s_maxbytes)) return 0; if (unlikely(!iov_iter_count(iter))) return 0; iov_iter_truncate(iter, inode->i_sb->s_maxbytes); folio_batch_init(&fbatch); do { cond_resched(); /* * If we've already successfully copied some data, then we * can no longer safely return -EIOCBQUEUED. Hence mark * an async read NOWAIT at that point. */ if ((iocb->ki_flags & IOCB_WAITQ) && already_read) iocb->ki_flags |= IOCB_NOWAIT; if (unlikely(iocb->ki_pos >= i_size_read(inode))) break; error = filemap_get_pages(iocb, iter->count, &fbatch, false); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(inode); if (unlikely(iocb->ki_pos >= isize)) goto put_folios; end_offset = min_t(loff_t, isize, iocb->ki_pos + iter->count); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(mapping); /* * When a read accesses the same folio several times, only * mark it as accessed the first time. */ if (!pos_same_folio(iocb->ki_pos, last_pos - 1, fbatch.folios[0])) folio_mark_accessed(fbatch.folios[0]); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t fsize = folio_size(folio); size_t offset = iocb->ki_pos & (fsize - 1); size_t bytes = min_t(loff_t, end_offset - iocb->ki_pos, fsize - offset); size_t copied; if (end_offset < folio_pos(folio)) break; if (i > 0) folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); copied = copy_folio_to_iter(folio, offset, bytes, iter); already_read += copied; iocb->ki_pos += copied; last_pos = iocb->ki_pos; if (copied < bytes) { error = -EFAULT; break; } } put_folios: for (i = 0; i < folio_batch_count(&fbatch); i++) folio_put(fbatch.folios[i]); folio_batch_init(&fbatch); } while (iov_iter_count(iter) && iocb->ki_pos < isize && !error); file_accessed(filp); ra->prev_pos = last_pos; return already_read ? already_read : error; } EXPORT_SYMBOL_GPL(filemap_read); int kiocb_write_and_wait(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos; loff_t end = pos + count - 1; if (iocb->ki_flags & IOCB_NOWAIT) { if (filemap_range_needs_writeback(mapping, pos, end)) return -EAGAIN; return 0; } return filemap_write_and_wait_range(mapping, pos, end); } EXPORT_SYMBOL_GPL(kiocb_write_and_wait); int kiocb_invalidate_pages(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; loff_t pos = iocb->ki_pos; loff_t end = pos + count - 1; int ret; if (iocb->ki_flags & IOCB_NOWAIT) { /* we could block if there are any pages in the range */ if (filemap_range_has_page(mapping, pos, end)) return -EAGAIN; } else { ret = filemap_write_and_wait_range(mapping, pos, end); if (ret) return ret; } /* * After a write we want buffered reads to be sure to go to disk to get * the new data. We invalidate clean cached page from the region we're * about to write. We do this *before* the write so that we can return * without clobbering -EIOCBQUEUED from ->direct_IO(). */ return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, end >> PAGE_SHIFT); } EXPORT_SYMBOL_GPL(kiocb_invalidate_pages); /** * generic_file_read_iter - generic filesystem read routine * @iocb: kernel I/O control block * @iter: destination for the data read * * This is the "read_iter()" routine for all filesystems * that can use the page cache directly. * * The IOCB_NOWAIT flag in iocb->ki_flags indicates that -EAGAIN shall * be returned when no data can be read without waiting for I/O requests * to complete; it doesn't prevent readahead. * * The IOCB_NOIO flag in iocb->ki_flags indicates that no new I/O * requests shall be made for the read or for readahead. When no data * can be read, -EAGAIN shall be returned. When readahead would be * triggered, a partial, possibly empty read shall be returned. * * Return: * * number of bytes copied, even for partial reads * * negative error code (or 0 if IOCB_NOIO) if nothing was read */ ssize_t generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) { size_t count = iov_iter_count(iter); ssize_t retval = 0; if (!count) return 0; /* skip atime */ if (iocb->ki_flags & IOCB_DIRECT) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; retval = kiocb_write_and_wait(iocb, count); if (retval < 0) return retval; file_accessed(file); retval = mapping->a_ops->direct_IO(iocb, iter); if (retval >= 0) { iocb->ki_pos += retval; count -= retval; } if (retval != -EIOCBQUEUED) iov_iter_revert(iter, count - iov_iter_count(iter)); /* * Btrfs can have a short DIO read if we encounter * compressed extents, so if there was an error, or if * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for * the rest of the read. Buffered reads will not work for * DAX files, so don't bother trying. */ if (retval < 0 || !count || IS_DAX(inode)) return retval; if (iocb->ki_pos >= i_size_read(inode)) return retval; } return filemap_read(iocb, iter, retval); } EXPORT_SYMBOL(generic_file_read_iter); /* * Splice subpages from a folio into a pipe. */ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe, struct folio *folio, loff_t fpos, size_t size) { struct page *page; size_t spliced = 0, offset = offset_in_folio(folio, fpos); page = folio_page(folio, offset / PAGE_SIZE); size = min(size, folio_size(folio) - offset); offset %= PAGE_SIZE; while (spliced < size && !pipe_full(pipe->head, pipe->tail, pipe->max_usage)) { struct pipe_buffer *buf = pipe_head_buf(pipe); size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced); *buf = (struct pipe_buffer) { .ops = &page_cache_pipe_buf_ops, .page = page, .offset = offset, .len = part, }; folio_get(folio); pipe->head++; page++; spliced += part; offset = 0; } return spliced; } /** * filemap_splice_read - Splice data from a file's pagecache into a pipe * @in: The file to read from * @ppos: Pointer to the file position to read from * @pipe: The pipe to splice into * @len: The amount to splice * @flags: The SPLICE_F_* flags * * This function gets folios from a file's pagecache and splices them into the * pipe. Readahead will be called as necessary to fill more folios. This may * be used for blockdevs also. * * Return: On success, the number of bytes read will be returned and *@ppos * will be updated if appropriate; 0 will be returned if there is no more data * to be read; -EAGAIN will be returned if the pipe had no space, and some * other negative error code will be returned on error. A short read may occur * if the pipe has insufficient space, we reach the end of the data or we hit a * hole. */ ssize_t filemap_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct folio_batch fbatch; struct kiocb iocb; size_t total_spliced = 0, used, npages; loff_t isize, end_offset; bool writably_mapped; int i, error = 0; if (unlikely(*ppos >= in->f_mapping->host->i_sb->s_maxbytes)) return 0; init_sync_kiocb(&iocb, in); iocb.ki_pos = *ppos; /* Work out how much data we can actually add into the pipe */ used = pipe_occupancy(pipe->head, pipe->tail); npages = max_t(ssize_t, pipe->max_usage - used, 0); len = min_t(size_t, len, npages * PAGE_SIZE); folio_batch_init(&fbatch); do { cond_resched(); if (*ppos >= i_size_read(in->f_mapping->host)) break; iocb.ki_pos = *ppos; error = filemap_get_pages(&iocb, len, &fbatch, true); if (error < 0) break; /* * i_size must be checked after we know the pages are Uptodate. * * Checking i_size after the check allows us to calculate * the correct value for "nr", which means the zero-filled * part of the page is not copied back to userspace (unless * another truncate extends the file - this is desired though). */ isize = i_size_read(in->f_mapping->host); if (unlikely(*ppos >= isize)) break; end_offset = min_t(loff_t, isize, *ppos + len); /* * Once we start copying data, we don't want to be touching any * cachelines that might be contended: */ writably_mapped = mapping_writably_mapped(in->f_mapping); for (i = 0; i < folio_batch_count(&fbatch); i++) { struct folio *folio = fbatch.folios[i]; size_t n; if (folio_pos(folio) >= end_offset) goto out; folio_mark_accessed(folio); /* * If users can be writing to this folio using arbitrary * virtual addresses, take care of potential aliasing * before reading the folio on the kernel side. */ if (writably_mapped) flush_dcache_folio(folio); n = min_t(loff_t, len, isize - *ppos); n = splice_folio_into_pipe(pipe, folio, *ppos, n); if (!n) goto out; len -= n; total_spliced += n; *ppos += n; in->f_ra.prev_pos = *ppos; if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) goto out; } folio_batch_release(&fbatch); } while (len); out: folio_batch_release(&fbatch); file_accessed(in); return total_spliced ? total_spliced : error; } EXPORT_SYMBOL(filemap_splice_read); static inline loff_t folio_seek_hole_data(struct xa_state *xas, struct address_space *mapping, struct folio *folio, loff_t start, loff_t end, bool seek_data) { const struct address_space_operations *ops = mapping->a_ops; size_t offset, bsz = i_blocksize(mapping->host); if (xa_is_value(folio) || folio_test_uptodate(folio)) return seek_data ? start : end; if (!ops->is_partially_uptodate) return seek_data ? end : start; xas_pause(xas); rcu_read_unlock(); folio_lock(folio); if (unlikely(folio->mapping != mapping)) goto unlock; offset = offset_in_folio(folio, start) & ~(bsz - 1); do { if (ops->is_partially_uptodate(folio, offset, bsz) == seek_data) break; start = (start + bsz) & ~(bsz - 1); offset += bsz; } while (offset < folio_size(folio)); unlock: folio_unlock(folio); rcu_read_lock(); return start; } static inline size_t seek_folio_size(struct xa_state *xas, struct folio *folio) { if (xa_is_value(folio)) return PAGE_SIZE << xa_get_order(xas->xa, xas->xa_index); return folio_size(folio); } /** * mapping_seek_hole_data - Seek for SEEK_DATA / SEEK_HOLE in the page cache. * @mapping: Address space to search. * @start: First byte to consider. * @end: Limit of search (exclusive). * @whence: Either SEEK_HOLE or SEEK_DATA. * * If the page cache knows which blocks contain holes and which blocks * contain data, your filesystem can use this function to implement * SEEK_HOLE and SEEK_DATA. This is useful for filesystems which are * entirely memory-based such as tmpfs, and filesystems which support * unwritten extents. * * Return: The requested offset on success, or -ENXIO if @whence specifies * SEEK_DATA and there is no data after @start. There is an implicit hole * after @end - 1, so SEEK_HOLE returns @end if all the bytes between @start * and @end contain data. */ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start, loff_t end, int whence) { XA_STATE(xas, &mapping->i_pages, start >> PAGE_SHIFT); pgoff_t max = (end - 1) >> PAGE_SHIFT; bool seek_data = (whence == SEEK_DATA); struct folio *folio; if (end <= start) return -ENXIO; rcu_read_lock(); while ((folio = find_get_entry(&xas, max, XA_PRESENT))) { loff_t pos = (u64)xas.xa_index << PAGE_SHIFT; size_t seek_size; if (start < pos) { if (!seek_data) goto unlock; start = pos; } seek_size = seek_folio_size(&xas, folio); pos = round_up((u64)pos + 1, seek_size); start = folio_seek_hole_data(&xas, mapping, folio, start, pos, seek_data); if (start < pos) goto unlock; if (start >= end) break; if (seek_size > PAGE_SIZE) xas_set(&xas, pos >> PAGE_SHIFT); if (!xa_is_value(folio)) folio_put(folio); } if (seek_data) start = -ENXIO; unlock: rcu_read_unlock(); if (folio && !xa_is_value(folio)) folio_put(folio); if (start > end) return end; return start; } #ifdef CONFIG_MMU #define MMAP_LOTSAMISS (100) /* * lock_folio_maybe_drop_mmap - lock the page, possibly dropping the mmap_lock * @vmf - the vm_fault for this fault. * @folio - the folio to lock. * @fpin - the pointer to the file we may pin (or is already pinned). * * This works similar to lock_folio_or_retry in that it can drop the * mmap_lock. It differs in that it actually returns the folio locked * if it returns 1 and 0 if it couldn't lock the folio. If we did have * to drop the mmap_lock then fpin will point to the pinned file and * needs to be fput()'ed at a later point. */ static int lock_folio_maybe_drop_mmap(struct vm_fault *vmf, struct folio *folio, struct file **fpin) { if (folio_trylock(folio)) return 1; /* * NOTE! This will make us return with VM_FAULT_RETRY, but with * the fault lock still held. That's how FAULT_FLAG_RETRY_NOWAIT * is supposed to work. We have way too many special cases.. */ if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) return 0; *fpin = maybe_unlock_mmap_for_io(vmf, *fpin); if (vmf->flags & FAULT_FLAG_KILLABLE) { if (__folio_lock_killable(folio)) { /* * We didn't have the right flags to drop the * fault lock, but all fault_handlers only check * for fatal signals if we return VM_FAULT_RETRY, * so we need to drop the fault lock here and * return 0 if we don't have a fpin. */ if (*fpin == NULL) release_fault_lock(vmf); return 0; } } else __folio_lock(folio); return 1; } /* * Synchronous readahead happens when we don't even find a page in the page * cache at all. We don't want to perform IO under the mmap sem, so if we have * to drop the mmap sem we return the file that was pinned in order for us to do * that. If we didn't pin a file then we return NULL. The file that is * returned needs to be fput()'ed when we're done with it. */ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; struct address_space *mapping = file->f_mapping; DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff); struct file *fpin = NULL; unsigned long vm_flags = vmf->vma->vm_flags; unsigned int mmap_miss; #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* Use the readahead code, even if readahead is disabled */ if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); ractl._index &= ~((unsigned long)HPAGE_PMD_NR - 1); ra->size = HPAGE_PMD_NR; /* * Fetch two PMD folios, so we get the chance to actually * readahead, unless we've been told not to. */ if (!(vm_flags & VM_RAND_READ)) ra->size *= 2; ra->async_size = HPAGE_PMD_NR; page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER); return fpin; } #endif /* If we don't want any read-ahead, don't bother */ if (vm_flags & VM_RAND_READ) return fpin; if (!ra->ra_pages) return fpin; if (vm_flags & VM_SEQ_READ) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_sync_ra(&ractl, ra->ra_pages); return fpin; } /* Avoid banging the cache line if not needed */ mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss < MMAP_LOTSAMISS * 10) WRITE_ONCE(ra->mmap_miss, ++mmap_miss); /* * Do we miss much more than hit in this file? If so, * stop bothering with read-ahead. It will only hurt. */ if (mmap_miss > MMAP_LOTSAMISS) return fpin; /* * mmap read-around */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2); ra->size = ra->ra_pages; ra->async_size = ra->ra_pages / 4; ractl._index = ra->start; page_cache_ra_order(&ractl, ra, 0); return fpin; } /* * Asynchronous readahead happens when we find the page and PG_readahead, * so we want to possibly extend the readahead further. We return the file that * was pinned if we have to drop the mmap_lock in order to do IO. */ static struct file *do_async_mmap_readahead(struct vm_fault *vmf, struct folio *folio) { struct file *file = vmf->vma->vm_file; struct file_ra_state *ra = &file->f_ra; DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff); struct file *fpin = NULL; unsigned int mmap_miss; /* If we don't want any read-ahead, don't bother */ if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages) return fpin; mmap_miss = READ_ONCE(ra->mmap_miss); if (mmap_miss) WRITE_ONCE(ra->mmap_miss, --mmap_miss); if (folio_test_readahead(folio)) { fpin = maybe_unlock_mmap_for_io(vmf, fpin); page_cache_async_ra(&ractl, folio, ra->ra_pages); } return fpin; } static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; vm_fault_t ret = 0; pte_t *ptep; /* * We might have COW'ed a pagecache folio and might now have an mlocked * anon folio mapped. The original pagecache folio is not mlocked and * might have been evicted. During a read+clear/modify/write update of * the PTE, such as done in do_numa_page()/change_pte_range(), we * temporarily clear the PTE under PT lock and might detect it here as * "none" when not holding the PT lock. * * Not rechecking the PTE under PT lock could result in an unexpected * major fault in an mlock'ed region. Recheck only for this special * scenario while holding the PT lock, to not degrade non-mlocked * scenarios. Recheck the PTE without PT lock firstly, thereby reducing * the number of times we hold PT lock. */ if (!(vma->vm_flags & VM_LOCKED)) return 0; if (!(vmf->flags & FAULT_FLAG_ORIG_PTE_VALID)) return 0; ptep = pte_offset_map_nolock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl); if (unlikely(!ptep)) return VM_FAULT_NOPAGE; if (unlikely(!pte_none(ptep_get_lockless(ptep)))) { ret = VM_FAULT_NOPAGE; } else { spin_lock(vmf->ptl); if (unlikely(!pte_none(ptep_get(ptep)))) ret = VM_FAULT_NOPAGE; spin_unlock(vmf->ptl); } pte_unmap(ptep); return ret; } /** * filemap_fault - read in file data for page fault handling * @vmf: struct vm_fault containing details of the fault * * filemap_fault() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * * The goto's are kind of ugly, but this streamlines the normal case of having * it in the page cache, and handles the special cases reasonably without * having a lot of duplicated code. * * vma->vm_mm->mmap_lock must be held on entry. * * If our return value has VM_FAULT_RETRY set, it's because the mmap_lock * may be dropped before doing I/O or by lock_folio_maybe_drop_mmap(). * * If our return value does not have VM_FAULT_RETRY set, the mmap_lock * has not been released. * * We never return with VM_FAULT_RETRY and a bit from VM_FAULT_ERROR set. * * Return: bitwise-OR of %VM_FAULT_ codes. */ vm_fault_t filemap_fault(struct vm_fault *vmf) { int error; struct file *file = vmf->vma->vm_file; struct file *fpin = NULL; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; pgoff_t max_idx, index = vmf->pgoff; struct folio *folio; vm_fault_t ret = 0; bool mapping_locked = false; max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) return VM_FAULT_SIGBUS; /* * Do we have something in the page cache already? */ folio = filemap_get_folio(mapping, index); if (likely(!IS_ERR(folio))) { /* * We found the page, so try async readahead before waiting for * the lock. */ if (!(vmf->flags & FAULT_FLAG_TRIED)) fpin = do_async_mmap_readahead(vmf, folio); if (unlikely(!folio_test_uptodate(folio))) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } } else { ret = filemap_fault_recheck_pte_none(vmf); if (unlikely(ret)) return ret; /* No page in the page cache at all */ count_vm_event(PGMAJFAULT); count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT); ret = VM_FAULT_MAJOR; fpin = do_sync_mmap_readahead(vmf); retry_find: /* * See comment in filemap_create_folio() why we need * invalidate_lock */ if (!mapping_locked) { filemap_invalidate_lock_shared(mapping); mapping_locked = true; } folio = __filemap_get_folio(mapping, index, FGP_CREAT|FGP_FOR_MMAP, vmf->gfp_mask); if (IS_ERR(folio)) { if (fpin) goto out_retry; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_OOM; } } if (!lock_folio_maybe_drop_mmap(vmf, folio, &fpin)) goto out_retry; /* Did it get truncated? */ if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); folio_put(folio); goto retry_find; } VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio); /* * We have a locked folio in the page cache, now we need to check * that it's up-to-date. If not, it is going to be due to an error, * or because readahead was otherwise unable to retrieve it. */ if (unlikely(!folio_test_uptodate(folio))) { /* * If the invalidate lock is not held, the folio was in cache * and uptodate and now it is not. Strange but possible since we * didn't hold the page lock all the time. Let's drop * everything, get the invalidate lock and try again. */ if (!mapping_locked) { folio_unlock(folio); folio_put(folio); goto retry_find; } /* * OK, the folio is really not uptodate. This can be because the * VMA has the VM_RAND_READ flag set, or because an error * arose. Let's read it in directly. */ goto page_not_uptodate; } /* * We've made it this far and we had to drop our mmap_lock, now is the * time to return to the upper layer and have it re-find the vma and * redo the fault. */ if (fpin) { folio_unlock(folio); goto out_retry; } if (mapping_locked) filemap_invalidate_unlock_shared(mapping); /* * Found the page and have a reference on it. * We must recheck i_size under page lock. */ max_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (unlikely(index >= max_idx)) { folio_unlock(folio); folio_put(folio); return VM_FAULT_SIGBUS; } vmf->page = folio_file_page(folio, index); return ret | VM_FAULT_LOCKED; page_not_uptodate: /* * Umm, take care of errors if the page isn't up-to-date. * Try to re-read it _once_. We do this synchronously, * because there really aren't any performance issues here * and we need to check for errors. */ fpin = maybe_unlock_mmap_for_io(vmf, fpin); error = filemap_read_folio(file, mapping->a_ops->read_folio, folio); if (fpin) goto out_retry; folio_put(folio); if (!error || error == AOP_TRUNCATED_PAGE) goto retry_find; filemap_invalidate_unlock_shared(mapping); return VM_FAULT_SIGBUS; out_retry: /* * We dropped the mmap_lock, we need to return to the fault handler to * re-find the vma and come back and find our hopefully still populated * page. */ if (!IS_ERR(folio)) folio_put(folio); if (mapping_locked) filemap_invalidate_unlock_shared(mapping); if (fpin) fput(fpin); return ret | VM_FAULT_RETRY; } EXPORT_SYMBOL(filemap_fault); static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio, pgoff_t start) { struct mm_struct *mm = vmf->vma->vm_mm; /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) { folio_unlock(folio); folio_put(folio); return true; } if (pmd_none(*vmf->pmd) && folio_test_pmd_mappable(folio)) { struct page *page = folio_file_page(folio, start); vm_fault_t ret = do_set_pmd(vmf, page); if (!ret) { /* The page is mapped successfully, reference consumed. */ folio_unlock(folio); return true; } } if (pmd_none(*vmf->pmd) && vmf->prealloc_pte) pmd_install(mm, vmf->pmd, &vmf->prealloc_pte); return false; } static struct folio *next_uptodate_folio(struct xa_state *xas, struct address_space *mapping, pgoff_t end_pgoff) { struct folio *folio = xas_next_entry(xas, end_pgoff); unsigned long max_idx; do { if (!folio) return NULL; if (xas_retry(xas, folio)) continue; if (xa_is_value(folio)) continue; if (folio_test_locked(folio)) continue; if (!folio_try_get(folio)) continue; /* Has the page moved or been split? */ if (unlikely(folio != xas_reload(xas))) goto skip; if (!folio_test_uptodate(folio) || folio_test_readahead(folio)) goto skip; if (!folio_trylock(folio)) goto skip; if (folio->mapping != mapping) goto unlock; if (!folio_test_uptodate(folio)) goto unlock; max_idx = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (xas->xa_index >= max_idx) goto unlock; return folio; unlock: folio_unlock(folio); skip: folio_put(folio); } while ((folio = xas_next_entry(xas, end_pgoff)) != NULL); return NULL; } /* * Map page range [start_page, start_page + nr_pages) of folio. * start_page is gotten from start by folio_page(folio, start) */ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, struct folio *folio, unsigned long start, unsigned long addr, unsigned int nr_pages, unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = folio_page(folio, start); unsigned int count = 0; pte_t *old_ptep = vmf->pte; do { if (PageHWPoison(page + count)) goto skip; /* * If there are too many folios that are recently evicted * in a file, they will probably continue to be evicted. * In such situation, read-ahead is only a waste of IO. * Don't decrease mmap_miss in this scenario to make sure * we can stop read-ahead. */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit the * fault-around logic. */ if (!pte_none(ptep_get(&vmf->pte[count]))) goto skip; count++; continue; skip: if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } count++; page += count; vmf->pte += count; addr += count * PAGE_SIZE; count = 0; } while (--nr_pages > 0); if (count) { set_pte_range(vmf, folio, page, count, addr); *rss += count; folio_ref_add(folio, count); if (in_range(vmf->address, addr, count * PAGE_SIZE)) ret = VM_FAULT_NOPAGE; } vmf->pte = old_ptep; return ret; } static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf, struct folio *folio, unsigned long addr, unsigned long *rss, unsigned int *mmap_miss) { vm_fault_t ret = 0; struct page *page = &folio->page; if (PageHWPoison(page)) return ret; /* See comment of filemap_map_folio_range() */ if (!folio_test_workingset(folio)) (*mmap_miss)++; /* * NOTE: If there're PTE markers, we'll leave them to be * handled in the specific fault path, and it'll prohibit * the fault-around logic. */ if (!pte_none(ptep_get(vmf->pte))) return ret; if (vmf->address == addr) ret = VM_FAULT_NOPAGE; set_pte_range(vmf, folio, page, 1, addr); (*rss)++; folio_ref_inc(folio); return ret; } vm_fault_t filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { struct vm_area_struct *vma = vmf->vma; struct file *file = vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t last_pgoff = start_pgoff; unsigned long addr; XA_STATE(xas, &mapping->i_pages, start_pgoff); struct folio *folio; vm_fault_t ret = 0; unsigned long rss = 0; unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved, folio_type; rcu_read_lock(); folio = next_uptodate_folio(&xas, mapping, end_pgoff); if (!folio) goto out; if (filemap_map_pmd(vmf, folio, start_pgoff)) { ret = VM_FAULT_NOPAGE; goto out; } addr = vma->vm_start + ((start_pgoff - vma->vm_pgoff) << PAGE_SHIFT); vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, addr, &vmf->ptl); if (!vmf->pte) { folio_unlock(folio); folio_put(folio); goto out; } folio_type = mm_counter_file(folio); do { unsigned long end; addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT; vmf->pte += xas.xa_index - last_pgoff; last_pgoff = xas.xa_index; end = folio_next_index(folio) - 1; nr_pages = min(end, end_pgoff) - xas.xa_index + 1; if (!folio_test_large(folio)) ret |= filemap_map_order0_folio(vmf, folio, addr, &rss, &mmap_miss); else ret |= filemap_map_folio_range(vmf, folio, xas.xa_index - folio->index, addr, nr_pages, &rss, &mmap_miss); folio_unlock(folio); folio_put(folio); } while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL); add_mm_counter(vma->vm_mm, folio_type, rss); pte_unmap_unlock(vmf->pte, vmf->ptl); out: rcu_read_unlock(); mmap_miss_saved = READ_ONCE(file->f_ra.mmap_miss); if (mmap_miss >= mmap_miss_saved) WRITE_ONCE(file->f_ra.mmap_miss, 0); else WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss_saved - mmap_miss); return ret; } EXPORT_SYMBOL(filemap_map_pages); vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { struct address_space *mapping = vmf->vma->vm_file->f_mapping; struct folio *folio = page_folio(vmf->page); vm_fault_t ret = VM_FAULT_LOCKED; sb_start_pagefault(mapping->host->i_sb); file_update_time(vmf->vma->vm_file); folio_lock(folio); if (folio->mapping != mapping) { folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } /* * We mark the folio dirty already here so that when freeze is in * progress, we are guaranteed that writeback during freezing will * see the dirty folio and writeprotect it again. */ folio_mark_dirty(folio); folio_wait_stable(folio); out: sb_end_pagefault(mapping->host->i_sb); return ret; } const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, }; /* This is used for a general mmap of a disk file */ int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { struct address_space *mapping = file->f_mapping; if (!mapping->a_ops->read_folio) return -ENOEXEC; file_accessed(file); vma->vm_ops = &generic_file_vm_ops; return 0; } /* * This is for filesystems which do not implement ->writepage. */ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { if (vma_is_shared_maywrite(vma)) return -EINVAL; return generic_file_mmap(file, vma); } #else vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) { return -ENOSYS; } #endif /* CONFIG_MMU */ EXPORT_SYMBOL(filemap_page_mkwrite); EXPORT_SYMBOL(generic_file_mmap); EXPORT_SYMBOL(generic_file_readonly_mmap); static struct folio *do_read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file, gfp_t gfp) { struct folio *folio; int err; if (!filler) filler = mapping->a_ops->read_folio; repeat: folio = filemap_get_folio(mapping, index); if (IS_ERR(folio)) { folio = filemap_alloc_folio(gfp, 0); if (!folio) return ERR_PTR(-ENOMEM); err = filemap_add_folio(mapping, folio, index, gfp); if (unlikely(err)) { folio_put(folio); if (err == -EEXIST) goto repeat; /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } goto filler; } if (folio_test_uptodate(folio)) goto out; if (!folio_trylock(folio)) { folio_put_wait_locked(folio, TASK_UNINTERRUPTIBLE); goto repeat; } /* Folio was truncated from mapping */ if (!folio->mapping) { folio_unlock(folio); folio_put(folio); goto repeat; } /* Someone else locked and filled the page in a very small window */ if (folio_test_uptodate(folio)) { folio_unlock(folio); goto out; } filler: err = filemap_read_folio(file, filler, folio); if (err) { folio_put(folio); if (err == AOP_TRUNCATED_PAGE) goto repeat; return ERR_PTR(err); } out: folio_mark_accessed(folio); return folio; } /** * read_cache_folio - Read into page cache, fill it if needed. * @mapping: The address_space to read from. * @index: The index to read. * @filler: Function to perform the read, or NULL to use aops->read_folio(). * @file: Passed to filler function, may be NULL if not required. * * Read one page into the page cache. If it succeeds, the folio returned * will contain @index, but it may not be the first page of the folio. * * If the filler function returns an error, it will be returned to the * caller. * * Context: May sleep. Expects mapping->invalidate_lock to be held. * Return: An uptodate folio on success, ERR_PTR() on failure. */ struct folio *read_cache_folio(struct address_space *mapping, pgoff_t index, filler_t filler, struct file *file) { return do_read_cache_folio(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_folio); /** * mapping_read_folio_gfp - Read into page cache, using specified allocation flags. * @mapping: The address_space for the folio. * @index: The index that the allocated folio will contain. * @gfp: The page allocator flags to use if allocating. * * This is the same as "read_cache_folio(mapping, index, NULL, NULL)", but with * any new memory allocations done using the specified allocation flags. * * The most likely error from this function is EIO, but ENOMEM is * possible and so is EINTR. If ->read_folio returns another error, * that will be returned to the caller. * * The function expects mapping->invalidate_lock to be already held. * * Return: Uptodate folio on success, ERR_PTR() on failure. */ struct folio *mapping_read_folio_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_folio(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(mapping_read_folio_gfp); static struct page *do_read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file, gfp_t gfp) { struct folio *folio; folio = do_read_cache_folio(mapping, index, filler, file, gfp); if (IS_ERR(folio)) return &folio->page; return folio_file_page(folio, index); } struct page *read_cache_page(struct address_space *mapping, pgoff_t index, filler_t *filler, struct file *file) { return do_read_cache_page(mapping, index, filler, file, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(read_cache_page); /** * read_cache_page_gfp - read into page cache, using specified page allocation flags. * @mapping: the page's address_space * @index: the page index * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. * * The function expects mapping->invalidate_lock to be already held. * * Return: up to date page on success, ERR_PTR() on failure. */ struct page *read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp) { return do_read_cache_page(mapping, index, NULL, NULL, gfp); } EXPORT_SYMBOL(read_cache_page_gfp); /* * Warn about a page cache invalidation failure during a direct I/O write. */ static void dio_warn_stale_pagecache(struct file *filp) { static DEFINE_RATELIMIT_STATE(_rs, 86400 * HZ, DEFAULT_RATELIMIT_BURST); char pathname[128]; char *path; errseq_set(&filp->f_mapping->wb_err, -EIO); if (__ratelimit(&_rs)) { path = file_path(filp, pathname, sizeof(pathname)); if (IS_ERR(path)) path = "(unknown)"; pr_crit("Page cache invalidation failure on direct I/O. Possible data corruption due to collision with buffered I/O!\n"); pr_crit("File: %s PID: %d Comm: %.20s\n", path, current->pid, current->comm); } } void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count) { struct address_space *mapping = iocb->ki_filp->f_mapping; if (mapping->nrpages && invalidate_inode_pages2_range(mapping, iocb->ki_pos >> PAGE_SHIFT, (iocb->ki_pos + count - 1) >> PAGE_SHIFT)) dio_warn_stale_pagecache(iocb->ki_filp); } ssize_t generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) { struct address_space *mapping = iocb->ki_filp->f_mapping; size_t write_len = iov_iter_count(from); ssize_t written; /* * If a page can not be invalidated, return 0 to fall back * to buffered write. */ written = kiocb_invalidate_pages(iocb, write_len); if (written) { if (written == -EBUSY) return 0; return written; } written = mapping->a_ops->direct_IO(iocb, from); /* * Finally, try again to invalidate clean pages which might have been * cached by non-direct readahead, or faulted in by get_user_pages() * if the source of the write was an mmap'ed region of the file * we're writing. Either one is a pretty crazy thing to do, * so we don't support it 100%. If this invalidation * fails, tough, the write still worked... * * Most of the time we do not need this since dio_complete() will do * the invalidation for us. However there are some file systems that * do not end up with dio_complete() being called, so let's not break * them by removing it completely. * * Noticeable example is a blkdev_direct_IO(). * * Skip invalidation for async writes or if mapping has no pages. */ if (written > 0) { struct inode *inode = mapping->host; loff_t pos = iocb->ki_pos; kiocb_invalidate_post_direct_write(iocb, written); pos += written; write_len -= written; if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) { i_size_write(inode, pos); mark_inode_dirty(inode); } iocb->ki_pos = pos; } if (written != -EIOCBQUEUED) iov_iter_revert(from, write_len - iov_iter_count(from)); return written; } EXPORT_SYMBOL(generic_file_direct_write); ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i) { struct file *file = iocb->ki_filp; loff_t pos = iocb->ki_pos; struct address_space *mapping = file->f_mapping; const struct address_space_operations *a_ops = mapping->a_ops; size_t chunk = mapping_max_folio_size(mapping); long status = 0; ssize_t written = 0; do { struct page *page; struct folio *folio; size_t offset; /* Offset into folio */ size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ void *fsdata = NULL; bytes = iov_iter_count(i); retry: offset = pos & (chunk - 1); bytes = min(chunk - offset, bytes); balance_dirty_pages_ratelimited(mapping); /* * Bring in the user page that we will copy from _first_. * Otherwise there's a nasty deadlock on copying from the * same page as we're writing to, without it being marked * up-to-date. */ if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) { status = -EFAULT; break; } if (fatal_signal_pending(current)) { status = -EINTR; break; } status = a_ops->write_begin(file, mapping, pos, bytes, &page, &fsdata); if (unlikely(status < 0)) break; folio = page_folio(page); offset = offset_in_folio(folio, pos); if (bytes > folio_size(folio) - offset) bytes = folio_size(folio) - offset; if (mapping_writably_mapped(mapping)) flush_dcache_folio(folio); copied = copy_folio_from_iter_atomic(folio, offset, bytes, i); flush_dcache_folio(folio); status = a_ops->write_end(file, mapping, pos, bytes, copied, page, fsdata); if (unlikely(status != copied)) { iov_iter_revert(i, copied - max(status, 0L)); if (unlikely(status < 0)) break; } cond_resched(); if (unlikely(status == 0)) { /* * A short copy made ->write_end() reject the * thing entirely. Might be memory poisoning * halfway through, might be a race with munmap, * might be severe memory pressure. */ if (chunk > PAGE_SIZE) chunk /= 2; if (copied) { bytes = copied; goto retry; } } else { pos += status; written += status; } } while (iov_iter_count(i)); if (!written) return status; iocb->ki_pos += written; return written; } EXPORT_SYMBOL(generic_perform_write); /** * __generic_file_write_iter - write data to a file * @iocb: IO state structure (file, offset, etc.) * @from: iov_iter with data to write * * This function does all the work needed for actually writing data to a * file. It does all basic checks, removes SUID from the file, updates * modification times and calls proper subroutines depending on whether we * do direct IO or a standard buffered write. * * It expects i_rwsem to be grabbed unless we work on a block device or similar * object which does not need locking at all. * * This function does *not* take care of syncing data in case of O_SYNC write. * A caller has to handle it. This is mainly due to the fact that we want to * avoid syncing under i_rwsem. * * Return: * * number of bytes written, even for truncated writes * * negative error code if no data has been written at all */ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; ret = file_remove_privs(file); if (ret) return ret; ret = file_update_time(file); if (ret) return ret; if (iocb->ki_flags & IOCB_DIRECT) { ret = generic_file_direct_write(iocb, from); /* * If the write stopped short of completing, fall back to * buffered writes. Some filesystems do this for writes to * holes, for example. For DAX files, a buffered write will * not succeed (even if it did, DAX does not handle dirty * page-cache pages correctly). */ if (ret < 0 || !iov_iter_count(from) || IS_DAX(inode)) return ret; return direct_write_fallback(iocb, from, ret, generic_perform_write(iocb, from)); } return generic_perform_write(iocb, from); } EXPORT_SYMBOL(__generic_file_write_iter); /** * generic_file_write_iter - write data to a file * @iocb: IO state structure * @from: iov_iter with data to write * * This is a wrapper around __generic_file_write_iter() to be used by most * filesystems. It takes care of syncing the file in case of O_SYNC file * and acquires i_rwsem as needed. * Return: * * negative error code if no data has been written at all of * vfs_fsync_range() failed for a synchronous write * * number of bytes written, even for truncated writes */ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; ssize_t ret; inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); inode_unlock(inode); if (ret > 0) ret = generic_write_sync(iocb, ret); return ret; } EXPORT_SYMBOL(generic_file_write_iter); /** * filemap_release_folio() - Release fs-specific metadata on a folio. * @folio: The folio which the kernel is trying to free. * @gfp: Memory allocation flags (and I/O mode). * * The address_space is trying to release any data attached to a folio * (presumably at folio->private). * * This will also be called if the private_2 flag is set on a page, * indicating that the folio has other metadata associated with it. * * The @gfp argument specifies whether I/O may be performed to release * this page (__GFP_IO), and whether the call may block * (__GFP_RECLAIM & __GFP_FS). * * Return: %true if the release was successful, otherwise %false. */ bool filemap_release_folio(struct folio *folio, gfp_t gfp) { struct address_space * const mapping = folio->mapping; BUG_ON(!folio_test_locked(folio)); if (!folio_needs_release(folio)) return true; if (folio_test_writeback(folio)) return false; if (mapping && mapping->a_ops->release_folio) return mapping->a_ops->release_folio(folio, gfp); return try_to_free_buffers(folio); } EXPORT_SYMBOL(filemap_release_folio); /** * filemap_invalidate_inode - Invalidate/forcibly write back a range of an inode's pagecache * @inode: The inode to flush * @flush: Set to write back rather than simply invalidate. * @start: First byte to in range. * @end: Last byte in range (inclusive), or LLONG_MAX for everything from start * onwards. * * Invalidate all the folios on an inode that contribute to the specified * range, possibly writing them back first. Whilst the operation is * undertaken, the invalidate lock is held to prevent new folios from being * installed. */ int filemap_invalidate_inode(struct inode *inode, bool flush, loff_t start, loff_t end) { struct address_space *mapping = inode->i_mapping; pgoff_t first = start >> PAGE_SHIFT; pgoff_t last = end >> PAGE_SHIFT; pgoff_t nr = end == LLONG_MAX ? ULONG_MAX : last - first + 1; if (!mapping || !mapping->nrpages || end < start) goto out; /* Prevent new folios from being added to the inode. */ filemap_invalidate_lock(mapping); if (!mapping->nrpages) goto unlock; unmap_mapping_pages(mapping, first, nr, false); /* Write back the data if we're asked to. */ if (flush) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .range_start = start, .range_end = end, }; filemap_fdatawrite_wbc(mapping, &wbc); } /* Wait for writeback to complete on all folios and discard. */ invalidate_inode_pages2_range(mapping, start / PAGE_SIZE, end / PAGE_SIZE); unlock: filemap_invalidate_unlock(mapping); out: return filemap_check_errors(mapping); } EXPORT_SYMBOL_GPL(filemap_invalidate_inode); #ifdef CONFIG_CACHESTAT_SYSCALL /** * filemap_cachestat() - compute the page cache statistics of a mapping * @mapping: The mapping to compute the statistics for. * @first_index: The starting page cache index. * @last_index: The final page index (inclusive). * @cs: the cachestat struct to write the result to. * * This will query the page cache statistics of a mapping in the * page range of [first_index, last_index] (inclusive). The statistics * queried include: number of dirty pages, number of pages marked for * writeback, and the number of (recently) evicted pages. */ static void filemap_cachestat(struct address_space *mapping, pgoff_t first_index, pgoff_t last_index, struct cachestat *cs) { XA_STATE(xas, &mapping->i_pages, first_index); struct folio *folio; /* Flush stats (and potentially sleep) outside the RCU read section. */ mem_cgroup_flush_stats_ratelimited(NULL); rcu_read_lock(); xas_for_each(&xas, folio, last_index) { int order; unsigned long nr_pages; pgoff_t folio_first_index, folio_last_index; /* * Don't deref the folio. It is not pinned, and might * get freed (and reused) underneath us. * * We *could* pin it, but that would be expensive for * what should be a fast and lightweight syscall. * * Instead, derive all information of interest from * the rcu-protected xarray. */ if (xas_retry(&xas, folio)) continue; order = xa_get_order(xas.xa, xas.xa_index); nr_pages = 1 << order; folio_first_index = round_down(xas.xa_index, 1 << order); folio_last_index = folio_first_index + nr_pages - 1; /* Folios might straddle the range boundaries, only count covered pages */ if (folio_first_index < first_index) nr_pages -= first_index - folio_first_index; if (folio_last_index > last_index) nr_pages -= folio_last_index - last_index; if (xa_is_value(folio)) { /* page is evicted */ void *shadow = (void *)folio; bool workingset; /* not used */ cs->nr_evicted += nr_pages; #ifdef CONFIG_SWAP /* implies CONFIG_MMU */ if (shmem_mapping(mapping)) { /* shmem file - in swap cache */ swp_entry_t swp = radix_to_swp_entry(folio); /* swapin error results in poisoned entry */ if (non_swap_entry(swp)) goto resched; /* * Getting a swap entry from the shmem * inode means we beat * shmem_unuse(). rcu_read_lock() * ensures swapoff waits for us before * freeing the swapper space. However, * we can race with swapping and * invalidation, so there might not be * a shadow in the swapcache (yet). */ shadow = get_shadow_from_swap_cache(swp); if (!shadow) goto resched; } #endif if (workingset_test_recent(shadow, true, &workingset, false)) cs->nr_recently_evicted += nr_pages; goto resched; } /* page is in cache */ cs->nr_cache += nr_pages; if (xas_get_mark(&xas, PAGECACHE_TAG_DIRTY)) cs->nr_dirty += nr_pages; if (xas_get_mark(&xas, PAGECACHE_TAG_WRITEBACK)) cs->nr_writeback += nr_pages; resched: if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); } /* * The cachestat(2) system call. * * cachestat() returns the page cache statistics of a file in the * bytes range specified by `off` and `len`: number of cached pages, * number of dirty pages, number of pages marked for writeback, * number of evicted pages, and number of recently evicted pages. * * An evicted page is a page that is previously in the page cache * but has been evicted since. A page is recently evicted if its last * eviction was recent enough that its reentry to the cache would * indicate that it is actively being used by the system, and that * there is memory pressure on the system. * * `off` and `len` must be non-negative integers. If `len` > 0, * the queried range is [`off`, `off` + `len`]. If `len` == 0, * we will query in the range from `off` to the end of the file. * * The `flags` argument is unused for now, but is included for future * extensibility. User should pass 0 (i.e no flag specified). * * Currently, hugetlbfs is not supported. * * Because the status of a page can change after cachestat() checks it * but before it returns to the application, the returned values may * contain stale information. * * return values: * zero - success * -EFAULT - cstat or cstat_range points to an illegal address * -EINVAL - invalid flags * -EBADF - invalid file descriptor * -EOPNOTSUPP - file descriptor is of a hugetlbfs file */ SYSCALL_DEFINE4(cachestat, unsigned int, fd, struct cachestat_range __user *, cstat_range, struct cachestat __user *, cstat, unsigned int, flags) { struct fd f = fdget(fd); struct address_space *mapping; struct cachestat_range csr; struct cachestat cs; pgoff_t first_index, last_index; if (!f.file) return -EBADF; if (copy_from_user(&csr, cstat_range, sizeof(struct cachestat_range))) { fdput(f); return -EFAULT; } /* hugetlbfs is not supported */ if (is_file_hugepages(f.file)) { fdput(f); return -EOPNOTSUPP; } if (flags != 0) { fdput(f); return -EINVAL; } first_index = csr.off >> PAGE_SHIFT; last_index = csr.len == 0 ? ULONG_MAX : (csr.off + csr.len - 1) >> PAGE_SHIFT; memset(&cs, 0, sizeof(struct cachestat)); mapping = f.file->f_mapping; filemap_cachestat(mapping, first_index, last_index, &cs); fdput(f); if (copy_to_user(cstat, &cs, sizeof(struct cachestat))) return -EFAULT; return 0; } #endif /* CONFIG_CACHESTAT_SYSCALL */ |
| 16 16 2 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 | // SPDX-License-Identifier: GPL-2.0-or-later // Copyright (c) 2020, Nikolay Aleksandrov <nikolay@nvidia.com> #include <linux/err.h> #include <linux/export.h> #include <linux/if_ether.h> #include <linux/igmp.h> #include <linux/in.h> #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/log2.h> #include <linux/netdevice.h> #include <linux/netfilter_bridge.h> #include <linux/random.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/inetdevice.h> #include <linux/mroute.h> #include <net/ip.h> #include <net/switchdev.h> #if IS_ENABLED(CONFIG_IPV6) #include <linux/icmpv6.h> #include <net/ipv6.h> #include <net/mld.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #endif #include "br_private.h" #include "br_private_mcast_eht.h" static bool br_multicast_del_eht_set_entry(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr); static void br_multicast_create_eht_set_entry(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr, int filter_mode, bool allow_zero_src); static struct net_bridge_group_eht_host * br_multicast_eht_host_lookup(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr) { struct rb_node *node = pg->eht_host_tree.rb_node; while (node) { struct net_bridge_group_eht_host *this; int result; this = rb_entry(node, struct net_bridge_group_eht_host, rb_node); result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return this; } return NULL; } static int br_multicast_eht_host_filter_mode(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr) { struct net_bridge_group_eht_host *eht_host; eht_host = br_multicast_eht_host_lookup(pg, h_addr); if (!eht_host) return MCAST_INCLUDE; return eht_host->filter_mode; } static struct net_bridge_group_eht_set_entry * br_multicast_eht_set_entry_lookup(struct net_bridge_group_eht_set *eht_set, union net_bridge_eht_addr *h_addr) { struct rb_node *node = eht_set->entry_tree.rb_node; while (node) { struct net_bridge_group_eht_set_entry *this; int result; this = rb_entry(node, struct net_bridge_group_eht_set_entry, rb_node); result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return this; } return NULL; } static struct net_bridge_group_eht_set * br_multicast_eht_set_lookup(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr) { struct rb_node *node = pg->eht_set_tree.rb_node; while (node) { struct net_bridge_group_eht_set *this; int result; this = rb_entry(node, struct net_bridge_group_eht_set, rb_node); result = memcmp(src_addr, &this->src_addr, sizeof(*src_addr)); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return this; } return NULL; } static void __eht_destroy_host(struct net_bridge_group_eht_host *eht_host) { WARN_ON(!hlist_empty(&eht_host->set_entries)); br_multicast_eht_hosts_dec(eht_host->pg); rb_erase(&eht_host->rb_node, &eht_host->pg->eht_host_tree); RB_CLEAR_NODE(&eht_host->rb_node); kfree(eht_host); } static void br_multicast_destroy_eht_set_entry(struct net_bridge_mcast_gc *gc) { struct net_bridge_group_eht_set_entry *set_h; set_h = container_of(gc, struct net_bridge_group_eht_set_entry, mcast_gc); WARN_ON(!RB_EMPTY_NODE(&set_h->rb_node)); timer_shutdown_sync(&set_h->timer); kfree(set_h); } static void br_multicast_destroy_eht_set(struct net_bridge_mcast_gc *gc) { struct net_bridge_group_eht_set *eht_set; eht_set = container_of(gc, struct net_bridge_group_eht_set, mcast_gc); WARN_ON(!RB_EMPTY_NODE(&eht_set->rb_node)); WARN_ON(!RB_EMPTY_ROOT(&eht_set->entry_tree)); timer_shutdown_sync(&eht_set->timer); kfree(eht_set); } static void __eht_del_set_entry(struct net_bridge_group_eht_set_entry *set_h) { struct net_bridge_group_eht_host *eht_host = set_h->h_parent; union net_bridge_eht_addr zero_addr; rb_erase(&set_h->rb_node, &set_h->eht_set->entry_tree); RB_CLEAR_NODE(&set_h->rb_node); hlist_del_init(&set_h->host_list); memset(&zero_addr, 0, sizeof(zero_addr)); if (memcmp(&set_h->h_addr, &zero_addr, sizeof(zero_addr))) eht_host->num_entries--; hlist_add_head(&set_h->mcast_gc.gc_node, &set_h->br->mcast_gc_list); queue_work(system_long_wq, &set_h->br->mcast_gc_work); if (hlist_empty(&eht_host->set_entries)) __eht_destroy_host(eht_host); } static void br_multicast_del_eht_set(struct net_bridge_group_eht_set *eht_set) { struct net_bridge_group_eht_set_entry *set_h; struct rb_node *node; while ((node = rb_first(&eht_set->entry_tree))) { set_h = rb_entry(node, struct net_bridge_group_eht_set_entry, rb_node); __eht_del_set_entry(set_h); } rb_erase(&eht_set->rb_node, &eht_set->pg->eht_set_tree); RB_CLEAR_NODE(&eht_set->rb_node); hlist_add_head(&eht_set->mcast_gc.gc_node, &eht_set->br->mcast_gc_list); queue_work(system_long_wq, &eht_set->br->mcast_gc_work); } void br_multicast_eht_clean_sets(struct net_bridge_port_group *pg) { struct net_bridge_group_eht_set *eht_set; struct rb_node *node; while ((node = rb_first(&pg->eht_set_tree))) { eht_set = rb_entry(node, struct net_bridge_group_eht_set, rb_node); br_multicast_del_eht_set(eht_set); } } static void br_multicast_eht_set_entry_expired(struct timer_list *t) { struct net_bridge_group_eht_set_entry *set_h = from_timer(set_h, t, timer); struct net_bridge *br = set_h->br; spin_lock(&br->multicast_lock); if (RB_EMPTY_NODE(&set_h->rb_node) || timer_pending(&set_h->timer)) goto out; br_multicast_del_eht_set_entry(set_h->eht_set->pg, &set_h->eht_set->src_addr, &set_h->h_addr); out: spin_unlock(&br->multicast_lock); } static void br_multicast_eht_set_expired(struct timer_list *t) { struct net_bridge_group_eht_set *eht_set = from_timer(eht_set, t, timer); struct net_bridge *br = eht_set->br; spin_lock(&br->multicast_lock); if (RB_EMPTY_NODE(&eht_set->rb_node) || timer_pending(&eht_set->timer)) goto out; br_multicast_del_eht_set(eht_set); out: spin_unlock(&br->multicast_lock); } static struct net_bridge_group_eht_host * __eht_lookup_create_host(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, unsigned char filter_mode) { struct rb_node **link = &pg->eht_host_tree.rb_node, *parent = NULL; struct net_bridge_group_eht_host *eht_host; while (*link) { struct net_bridge_group_eht_host *this; int result; this = rb_entry(*link, struct net_bridge_group_eht_host, rb_node); result = memcmp(h_addr, &this->h_addr, sizeof(*h_addr)); parent = *link; if (result < 0) link = &((*link)->rb_left); else if (result > 0) link = &((*link)->rb_right); else return this; } if (br_multicast_eht_hosts_over_limit(pg)) return NULL; eht_host = kzalloc(sizeof(*eht_host), GFP_ATOMIC); if (!eht_host) return NULL; memcpy(&eht_host->h_addr, h_addr, sizeof(*h_addr)); INIT_HLIST_HEAD(&eht_host->set_entries); eht_host->pg = pg; eht_host->filter_mode = filter_mode; rb_link_node(&eht_host->rb_node, parent, link); rb_insert_color(&eht_host->rb_node, &pg->eht_host_tree); br_multicast_eht_hosts_inc(pg); return eht_host; } static struct net_bridge_group_eht_set_entry * __eht_lookup_create_set_entry(struct net_bridge *br, struct net_bridge_group_eht_set *eht_set, struct net_bridge_group_eht_host *eht_host, bool allow_zero_src) { struct rb_node **link = &eht_set->entry_tree.rb_node, *parent = NULL; struct net_bridge_group_eht_set_entry *set_h; while (*link) { struct net_bridge_group_eht_set_entry *this; int result; this = rb_entry(*link, struct net_bridge_group_eht_set_entry, rb_node); result = memcmp(&eht_host->h_addr, &this->h_addr, sizeof(union net_bridge_eht_addr)); parent = *link; if (result < 0) link = &((*link)->rb_left); else if (result > 0) link = &((*link)->rb_right); else return this; } /* always allow auto-created zero entry */ if (!allow_zero_src && eht_host->num_entries >= PG_SRC_ENT_LIMIT) return NULL; set_h = kzalloc(sizeof(*set_h), GFP_ATOMIC); if (!set_h) return NULL; memcpy(&set_h->h_addr, &eht_host->h_addr, sizeof(union net_bridge_eht_addr)); set_h->mcast_gc.destroy = br_multicast_destroy_eht_set_entry; set_h->eht_set = eht_set; set_h->h_parent = eht_host; set_h->br = br; timer_setup(&set_h->timer, br_multicast_eht_set_entry_expired, 0); hlist_add_head(&set_h->host_list, &eht_host->set_entries); rb_link_node(&set_h->rb_node, parent, link); rb_insert_color(&set_h->rb_node, &eht_set->entry_tree); /* we must not count the auto-created zero entry otherwise we won't be * able to track the full list of PG_SRC_ENT_LIMIT entries */ if (!allow_zero_src) eht_host->num_entries++; return set_h; } static struct net_bridge_group_eht_set * __eht_lookup_create_set(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr) { struct rb_node **link = &pg->eht_set_tree.rb_node, *parent = NULL; struct net_bridge_group_eht_set *eht_set; while (*link) { struct net_bridge_group_eht_set *this; int result; this = rb_entry(*link, struct net_bridge_group_eht_set, rb_node); result = memcmp(src_addr, &this->src_addr, sizeof(*src_addr)); parent = *link; if (result < 0) link = &((*link)->rb_left); else if (result > 0) link = &((*link)->rb_right); else return this; } eht_set = kzalloc(sizeof(*eht_set), GFP_ATOMIC); if (!eht_set) return NULL; memcpy(&eht_set->src_addr, src_addr, sizeof(*src_addr)); eht_set->mcast_gc.destroy = br_multicast_destroy_eht_set; eht_set->pg = pg; eht_set->br = pg->key.port->br; eht_set->entry_tree = RB_ROOT; timer_setup(&eht_set->timer, br_multicast_eht_set_expired, 0); rb_link_node(&eht_set->rb_node, parent, link); rb_insert_color(&eht_set->rb_node, &pg->eht_set_tree); return eht_set; } static void br_multicast_ip_src_to_eht_addr(const struct br_ip *src, union net_bridge_eht_addr *dest) { switch (src->proto) { case htons(ETH_P_IP): dest->ip4 = src->src.ip4; break; #if IS_ENABLED(CONFIG_IPV6) case htons(ETH_P_IPV6): memcpy(&dest->ip6, &src->src.ip6, sizeof(struct in6_addr)); break; #endif } } static void br_eht_convert_host_filter_mode(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, int filter_mode) { struct net_bridge_group_eht_host *eht_host; union net_bridge_eht_addr zero_addr; eht_host = br_multicast_eht_host_lookup(pg, h_addr); if (eht_host) eht_host->filter_mode = filter_mode; memset(&zero_addr, 0, sizeof(zero_addr)); switch (filter_mode) { case MCAST_INCLUDE: br_multicast_del_eht_set_entry(pg, &zero_addr, h_addr); break; case MCAST_EXCLUDE: br_multicast_create_eht_set_entry(brmctx, pg, &zero_addr, h_addr, MCAST_EXCLUDE, true); break; } } static void br_multicast_create_eht_set_entry(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr, int filter_mode, bool allow_zero_src) { struct net_bridge_group_eht_set_entry *set_h; struct net_bridge_group_eht_host *eht_host; struct net_bridge *br = pg->key.port->br; struct net_bridge_group_eht_set *eht_set; union net_bridge_eht_addr zero_addr; memset(&zero_addr, 0, sizeof(zero_addr)); if (!allow_zero_src && !memcmp(src_addr, &zero_addr, sizeof(zero_addr))) return; eht_set = __eht_lookup_create_set(pg, src_addr); if (!eht_set) return; eht_host = __eht_lookup_create_host(pg, h_addr, filter_mode); if (!eht_host) goto fail_host; set_h = __eht_lookup_create_set_entry(br, eht_set, eht_host, allow_zero_src); if (!set_h) goto fail_set_entry; mod_timer(&set_h->timer, jiffies + br_multicast_gmi(brmctx)); mod_timer(&eht_set->timer, jiffies + br_multicast_gmi(brmctx)); return; fail_set_entry: if (hlist_empty(&eht_host->set_entries)) __eht_destroy_host(eht_host); fail_host: if (RB_EMPTY_ROOT(&eht_set->entry_tree)) br_multicast_del_eht_set(eht_set); } static bool br_multicast_del_eht_set_entry(struct net_bridge_port_group *pg, union net_bridge_eht_addr *src_addr, union net_bridge_eht_addr *h_addr) { struct net_bridge_group_eht_set_entry *set_h; struct net_bridge_group_eht_set *eht_set; bool set_deleted = false; eht_set = br_multicast_eht_set_lookup(pg, src_addr); if (!eht_set) goto out; set_h = br_multicast_eht_set_entry_lookup(eht_set, h_addr); if (!set_h) goto out; __eht_del_set_entry(set_h); if (RB_EMPTY_ROOT(&eht_set->entry_tree)) { br_multicast_del_eht_set(eht_set); set_deleted = true; } out: return set_deleted; } static void br_multicast_del_eht_host(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr) { struct net_bridge_group_eht_set_entry *set_h; struct net_bridge_group_eht_host *eht_host; struct hlist_node *tmp; eht_host = br_multicast_eht_host_lookup(pg, h_addr); if (!eht_host) return; hlist_for_each_entry_safe(set_h, tmp, &eht_host->set_entries, host_list) br_multicast_del_eht_set_entry(set_h->eht_set->pg, &set_h->eht_set->src_addr, &set_h->h_addr); } /* create new set entries from reports */ static void __eht_create_set_entries(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int filter_mode) { union net_bridge_eht_addr eht_src_addr; u32 src_idx; memset(&eht_src_addr, 0, sizeof(eht_src_addr)); for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); br_multicast_create_eht_set_entry(brmctx, pg, &eht_src_addr, h_addr, filter_mode, false); } } /* delete existing set entries and their (S,G) entries if they were the last */ static bool __eht_del_set_entries(struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size) { union net_bridge_eht_addr eht_src_addr; struct net_bridge_group_src *src_ent; bool changed = false; struct br_ip src_ip; u32 src_idx; memset(&eht_src_addr, 0, sizeof(eht_src_addr)); memset(&src_ip, 0, sizeof(src_ip)); src_ip.proto = pg->key.addr.proto; for (src_idx = 0; src_idx < nsrcs; src_idx++) { memcpy(&eht_src_addr, srcs + (src_idx * addr_size), addr_size); if (!br_multicast_del_eht_set_entry(pg, &eht_src_addr, h_addr)) continue; memcpy(&src_ip, srcs + (src_idx * addr_size), addr_size); src_ent = br_multicast_find_group_src(pg, &src_ip); if (!src_ent) continue; br_multicast_del_group_src(src_ent, true); changed = true; } return changed; } static bool br_multicast_eht_allow(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size) { bool changed = false; switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { case MCAST_INCLUDE: __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_INCLUDE); break; case MCAST_EXCLUDE: changed = __eht_del_set_entries(pg, h_addr, srcs, nsrcs, addr_size); break; } return changed; } static bool br_multicast_eht_block(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size) { bool changed = false; switch (br_multicast_eht_host_filter_mode(pg, h_addr)) { case MCAST_INCLUDE: changed = __eht_del_set_entries(pg, h_addr, srcs, nsrcs, addr_size); break; case MCAST_EXCLUDE: __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_EXCLUDE); break; } return changed; } /* flush_entries is true when changing mode */ static bool __eht_inc_exc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, unsigned char filter_mode, bool to_report) { bool changed = false, flush_entries = to_report; union net_bridge_eht_addr eht_src_addr; if (br_multicast_eht_host_filter_mode(pg, h_addr) != filter_mode) flush_entries = true; memset(&eht_src_addr, 0, sizeof(eht_src_addr)); /* if we're changing mode del host and its entries */ if (flush_entries) br_multicast_del_eht_host(pg, h_addr); __eht_create_set_entries(brmctx, pg, h_addr, srcs, nsrcs, addr_size, filter_mode); /* we can be missing sets only if we've deleted some entries */ if (flush_entries) { struct net_bridge_group_eht_set *eht_set; struct net_bridge_group_src *src_ent; struct hlist_node *tmp; hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) { br_multicast_ip_src_to_eht_addr(&src_ent->addr, &eht_src_addr); if (!br_multicast_eht_set_lookup(pg, &eht_src_addr)) { br_multicast_del_group_src(src_ent, true); changed = true; continue; } /* this is an optimization for TO_INCLUDE where we lower * the set's timeout to LMQT to catch timeout hosts: * - host A (timing out): set entries X, Y * - host B: set entry Z (new from current TO_INCLUDE) * sends BLOCK Z after LMQT but host A's EHT * entries still exist (unless lowered to LMQT * so they can timeout with the S,Gs) * => we wait another LMQT, when we can just delete the * group immediately */ if (!(src_ent->flags & BR_SGRP_F_SEND) || filter_mode != MCAST_INCLUDE || !to_report) continue; eht_set = br_multicast_eht_set_lookup(pg, &eht_src_addr); if (!eht_set) continue; mod_timer(&eht_set->timer, jiffies + br_multicast_lmqt(brmctx)); } } return changed; } static bool br_multicast_eht_inc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, bool to_report) { bool changed; changed = __eht_inc_exc(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_INCLUDE, to_report); br_eht_convert_host_filter_mode(brmctx, pg, h_addr, MCAST_INCLUDE); return changed; } static bool br_multicast_eht_exc(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, size_t addr_size, bool to_report) { bool changed; changed = __eht_inc_exc(brmctx, pg, h_addr, srcs, nsrcs, addr_size, MCAST_EXCLUDE, to_report); br_eht_convert_host_filter_mode(brmctx, pg, h_addr, MCAST_EXCLUDE); return changed; } static bool __eht_ip4_handle(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, int grec_type) { bool changed = false, to_report = false; switch (grec_type) { case IGMPV3_ALLOW_NEW_SOURCES: br_multicast_eht_allow(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32)); break; case IGMPV3_BLOCK_OLD_SOURCES: changed = br_multicast_eht_block(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32)); break; case IGMPV3_CHANGE_TO_INCLUDE: to_report = true; fallthrough; case IGMPV3_MODE_IS_INCLUDE: changed = br_multicast_eht_inc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32), to_report); break; case IGMPV3_CHANGE_TO_EXCLUDE: to_report = true; fallthrough; case IGMPV3_MODE_IS_EXCLUDE: changed = br_multicast_eht_exc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(__be32), to_report); break; } return changed; } #if IS_ENABLED(CONFIG_IPV6) static bool __eht_ip6_handle(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, union net_bridge_eht_addr *h_addr, void *srcs, u32 nsrcs, int grec_type) { bool changed = false, to_report = false; switch (grec_type) { case MLD2_ALLOW_NEW_SOURCES: br_multicast_eht_allow(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr)); break; case MLD2_BLOCK_OLD_SOURCES: changed = br_multicast_eht_block(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr)); break; case MLD2_CHANGE_TO_INCLUDE: to_report = true; fallthrough; case MLD2_MODE_IS_INCLUDE: changed = br_multicast_eht_inc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr), to_report); break; case MLD2_CHANGE_TO_EXCLUDE: to_report = true; fallthrough; case MLD2_MODE_IS_EXCLUDE: changed = br_multicast_eht_exc(brmctx, pg, h_addr, srcs, nsrcs, sizeof(struct in6_addr), to_report); break; } return changed; } #endif /* true means an entry was deleted */ bool br_multicast_eht_handle(const struct net_bridge_mcast *brmctx, struct net_bridge_port_group *pg, void *h_addr, void *srcs, u32 nsrcs, size_t addr_size, int grec_type) { bool eht_enabled = !!(pg->key.port->flags & BR_MULTICAST_FAST_LEAVE); union net_bridge_eht_addr eht_host_addr; bool changed = false; if (!eht_enabled) goto out; memset(&eht_host_addr, 0, sizeof(eht_host_addr)); memcpy(&eht_host_addr, h_addr, addr_size); if (addr_size == sizeof(__be32)) changed = __eht_ip4_handle(brmctx, pg, &eht_host_addr, srcs, nsrcs, grec_type); #if IS_ENABLED(CONFIG_IPV6) else changed = __eht_ip6_handle(brmctx, pg, &eht_host_addr, srcs, nsrcs, grec_type); #endif out: return changed; } int br_multicast_eht_set_hosts_limit(struct net_bridge_port *p, u32 eht_hosts_limit) { struct net_bridge *br = p->br; if (!eht_hosts_limit) return -EINVAL; spin_lock_bh(&br->multicast_lock); p->multicast_eht_hosts_limit = eht_hosts_limit; spin_unlock_bh(&br->multicast_lock); return 0; } |
| 21 22 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 | #include <linux/dcache.h> #include "internal.h" unsigned name_to_int(const struct qstr *qstr) { const char *name = qstr->name; int len = qstr->len; unsigned n = 0; if (len > 1 && *name == '0') goto out; do { unsigned c = *name++ - '0'; if (c > 9) goto out; if (n >= (~0U-9)/10) goto out; n *= 10; n += c; } while (--len > 0); return n; out: return ~0U; } |
| 6 6 6 6 6 6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 | /* * llc_c_ac.c - actions performed during connection state transition. * * Description: * Functions in this module are implementation of connection component actions * Details of actions can be found in IEEE-802.2 standard document. * All functions have one connection and one event as input argument. All of * them return 0 On success and 1 otherwise. * * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/netdevice.h> #include <linux/slab.h> #include <net/llc_conn.h> #include <net/llc_sap.h> #include <net/sock.h> #include <net/llc_c_ev.h> #include <net/llc_c_ac.h> #include <net/llc_c_st.h> #include <net/llc_pdu.h> #include <net/llc.h> static int llc_conn_ac_inc_vs_by_1(struct sock *sk, struct sk_buff *skb); static void llc_process_tmr_ev(struct sock *sk, struct sk_buff *skb); static int llc_conn_ac_data_confirm(struct sock *sk, struct sk_buff *ev); static int llc_conn_ac_inc_npta_value(struct sock *sk, struct sk_buff *skb); static int llc_conn_ac_send_rr_rsp_f_set_ackpf(struct sock *sk, struct sk_buff *skb); static int llc_conn_ac_set_p_flag_1(struct sock *sk, struct sk_buff *skb); #define INCORRECT 0 int llc_conn_ac_clear_remote_busy(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); if (llc->remote_busy_flag) { u8 nr; struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); llc->remote_busy_flag = 0; del_timer(&llc->busy_state_timer.timer); nr = LLC_I_GET_NR(pdu); llc_conn_resend_i_pdu_as_cmd(sk, nr, 0); } return 0; } int llc_conn_ac_conn_ind(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->ind_prim = LLC_CONN_PRIM; return 0; } int llc_conn_ac_conn_confirm(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->cfm_prim = LLC_CONN_PRIM; return 0; } static int llc_conn_ac_data_confirm(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->cfm_prim = LLC_DATA_PRIM; return 0; } int llc_conn_ac_data_ind(struct sock *sk, struct sk_buff *skb) { llc_conn_rtn_pdu(sk, skb); return 0; } int llc_conn_ac_disc_ind(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); u8 reason = 0; int rc = 0; if (ev->type == LLC_CONN_EV_TYPE_PDU) { struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); if (LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_RSP(pdu) == LLC_2_PDU_RSP_DM) reason = LLC_DISC_REASON_RX_DM_RSP_PDU; else if (LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_CMD(pdu) == LLC_2_PDU_CMD_DISC) reason = LLC_DISC_REASON_RX_DISC_CMD_PDU; } else if (ev->type == LLC_CONN_EV_TYPE_ACK_TMR) reason = LLC_DISC_REASON_ACK_TMR_EXP; else rc = -EINVAL; if (!rc) { ev->reason = reason; ev->ind_prim = LLC_DISC_PRIM; } return rc; } int llc_conn_ac_disc_confirm(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->reason = ev->status; ev->cfm_prim = LLC_DISC_PRIM; return 0; } int llc_conn_ac_rst_ind(struct sock *sk, struct sk_buff *skb) { u8 reason = 0; int rc = 1; struct llc_conn_state_ev *ev = llc_conn_ev(skb); struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); struct llc_sock *llc = llc_sk(sk); switch (ev->type) { case LLC_CONN_EV_TYPE_PDU: if (LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_RSP(pdu) == LLC_2_PDU_RSP_FRMR) { reason = LLC_RESET_REASON_LOCAL; rc = 0; } else if (LLC_PDU_IS_CMD(pdu) && LLC_PDU_TYPE_IS_U(pdu) && LLC_U_PDU_CMD(pdu) == LLC_2_PDU_CMD_SABME) { reason = LLC_RESET_REASON_REMOTE; rc = 0; } break; case LLC_CONN_EV_TYPE_ACK_TMR: case LLC_CONN_EV_TYPE_P_TMR: case LLC_CONN_EV_TYPE_REJ_TMR: case LLC_CONN_EV_TYPE_BUSY_TMR: if (llc->retry_count > llc->n2) { reason = LLC_RESET_REASON_LOCAL; rc = 0; } break; } if (!rc) { ev->reason = reason; ev->ind_prim = LLC_RESET_PRIM; } return rc; } int llc_conn_ac_rst_confirm(struct sock *sk, struct sk_buff *skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); ev->reason = 0; ev->cfm_prim = LLC_RESET_PRIM; return 0; } int llc_conn_ac_clear_remote_busy_if_f_eq_1(struct sock *sk, struct sk_buff *skb) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); if (LLC_PDU_IS_RSP(pdu) && LLC_PDU_TYPE_IS_I(pdu) && LLC_I_PF_IS_1(pdu) && llc_sk(sk)->ack_pf) llc_conn_ac_clear_remote_busy(sk, skb); return 0; } int llc_conn_ac_stop_rej_tmr_if_data_flag_eq_2(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); if (llc->data_flag == 2) del_timer(&llc->rej_sent_timer.timer); return 0; } int llc_conn_ac_send_disc_cmd_p_set_x(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_U, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_disc_cmd(nskb, 1); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); llc_conn_ac_set_p_flag_1(sk, skb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_dm_rsp_f_set_p(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_U, 0); if (nskb) { struct llc_sap *sap = llc->sap; u8 f_bit; llc_pdu_decode_pf_bit(skb, &f_bit); llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_dm_rsp(nskb, f_bit); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_dm_rsp_f_set_1(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_U, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_dm_rsp(nskb, 1); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_frmr_rsp_f_set_x(struct sock *sk, struct sk_buff *skb) { u8 f_bit; int rc = -ENOBUFS; struct sk_buff *nskb; struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); struct llc_sock *llc = llc_sk(sk); llc->rx_pdu_hdr = *((u32 *)pdu); if (LLC_PDU_IS_CMD(pdu)) llc_pdu_decode_pf_bit(skb, &f_bit); else f_bit = 0; nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_U, sizeof(struct llc_frmr_info)); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_frmr_rsp(nskb, pdu, f_bit, llc->vS, llc->vR, INCORRECT); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_resend_frmr_rsp_f_set_0(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_U, sizeof(struct llc_frmr_info)); if (nskb) { struct llc_sap *sap = llc->sap; struct llc_pdu_sn *pdu = (struct llc_pdu_sn *)&llc->rx_pdu_hdr; llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_frmr_rsp(nskb, pdu, 0, llc->vS, llc->vR, INCORRECT); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_resend_frmr_rsp_f_set_p(struct sock *sk, struct sk_buff *skb) { u8 f_bit; int rc = -ENOBUFS; struct sk_buff *nskb; struct llc_sock *llc = llc_sk(sk); llc_pdu_decode_pf_bit(skb, &f_bit); nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_U, sizeof(struct llc_frmr_info)); if (nskb) { struct llc_sap *sap = llc->sap; struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_frmr_rsp(nskb, pdu, f_bit, llc->vS, llc->vR, INCORRECT); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_i_cmd_p_set_1(struct sock *sk, struct sk_buff *skb) { int rc; struct llc_sock *llc = llc_sk(sk); struct llc_sap *sap = llc->sap; llc_pdu_header_init(skb, LLC_PDU_TYPE_I, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_i_cmd(skb, 1, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; } static int llc_conn_ac_send_i_cmd_p_set_0(struct sock *sk, struct sk_buff *skb) { int rc; struct llc_sock *llc = llc_sk(sk); struct llc_sap *sap = llc->sap; llc_pdu_header_init(skb, LLC_PDU_TYPE_I, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; } int llc_conn_ac_send_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) { int rc; struct llc_sock *llc = llc_sk(sk); struct llc_sap *sap = llc->sap; llc_pdu_header_init(skb, LLC_PDU_TYPE_I, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return 0; } int llc_conn_ac_resend_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); u8 nr = LLC_I_GET_NR(pdu); llc_conn_resend_i_pdu_as_cmd(sk, nr, 0); return 0; } int llc_conn_ac_resend_i_xxx_x_set_0_or_send_rr(struct sock *sk, struct sk_buff *skb) { u8 nr; struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_U, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rr_rsp(nskb, 0, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) llc_conn_send_pdu(sk, nskb); else kfree_skb(skb); } if (rc) { nr = LLC_I_GET_NR(pdu); rc = 0; llc_conn_resend_i_pdu_as_cmd(sk, nr, 0); } return rc; } int llc_conn_ac_resend_i_rsp_f_set_1(struct sock *sk, struct sk_buff *skb) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); u8 nr = LLC_I_GET_NR(pdu); llc_conn_resend_i_pdu_as_rsp(sk, nr, 1); return 0; } int llc_conn_ac_send_rej_cmd_p_set_1(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_rej_cmd(nskb, 1, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_rej_rsp_f_set_1(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rej_rsp(nskb, 1, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_rej_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rej_rsp(nskb, 0, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_rnr_cmd_p_set_1(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_rnr_cmd(nskb, 1, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_rnr_rsp_f_set_1(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rnr_rsp(nskb, 1, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_rnr_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rnr_rsp(nskb, 0, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_set_remote_busy(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); if (!llc->remote_busy_flag) { llc->remote_busy_flag = 1; mod_timer(&llc->busy_state_timer.timer, jiffies + llc->busy_state_timer.expire); } return 0; } int llc_conn_ac_opt_send_rnr_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rnr_rsp(nskb, 0, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_rr_cmd_p_set_1(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_rr_cmd(nskb, 1, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_rr_rsp_f_set_1(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; u8 f_bit = 1; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rr_rsp(nskb, f_bit, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_ack_rsp_f_set_1(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rr_rsp(nskb, 1, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_rr_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rr_rsp(nskb, 0, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_ack_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rr_rsp(nskb, 0, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } void llc_conn_set_p_flag(struct sock *sk, u8 value) { int state_changed = llc_sk(sk)->p_flag && !value; llc_sk(sk)->p_flag = value; if (state_changed) sk->sk_state_change(sk); } int llc_conn_ac_send_sabme_cmd_p_set_x(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_U, 0); if (nskb) { struct llc_sap *sap = llc->sap; const u8 *dmac = llc->daddr.mac; if (llc->dev->flags & IFF_LOOPBACK) dmac = llc->dev->dev_addr; llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_sabme_cmd(nskb, 1); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, dmac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); llc_conn_set_p_flag(sk, 1); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_send_ua_rsp_f_set_p(struct sock *sk, struct sk_buff *skb) { u8 f_bit; int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_U, 0); llc_pdu_decode_pf_bit(skb, &f_bit); if (nskb) { struct llc_sap *sap = llc->sap; nskb->dev = llc->dev; llc_pdu_header_init(nskb, LLC_PDU_TYPE_U, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_ua_rsp(nskb, f_bit); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } int llc_conn_ac_set_s_flag_0(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->s_flag = 0; return 0; } int llc_conn_ac_set_s_flag_1(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->s_flag = 1; return 0; } int llc_conn_ac_start_p_timer(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); llc_conn_set_p_flag(sk, 1); mod_timer(&llc->pf_cycle_timer.timer, jiffies + llc->pf_cycle_timer.expire); return 0; } /** * llc_conn_ac_send_ack_if_needed - check if ack is needed * @sk: current connection structure * @skb: current event * * Checks number of received PDUs which have not been acknowledged, yet, * If number of them reaches to "npta"(Number of PDUs To Acknowledge) then * sends an RR response as acknowledgement for them. Returns 0 for * success, 1 otherwise. */ int llc_conn_ac_send_ack_if_needed(struct sock *sk, struct sk_buff *skb) { u8 pf_bit; struct llc_sock *llc = llc_sk(sk); llc_pdu_decode_pf_bit(skb, &pf_bit); llc->ack_pf |= pf_bit & 1; if (!llc->ack_must_be_send) { llc->first_pdu_Ns = llc->vR; llc->ack_must_be_send = 1; llc->ack_pf = pf_bit & 1; } if (((llc->vR - llc->first_pdu_Ns + 1 + LLC_2_SEQ_NBR_MODULO) % LLC_2_SEQ_NBR_MODULO) >= llc->npta) { llc_conn_ac_send_rr_rsp_f_set_ackpf(sk, skb); llc->ack_must_be_send = 0; llc->ack_pf = 0; llc_conn_ac_inc_npta_value(sk, skb); } return 0; } /** * llc_conn_ac_rst_sendack_flag - resets ack_must_be_send flag * @sk: current connection structure * @skb: current event * * This action resets ack_must_be_send flag of given connection, this flag * indicates if there is any PDU which has not been acknowledged yet. * Returns 0 for success, 1 otherwise. */ int llc_conn_ac_rst_sendack_flag(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->ack_must_be_send = llc_sk(sk)->ack_pf = 0; return 0; } /** * llc_conn_ac_send_i_rsp_f_set_ackpf - acknowledge received PDUs * @sk: current connection structure * @skb: current event * * Sends an I response PDU with f-bit set to ack_pf flag as acknowledge to * all received PDUs which have not been acknowledged, yet. ack_pf flag is * set to one if one PDU with p-bit set to one is received. Returns 0 for * success, 1 otherwise. */ static int llc_conn_ac_send_i_rsp_f_set_ackpf(struct sock *sk, struct sk_buff *skb) { int rc; struct llc_sock *llc = llc_sk(sk); struct llc_sap *sap = llc->sap; llc_pdu_header_init(skb, LLC_PDU_TYPE_I, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_i_cmd(skb, llc->ack_pf, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; } /** * llc_conn_ac_send_i_as_ack - sends an I-format PDU to acknowledge rx PDUs * @sk: current connection structure. * @skb: current event. * * This action sends an I-format PDU as acknowledge to received PDUs which * have not been acknowledged, yet, if there is any. By using of this * action number of acknowledgements decreases, this technic is called * piggy backing. Returns 0 for success, 1 otherwise. */ int llc_conn_ac_send_i_as_ack(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); int ret; if (llc->ack_must_be_send) { ret = llc_conn_ac_send_i_rsp_f_set_ackpf(sk, skb); llc->ack_must_be_send = 0 ; llc->ack_pf = 0; } else { ret = llc_conn_ac_send_i_cmd_p_set_0(sk, skb); } return ret; } /** * llc_conn_ac_send_rr_rsp_f_set_ackpf - ack all rx PDUs not yet acked * @sk: current connection structure. * @skb: current event. * * This action sends an RR response with f-bit set to ack_pf flag as * acknowledge to all received PDUs which have not been acknowledged, yet, * if there is any. ack_pf flag indicates if a PDU has been received with * p-bit set to one. Returns 0 for success, 1 otherwise. */ static int llc_conn_ac_send_rr_rsp_f_set_ackpf(struct sock *sk, struct sk_buff *skb) { int rc = -ENOBUFS; struct llc_sock *llc = llc_sk(sk); struct sk_buff *nskb = llc_alloc_frame(sk, llc->dev, LLC_PDU_TYPE_S, 0); if (nskb) { struct llc_sap *sap = llc->sap; llc_pdu_header_init(nskb, LLC_PDU_TYPE_S, sap->laddr.lsap, llc->daddr.lsap, LLC_PDU_RSP); llc_pdu_init_as_rr_rsp(nskb, llc->ack_pf, llc->vR); rc = llc_mac_hdr_init(nskb, llc->dev->dev_addr, llc->daddr.mac); if (unlikely(rc)) goto free; llc_conn_send_pdu(sk, nskb); } out: return rc; free: kfree_skb(nskb); goto out; } /** * llc_conn_ac_inc_npta_value - tries to make value of npta greater * @sk: current connection structure. * @skb: current event. * * After "inc_cntr" times calling of this action, "npta" increase by one. * this action tries to make vale of "npta" greater as possible; number of * acknowledgements decreases by increasing of "npta". Returns 0 for * success, 1 otherwise. */ static int llc_conn_ac_inc_npta_value(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); if (!llc->inc_cntr) { llc->dec_step = 0; llc->dec_cntr = llc->inc_cntr = 2; ++llc->npta; if (llc->npta > (u8) ~LLC_2_SEQ_NBR_MODULO) llc->npta = (u8) ~LLC_2_SEQ_NBR_MODULO; } else --llc->inc_cntr; return 0; } /** * llc_conn_ac_adjust_npta_by_rr - decreases "npta" by one * @sk: current connection structure. * @skb: current event. * * After receiving "dec_cntr" times RR command, this action decreases * "npta" by one. Returns 0 for success, 1 otherwise. */ int llc_conn_ac_adjust_npta_by_rr(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); if (!llc->connect_step && !llc->remote_busy_flag) { if (!llc->dec_step) { if (!llc->dec_cntr) { llc->inc_cntr = llc->dec_cntr = 2; if (llc->npta > 0) llc->npta = llc->npta - 1; } else llc->dec_cntr -=1; } } else llc->connect_step = 0 ; return 0; } /** * llc_conn_ac_adjust_npta_by_rnr - decreases "npta" by one * @sk: current connection structure. * @skb: current event. * * After receiving "dec_cntr" times RNR command, this action decreases * "npta" by one. Returns 0 for success, 1 otherwise. */ int llc_conn_ac_adjust_npta_by_rnr(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); if (llc->remote_busy_flag) if (!llc->dec_step) { if (!llc->dec_cntr) { llc->inc_cntr = llc->dec_cntr = 2; if (llc->npta > 0) --llc->npta; } else --llc->dec_cntr; } return 0; } /** * llc_conn_ac_dec_tx_win_size - decreases tx window size * @sk: current connection structure. * @skb: current event. * * After receiving of a REJ command or response, transmit window size is * decreased by number of PDUs which are outstanding yet. Returns 0 for * success, 1 otherwise. */ int llc_conn_ac_dec_tx_win_size(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); u8 unacked_pdu = skb_queue_len(&llc->pdu_unack_q); if (llc->k - unacked_pdu < 1) llc->k = 1; else llc->k -= unacked_pdu; return 0; } /** * llc_conn_ac_inc_tx_win_size - tx window size is inc by 1 * @sk: current connection structure. * @skb: current event. * * After receiving an RR response with f-bit set to one, transmit window * size is increased by one. Returns 0 for success, 1 otherwise. */ int llc_conn_ac_inc_tx_win_size(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); llc->k += 1; if (llc->k > (u8) ~LLC_2_SEQ_NBR_MODULO) llc->k = (u8) ~LLC_2_SEQ_NBR_MODULO; return 0; } int llc_conn_ac_stop_all_timers(struct sock *sk, struct sk_buff *skb) { llc_sk_stop_all_timers(sk, false); return 0; } int llc_conn_ac_stop_other_timers(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); del_timer(&llc->rej_sent_timer.timer); del_timer(&llc->pf_cycle_timer.timer); del_timer(&llc->busy_state_timer.timer); llc->ack_must_be_send = 0; llc->ack_pf = 0; return 0; } int llc_conn_ac_start_ack_timer(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); mod_timer(&llc->ack_timer.timer, jiffies + llc->ack_timer.expire); return 0; } int llc_conn_ac_start_rej_timer(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); mod_timer(&llc->rej_sent_timer.timer, jiffies + llc->rej_sent_timer.expire); return 0; } int llc_conn_ac_start_ack_tmr_if_not_running(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); if (!timer_pending(&llc->ack_timer.timer)) mod_timer(&llc->ack_timer.timer, jiffies + llc->ack_timer.expire); return 0; } int llc_conn_ac_stop_ack_timer(struct sock *sk, struct sk_buff *skb) { del_timer(&llc_sk(sk)->ack_timer.timer); return 0; } int llc_conn_ac_stop_p_timer(struct sock *sk, struct sk_buff *skb) { struct llc_sock *llc = llc_sk(sk); del_timer(&llc->pf_cycle_timer.timer); llc_conn_set_p_flag(sk, 0); return 0; } int llc_conn_ac_stop_rej_timer(struct sock *sk, struct sk_buff *skb) { del_timer(&llc_sk(sk)->rej_sent_timer.timer); return 0; } int llc_conn_ac_upd_nr_received(struct sock *sk, struct sk_buff *skb) { int acked; u16 unacked = 0; struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); struct llc_sock *llc = llc_sk(sk); llc->last_nr = PDU_SUPV_GET_Nr(pdu); acked = llc_conn_remove_acked_pdus(sk, llc->last_nr, &unacked); /* On loopback we don't queue I frames in unack_pdu_q queue. */ if (acked > 0 || (llc->dev->flags & IFF_LOOPBACK)) { llc->retry_count = 0; del_timer(&llc->ack_timer.timer); if (llc->failed_data_req) { /* already, we did not accept data from upper layer * (tx_window full or unacceptable state). Now, we * can send data and must inform to upper layer. */ llc->failed_data_req = 0; llc_conn_ac_data_confirm(sk, skb); } if (unacked) mod_timer(&llc->ack_timer.timer, jiffies + llc->ack_timer.expire); } else if (llc->failed_data_req) { u8 f_bit; llc_pdu_decode_pf_bit(skb, &f_bit); if (f_bit == 1) { llc->failed_data_req = 0; llc_conn_ac_data_confirm(sk, skb); } } return 0; } int llc_conn_ac_upd_p_flag(struct sock *sk, struct sk_buff *skb) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); if (LLC_PDU_IS_RSP(pdu)) { u8 f_bit; llc_pdu_decode_pf_bit(skb, &f_bit); if (f_bit) { llc_conn_set_p_flag(sk, 0); llc_conn_ac_stop_p_timer(sk, skb); } } return 0; } int llc_conn_ac_set_data_flag_2(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->data_flag = 2; return 0; } int llc_conn_ac_set_data_flag_0(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->data_flag = 0; return 0; } int llc_conn_ac_set_data_flag_1(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->data_flag = 1; return 0; } int llc_conn_ac_set_data_flag_1_if_data_flag_eq_0(struct sock *sk, struct sk_buff *skb) { if (!llc_sk(sk)->data_flag) llc_sk(sk)->data_flag = 1; return 0; } int llc_conn_ac_set_p_flag_0(struct sock *sk, struct sk_buff *skb) { llc_conn_set_p_flag(sk, 0); return 0; } static int llc_conn_ac_set_p_flag_1(struct sock *sk, struct sk_buff *skb) { llc_conn_set_p_flag(sk, 1); return 0; } int llc_conn_ac_set_remote_busy_0(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->remote_busy_flag = 0; return 0; } int llc_conn_ac_set_cause_flag_0(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->cause_flag = 0; return 0; } int llc_conn_ac_set_cause_flag_1(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->cause_flag = 1; return 0; } int llc_conn_ac_set_retry_cnt_0(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->retry_count = 0; return 0; } int llc_conn_ac_inc_retry_cnt_by_1(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->retry_count++; return 0; } int llc_conn_ac_set_vr_0(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->vR = 0; return 0; } int llc_conn_ac_inc_vr_by_1(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->vR = PDU_GET_NEXT_Vr(llc_sk(sk)->vR); return 0; } int llc_conn_ac_set_vs_0(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->vS = 0; return 0; } int llc_conn_ac_set_vs_nr(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->vS = llc_sk(sk)->last_nr; return 0; } static int llc_conn_ac_inc_vs_by_1(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->vS = (llc_sk(sk)->vS + 1) % LLC_2_SEQ_NBR_MODULO; return 0; } static void llc_conn_tmr_common_cb(struct sock *sk, u8 type) { struct sk_buff *skb = alloc_skb(0, GFP_ATOMIC); bh_lock_sock(sk); if (skb) { struct llc_conn_state_ev *ev = llc_conn_ev(skb); skb_set_owner_r(skb, sk); ev->type = type; llc_process_tmr_ev(sk, skb); } bh_unlock_sock(sk); } void llc_conn_pf_cycle_tmr_cb(struct timer_list *t) { struct llc_sock *llc = from_timer(llc, t, pf_cycle_timer.timer); llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_P_TMR); } void llc_conn_busy_tmr_cb(struct timer_list *t) { struct llc_sock *llc = from_timer(llc, t, busy_state_timer.timer); llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_BUSY_TMR); } void llc_conn_ack_tmr_cb(struct timer_list *t) { struct llc_sock *llc = from_timer(llc, t, ack_timer.timer); llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_ACK_TMR); } void llc_conn_rej_tmr_cb(struct timer_list *t) { struct llc_sock *llc = from_timer(llc, t, rej_sent_timer.timer); llc_conn_tmr_common_cb(&llc->sk, LLC_CONN_EV_TYPE_REJ_TMR); } int llc_conn_ac_rst_vs(struct sock *sk, struct sk_buff *skb) { llc_sk(sk)->X = llc_sk(sk)->vS; llc_conn_ac_set_vs_nr(sk, skb); return 0; } int llc_conn_ac_upd_vs(struct sock *sk, struct sk_buff *skb) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); u8 nr = PDU_SUPV_GET_Nr(pdu); if (llc_circular_between(llc_sk(sk)->vS, nr, llc_sk(sk)->X)) llc_conn_ac_set_vs_nr(sk, skb); return 0; } /* * Non-standard actions; these not contained in IEEE specification; for * our own usage */ /** * llc_conn_disc - removes connection from SAP list and frees it * @sk: closed connection * @skb: occurred event */ int llc_conn_disc(struct sock *sk, struct sk_buff *skb) { /* FIXME: this thing seems to want to die */ return 0; } /** * llc_conn_reset - resets connection * @sk : reseting connection. * @skb: occurred event. * * Stop all timers, empty all queues and reset all flags. */ int llc_conn_reset(struct sock *sk, struct sk_buff *skb) { llc_sk_reset(sk); return 0; } /** * llc_circular_between - designates that b is between a and c or not * @a: lower bound * @b: element to see if is between a and b * @c: upper bound * * This function designates that b is between a and c or not (for example, * 0 is between 127 and 1). Returns 1 if b is between a and c, 0 * otherwise. */ u8 llc_circular_between(u8 a, u8 b, u8 c) { b = b - a; c = c - a; return b <= c; } /** * llc_process_tmr_ev - timer backend * @sk: active connection * @skb: occurred event * * This function is called from timer callback functions. When connection * is busy (during sending a data frame) timer expiration event must be * queued. Otherwise this event can be sent to connection state machine. * Queued events will process by llc_backlog_rcv function after sending * data frame. */ static void llc_process_tmr_ev(struct sock *sk, struct sk_buff *skb) { if (llc_sk(sk)->state == LLC_CONN_OUT_OF_SVC) { printk(KERN_WARNING "%s: timer called on closed connection\n", __func__); kfree_skb(skb); } else { if (!sock_owned_by_user(sk)) llc_conn_state_process(sk, skb); else { llc_set_backlog_type(skb, LLC_EVENT); __sk_add_backlog(sk, skb); } } } |
| 4 2 2 4 4 4 2 2 2 3 3 4 4 2 2 2 2 2 2 4 4 4 4 4 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 | /* * Copyright (c) 2004, 2005 Intel Corporation. All rights reserved. * Copyright (c) 2004 Topspin Corporation. All rights reserved. * Copyright (c) 2004, 2005 Voltaire Corporation. All rights reserved. * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved. * Copyright (c) 2005 Open Grid Computing, Inc. All rights reserved. * Copyright (c) 2005 Network Appliance, Inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/dma-mapping.h> #include <linux/err.h> #include <linux/idr.h> #include <linux/interrupt.h> #include <linux/rbtree.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/workqueue.h> #include <linux/completion.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/sysctl.h> #include <rdma/iw_cm.h> #include <rdma/ib_addr.h> #include <rdma/iw_portmap.h> #include <rdma/rdma_netlink.h> #include "iwcm.h" MODULE_AUTHOR("Tom Tucker"); MODULE_DESCRIPTION("iWARP CM"); MODULE_LICENSE("Dual BSD/GPL"); static const char * const iwcm_rej_reason_strs[] = { [ECONNRESET] = "reset by remote host", [ECONNREFUSED] = "refused by remote application", [ETIMEDOUT] = "setup timeout", }; const char *__attribute_const__ iwcm_reject_msg(int reason) { size_t index; /* iWARP uses negative errnos */ index = -reason; if (index < ARRAY_SIZE(iwcm_rej_reason_strs) && iwcm_rej_reason_strs[index]) return iwcm_rej_reason_strs[index]; else return "unrecognized reason"; } EXPORT_SYMBOL(iwcm_reject_msg); static struct rdma_nl_cbs iwcm_nl_cb_table[RDMA_NL_IWPM_NUM_OPS] = { [RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb}, [RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb}, [RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb}, [RDMA_NL_IWPM_REMOTE_INFO] = {.dump = iwpm_remote_info_cb}, [RDMA_NL_IWPM_HANDLE_ERR] = {.dump = iwpm_mapping_error_cb}, [RDMA_NL_IWPM_MAPINFO] = {.dump = iwpm_mapping_info_cb}, [RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb}, [RDMA_NL_IWPM_HELLO] = {.dump = iwpm_hello_cb} }; static struct workqueue_struct *iwcm_wq; struct iwcm_work { struct work_struct work; struct iwcm_id_private *cm_id; struct list_head list; struct iw_cm_event event; struct list_head free_list; }; static unsigned int default_backlog = 256; static struct ctl_table_header *iwcm_ctl_table_hdr; static struct ctl_table iwcm_ctl_table[] = { { .procname = "default_backlog", .data = &default_backlog, .maxlen = sizeof(default_backlog), .mode = 0644, .proc_handler = proc_dointvec, }, }; /* * The following services provide a mechanism for pre-allocating iwcm_work * elements. The design pre-allocates them based on the cm_id type: * LISTENING IDS: Get enough elements preallocated to handle the * listen backlog. * ACTIVE IDS: 4: CONNECT_REPLY, ESTABLISHED, DISCONNECT, CLOSE * PASSIVE IDS: 3: ESTABLISHED, DISCONNECT, CLOSE * * Allocating them in connect and listen avoids having to deal * with allocation failures on the event upcall from the provider (which * is called in the interrupt context). * * One exception is when creating the cm_id for incoming connection requests. * There are two cases: * 1) in the event upcall, cm_event_handler(), for a listening cm_id. If * the backlog is exceeded, then no more connection request events will * be processed. cm_event_handler() returns -ENOMEM in this case. Its up * to the provider to reject the connection request. * 2) in the connection request workqueue handler, cm_conn_req_handler(). * If work elements cannot be allocated for the new connect request cm_id, * then IWCM will call the provider reject method. This is ok since * cm_conn_req_handler() runs in the workqueue thread context. */ static struct iwcm_work *get_work(struct iwcm_id_private *cm_id_priv) { struct iwcm_work *work; if (list_empty(&cm_id_priv->work_free_list)) return NULL; work = list_first_entry(&cm_id_priv->work_free_list, struct iwcm_work, free_list); list_del_init(&work->free_list); return work; } static void put_work(struct iwcm_work *work) { list_add(&work->free_list, &work->cm_id->work_free_list); } static void dealloc_work_entries(struct iwcm_id_private *cm_id_priv) { struct list_head *e, *tmp; list_for_each_safe(e, tmp, &cm_id_priv->work_free_list) { list_del(e); kfree(list_entry(e, struct iwcm_work, free_list)); } } static int alloc_work_entries(struct iwcm_id_private *cm_id_priv, int count) { struct iwcm_work *work; BUG_ON(!list_empty(&cm_id_priv->work_free_list)); while (count--) { work = kmalloc(sizeof(struct iwcm_work), GFP_KERNEL); if (!work) { dealloc_work_entries(cm_id_priv); return -ENOMEM; } work->cm_id = cm_id_priv; INIT_LIST_HEAD(&work->list); put_work(work); } return 0; } /* * Save private data from incoming connection requests to * iw_cm_event, so the low level driver doesn't have to. Adjust * the event ptr to point to the local copy. */ static int copy_private_data(struct iw_cm_event *event) { void *p; p = kmemdup(event->private_data, event->private_data_len, GFP_ATOMIC); if (!p) return -ENOMEM; event->private_data = p; return 0; } static void free_cm_id(struct iwcm_id_private *cm_id_priv) { dealloc_work_entries(cm_id_priv); kfree(cm_id_priv); } /* * Release a reference on cm_id. If the last reference is being * released, free the cm_id and return 'true'. */ static bool iwcm_deref_id(struct iwcm_id_private *cm_id_priv) { if (refcount_dec_and_test(&cm_id_priv->refcount)) { BUG_ON(!list_empty(&cm_id_priv->work_list)); free_cm_id(cm_id_priv); return true; } return false; } static void add_ref(struct iw_cm_id *cm_id) { struct iwcm_id_private *cm_id_priv; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); refcount_inc(&cm_id_priv->refcount); } static void rem_ref(struct iw_cm_id *cm_id) { struct iwcm_id_private *cm_id_priv; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); (void)iwcm_deref_id(cm_id_priv); } static int cm_event_handler(struct iw_cm_id *cm_id, struct iw_cm_event *event); struct iw_cm_id *iw_create_cm_id(struct ib_device *device, iw_cm_handler cm_handler, void *context) { struct iwcm_id_private *cm_id_priv; cm_id_priv = kzalloc(sizeof(*cm_id_priv), GFP_KERNEL); if (!cm_id_priv) return ERR_PTR(-ENOMEM); cm_id_priv->state = IW_CM_STATE_IDLE; cm_id_priv->id.device = device; cm_id_priv->id.cm_handler = cm_handler; cm_id_priv->id.context = context; cm_id_priv->id.event_handler = cm_event_handler; cm_id_priv->id.add_ref = add_ref; cm_id_priv->id.rem_ref = rem_ref; spin_lock_init(&cm_id_priv->lock); refcount_set(&cm_id_priv->refcount, 1); init_waitqueue_head(&cm_id_priv->connect_wait); init_completion(&cm_id_priv->destroy_comp); INIT_LIST_HEAD(&cm_id_priv->work_list); INIT_LIST_HEAD(&cm_id_priv->work_free_list); return &cm_id_priv->id; } EXPORT_SYMBOL(iw_create_cm_id); static int iwcm_modify_qp_err(struct ib_qp *qp) { struct ib_qp_attr qp_attr; if (!qp) return -EINVAL; qp_attr.qp_state = IB_QPS_ERR; return ib_modify_qp(qp, &qp_attr, IB_QP_STATE); } /* * This is really the RDMAC CLOSING state. It is most similar to the * IB SQD QP state. */ static int iwcm_modify_qp_sqd(struct ib_qp *qp) { struct ib_qp_attr qp_attr; BUG_ON(qp == NULL); qp_attr.qp_state = IB_QPS_SQD; return ib_modify_qp(qp, &qp_attr, IB_QP_STATE); } /* * CM_ID <-- CLOSING * * Block if a passive or active connection is currently being processed. Then * process the event as follows: * - If we are ESTABLISHED, move to CLOSING and modify the QP state * based on the abrupt flag * - If the connection is already in the CLOSING or IDLE state, the peer is * disconnecting concurrently with us and we've already seen the * DISCONNECT event -- ignore the request and return 0 * - Disconnect on a listening endpoint returns -EINVAL */ int iw_cm_disconnect(struct iw_cm_id *cm_id, int abrupt) { struct iwcm_id_private *cm_id_priv; unsigned long flags; int ret = 0; struct ib_qp *qp = NULL; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); /* Wait if we're currently in a connect or accept downcall */ wait_event(cm_id_priv->connect_wait, !test_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags)); spin_lock_irqsave(&cm_id_priv->lock, flags); switch (cm_id_priv->state) { case IW_CM_STATE_ESTABLISHED: cm_id_priv->state = IW_CM_STATE_CLOSING; /* QP could be <nul> for user-mode client */ if (cm_id_priv->qp) qp = cm_id_priv->qp; else ret = -EINVAL; break; case IW_CM_STATE_LISTEN: ret = -EINVAL; break; case IW_CM_STATE_CLOSING: /* remote peer closed first */ case IW_CM_STATE_IDLE: /* accept or connect returned !0 */ break; case IW_CM_STATE_CONN_RECV: /* * App called disconnect before/without calling accept after * connect_request event delivered. */ break; case IW_CM_STATE_CONN_SENT: /* Can only get here if wait above fails */ default: BUG(); } spin_unlock_irqrestore(&cm_id_priv->lock, flags); if (qp) { if (abrupt) ret = iwcm_modify_qp_err(qp); else ret = iwcm_modify_qp_sqd(qp); /* * If both sides are disconnecting the QP could * already be in ERR or SQD states */ ret = 0; } return ret; } EXPORT_SYMBOL(iw_cm_disconnect); /* * CM_ID <-- DESTROYING * * Clean up all resources associated with the connection and release * the initial reference taken by iw_create_cm_id. * * Returns true if and only if the last cm_id_priv reference has been dropped. */ static bool destroy_cm_id(struct iw_cm_id *cm_id) { struct iwcm_id_private *cm_id_priv; struct ib_qp *qp; unsigned long flags; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); /* * Wait if we're currently in a connect or accept downcall. A * listening endpoint should never block here. */ wait_event(cm_id_priv->connect_wait, !test_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags)); /* * Since we're deleting the cm_id, drop any events that * might arrive before the last dereference. */ set_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags); spin_lock_irqsave(&cm_id_priv->lock, flags); qp = cm_id_priv->qp; cm_id_priv->qp = NULL; switch (cm_id_priv->state) { case IW_CM_STATE_LISTEN: cm_id_priv->state = IW_CM_STATE_DESTROYING; spin_unlock_irqrestore(&cm_id_priv->lock, flags); /* destroy the listening endpoint */ cm_id->device->ops.iw_destroy_listen(cm_id); spin_lock_irqsave(&cm_id_priv->lock, flags); break; case IW_CM_STATE_ESTABLISHED: cm_id_priv->state = IW_CM_STATE_DESTROYING; spin_unlock_irqrestore(&cm_id_priv->lock, flags); /* Abrupt close of the connection */ (void)iwcm_modify_qp_err(qp); spin_lock_irqsave(&cm_id_priv->lock, flags); break; case IW_CM_STATE_IDLE: case IW_CM_STATE_CLOSING: cm_id_priv->state = IW_CM_STATE_DESTROYING; break; case IW_CM_STATE_CONN_RECV: /* * App called destroy before/without calling accept after * receiving connection request event notification or * returned non zero from the event callback function. * In either case, must tell the provider to reject. */ cm_id_priv->state = IW_CM_STATE_DESTROYING; spin_unlock_irqrestore(&cm_id_priv->lock, flags); cm_id->device->ops.iw_reject(cm_id, NULL, 0); spin_lock_irqsave(&cm_id_priv->lock, flags); break; case IW_CM_STATE_CONN_SENT: case IW_CM_STATE_DESTROYING: default: BUG(); break; } spin_unlock_irqrestore(&cm_id_priv->lock, flags); if (qp) cm_id_priv->id.device->ops.iw_rem_ref(qp); if (cm_id->mapped) { iwpm_remove_mapinfo(&cm_id->local_addr, &cm_id->m_local_addr); iwpm_remove_mapping(&cm_id->local_addr, RDMA_NL_IWCM); } return iwcm_deref_id(cm_id_priv); } /* * This function is only called by the application thread and cannot * be called by the event thread. The function will wait for all * references to be released on the cm_id and then kfree the cm_id * object. */ void iw_destroy_cm_id(struct iw_cm_id *cm_id) { if (!destroy_cm_id(cm_id)) flush_workqueue(iwcm_wq); } EXPORT_SYMBOL(iw_destroy_cm_id); /** * iw_cm_check_wildcard - If IP address is 0 then use original * @pm_addr: sockaddr containing the ip to check for wildcard * @cm_addr: sockaddr containing the actual IP address * @cm_outaddr: sockaddr to set IP addr which leaving port * * Checks the pm_addr for wildcard and then sets cm_outaddr's * IP to the actual (cm_addr). */ static void iw_cm_check_wildcard(struct sockaddr_storage *pm_addr, struct sockaddr_storage *cm_addr, struct sockaddr_storage *cm_outaddr) { if (pm_addr->ss_family == AF_INET) { struct sockaddr_in *pm4_addr = (struct sockaddr_in *)pm_addr; if (pm4_addr->sin_addr.s_addr == htonl(INADDR_ANY)) { struct sockaddr_in *cm4_addr = (struct sockaddr_in *)cm_addr; struct sockaddr_in *cm4_outaddr = (struct sockaddr_in *)cm_outaddr; cm4_outaddr->sin_addr = cm4_addr->sin_addr; } } else { struct sockaddr_in6 *pm6_addr = (struct sockaddr_in6 *)pm_addr; if (ipv6_addr_type(&pm6_addr->sin6_addr) == IPV6_ADDR_ANY) { struct sockaddr_in6 *cm6_addr = (struct sockaddr_in6 *)cm_addr; struct sockaddr_in6 *cm6_outaddr = (struct sockaddr_in6 *)cm_outaddr; cm6_outaddr->sin6_addr = cm6_addr->sin6_addr; } } } /** * iw_cm_map - Use portmapper to map the ports * @cm_id: connection manager pointer * @active: Indicates the active side when true * returns nonzero for error only if iwpm_create_mapinfo() fails * * Tries to add a mapping for a port using the Portmapper. If * successful in mapping the IP/Port it will check the remote * mapped IP address for a wildcard IP address and replace the * zero IP address with the remote_addr. */ static int iw_cm_map(struct iw_cm_id *cm_id, bool active) { const char *devname = dev_name(&cm_id->device->dev); const char *ifname = cm_id->device->iw_ifname; struct iwpm_dev_data pm_reg_msg = {}; struct iwpm_sa_data pm_msg; int status; if (strlen(devname) >= sizeof(pm_reg_msg.dev_name) || strlen(ifname) >= sizeof(pm_reg_msg.if_name)) return -EINVAL; cm_id->m_local_addr = cm_id->local_addr; cm_id->m_remote_addr = cm_id->remote_addr; strcpy(pm_reg_msg.dev_name, devname); strcpy(pm_reg_msg.if_name, ifname); if (iwpm_register_pid(&pm_reg_msg, RDMA_NL_IWCM) || !iwpm_valid_pid()) return 0; cm_id->mapped = true; pm_msg.loc_addr = cm_id->local_addr; pm_msg.rem_addr = cm_id->remote_addr; pm_msg.flags = (cm_id->device->iw_driver_flags & IW_F_NO_PORT_MAP) ? IWPM_FLAGS_NO_PORT_MAP : 0; if (active) status = iwpm_add_and_query_mapping(&pm_msg, RDMA_NL_IWCM); else status = iwpm_add_mapping(&pm_msg, RDMA_NL_IWCM); if (!status) { cm_id->m_local_addr = pm_msg.mapped_loc_addr; if (active) { cm_id->m_remote_addr = pm_msg.mapped_rem_addr; iw_cm_check_wildcard(&pm_msg.mapped_rem_addr, &cm_id->remote_addr, &cm_id->m_remote_addr); } } return iwpm_create_mapinfo(&cm_id->local_addr, &cm_id->m_local_addr, RDMA_NL_IWCM, pm_msg.flags); } /* * CM_ID <-- LISTEN * * Start listening for connect requests. Generates one CONNECT_REQUEST * event for each inbound connect request. */ int iw_cm_listen(struct iw_cm_id *cm_id, int backlog) { struct iwcm_id_private *cm_id_priv; unsigned long flags; int ret; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); if (!backlog) backlog = default_backlog; ret = alloc_work_entries(cm_id_priv, backlog); if (ret) return ret; spin_lock_irqsave(&cm_id_priv->lock, flags); switch (cm_id_priv->state) { case IW_CM_STATE_IDLE: cm_id_priv->state = IW_CM_STATE_LISTEN; spin_unlock_irqrestore(&cm_id_priv->lock, flags); ret = iw_cm_map(cm_id, false); if (!ret) ret = cm_id->device->ops.iw_create_listen(cm_id, backlog); if (ret) cm_id_priv->state = IW_CM_STATE_IDLE; spin_lock_irqsave(&cm_id_priv->lock, flags); break; default: ret = -EINVAL; } spin_unlock_irqrestore(&cm_id_priv->lock, flags); return ret; } EXPORT_SYMBOL(iw_cm_listen); /* * CM_ID <-- IDLE * * Rejects an inbound connection request. No events are generated. */ int iw_cm_reject(struct iw_cm_id *cm_id, const void *private_data, u8 private_data_len) { struct iwcm_id_private *cm_id_priv; unsigned long flags; int ret; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); set_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); spin_lock_irqsave(&cm_id_priv->lock, flags); if (cm_id_priv->state != IW_CM_STATE_CONN_RECV) { spin_unlock_irqrestore(&cm_id_priv->lock, flags); clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); wake_up_all(&cm_id_priv->connect_wait); return -EINVAL; } cm_id_priv->state = IW_CM_STATE_IDLE; spin_unlock_irqrestore(&cm_id_priv->lock, flags); ret = cm_id->device->ops.iw_reject(cm_id, private_data, private_data_len); clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); wake_up_all(&cm_id_priv->connect_wait); return ret; } EXPORT_SYMBOL(iw_cm_reject); /* * CM_ID <-- ESTABLISHED * * Accepts an inbound connection request and generates an ESTABLISHED * event. Callers of iw_cm_disconnect and iw_destroy_cm_id will block * until the ESTABLISHED event is received from the provider. */ int iw_cm_accept(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param) { struct iwcm_id_private *cm_id_priv; struct ib_qp *qp; unsigned long flags; int ret; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); set_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); spin_lock_irqsave(&cm_id_priv->lock, flags); if (cm_id_priv->state != IW_CM_STATE_CONN_RECV) { spin_unlock_irqrestore(&cm_id_priv->lock, flags); clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); wake_up_all(&cm_id_priv->connect_wait); return -EINVAL; } /* Get the ib_qp given the QPN */ qp = cm_id->device->ops.iw_get_qp(cm_id->device, iw_param->qpn); if (!qp) { spin_unlock_irqrestore(&cm_id_priv->lock, flags); clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); wake_up_all(&cm_id_priv->connect_wait); return -EINVAL; } cm_id->device->ops.iw_add_ref(qp); cm_id_priv->qp = qp; spin_unlock_irqrestore(&cm_id_priv->lock, flags); ret = cm_id->device->ops.iw_accept(cm_id, iw_param); if (ret) { /* An error on accept precludes provider events */ BUG_ON(cm_id_priv->state != IW_CM_STATE_CONN_RECV); cm_id_priv->state = IW_CM_STATE_IDLE; spin_lock_irqsave(&cm_id_priv->lock, flags); qp = cm_id_priv->qp; cm_id_priv->qp = NULL; spin_unlock_irqrestore(&cm_id_priv->lock, flags); if (qp) cm_id->device->ops.iw_rem_ref(qp); clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); wake_up_all(&cm_id_priv->connect_wait); } return ret; } EXPORT_SYMBOL(iw_cm_accept); /* * Active Side: CM_ID <-- CONN_SENT * * If successful, results in the generation of a CONNECT_REPLY * event. iw_cm_disconnect and iw_cm_destroy will block until the * CONNECT_REPLY event is received from the provider. */ int iw_cm_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param) { struct iwcm_id_private *cm_id_priv; int ret; unsigned long flags; struct ib_qp *qp = NULL; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); ret = alloc_work_entries(cm_id_priv, 4); if (ret) return ret; set_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); spin_lock_irqsave(&cm_id_priv->lock, flags); if (cm_id_priv->state != IW_CM_STATE_IDLE) { ret = -EINVAL; goto err; } /* Get the ib_qp given the QPN */ qp = cm_id->device->ops.iw_get_qp(cm_id->device, iw_param->qpn); if (!qp) { ret = -EINVAL; goto err; } cm_id->device->ops.iw_add_ref(qp); cm_id_priv->qp = qp; cm_id_priv->state = IW_CM_STATE_CONN_SENT; spin_unlock_irqrestore(&cm_id_priv->lock, flags); ret = iw_cm_map(cm_id, true); if (!ret) ret = cm_id->device->ops.iw_connect(cm_id, iw_param); if (!ret) return 0; /* success */ spin_lock_irqsave(&cm_id_priv->lock, flags); qp = cm_id_priv->qp; cm_id_priv->qp = NULL; cm_id_priv->state = IW_CM_STATE_IDLE; err: spin_unlock_irqrestore(&cm_id_priv->lock, flags); if (qp) cm_id->device->ops.iw_rem_ref(qp); clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); wake_up_all(&cm_id_priv->connect_wait); return ret; } EXPORT_SYMBOL(iw_cm_connect); /* * Passive Side: new CM_ID <-- CONN_RECV * * Handles an inbound connect request. The function creates a new * iw_cm_id to represent the new connection and inherits the client * callback function and other attributes from the listening parent. * * The work item contains a pointer to the listen_cm_id and the event. The * listen_cm_id contains the client cm_handler, context and * device. These are copied when the device is cloned. The event * contains the new four tuple. * * An error on the child should not affect the parent, so this * function does not return a value. */ static void cm_conn_req_handler(struct iwcm_id_private *listen_id_priv, struct iw_cm_event *iw_event) { unsigned long flags; struct iw_cm_id *cm_id; struct iwcm_id_private *cm_id_priv; int ret; /* * The provider should never generate a connection request * event with a bad status. */ BUG_ON(iw_event->status); cm_id = iw_create_cm_id(listen_id_priv->id.device, listen_id_priv->id.cm_handler, listen_id_priv->id.context); /* If the cm_id could not be created, ignore the request */ if (IS_ERR(cm_id)) goto out; cm_id->provider_data = iw_event->provider_data; cm_id->m_local_addr = iw_event->local_addr; cm_id->m_remote_addr = iw_event->remote_addr; cm_id->local_addr = listen_id_priv->id.local_addr; ret = iwpm_get_remote_info(&listen_id_priv->id.m_local_addr, &iw_event->remote_addr, &cm_id->remote_addr, RDMA_NL_IWCM); if (ret) { cm_id->remote_addr = iw_event->remote_addr; } else { iw_cm_check_wildcard(&listen_id_priv->id.m_local_addr, &iw_event->local_addr, &cm_id->local_addr); iw_event->local_addr = cm_id->local_addr; iw_event->remote_addr = cm_id->remote_addr; } cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); cm_id_priv->state = IW_CM_STATE_CONN_RECV; /* * We could be destroying the listening id. If so, ignore this * upcall. */ spin_lock_irqsave(&listen_id_priv->lock, flags); if (listen_id_priv->state != IW_CM_STATE_LISTEN) { spin_unlock_irqrestore(&listen_id_priv->lock, flags); iw_cm_reject(cm_id, NULL, 0); iw_destroy_cm_id(cm_id); goto out; } spin_unlock_irqrestore(&listen_id_priv->lock, flags); ret = alloc_work_entries(cm_id_priv, 3); if (ret) { iw_cm_reject(cm_id, NULL, 0); iw_destroy_cm_id(cm_id); goto out; } /* Call the client CM handler */ ret = cm_id->cm_handler(cm_id, iw_event); if (ret) { iw_cm_reject(cm_id, NULL, 0); iw_destroy_cm_id(cm_id); } out: if (iw_event->private_data_len) kfree(iw_event->private_data); } /* * Passive Side: CM_ID <-- ESTABLISHED * * The provider generated an ESTABLISHED event which means that * the MPA negotion has completed successfully and we are now in MPA * FPDU mode. * * This event can only be received in the CONN_RECV state. If the * remote peer closed, the ESTABLISHED event would be received followed * by the CLOSE event. If the app closes, it will block until we wake * it up after processing this event. */ static int cm_conn_est_handler(struct iwcm_id_private *cm_id_priv, struct iw_cm_event *iw_event) { unsigned long flags; int ret; spin_lock_irqsave(&cm_id_priv->lock, flags); /* * We clear the CONNECT_WAIT bit here to allow the callback * function to call iw_cm_disconnect. Calling iw_destroy_cm_id * from a callback handler is not allowed. */ clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); BUG_ON(cm_id_priv->state != IW_CM_STATE_CONN_RECV); cm_id_priv->state = IW_CM_STATE_ESTABLISHED; spin_unlock_irqrestore(&cm_id_priv->lock, flags); ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event); wake_up_all(&cm_id_priv->connect_wait); return ret; } /* * Active Side: CM_ID <-- ESTABLISHED * * The app has called connect and is waiting for the established event to * post it's requests to the server. This event will wake up anyone * blocked in iw_cm_disconnect or iw_destroy_id. */ static int cm_conn_rep_handler(struct iwcm_id_private *cm_id_priv, struct iw_cm_event *iw_event) { struct ib_qp *qp = NULL; unsigned long flags; int ret; spin_lock_irqsave(&cm_id_priv->lock, flags); /* * Clear the connect wait bit so a callback function calling * iw_cm_disconnect will not wait and deadlock this thread */ clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags); BUG_ON(cm_id_priv->state != IW_CM_STATE_CONN_SENT); if (iw_event->status == 0) { cm_id_priv->id.m_local_addr = iw_event->local_addr; cm_id_priv->id.m_remote_addr = iw_event->remote_addr; iw_event->local_addr = cm_id_priv->id.local_addr; iw_event->remote_addr = cm_id_priv->id.remote_addr; cm_id_priv->state = IW_CM_STATE_ESTABLISHED; } else { /* REJECTED or RESET */ qp = cm_id_priv->qp; cm_id_priv->qp = NULL; cm_id_priv->state = IW_CM_STATE_IDLE; } spin_unlock_irqrestore(&cm_id_priv->lock, flags); if (qp) cm_id_priv->id.device->ops.iw_rem_ref(qp); ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event); if (iw_event->private_data_len) kfree(iw_event->private_data); /* Wake up waiters on connect complete */ wake_up_all(&cm_id_priv->connect_wait); return ret; } /* * CM_ID <-- CLOSING * * If in the ESTABLISHED state, move to CLOSING. */ static void cm_disconnect_handler(struct iwcm_id_private *cm_id_priv, struct iw_cm_event *iw_event) { unsigned long flags; spin_lock_irqsave(&cm_id_priv->lock, flags); if (cm_id_priv->state == IW_CM_STATE_ESTABLISHED) cm_id_priv->state = IW_CM_STATE_CLOSING; spin_unlock_irqrestore(&cm_id_priv->lock, flags); } /* * CM_ID <-- IDLE * * If in the ESTBLISHED or CLOSING states, the QP will have have been * moved by the provider to the ERR state. Disassociate the CM_ID from * the QP, move to IDLE, and remove the 'connected' reference. * * If in some other state, the cm_id was destroyed asynchronously. * This is the last reference that will result in waking up * the app thread blocked in iw_destroy_cm_id. */ static int cm_close_handler(struct iwcm_id_private *cm_id_priv, struct iw_cm_event *iw_event) { struct ib_qp *qp; unsigned long flags; int ret = 0, notify_event = 0; spin_lock_irqsave(&cm_id_priv->lock, flags); qp = cm_id_priv->qp; cm_id_priv->qp = NULL; switch (cm_id_priv->state) { case IW_CM_STATE_ESTABLISHED: case IW_CM_STATE_CLOSING: cm_id_priv->state = IW_CM_STATE_IDLE; notify_event = 1; break; case IW_CM_STATE_DESTROYING: break; default: BUG(); } spin_unlock_irqrestore(&cm_id_priv->lock, flags); if (qp) cm_id_priv->id.device->ops.iw_rem_ref(qp); if (notify_event) ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event); return ret; } static int process_event(struct iwcm_id_private *cm_id_priv, struct iw_cm_event *iw_event) { int ret = 0; switch (iw_event->event) { case IW_CM_EVENT_CONNECT_REQUEST: cm_conn_req_handler(cm_id_priv, iw_event); break; case IW_CM_EVENT_CONNECT_REPLY: ret = cm_conn_rep_handler(cm_id_priv, iw_event); break; case IW_CM_EVENT_ESTABLISHED: ret = cm_conn_est_handler(cm_id_priv, iw_event); break; case IW_CM_EVENT_DISCONNECT: cm_disconnect_handler(cm_id_priv, iw_event); break; case IW_CM_EVENT_CLOSE: ret = cm_close_handler(cm_id_priv, iw_event); break; default: BUG(); } return ret; } /* * Process events on the work_list for the cm_id. If the callback * function requests that the cm_id be deleted, a flag is set in the * cm_id flags to indicate that when the last reference is * removed, the cm_id is to be destroyed. This is necessary to * distinguish between an object that will be destroyed by the app * thread asleep on the destroy_comp list vs. an object destroyed * here synchronously when the last reference is removed. */ static void cm_work_handler(struct work_struct *_work) { struct iwcm_work *work = container_of(_work, struct iwcm_work, work); struct iw_cm_event levent; struct iwcm_id_private *cm_id_priv = work->cm_id; unsigned long flags; int ret = 0; spin_lock_irqsave(&cm_id_priv->lock, flags); while (!list_empty(&cm_id_priv->work_list)) { work = list_first_entry(&cm_id_priv->work_list, struct iwcm_work, list); list_del_init(&work->list); levent = work->event; put_work(work); spin_unlock_irqrestore(&cm_id_priv->lock, flags); if (!test_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags)) { ret = process_event(cm_id_priv, &levent); if (ret) WARN_ON_ONCE(destroy_cm_id(&cm_id_priv->id)); } else pr_debug("dropping event %d\n", levent.event); if (iwcm_deref_id(cm_id_priv)) return; spin_lock_irqsave(&cm_id_priv->lock, flags); } spin_unlock_irqrestore(&cm_id_priv->lock, flags); } /* * This function is called on interrupt context. Schedule events on * the iwcm_wq thread to allow callback functions to downcall into * the CM and/or block. Events are queued to a per-CM_ID * work_list. If this is the first event on the work_list, the work * element is also queued on the iwcm_wq thread. * * Each event holds a reference on the cm_id. Until the last posted * event has been delivered and processed, the cm_id cannot be * deleted. * * Returns: * 0 - the event was handled. * -ENOMEM - the event was not handled due to lack of resources. */ static int cm_event_handler(struct iw_cm_id *cm_id, struct iw_cm_event *iw_event) { struct iwcm_work *work; struct iwcm_id_private *cm_id_priv; unsigned long flags; int ret = 0; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); spin_lock_irqsave(&cm_id_priv->lock, flags); work = get_work(cm_id_priv); if (!work) { ret = -ENOMEM; goto out; } INIT_WORK(&work->work, cm_work_handler); work->cm_id = cm_id_priv; work->event = *iw_event; if ((work->event.event == IW_CM_EVENT_CONNECT_REQUEST || work->event.event == IW_CM_EVENT_CONNECT_REPLY) && work->event.private_data_len) { ret = copy_private_data(&work->event); if (ret) { put_work(work); goto out; } } refcount_inc(&cm_id_priv->refcount); list_add_tail(&work->list, &cm_id_priv->work_list); queue_work(iwcm_wq, &work->work); out: spin_unlock_irqrestore(&cm_id_priv->lock, flags); return ret; } static int iwcm_init_qp_init_attr(struct iwcm_id_private *cm_id_priv, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { unsigned long flags; int ret; spin_lock_irqsave(&cm_id_priv->lock, flags); switch (cm_id_priv->state) { case IW_CM_STATE_IDLE: case IW_CM_STATE_CONN_SENT: case IW_CM_STATE_CONN_RECV: case IW_CM_STATE_ESTABLISHED: *qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS; qp_attr->qp_access_flags = IB_ACCESS_REMOTE_WRITE| IB_ACCESS_REMOTE_READ; ret = 0; break; default: ret = -EINVAL; break; } spin_unlock_irqrestore(&cm_id_priv->lock, flags); return ret; } static int iwcm_init_qp_rts_attr(struct iwcm_id_private *cm_id_priv, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { unsigned long flags; int ret; spin_lock_irqsave(&cm_id_priv->lock, flags); switch (cm_id_priv->state) { case IW_CM_STATE_IDLE: case IW_CM_STATE_CONN_SENT: case IW_CM_STATE_CONN_RECV: case IW_CM_STATE_ESTABLISHED: *qp_attr_mask = 0; ret = 0; break; default: ret = -EINVAL; break; } spin_unlock_irqrestore(&cm_id_priv->lock, flags); return ret; } int iw_cm_init_qp_attr(struct iw_cm_id *cm_id, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct iwcm_id_private *cm_id_priv; int ret; cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); switch (qp_attr->qp_state) { case IB_QPS_INIT: case IB_QPS_RTR: ret = iwcm_init_qp_init_attr(cm_id_priv, qp_attr, qp_attr_mask); break; case IB_QPS_RTS: ret = iwcm_init_qp_rts_attr(cm_id_priv, qp_attr, qp_attr_mask); break; default: ret = -EINVAL; break; } return ret; } EXPORT_SYMBOL(iw_cm_init_qp_attr); static int __init iw_cm_init(void) { int ret; ret = iwpm_init(RDMA_NL_IWCM); if (ret) return ret; iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", 0); if (!iwcm_wq) goto err_alloc; iwcm_ctl_table_hdr = register_net_sysctl(&init_net, "net/iw_cm", iwcm_ctl_table); if (!iwcm_ctl_table_hdr) { pr_err("iw_cm: couldn't register sysctl paths\n"); goto err_sysctl; } rdma_nl_register(RDMA_NL_IWCM, iwcm_nl_cb_table); return 0; err_sysctl: destroy_workqueue(iwcm_wq); err_alloc: iwpm_exit(RDMA_NL_IWCM); return -ENOMEM; } static void __exit iw_cm_cleanup(void) { rdma_nl_unregister(RDMA_NL_IWCM); unregister_net_sysctl_table(iwcm_ctl_table_hdr); destroy_workqueue(iwcm_wq); iwpm_exit(RDMA_NL_IWCM); } MODULE_ALIAS_RDMA_NETLINK(RDMA_NL_IWCM, 2); module_init(iw_cm_init); module_exit(iw_cm_cleanup); |
| 906 276 194 60 2 197 199 8 195 199 340 450 6 348 223 66 67 67 9 20 8 20 194 17 906 48 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _IP6_FIB_H #define _IP6_FIB_H #include <linux/ipv6_route.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> #include <linux/notifier.h> #include <net/dst.h> #include <net/flow.h> #include <net/ip_fib.h> #include <net/netlink.h> #include <net/inetpeer.h> #include <net/fib_notifier.h> #include <linux/indirect_call_wrapper.h> #include <uapi/linux/bpf.h> #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_HASHSZ 256 #else #define FIB6_TABLE_HASHSZ 1 #endif #define RT6_DEBUG 2 struct rt6_info; struct fib6_info; struct fib6_config { u32 fc_table; u32 fc_metric; int fc_dst_len; int fc_src_len; int fc_ifindex; u32 fc_flags; u32 fc_protocol; u16 fc_type; /* only 8 bits are used */ u16 fc_delete_all_nh : 1, fc_ignore_dev_down:1, __unused : 14; u32 fc_nh_id; struct in6_addr fc_dst; struct in6_addr fc_src; struct in6_addr fc_prefsrc; struct in6_addr fc_gateway; unsigned long fc_expires; struct nlattr *fc_mx; int fc_mx_len; int fc_mp_len; struct nlattr *fc_mp; struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; bool fc_is_fdb; }; struct fib6_node { struct fib6_node __rcu *parent; struct fib6_node __rcu *left; struct fib6_node __rcu *right; #ifdef CONFIG_IPV6_SUBTREES struct fib6_node __rcu *subtree; #endif struct fib6_info __rcu *leaf; __u16 fn_bit; /* bit key */ __u16 fn_flags; int fn_sernum; struct fib6_info __rcu *rr_ptr; struct rcu_head rcu; }; struct fib6_gc_args { int timeout; int more; }; #ifndef CONFIG_IPV6_SUBTREES #define FIB6_SUBTREE(fn) NULL static inline bool fib6_routes_require_src(const struct net *net) { return false; } static inline void fib6_routes_require_src_inc(struct net *net) {} static inline void fib6_routes_require_src_dec(struct net *net) {} #else static inline bool fib6_routes_require_src(const struct net *net) { return net->ipv6.fib6_routes_require_src > 0; } static inline void fib6_routes_require_src_inc(struct net *net) { net->ipv6.fib6_routes_require_src++; } static inline void fib6_routes_require_src_dec(struct net *net) { net->ipv6.fib6_routes_require_src--; } #define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1)) #endif /* * routing information * */ struct rt6key { struct in6_addr addr; int plen; }; struct fib6_table; struct rt6_exception_bucket { struct hlist_head chain; int depth; }; struct rt6_exception { struct hlist_node hlist; struct rt6_info *rt6i; unsigned long stamp; struct rcu_head rcu; }; #define FIB6_EXCEPTION_BUCKET_SIZE_SHIFT 10 #define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT) #define FIB6_MAX_DEPTH 5 struct fib6_nh { struct fib_nh_common nh_common; #ifdef CONFIG_IPV6_ROUTER_PREF unsigned long last_probe; #endif struct rt6_info * __percpu *rt6i_pcpu; struct rt6_exception_bucket __rcu *rt6i_exception_bucket; }; struct fib6_info { struct fib6_table *fib6_table; struct fib6_info __rcu *fib6_next; struct fib6_node __rcu *fib6_node; /* Multipath routes: * siblings is a list of fib6_info that have the same metric/weight, * destination, but not the same gateway. nsiblings is just a cache * to speed up lookup. */ union { struct list_head fib6_siblings; struct list_head nh_list; }; unsigned int fib6_nsiblings; refcount_t fib6_ref; unsigned long expires; struct hlist_node gc_link; struct dst_metrics *fib6_metrics; #define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] struct rt6key fib6_dst; u32 fib6_flags; struct rt6key fib6_src; struct rt6key fib6_prefsrc; u32 fib6_metric; u8 fib6_protocol; u8 fib6_type; u8 offload; u8 trap; u8 offload_failed; u8 should_flush:1, dst_nocount:1, dst_nopolicy:1, fib6_destroying:1, unused:4; struct rcu_head rcu; struct nexthop *nh; struct fib6_nh fib6_nh[]; }; struct rt6_info { struct dst_entry dst; struct fib6_info __rcu *from; int sernum; struct rt6key rt6i_dst; struct rt6key rt6i_src; struct in6_addr rt6i_gateway; struct inet6_dev *rt6i_idev; u32 rt6i_flags; /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; }; struct fib6_result { struct fib6_nh *nh; struct fib6_info *f6i; u32 fib6_flags; u8 fib6_type; struct rt6_info *rt6; }; #define for_each_fib6_node_rt_rcu(fn) \ for (rt = rcu_dereference((fn)->leaf); rt; \ rt = rcu_dereference(rt->fib6_next)) #define for_each_fib6_walker_rt(w) \ for (rt = (w)->leaf; rt; \ rt = rcu_dereference_protected(rt->fib6_next, 1)) #define dst_rt6_info(_ptr) container_of_const(_ptr, struct rt6_info, dst) static inline struct inet6_dev *ip6_dst_idev(const struct dst_entry *dst) { return dst_rt6_info(dst)->rt6i_idev; } static inline bool fib6_requires_src(const struct fib6_info *rt) { return rt->fib6_src.plen > 0; } /* The callers should hold f6i->fib6_table->tb6_lock if a route has ever * been added to a table before. */ static inline void fib6_clean_expires(struct fib6_info *f6i) { f6i->fib6_flags &= ~RTF_EXPIRES; f6i->expires = 0; } /* The callers should hold f6i->fib6_table->tb6_lock if a route has ever * been added to a table before. */ static inline void fib6_set_expires(struct fib6_info *f6i, unsigned long expires) { f6i->expires = expires; f6i->fib6_flags |= RTF_EXPIRES; } static inline bool fib6_check_expired(const struct fib6_info *f6i) { if (f6i->fib6_flags & RTF_EXPIRES) return time_after(jiffies, f6i->expires); return false; } /* Function to safely get fn->fn_sernum for passed in rt * and store result in passed in cookie. * Return true if we can get cookie safely * Return false if not */ static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, u32 *cookie) { struct fib6_node *fn; bool status = false; fn = rcu_dereference(f6i->fib6_node); if (fn) { *cookie = READ_ONCE(fn->fn_sernum); /* pairs with smp_wmb() in __fib6_update_sernum_upto_root() */ smp_rmb(); status = true; } return status; } static inline u32 rt6_get_cookie(const struct rt6_info *rt) { struct fib6_info *from; u32 cookie = 0; if (rt->sernum) return rt->sernum; rcu_read_lock(); from = rcu_dereference(rt->from); if (from) fib6_get_cookie_safe(from, &cookie); rcu_read_unlock(); return cookie; } static inline void ip6_rt_put(struct rt6_info *rt) { /* dst_release() accepts a NULL parameter. * We rely on dst being first structure in struct rt6_info */ BUILD_BUG_ON(offsetof(struct rt6_info, dst) != 0); dst_release(&rt->dst); } struct fib6_info *fib6_info_alloc(gfp_t gfp_flags, bool with_fib6_nh); void fib6_info_destroy_rcu(struct rcu_head *head); static inline void fib6_info_hold(struct fib6_info *f6i) { refcount_inc(&f6i->fib6_ref); } static inline bool fib6_info_hold_safe(struct fib6_info *f6i) { return refcount_inc_not_zero(&f6i->fib6_ref); } static inline void fib6_info_release(struct fib6_info *f6i) { if (f6i && refcount_dec_and_test(&f6i->fib6_ref)) { DEBUG_NET_WARN_ON_ONCE(!hlist_unhashed(&f6i->gc_link)); call_rcu_hurry(&f6i->rcu, fib6_info_destroy_rcu); } } enum fib6_walk_state { #ifdef CONFIG_IPV6_SUBTREES FWS_S, #endif FWS_L, FWS_R, FWS_C, FWS_U }; struct fib6_walker { struct list_head lh; struct fib6_node *root, *node; struct fib6_info *leaf; enum fib6_walk_state state; unsigned int skip; unsigned int count; unsigned int skip_in_node; int (*func)(struct fib6_walker *); void *args; }; struct rt6_statistics { __u32 fib_nodes; /* all fib6 nodes */ __u32 fib_route_nodes; /* intermediate nodes */ __u32 fib_rt_entries; /* rt entries in fib table */ __u32 fib_rt_cache; /* cached rt entries in exception table */ __u32 fib_discarded_routes; /* total number of routes delete */ /* The following stat is not protected by any lock */ atomic_t fib_rt_alloc; /* total number of routes alloced */ }; #define RTN_TL_ROOT 0x0001 #define RTN_ROOT 0x0002 /* tree root node */ #define RTN_RTINFO 0x0004 /* node with valid routing info */ /* * priority levels (or metrics) * */ struct fib6_table { struct hlist_node tb6_hlist; u32 tb6_id; spinlock_t tb6_lock; struct fib6_node tb6_root; struct inet_peer_base tb6_peers; unsigned int flags; unsigned int fib_seq; struct hlist_head tb6_gc_hlist; /* GC candidates */ #define RT6_TABLE_HAS_DFLT_ROUTER BIT(0) }; #define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC #define RT6_TABLE_MAIN RT_TABLE_MAIN #define RT6_TABLE_DFLT RT6_TABLE_MAIN #define RT6_TABLE_INFO RT6_TABLE_MAIN #define RT6_TABLE_PREFIX RT6_TABLE_MAIN #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_MIN 1 #define FIB6_TABLE_MAX RT_TABLE_MAX #define RT6_TABLE_LOCAL RT_TABLE_LOCAL #else #define FIB6_TABLE_MIN RT_TABLE_MAIN #define FIB6_TABLE_MAX FIB6_TABLE_MIN #define RT6_TABLE_LOCAL RT6_TABLE_MAIN #endif typedef struct rt6_info *(*pol_lookup_t)(struct net *, struct fib6_table *, struct flowi6 *, const struct sk_buff *, int); struct fib6_entry_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib6_info *rt; unsigned int nsiblings; }; /* * exported functions */ struct fib6_table *fib6_get_table(struct net *net, u32 id); struct fib6_table *fib6_new_table(struct net *net, u32 id); struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags, pol_lookup_t lookup); /* called with rcu lock held; can return error pointer * caller needs to select path */ int fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags); /* called with rcu lock held; caller needs to select path */ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int strict); void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict); struct fib6_node *fib6_node_lookup(struct fib6_node *root, const struct in6_addr *daddr, const struct in6_addr *saddr); struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *daddr, int dst_len, const struct in6_addr *saddr, int src_len, bool exact_match); void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg), void *arg); void fib6_clean_all_skip_notify(struct net *net, int (*func)(struct fib6_info *, void *arg), void *arg); int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack); int fib6_del(struct fib6_info *rt, struct nl_info *info); static inline void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) { const struct fib6_info *from; rcu_read_lock(); from = rcu_dereference(rt->from); if (from) *addr = from->fib6_prefsrc.addr; else *addr = in6addr_any; rcu_read_unlock(); } int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib6_nh_release(struct fib6_nh *fib6_nh); void fib6_nh_release_dsts(struct fib6_nh *fib6_nh); int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, struct netlink_ext_ack *extack); int call_fib6_multipath_entry_notifiers(struct net *net, enum fib_event_type event_type, struct fib6_info *rt, unsigned int nsiblings, struct netlink_ext_ack *extack); int call_fib6_entry_notifiers_replace(struct net *net, struct fib6_info *rt); void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info); void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); void fib6_run_gc(unsigned long expires, struct net *net, bool force); void fib6_gc_cleanup(void); int fib6_init(void); /* Add the route to the gc list if it is not already there * * The callers should hold f6i->fib6_table->tb6_lock. */ static inline void fib6_add_gc_list(struct fib6_info *f6i) { /* If fib6_node is null, the f6i is not in (or removed from) the * table. * * There is a gap between finding the f6i from the table and * calling this function without the protection of the tb6_lock. * This check makes sure the f6i is not added to the gc list when * it is not on the table. */ if (!rcu_dereference_protected(f6i->fib6_node, lockdep_is_held(&f6i->fib6_table->tb6_lock))) return; if (hlist_unhashed(&f6i->gc_link)) hlist_add_head(&f6i->gc_link, &f6i->fib6_table->tb6_gc_hlist); } /* Remove the route from the gc list if it is on the list. * * The callers should hold f6i->fib6_table->tb6_lock. */ static inline void fib6_remove_gc_list(struct fib6_info *f6i) { if (!hlist_unhashed(&f6i->gc_link)) hlist_del_init(&f6i->gc_link); } struct ipv6_route_iter { struct seq_net_private p; struct fib6_walker w; loff_t skip; struct fib6_table *tbl; int sernum; }; extern const struct seq_operations ipv6_route_seq_ops; int call_fib6_notifier(struct notifier_block *nb, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib6_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int __net_init fib6_notifier_init(struct net *net); void __net_exit fib6_notifier_exit(struct net *net); unsigned int fib6_tables_seq_read(struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); void fib6_update_sernum(struct net *net, struct fib6_info *rt); void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); void fib6_update_sernum_stub(struct net *net, struct fib6_info *f6i); void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val); static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) { return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric)); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, bool trap, bool offload_failed); #if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL) struct bpf_iter__ipv6_route { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct fib6_info *, rt); }; #endif INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); INDIRECT_CALLABLE_DECLARE(struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags)); static inline struct rt6_info *pol_lookup_func(pol_lookup_t lookup, struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return INDIRECT_CALL_4(lookup, ip6_pol_route_output, ip6_pol_route_input, ip6_pol_route_lookup, __ip6_route_redirect, net, table, fl6, skb, flags); } #ifdef CONFIG_IPV6_MULTIPLE_TABLES static inline bool fib6_has_custom_rules(const struct net *net) { return net->ipv6.fib6_has_custom_rules; } int fib6_rules_init(void); void fib6_rules_cleanup(void); bool fib6_rule_default(const struct fib_rule *rule); int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack); unsigned int fib6_rules_seq_read(struct net *net); static inline bool fib6_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi6 *fl6, struct flow_keys *flkeys) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; if (!net->ipv6.fib6_rules_require_fldissect) return false; memset(flkeys, 0, sizeof(*flkeys)); __skb_flow_dissect(net, skb, &flow_keys_dissector, flkeys, NULL, 0, 0, 0, flag); fl6->fl6_sport = flkeys->ports.src; fl6->fl6_dport = flkeys->ports.dst; fl6->flowi6_proto = flkeys->basic.ip_proto; return true; } #else static inline bool fib6_has_custom_rules(const struct net *net) { return false; } static inline int fib6_rules_init(void) { return 0; } static inline void fib6_rules_cleanup(void) { return ; } static inline bool fib6_rule_default(const struct fib_rule *rule) { return true; } static inline int fib6_rules_dump(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack) { return 0; } static inline unsigned int fib6_rules_seq_read(struct net *net) { return 0; } static inline bool fib6_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi6 *fl6, struct flow_keys *flkeys) { return false; } #endif #endif |
| 11 10 | 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cache.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/pid_namespace.h> #include "internal.h" /* * /proc/thread_self: */ static const char *proc_thread_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct pid_namespace *ns = proc_pid_ns(inode->i_sb); pid_t tgid = task_tgid_nr_ns(current, ns); pid_t pid = task_pid_nr_ns(current, ns); char *name; if (!pid) return ERR_PTR(-ENOENT); name = kmalloc(10 + 6 + 10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); if (unlikely(!name)) return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%u/task/%u", tgid, pid); set_delayed_call(done, kfree_link, name); return name; } static const struct inode_operations proc_thread_self_inode_operations = { .get_link = proc_thread_self_get_link, }; static unsigned thread_self_inum __ro_after_init; int proc_setup_thread_self(struct super_block *s) { struct inode *root_inode = d_inode(s->s_root); struct proc_fs_info *fs_info = proc_sb_info(s); struct dentry *thread_self; int ret = -ENOMEM; inode_lock(root_inode); thread_self = d_alloc_name(s->s_root, "thread-self"); if (thread_self) { struct inode *inode = new_inode(s); if (inode) { inode->i_ino = thread_self_inum; simple_inode_init_ts(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_thread_self_inode_operations; d_add(thread_self, inode); ret = 0; } else { dput(thread_self); } } inode_unlock(root_inode); if (ret) pr_err("proc_fill_super: can't allocate /proc/thread-self\n"); else fs_info->proc_thread_self = thread_self; return ret; } void __init proc_thread_self_init(void) { proc_alloc_inum(&thread_self_inum); } |
| 3 3 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This is a module which is used for logging packets. */ /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/spinlock.h> #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/ip.h> #include <net/ipv6.h> #include <net/icmp.h> #include <net/udp.h> #include <net/tcp.h> #include <net/route.h> #include <linux/netfilter.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_LOG.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <net/netfilter/nf_log.h> static unsigned int log_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_log_info *loginfo = par->targinfo; struct net *net = xt_net(par); struct nf_loginfo li; li.type = NF_LOG_TYPE_LOG; li.u.log.level = loginfo->level; li.u.log.logflags = loginfo->logflags; nf_log_packet(net, xt_family(par), xt_hooknum(par), skb, xt_in(par), xt_out(par), &li, "%s", loginfo->prefix); return XT_CONTINUE; } static int log_tg_check(const struct xt_tgchk_param *par) { const struct xt_log_info *loginfo = par->targinfo; int ret; if (par->family != NFPROTO_IPV4 && par->family != NFPROTO_IPV6) return -EINVAL; if (loginfo->level >= 8) { pr_debug("level %u >= 8\n", loginfo->level); return -EINVAL; } if (loginfo->prefix[sizeof(loginfo->prefix)-1] != '\0') { pr_debug("prefix is not null-terminated\n"); return -EINVAL; } ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); if (ret != 0 && !par->nft_compat) { request_module("%s", "nf_log_syslog"); ret = nf_logger_find_get(par->family, NF_LOG_TYPE_LOG); } return ret; } static void log_tg_destroy(const struct xt_tgdtor_param *par) { nf_logger_put(par->family, NF_LOG_TYPE_LOG); } static struct xt_target log_tg_regs[] __read_mostly = { { .name = "LOG", .family = NFPROTO_IPV4, .target = log_tg, .targetsize = sizeof(struct xt_log_info), .checkentry = log_tg_check, .destroy = log_tg_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "LOG", .family = NFPROTO_IPV6, .target = log_tg, .targetsize = sizeof(struct xt_log_info), .checkentry = log_tg_check, .destroy = log_tg_destroy, .me = THIS_MODULE, }, #endif }; static int __init log_tg_init(void) { return xt_register_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); } static void __exit log_tg_exit(void) { xt_unregister_targets(log_tg_regs, ARRAY_SIZE(log_tg_regs)); } module_init(log_tg_init); module_exit(log_tg_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_AUTHOR("Jan Rekorajski <baggins@pld.org.pl>"); MODULE_DESCRIPTION("Xtables: IPv4/IPv6 packet logging"); MODULE_ALIAS("ipt_LOG"); MODULE_ALIAS("ip6t_LOG"); MODULE_SOFTDEP("pre: nf_log_syslog"); |
| 6 6 6 6 6 6 6 6 6 6 6 6 1 6 6 6 6 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 | /* * POSIX message queues filesystem for Linux. * * Copyright (C) 2003,2004 Krzysztof Benedyczak (golbi@mat.uni.torun.pl) * Michal Wronski (michal.wronski@gmail.com) * * Spinlocks: Mohamed Abbas (abbas.mohamed@intel.com) * Lockless receive & send, fd based notify: * Manfred Spraul (manfred@colorfullife.com) * * Audit: George Wilson (ltcgcw@us.ibm.com) * * This file is released under the GPL. */ #include <linux/capability.h> #include <linux/init.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/namei.h> #include <linux/sysctl.h> #include <linux/poll.h> #include <linux/mqueue.h> #include <linux/msg.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> #include <linux/netlink.h> #include <linux/syscalls.h> #include <linux/audit.h> #include <linux/signal.h> #include <linux/mutex.h> #include <linux/nsproxy.h> #include <linux/pid.h> #include <linux/ipc_namespace.h> #include <linux/user_namespace.h> #include <linux/slab.h> #include <linux/sched/wake_q.h> #include <linux/sched/signal.h> #include <linux/sched/user.h> #include <net/sock.h> #include "util.h" struct mqueue_fs_context { struct ipc_namespace *ipc_ns; bool newns; /* Set if newly created ipc namespace */ }; #define MQUEUE_MAGIC 0x19800202 #define DIRENT_SIZE 20 #define FILENT_SIZE 80 #define SEND 0 #define RECV 1 #define STATE_NONE 0 #define STATE_READY 1 struct posix_msg_tree_node { struct rb_node rb_node; struct list_head msg_list; int priority; }; /* * Locking: * * Accesses to a message queue are synchronized by acquiring info->lock. * * There are two notable exceptions: * - The actual wakeup of a sleeping task is performed using the wake_q * framework. info->lock is already released when wake_up_q is called. * - The exit codepaths after sleeping check ext_wait_queue->state without * any locks. If it is STATE_READY, then the syscall is completed without * acquiring info->lock. * * MQ_BARRIER: * To achieve proper release/acquire memory barrier pairing, the state is set to * STATE_READY with smp_store_release(), and it is read with READ_ONCE followed * by smp_acquire__after_ctrl_dep(). In addition, wake_q_add_safe() is used. * * This prevents the following races: * * 1) With the simple wake_q_add(), the task could be gone already before * the increase of the reference happens * Thread A * Thread B * WRITE_ONCE(wait.state, STATE_NONE); * schedule_hrtimeout() * wake_q_add(A) * if (cmpxchg()) // success * ->state = STATE_READY (reordered) * <timeout returns> * if (wait.state == STATE_READY) return; * sysret to user space * sys_exit() * get_task_struct() // UaF * * Solution: Use wake_q_add_safe() and perform the get_task_struct() before * the smp_store_release() that does ->state = STATE_READY. * * 2) Without proper _release/_acquire barriers, the woken up task * could read stale data * * Thread A * Thread B * do_mq_timedreceive * WRITE_ONCE(wait.state, STATE_NONE); * schedule_hrtimeout() * state = STATE_READY; * <timeout returns> * if (wait.state == STATE_READY) return; * msg_ptr = wait.msg; // Access to stale data! * receiver->msg = message; (reordered) * * Solution: use _release and _acquire barriers. * * 3) There is intentionally no barrier when setting current->state * to TASK_INTERRUPTIBLE: spin_unlock(&info->lock) provides the * release memory barrier, and the wakeup is triggered when holding * info->lock, i.e. spin_lock(&info->lock) provided a pairing * acquire memory barrier. */ struct ext_wait_queue { /* queue of sleeping tasks */ struct task_struct *task; struct list_head list; struct msg_msg *msg; /* ptr of loaded message */ int state; /* one of STATE_* values */ }; struct mqueue_inode_info { spinlock_t lock; struct inode vfs_inode; wait_queue_head_t wait_q; struct rb_root msg_tree; struct rb_node *msg_tree_rightmost; struct posix_msg_tree_node *node_cache; struct mq_attr attr; struct sigevent notify; struct pid *notify_owner; u32 notify_self_exec_id; struct user_namespace *notify_user_ns; struct ucounts *ucounts; /* user who created, for accounting */ struct sock *notify_sock; struct sk_buff *notify_cookie; /* for tasks waiting for free space and messages, respectively */ struct ext_wait_queue e_wait_q[2]; unsigned long qsize; /* size of queue in memory (sum of all msgs) */ }; static struct file_system_type mqueue_fs_type; static const struct inode_operations mqueue_dir_inode_operations; static const struct file_operations mqueue_file_operations; static const struct super_operations mqueue_super_ops; static const struct fs_context_operations mqueue_fs_context_ops; static void remove_notification(struct mqueue_inode_info *info); static struct kmem_cache *mqueue_inode_cachep; static inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode) { return container_of(inode, struct mqueue_inode_info, vfs_inode); } /* * This routine should be called with the mq_lock held. */ static inline struct ipc_namespace *__get_ns_from_inode(struct inode *inode) { return get_ipc_ns(inode->i_sb->s_fs_info); } static struct ipc_namespace *get_ns_from_inode(struct inode *inode) { struct ipc_namespace *ns; spin_lock(&mq_lock); ns = __get_ns_from_inode(inode); spin_unlock(&mq_lock); return ns; } /* Auxiliary functions to manipulate messages' list */ static int msg_insert(struct msg_msg *msg, struct mqueue_inode_info *info) { struct rb_node **p, *parent = NULL; struct posix_msg_tree_node *leaf; bool rightmost = true; p = &info->msg_tree.rb_node; while (*p) { parent = *p; leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node); if (likely(leaf->priority == msg->m_type)) goto insert_msg; else if (msg->m_type < leaf->priority) { p = &(*p)->rb_left; rightmost = false; } else p = &(*p)->rb_right; } if (info->node_cache) { leaf = info->node_cache; info->node_cache = NULL; } else { leaf = kmalloc(sizeof(*leaf), GFP_ATOMIC); if (!leaf) return -ENOMEM; INIT_LIST_HEAD(&leaf->msg_list); } leaf->priority = msg->m_type; if (rightmost) info->msg_tree_rightmost = &leaf->rb_node; rb_link_node(&leaf->rb_node, parent, p); rb_insert_color(&leaf->rb_node, &info->msg_tree); insert_msg: info->attr.mq_curmsgs++; info->qsize += msg->m_ts; list_add_tail(&msg->m_list, &leaf->msg_list); return 0; } static inline void msg_tree_erase(struct posix_msg_tree_node *leaf, struct mqueue_inode_info *info) { struct rb_node *node = &leaf->rb_node; if (info->msg_tree_rightmost == node) info->msg_tree_rightmost = rb_prev(node); rb_erase(node, &info->msg_tree); if (info->node_cache) kfree(leaf); else info->node_cache = leaf; } static inline struct msg_msg *msg_get(struct mqueue_inode_info *info) { struct rb_node *parent = NULL; struct posix_msg_tree_node *leaf; struct msg_msg *msg; try_again: /* * During insert, low priorities go to the left and high to the * right. On receive, we want the highest priorities first, so * walk all the way to the right. */ parent = info->msg_tree_rightmost; if (!parent) { if (info->attr.mq_curmsgs) { pr_warn_once("Inconsistency in POSIX message queue, " "no tree element, but supposedly messages " "should exist!\n"); info->attr.mq_curmsgs = 0; } return NULL; } leaf = rb_entry(parent, struct posix_msg_tree_node, rb_node); if (unlikely(list_empty(&leaf->msg_list))) { pr_warn_once("Inconsistency in POSIX message queue, " "empty leaf node but we haven't implemented " "lazy leaf delete!\n"); msg_tree_erase(leaf, info); goto try_again; } else { msg = list_first_entry(&leaf->msg_list, struct msg_msg, m_list); list_del(&msg->m_list); if (list_empty(&leaf->msg_list)) { msg_tree_erase(leaf, info); } } info->attr.mq_curmsgs--; info->qsize -= msg->m_ts; return msg; } static struct inode *mqueue_get_inode(struct super_block *sb, struct ipc_namespace *ipc_ns, umode_t mode, struct mq_attr *attr) { struct inode *inode; int ret = -ENOMEM; inode = new_inode(sb); if (!inode) goto err; inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); simple_inode_init_ts(inode); if (S_ISREG(mode)) { struct mqueue_inode_info *info; unsigned long mq_bytes, mq_treesize; inode->i_fop = &mqueue_file_operations; inode->i_size = FILENT_SIZE; /* mqueue specific info */ info = MQUEUE_I(inode); spin_lock_init(&info->lock); init_waitqueue_head(&info->wait_q); INIT_LIST_HEAD(&info->e_wait_q[0].list); INIT_LIST_HEAD(&info->e_wait_q[1].list); info->notify_owner = NULL; info->notify_user_ns = NULL; info->qsize = 0; info->ucounts = NULL; /* set when all is ok */ info->msg_tree = RB_ROOT; info->msg_tree_rightmost = NULL; info->node_cache = NULL; memset(&info->attr, 0, sizeof(info->attr)); info->attr.mq_maxmsg = min(ipc_ns->mq_msg_max, ipc_ns->mq_msg_default); info->attr.mq_msgsize = min(ipc_ns->mq_msgsize_max, ipc_ns->mq_msgsize_default); if (attr) { info->attr.mq_maxmsg = attr->mq_maxmsg; info->attr.mq_msgsize = attr->mq_msgsize; } /* * We used to allocate a static array of pointers and account * the size of that array as well as one msg_msg struct per * possible message into the queue size. That's no longer * accurate as the queue is now an rbtree and will grow and * shrink depending on usage patterns. We can, however, still * account one msg_msg struct per message, but the nodes are * allocated depending on priority usage, and most programs * only use one, or a handful, of priorities. However, since * this is pinned memory, we need to assume worst case, so * that means the min(mq_maxmsg, max_priorities) * struct * posix_msg_tree_node. */ ret = -EINVAL; if (info->attr.mq_maxmsg <= 0 || info->attr.mq_msgsize <= 0) goto out_inode; if (capable(CAP_SYS_RESOURCE)) { if (info->attr.mq_maxmsg > HARD_MSGMAX || info->attr.mq_msgsize > HARD_MSGSIZEMAX) goto out_inode; } else { if (info->attr.mq_maxmsg > ipc_ns->mq_msg_max || info->attr.mq_msgsize > ipc_ns->mq_msgsize_max) goto out_inode; } ret = -EOVERFLOW; /* check for overflow */ if (info->attr.mq_msgsize > ULONG_MAX/info->attr.mq_maxmsg) goto out_inode; mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) + min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) * sizeof(struct posix_msg_tree_node); mq_bytes = info->attr.mq_maxmsg * info->attr.mq_msgsize; if (mq_bytes + mq_treesize < mq_bytes) goto out_inode; mq_bytes += mq_treesize; info->ucounts = get_ucounts(current_ucounts()); if (info->ucounts) { long msgqueue; spin_lock(&mq_lock); msgqueue = inc_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes); if (msgqueue == LONG_MAX || msgqueue > rlimit(RLIMIT_MSGQUEUE)) { dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes); spin_unlock(&mq_lock); put_ucounts(info->ucounts); info->ucounts = NULL; /* mqueue_evict_inode() releases info->messages */ ret = -EMFILE; goto out_inode; } spin_unlock(&mq_lock); } } else if (S_ISDIR(mode)) { inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * DIRENT_SIZE; inode->i_op = &mqueue_dir_inode_operations; inode->i_fop = &simple_dir_operations; } return inode; out_inode: iput(inode); err: return ERR_PTR(ret); } static int mqueue_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct ipc_namespace *ns = sb->s_fs_info; sb->s_iflags |= SB_I_NOEXEC | SB_I_NODEV; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = MQUEUE_MAGIC; sb->s_op = &mqueue_super_ops; inode = mqueue_get_inode(sb, ns, S_IFDIR | S_ISVTX | S_IRWXUGO, NULL); if (IS_ERR(inode)) return PTR_ERR(inode); sb->s_root = d_make_root(inode); if (!sb->s_root) return -ENOMEM; return 0; } static int mqueue_get_tree(struct fs_context *fc) { struct mqueue_fs_context *ctx = fc->fs_private; /* * With a newly created ipc namespace, we don't need to do a search * for an ipc namespace match, but we still need to set s_fs_info. */ if (ctx->newns) { fc->s_fs_info = ctx->ipc_ns; return get_tree_nodev(fc, mqueue_fill_super); } return get_tree_keyed(fc, mqueue_fill_super, ctx->ipc_ns); } static void mqueue_fs_context_free(struct fs_context *fc) { struct mqueue_fs_context *ctx = fc->fs_private; put_ipc_ns(ctx->ipc_ns); kfree(ctx); } static int mqueue_init_fs_context(struct fs_context *fc) { struct mqueue_fs_context *ctx; ctx = kzalloc(sizeof(struct mqueue_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ipc_ns = get_ipc_ns(current->nsproxy->ipc_ns); put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns); fc->fs_private = ctx; fc->ops = &mqueue_fs_context_ops; return 0; } /* * mq_init_ns() is currently the only caller of mq_create_mount(). * So the ns parameter is always a newly created ipc namespace. */ static struct vfsmount *mq_create_mount(struct ipc_namespace *ns) { struct mqueue_fs_context *ctx; struct fs_context *fc; struct vfsmount *mnt; fc = fs_context_for_mount(&mqueue_fs_type, SB_KERNMOUNT); if (IS_ERR(fc)) return ERR_CAST(fc); ctx = fc->fs_private; ctx->newns = true; put_ipc_ns(ctx->ipc_ns); ctx->ipc_ns = get_ipc_ns(ns); put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns); mnt = fc_mount(fc); put_fs_context(fc); return mnt; } static void init_once(void *foo) { struct mqueue_inode_info *p = foo; inode_init_once(&p->vfs_inode); } static struct inode *mqueue_alloc_inode(struct super_block *sb) { struct mqueue_inode_info *ei; ei = alloc_inode_sb(sb, mqueue_inode_cachep, GFP_KERNEL); if (!ei) return NULL; return &ei->vfs_inode; } static void mqueue_free_inode(struct inode *inode) { kmem_cache_free(mqueue_inode_cachep, MQUEUE_I(inode)); } static void mqueue_evict_inode(struct inode *inode) { struct mqueue_inode_info *info; struct ipc_namespace *ipc_ns; struct msg_msg *msg, *nmsg; LIST_HEAD(tmp_msg); clear_inode(inode); if (S_ISDIR(inode->i_mode)) return; ipc_ns = get_ns_from_inode(inode); info = MQUEUE_I(inode); spin_lock(&info->lock); while ((msg = msg_get(info)) != NULL) list_add_tail(&msg->m_list, &tmp_msg); kfree(info->node_cache); spin_unlock(&info->lock); list_for_each_entry_safe(msg, nmsg, &tmp_msg, m_list) { list_del(&msg->m_list); free_msg(msg); } if (info->ucounts) { unsigned long mq_bytes, mq_treesize; /* Total amount of bytes accounted for the mqueue */ mq_treesize = info->attr.mq_maxmsg * sizeof(struct msg_msg) + min_t(unsigned int, info->attr.mq_maxmsg, MQ_PRIO_MAX) * sizeof(struct posix_msg_tree_node); mq_bytes = mq_treesize + (info->attr.mq_maxmsg * info->attr.mq_msgsize); spin_lock(&mq_lock); dec_rlimit_ucounts(info->ucounts, UCOUNT_RLIMIT_MSGQUEUE, mq_bytes); /* * get_ns_from_inode() ensures that the * (ipc_ns = sb->s_fs_info) is either a valid ipc_ns * to which we now hold a reference, or it is NULL. * We can't put it here under mq_lock, though. */ if (ipc_ns) ipc_ns->mq_queues_count--; spin_unlock(&mq_lock); put_ucounts(info->ucounts); info->ucounts = NULL; } if (ipc_ns) put_ipc_ns(ipc_ns); } static int mqueue_create_attr(struct dentry *dentry, umode_t mode, void *arg) { struct inode *dir = dentry->d_parent->d_inode; struct inode *inode; struct mq_attr *attr = arg; int error; struct ipc_namespace *ipc_ns; spin_lock(&mq_lock); ipc_ns = __get_ns_from_inode(dir); if (!ipc_ns) { error = -EACCES; goto out_unlock; } if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max && !capable(CAP_SYS_RESOURCE)) { error = -ENOSPC; goto out_unlock; } ipc_ns->mq_queues_count++; spin_unlock(&mq_lock); inode = mqueue_get_inode(dir->i_sb, ipc_ns, mode, attr); if (IS_ERR(inode)) { error = PTR_ERR(inode); spin_lock(&mq_lock); ipc_ns->mq_queues_count--; goto out_unlock; } put_ipc_ns(ipc_ns); dir->i_size += DIRENT_SIZE; simple_inode_init_ts(dir); d_instantiate(dentry, inode); dget(dentry); return 0; out_unlock: spin_unlock(&mq_lock); if (ipc_ns) put_ipc_ns(ipc_ns); return error; } static int mqueue_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return mqueue_create_attr(dentry, mode, NULL); } static int mqueue_unlink(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); simple_inode_init_ts(dir); dir->i_size -= DIRENT_SIZE; drop_nlink(inode); dput(dentry); return 0; } /* * This is routine for system read from queue file. * To avoid mess with doing here some sort of mq_receive we allow * to read only queue size & notification info (the only values * that are interesting from user point of view and aren't accessible * through std routines) */ static ssize_t mqueue_read_file(struct file *filp, char __user *u_data, size_t count, loff_t *off) { struct inode *inode = file_inode(filp); struct mqueue_inode_info *info = MQUEUE_I(inode); char buffer[FILENT_SIZE]; ssize_t ret; spin_lock(&info->lock); snprintf(buffer, sizeof(buffer), "QSIZE:%-10lu NOTIFY:%-5d SIGNO:%-5d NOTIFY_PID:%-6d\n", info->qsize, info->notify_owner ? info->notify.sigev_notify : 0, (info->notify_owner && info->notify.sigev_notify == SIGEV_SIGNAL) ? info->notify.sigev_signo : 0, pid_vnr(info->notify_owner)); spin_unlock(&info->lock); buffer[sizeof(buffer)-1] = '\0'; ret = simple_read_from_buffer(u_data, count, off, buffer, strlen(buffer)); if (ret <= 0) return ret; inode_set_atime_to_ts(inode, inode_set_ctime_current(inode)); return ret; } static int mqueue_flush_file(struct file *filp, fl_owner_t id) { struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp)); spin_lock(&info->lock); if (task_tgid(current) == info->notify_owner) remove_notification(info); spin_unlock(&info->lock); return 0; } static __poll_t mqueue_poll_file(struct file *filp, struct poll_table_struct *poll_tab) { struct mqueue_inode_info *info = MQUEUE_I(file_inode(filp)); __poll_t retval = 0; poll_wait(filp, &info->wait_q, poll_tab); spin_lock(&info->lock); if (info->attr.mq_curmsgs) retval = EPOLLIN | EPOLLRDNORM; if (info->attr.mq_curmsgs < info->attr.mq_maxmsg) retval |= EPOLLOUT | EPOLLWRNORM; spin_unlock(&info->lock); return retval; } /* Adds current to info->e_wait_q[sr] before element with smaller prio */ static void wq_add(struct mqueue_inode_info *info, int sr, struct ext_wait_queue *ewp) { struct ext_wait_queue *walk; list_for_each_entry(walk, &info->e_wait_q[sr].list, list) { if (walk->task->prio <= current->prio) { list_add_tail(&ewp->list, &walk->list); return; } } list_add_tail(&ewp->list, &info->e_wait_q[sr].list); } /* * Puts current task to sleep. Caller must hold queue lock. After return * lock isn't held. * sr: SEND or RECV */ static int wq_sleep(struct mqueue_inode_info *info, int sr, ktime_t *timeout, struct ext_wait_queue *ewp) __releases(&info->lock) { int retval; signed long time; wq_add(info, sr, ewp); for (;;) { /* memory barrier not required, we hold info->lock */ __set_current_state(TASK_INTERRUPTIBLE); spin_unlock(&info->lock); time = schedule_hrtimeout_range_clock(timeout, 0, HRTIMER_MODE_ABS, CLOCK_REALTIME); if (READ_ONCE(ewp->state) == STATE_READY) { /* see MQ_BARRIER for purpose/pairing */ smp_acquire__after_ctrl_dep(); retval = 0; goto out; } spin_lock(&info->lock); /* we hold info->lock, so no memory barrier required */ if (READ_ONCE(ewp->state) == STATE_READY) { retval = 0; goto out_unlock; } if (signal_pending(current)) { retval = -ERESTARTSYS; break; } if (time == 0) { retval = -ETIMEDOUT; break; } } list_del(&ewp->list); out_unlock: spin_unlock(&info->lock); out: return retval; } /* * Returns waiting task that should be serviced first or NULL if none exists */ static struct ext_wait_queue *wq_get_first_waiter( struct mqueue_inode_info *info, int sr) { struct list_head *ptr; ptr = info->e_wait_q[sr].list.prev; if (ptr == &info->e_wait_q[sr].list) return NULL; return list_entry(ptr, struct ext_wait_queue, list); } static inline void set_cookie(struct sk_buff *skb, char code) { ((char *)skb->data)[NOTIFY_COOKIE_LEN-1] = code; } /* * The next function is only to split too long sys_mq_timedsend */ static void __do_notify(struct mqueue_inode_info *info) { /* notification * invoked when there is registered process and there isn't process * waiting synchronously for message AND state of queue changed from * empty to not empty. Here we are sure that no one is waiting * synchronously. */ if (info->notify_owner && info->attr.mq_curmsgs == 1) { switch (info->notify.sigev_notify) { case SIGEV_NONE: break; case SIGEV_SIGNAL: { struct kernel_siginfo sig_i; struct task_struct *task; /* do_mq_notify() accepts sigev_signo == 0, why?? */ if (!info->notify.sigev_signo) break; clear_siginfo(&sig_i); sig_i.si_signo = info->notify.sigev_signo; sig_i.si_errno = 0; sig_i.si_code = SI_MESGQ; sig_i.si_value = info->notify.sigev_value; rcu_read_lock(); /* map current pid/uid into info->owner's namespaces */ sig_i.si_pid = task_tgid_nr_ns(current, ns_of_pid(info->notify_owner)); sig_i.si_uid = from_kuid_munged(info->notify_user_ns, current_uid()); /* * We can't use kill_pid_info(), this signal should * bypass check_kill_permission(). It is from kernel * but si_fromuser() can't know this. * We do check the self_exec_id, to avoid sending * signals to programs that don't expect them. */ task = pid_task(info->notify_owner, PIDTYPE_TGID); if (task && task->self_exec_id == info->notify_self_exec_id) { do_send_sig_info(info->notify.sigev_signo, &sig_i, task, PIDTYPE_TGID); } rcu_read_unlock(); break; } case SIGEV_THREAD: set_cookie(info->notify_cookie, NOTIFY_WOKENUP); netlink_sendskb(info->notify_sock, info->notify_cookie); break; } /* after notification unregisters process */ put_pid(info->notify_owner); put_user_ns(info->notify_user_ns); info->notify_owner = NULL; info->notify_user_ns = NULL; } wake_up(&info->wait_q); } static int prepare_timeout(const struct __kernel_timespec __user *u_abs_timeout, struct timespec64 *ts) { if (get_timespec64(ts, u_abs_timeout)) return -EFAULT; if (!timespec64_valid(ts)) return -EINVAL; return 0; } static void remove_notification(struct mqueue_inode_info *info) { if (info->notify_owner != NULL && info->notify.sigev_notify == SIGEV_THREAD) { set_cookie(info->notify_cookie, NOTIFY_REMOVED); netlink_sendskb(info->notify_sock, info->notify_cookie); } put_pid(info->notify_owner); put_user_ns(info->notify_user_ns); info->notify_owner = NULL; info->notify_user_ns = NULL; } static int prepare_open(struct dentry *dentry, int oflag, int ro, umode_t mode, struct filename *name, struct mq_attr *attr) { static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE, MAY_READ | MAY_WRITE }; int acc; if (d_really_is_negative(dentry)) { if (!(oflag & O_CREAT)) return -ENOENT; if (ro) return ro; audit_inode_parent_hidden(name, dentry->d_parent); return vfs_mkobj(dentry, mode & ~current_umask(), mqueue_create_attr, attr); } /* it already existed */ audit_inode(name, dentry, 0); if ((oflag & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL)) return -EEXIST; if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) return -EINVAL; acc = oflag2acc[oflag & O_ACCMODE]; return inode_permission(&nop_mnt_idmap, d_inode(dentry), acc); } static int do_mq_open(const char __user *u_name, int oflag, umode_t mode, struct mq_attr *attr) { struct vfsmount *mnt = current->nsproxy->ipc_ns->mq_mnt; struct dentry *root = mnt->mnt_root; struct filename *name; struct path path; int fd, error; int ro; audit_mq_open(oflag, mode, attr); name = getname(u_name); if (IS_ERR(name)) return PTR_ERR(name); fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) goto out_putname; ro = mnt_want_write(mnt); /* we'll drop it in any case */ inode_lock(d_inode(root)); path.dentry = lookup_one_len(name->name, root, strlen(name->name)); if (IS_ERR(path.dentry)) { error = PTR_ERR(path.dentry); goto out_putfd; } path.mnt = mntget(mnt); error = prepare_open(path.dentry, oflag, ro, mode, name, attr); if (!error) { struct file *file = dentry_open(&path, oflag, current_cred()); if (!IS_ERR(file)) fd_install(fd, file); else error = PTR_ERR(file); } path_put(&path); out_putfd: if (error) { put_unused_fd(fd); fd = error; } inode_unlock(d_inode(root)); if (!ro) mnt_drop_write(mnt); out_putname: putname(name); return fd; } SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, umode_t, mode, struct mq_attr __user *, u_attr) { struct mq_attr attr; if (u_attr && copy_from_user(&attr, u_attr, sizeof(struct mq_attr))) return -EFAULT; return do_mq_open(u_name, oflag, mode, u_attr ? &attr : NULL); } SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) { int err; struct filename *name; struct dentry *dentry; struct inode *inode = NULL; struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; struct vfsmount *mnt = ipc_ns->mq_mnt; name = getname(u_name); if (IS_ERR(name)) return PTR_ERR(name); audit_inode_parent_hidden(name, mnt->mnt_root); err = mnt_want_write(mnt); if (err) goto out_name; inode_lock_nested(d_inode(mnt->mnt_root), I_MUTEX_PARENT); dentry = lookup_one_len(name->name, mnt->mnt_root, strlen(name->name)); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto out_unlock; } inode = d_inode(dentry); if (!inode) { err = -ENOENT; } else { ihold(inode); err = vfs_unlink(&nop_mnt_idmap, d_inode(dentry->d_parent), dentry, NULL); } dput(dentry); out_unlock: inode_unlock(d_inode(mnt->mnt_root)); iput(inode); mnt_drop_write(mnt); out_name: putname(name); return err; } /* Pipelined send and receive functions. * * If a receiver finds no waiting message, then it registers itself in the * list of waiting receivers. A sender checks that list before adding the new * message into the message array. If there is a waiting receiver, then it * bypasses the message array and directly hands the message over to the * receiver. The receiver accepts the message and returns without grabbing the * queue spinlock: * * - Set pointer to message. * - Queue the receiver task for later wakeup (without the info->lock). * - Update its state to STATE_READY. Now the receiver can continue. * - Wake up the process after the lock is dropped. Should the process wake up * before this wakeup (due to a timeout or a signal) it will either see * STATE_READY and continue or acquire the lock to check the state again. * * The same algorithm is used for senders. */ static inline void __pipelined_op(struct wake_q_head *wake_q, struct mqueue_inode_info *info, struct ext_wait_queue *this) { struct task_struct *task; list_del(&this->list); task = get_task_struct(this->task); /* see MQ_BARRIER for purpose/pairing */ smp_store_release(&this->state, STATE_READY); wake_q_add_safe(wake_q, task); } /* pipelined_send() - send a message directly to the task waiting in * sys_mq_timedreceive() (without inserting message into a queue). */ static inline void pipelined_send(struct wake_q_head *wake_q, struct mqueue_inode_info *info, struct msg_msg *message, struct ext_wait_queue *receiver) { receiver->msg = message; __pipelined_op(wake_q, info, receiver); } /* pipelined_receive() - if there is task waiting in sys_mq_timedsend() * gets its message and put to the queue (we have one free place for sure). */ static inline void pipelined_receive(struct wake_q_head *wake_q, struct mqueue_inode_info *info) { struct ext_wait_queue *sender = wq_get_first_waiter(info, SEND); if (!sender) { /* for poll */ wake_up_interruptible(&info->wait_q); return; } if (msg_insert(sender->msg, info)) return; __pipelined_op(wake_q, info, sender); } static int do_mq_timedsend(mqd_t mqdes, const char __user *u_msg_ptr, size_t msg_len, unsigned int msg_prio, struct timespec64 *ts) { struct fd f; struct inode *inode; struct ext_wait_queue wait; struct ext_wait_queue *receiver; struct msg_msg *msg_ptr; struct mqueue_inode_info *info; ktime_t expires, *timeout = NULL; struct posix_msg_tree_node *new_leaf = NULL; int ret = 0; DEFINE_WAKE_Q(wake_q); if (unlikely(msg_prio >= (unsigned long) MQ_PRIO_MAX)) return -EINVAL; if (ts) { expires = timespec64_to_ktime(*ts); timeout = &expires; } audit_mq_sendrecv(mqdes, msg_len, msg_prio, ts); f = fdget(mqdes); if (unlikely(!f.file)) { ret = -EBADF; goto out; } inode = file_inode(f.file); if (unlikely(f.file->f_op != &mqueue_file_operations)) { ret = -EBADF; goto out_fput; } info = MQUEUE_I(inode); audit_file(f.file); if (unlikely(!(f.file->f_mode & FMODE_WRITE))) { ret = -EBADF; goto out_fput; } if (unlikely(msg_len > info->attr.mq_msgsize)) { ret = -EMSGSIZE; goto out_fput; } /* First try to allocate memory, before doing anything with * existing queues. */ msg_ptr = load_msg(u_msg_ptr, msg_len); if (IS_ERR(msg_ptr)) { ret = PTR_ERR(msg_ptr); goto out_fput; } msg_ptr->m_ts = msg_len; msg_ptr->m_type = msg_prio; /* * msg_insert really wants us to have a valid, spare node struct so * it doesn't have to kmalloc a GFP_ATOMIC allocation, but it will * fall back to that if necessary. */ if (!info->node_cache) new_leaf = kmalloc(sizeof(*new_leaf), GFP_KERNEL); spin_lock(&info->lock); if (!info->node_cache && new_leaf) { /* Save our speculative allocation into the cache */ INIT_LIST_HEAD(&new_leaf->msg_list); info->node_cache = new_leaf; new_leaf = NULL; } else { kfree(new_leaf); } if (info->attr.mq_curmsgs == info->attr.mq_maxmsg) { if (f.file->f_flags & O_NONBLOCK) { ret = -EAGAIN; } else { wait.task = current; wait.msg = (void *) msg_ptr; /* memory barrier not required, we hold info->lock */ WRITE_ONCE(wait.state, STATE_NONE); ret = wq_sleep(info, SEND, timeout, &wait); /* * wq_sleep must be called with info->lock held, and * returns with the lock released */ goto out_free; } } else { receiver = wq_get_first_waiter(info, RECV); if (receiver) { pipelined_send(&wake_q, info, msg_ptr, receiver); } else { /* adds message to the queue */ ret = msg_insert(msg_ptr, info); if (ret) goto out_unlock; __do_notify(info); } simple_inode_init_ts(inode); } out_unlock: spin_unlock(&info->lock); wake_up_q(&wake_q); out_free: if (ret) free_msg(msg_ptr); out_fput: fdput(f); out: return ret; } static int do_mq_timedreceive(mqd_t mqdes, char __user *u_msg_ptr, size_t msg_len, unsigned int __user *u_msg_prio, struct timespec64 *ts) { ssize_t ret; struct msg_msg *msg_ptr; struct fd f; struct inode *inode; struct mqueue_inode_info *info; struct ext_wait_queue wait; ktime_t expires, *timeout = NULL; struct posix_msg_tree_node *new_leaf = NULL; if (ts) { expires = timespec64_to_ktime(*ts); timeout = &expires; } audit_mq_sendrecv(mqdes, msg_len, 0, ts); f = fdget(mqdes); if (unlikely(!f.file)) { ret = -EBADF; goto out; } inode = file_inode(f.file); if (unlikely(f.file->f_op != &mqueue_file_operations)) { ret = -EBADF; goto out_fput; } info = MQUEUE_I(inode); audit_file(f.file); if (unlikely(!(f.file->f_mode & FMODE_READ))) { ret = -EBADF; goto out_fput; } /* checks if buffer is big enough */ if (unlikely(msg_len < info->attr.mq_msgsize)) { ret = -EMSGSIZE; goto out_fput; } /* * msg_insert really wants us to have a valid, spare node struct so * it doesn't have to kmalloc a GFP_ATOMIC allocation, but it will * fall back to that if necessary. */ if (!info->node_cache) new_leaf = kmalloc(sizeof(*new_leaf), GFP_KERNEL); spin_lock(&info->lock); if (!info->node_cache && new_leaf) { /* Save our speculative allocation into the cache */ INIT_LIST_HEAD(&new_leaf->msg_list); info->node_cache = new_leaf; } else { kfree(new_leaf); } if (info->attr.mq_curmsgs == 0) { if (f.file->f_flags & O_NONBLOCK) { spin_unlock(&info->lock); ret = -EAGAIN; } else { wait.task = current; /* memory barrier not required, we hold info->lock */ WRITE_ONCE(wait.state, STATE_NONE); ret = wq_sleep(info, RECV, timeout, &wait); msg_ptr = wait.msg; } } else { DEFINE_WAKE_Q(wake_q); msg_ptr = msg_get(info); simple_inode_init_ts(inode); /* There is now free space in queue. */ pipelined_receive(&wake_q, info); spin_unlock(&info->lock); wake_up_q(&wake_q); ret = 0; } if (ret == 0) { ret = msg_ptr->m_ts; if ((u_msg_prio && put_user(msg_ptr->m_type, u_msg_prio)) || store_msg(u_msg_ptr, msg_ptr, msg_ptr->m_ts)) { ret = -EFAULT; } free_msg(msg_ptr); } out_fput: fdput(f); out: return ret; } SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr, size_t, msg_len, unsigned int, msg_prio, const struct __kernel_timespec __user *, u_abs_timeout) { struct timespec64 ts, *p = NULL; if (u_abs_timeout) { int res = prepare_timeout(u_abs_timeout, &ts); if (res) return res; p = &ts; } return do_mq_timedsend(mqdes, u_msg_ptr, msg_len, msg_prio, p); } SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr, size_t, msg_len, unsigned int __user *, u_msg_prio, const struct __kernel_timespec __user *, u_abs_timeout) { struct timespec64 ts, *p = NULL; if (u_abs_timeout) { int res = prepare_timeout(u_abs_timeout, &ts); if (res) return res; p = &ts; } return do_mq_timedreceive(mqdes, u_msg_ptr, msg_len, u_msg_prio, p); } /* * Notes: the case when user wants us to deregister (with NULL as pointer) * and he isn't currently owner of notification, will be silently discarded. * It isn't explicitly defined in the POSIX. */ static int do_mq_notify(mqd_t mqdes, const struct sigevent *notification) { int ret; struct fd f; struct sock *sock; struct inode *inode; struct mqueue_inode_info *info; struct sk_buff *nc; audit_mq_notify(mqdes, notification); nc = NULL; sock = NULL; if (notification != NULL) { if (unlikely(notification->sigev_notify != SIGEV_NONE && notification->sigev_notify != SIGEV_SIGNAL && notification->sigev_notify != SIGEV_THREAD)) return -EINVAL; if (notification->sigev_notify == SIGEV_SIGNAL && !valid_signal(notification->sigev_signo)) { return -EINVAL; } if (notification->sigev_notify == SIGEV_THREAD) { long timeo; /* create the notify skb */ nc = alloc_skb(NOTIFY_COOKIE_LEN, GFP_KERNEL); if (!nc) return -ENOMEM; if (copy_from_user(nc->data, notification->sigev_value.sival_ptr, NOTIFY_COOKIE_LEN)) { ret = -EFAULT; goto free_skb; } /* TODO: add a header? */ skb_put(nc, NOTIFY_COOKIE_LEN); /* and attach it to the socket */ retry: f = fdget(notification->sigev_signo); if (!f.file) { ret = -EBADF; goto out; } sock = netlink_getsockbyfilp(f.file); fdput(f); if (IS_ERR(sock)) { ret = PTR_ERR(sock); goto free_skb; } timeo = MAX_SCHEDULE_TIMEOUT; ret = netlink_attachskb(sock, nc, &timeo, NULL); if (ret == 1) { sock = NULL; goto retry; } if (ret) return ret; } } f = fdget(mqdes); if (!f.file) { ret = -EBADF; goto out; } inode = file_inode(f.file); if (unlikely(f.file->f_op != &mqueue_file_operations)) { ret = -EBADF; goto out_fput; } info = MQUEUE_I(inode); ret = 0; spin_lock(&info->lock); if (notification == NULL) { if (info->notify_owner == task_tgid(current)) { remove_notification(info); inode_set_atime_to_ts(inode, inode_set_ctime_current(inode)); } } else if (info->notify_owner != NULL) { ret = -EBUSY; } else { switch (notification->sigev_notify) { case SIGEV_NONE: info->notify.sigev_notify = SIGEV_NONE; break; case SIGEV_THREAD: info->notify_sock = sock; info->notify_cookie = nc; sock = NULL; nc = NULL; info->notify.sigev_notify = SIGEV_THREAD; break; case SIGEV_SIGNAL: info->notify.sigev_signo = notification->sigev_signo; info->notify.sigev_value = notification->sigev_value; info->notify.sigev_notify = SIGEV_SIGNAL; info->notify_self_exec_id = current->self_exec_id; break; } info->notify_owner = get_pid(task_tgid(current)); info->notify_user_ns = get_user_ns(current_user_ns()); inode_set_atime_to_ts(inode, inode_set_ctime_current(inode)); } spin_unlock(&info->lock); out_fput: fdput(f); out: if (sock) netlink_detachskb(sock, nc); else free_skb: dev_kfree_skb(nc); return ret; } SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes, const struct sigevent __user *, u_notification) { struct sigevent n, *p = NULL; if (u_notification) { if (copy_from_user(&n, u_notification, sizeof(struct sigevent))) return -EFAULT; p = &n; } return do_mq_notify(mqdes, p); } static int do_mq_getsetattr(int mqdes, struct mq_attr *new, struct mq_attr *old) { struct fd f; struct inode *inode; struct mqueue_inode_info *info; if (new && (new->mq_flags & (~O_NONBLOCK))) return -EINVAL; f = fdget(mqdes); if (!f.file) return -EBADF; if (unlikely(f.file->f_op != &mqueue_file_operations)) { fdput(f); return -EBADF; } inode = file_inode(f.file); info = MQUEUE_I(inode); spin_lock(&info->lock); if (old) { *old = info->attr; old->mq_flags = f.file->f_flags & O_NONBLOCK; } if (new) { audit_mq_getsetattr(mqdes, new); spin_lock(&f.file->f_lock); if (new->mq_flags & O_NONBLOCK) f.file->f_flags |= O_NONBLOCK; else f.file->f_flags &= ~O_NONBLOCK; spin_unlock(&f.file->f_lock); inode_set_atime_to_ts(inode, inode_set_ctime_current(inode)); } spin_unlock(&info->lock); fdput(f); return 0; } SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes, const struct mq_attr __user *, u_mqstat, struct mq_attr __user *, u_omqstat) { int ret; struct mq_attr mqstat, omqstat; struct mq_attr *new = NULL, *old = NULL; if (u_mqstat) { new = &mqstat; if (copy_from_user(new, u_mqstat, sizeof(struct mq_attr))) return -EFAULT; } if (u_omqstat) old = &omqstat; ret = do_mq_getsetattr(mqdes, new, old); if (ret || !old) return ret; if (copy_to_user(u_omqstat, old, sizeof(struct mq_attr))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT struct compat_mq_attr { compat_long_t mq_flags; /* message queue flags */ compat_long_t mq_maxmsg; /* maximum number of messages */ compat_long_t mq_msgsize; /* maximum message size */ compat_long_t mq_curmsgs; /* number of messages currently queued */ compat_long_t __reserved[4]; /* ignored for input, zeroed for output */ }; static inline int get_compat_mq_attr(struct mq_attr *attr, const struct compat_mq_attr __user *uattr) { struct compat_mq_attr v; if (copy_from_user(&v, uattr, sizeof(*uattr))) return -EFAULT; memset(attr, 0, sizeof(*attr)); attr->mq_flags = v.mq_flags; attr->mq_maxmsg = v.mq_maxmsg; attr->mq_msgsize = v.mq_msgsize; attr->mq_curmsgs = v.mq_curmsgs; return 0; } static inline int put_compat_mq_attr(const struct mq_attr *attr, struct compat_mq_attr __user *uattr) { struct compat_mq_attr v; memset(&v, 0, sizeof(v)); v.mq_flags = attr->mq_flags; v.mq_maxmsg = attr->mq_maxmsg; v.mq_msgsize = attr->mq_msgsize; v.mq_curmsgs = attr->mq_curmsgs; if (copy_to_user(uattr, &v, sizeof(*uattr))) return -EFAULT; return 0; } COMPAT_SYSCALL_DEFINE4(mq_open, const char __user *, u_name, int, oflag, compat_mode_t, mode, struct compat_mq_attr __user *, u_attr) { struct mq_attr attr, *p = NULL; if (u_attr && oflag & O_CREAT) { p = &attr; if (get_compat_mq_attr(&attr, u_attr)) return -EFAULT; } return do_mq_open(u_name, oflag, mode, p); } COMPAT_SYSCALL_DEFINE2(mq_notify, mqd_t, mqdes, const struct compat_sigevent __user *, u_notification) { struct sigevent n, *p = NULL; if (u_notification) { if (get_compat_sigevent(&n, u_notification)) return -EFAULT; if (n.sigev_notify == SIGEV_THREAD) n.sigev_value.sival_ptr = compat_ptr(n.sigev_value.sival_int); p = &n; } return do_mq_notify(mqdes, p); } COMPAT_SYSCALL_DEFINE3(mq_getsetattr, mqd_t, mqdes, const struct compat_mq_attr __user *, u_mqstat, struct compat_mq_attr __user *, u_omqstat) { int ret; struct mq_attr mqstat, omqstat; struct mq_attr *new = NULL, *old = NULL; if (u_mqstat) { new = &mqstat; if (get_compat_mq_attr(new, u_mqstat)) return -EFAULT; } if (u_omqstat) old = &omqstat; ret = do_mq_getsetattr(mqdes, new, old); if (ret || !old) return ret; if (put_compat_mq_attr(old, u_omqstat)) return -EFAULT; return 0; } #endif #ifdef CONFIG_COMPAT_32BIT_TIME static int compat_prepare_timeout(const struct old_timespec32 __user *p, struct timespec64 *ts) { if (get_old_timespec32(ts, p)) return -EFAULT; if (!timespec64_valid(ts)) return -EINVAL; return 0; } SYSCALL_DEFINE5(mq_timedsend_time32, mqd_t, mqdes, const char __user *, u_msg_ptr, unsigned int, msg_len, unsigned int, msg_prio, const struct old_timespec32 __user *, u_abs_timeout) { struct timespec64 ts, *p = NULL; if (u_abs_timeout) { int res = compat_prepare_timeout(u_abs_timeout, &ts); if (res) return res; p = &ts; } return do_mq_timedsend(mqdes, u_msg_ptr, msg_len, msg_prio, p); } SYSCALL_DEFINE5(mq_timedreceive_time32, mqd_t, mqdes, char __user *, u_msg_ptr, unsigned int, msg_len, unsigned int __user *, u_msg_prio, const struct old_timespec32 __user *, u_abs_timeout) { struct timespec64 ts, *p = NULL; if (u_abs_timeout) { int res = compat_prepare_timeout(u_abs_timeout, &ts); if (res) return res; p = &ts; } return do_mq_timedreceive(mqdes, u_msg_ptr, msg_len, u_msg_prio, p); } #endif static const struct inode_operations mqueue_dir_inode_operations = { .lookup = simple_lookup, .create = mqueue_create, .unlink = mqueue_unlink, }; static const struct file_operations mqueue_file_operations = { .flush = mqueue_flush_file, .poll = mqueue_poll_file, .read = mqueue_read_file, .llseek = default_llseek, }; static const struct super_operations mqueue_super_ops = { .alloc_inode = mqueue_alloc_inode, .free_inode = mqueue_free_inode, .evict_inode = mqueue_evict_inode, .statfs = simple_statfs, }; static const struct fs_context_operations mqueue_fs_context_ops = { .free = mqueue_fs_context_free, .get_tree = mqueue_get_tree, }; static struct file_system_type mqueue_fs_type = { .name = "mqueue", .init_fs_context = mqueue_init_fs_context, .kill_sb = kill_litter_super, .fs_flags = FS_USERNS_MOUNT, }; int mq_init_ns(struct ipc_namespace *ns) { struct vfsmount *m; ns->mq_queues_count = 0; ns->mq_queues_max = DFLT_QUEUESMAX; ns->mq_msg_max = DFLT_MSGMAX; ns->mq_msgsize_max = DFLT_MSGSIZEMAX; ns->mq_msg_default = DFLT_MSG; ns->mq_msgsize_default = DFLT_MSGSIZE; m = mq_create_mount(ns); if (IS_ERR(m)) return PTR_ERR(m); ns->mq_mnt = m; return 0; } void mq_clear_sbinfo(struct ipc_namespace *ns) { ns->mq_mnt->mnt_sb->s_fs_info = NULL; } static int __init init_mqueue_fs(void) { int error; mqueue_inode_cachep = kmem_cache_create("mqueue_inode_cache", sizeof(struct mqueue_inode_info), 0, SLAB_HWCACHE_ALIGN|SLAB_ACCOUNT, init_once); if (mqueue_inode_cachep == NULL) return -ENOMEM; if (!setup_mq_sysctls(&init_ipc_ns)) { pr_warn("sysctl registration failed\n"); error = -ENOMEM; goto out_kmem; } error = register_filesystem(&mqueue_fs_type); if (error) goto out_sysctl; spin_lock_init(&mq_lock); error = mq_init_ns(&init_ipc_ns); if (error) goto out_filesystem; return 0; out_filesystem: unregister_filesystem(&mqueue_fs_type); out_sysctl: retire_mq_sysctls(&init_ipc_ns); out_kmem: kmem_cache_destroy(mqueue_inode_cachep); return error; } device_initcall(init_mqueue_fs); |
| 7 5 2 6 1 5 1 1 4 2 3 1 2 4 1 1 4 2 1 1 3 1 3 3 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 | // SPDX-License-Identifier: GPL-2.0 #include <linux/types.h> #include <net/ip.h> #include <net/tcp.h> #include <net/netlink.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_synproxy.h> #include <net/netfilter/nf_synproxy.h> #include <linux/netfilter/nf_tables.h> #include <linux/netfilter/nf_synproxy.h> struct nft_synproxy { struct nf_synproxy_info info; }; static const struct nla_policy nft_synproxy_policy[NFTA_SYNPROXY_MAX + 1] = { [NFTA_SYNPROXY_MSS] = { .type = NLA_U16 }, [NFTA_SYNPROXY_WSCALE] = { .type = NLA_U8 }, [NFTA_SYNPROXY_FLAGS] = { .type = NLA_U32 }, }; static void nft_synproxy_tcp_options(struct synproxy_options *opts, const struct tcphdr *tcp, struct synproxy_net *snet, struct nf_synproxy_info *info, const struct nft_synproxy *priv) { this_cpu_inc(snet->stats->syn_received); if (tcp->ece && tcp->cwr) opts->options |= NF_SYNPROXY_OPT_ECN; opts->options &= priv->info.options; opts->mss_encode = opts->mss_option; opts->mss_option = info->mss; if (opts->options & NF_SYNPROXY_OPT_TIMESTAMP) synproxy_init_timestamp_cookie(info, opts); else opts->options &= ~(NF_SYNPROXY_OPT_WSCALE | NF_SYNPROXY_OPT_SACK_PERM | NF_SYNPROXY_OPT_ECN); } static void nft_synproxy_eval_v4(const struct nft_synproxy *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt, const struct tcphdr *tcp, struct tcphdr *_tcph, struct synproxy_options *opts) { struct nf_synproxy_info info = priv->info; struct net *net = nft_net(pkt); struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *skb = pkt->skb; if (tcp->syn) { /* Initial SYN from client */ nft_synproxy_tcp_options(opts, tcp, snet, &info, priv); synproxy_send_client_synack(net, skb, tcp, opts); consume_skb(skb); regs->verdict.code = NF_STOLEN; } else if (tcp->ack) { /* ACK from client */ if (synproxy_recv_client_ack(net, skb, tcp, opts, ntohl(tcp->seq))) { consume_skb(skb); regs->verdict.code = NF_STOLEN; } else { regs->verdict.code = NF_DROP; } } } #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) static void nft_synproxy_eval_v6(const struct nft_synproxy *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt, const struct tcphdr *tcp, struct tcphdr *_tcph, struct synproxy_options *opts) { struct nf_synproxy_info info = priv->info; struct net *net = nft_net(pkt); struct synproxy_net *snet = synproxy_pernet(net); struct sk_buff *skb = pkt->skb; if (tcp->syn) { /* Initial SYN from client */ nft_synproxy_tcp_options(opts, tcp, snet, &info, priv); synproxy_send_client_synack_ipv6(net, skb, tcp, opts); consume_skb(skb); regs->verdict.code = NF_STOLEN; } else if (tcp->ack) { /* ACK from client */ if (synproxy_recv_client_ack_ipv6(net, skb, tcp, opts, ntohl(tcp->seq))) { consume_skb(skb); regs->verdict.code = NF_STOLEN; } else { regs->verdict.code = NF_DROP; } } } #endif /* CONFIG_NF_TABLES_IPV6*/ static void nft_synproxy_do_eval(const struct nft_synproxy *priv, struct nft_regs *regs, const struct nft_pktinfo *pkt) { struct synproxy_options opts = {}; struct sk_buff *skb = pkt->skb; int thoff = nft_thoff(pkt); const struct tcphdr *tcp; struct tcphdr _tcph; if (pkt->tprot != IPPROTO_TCP) { regs->verdict.code = NFT_BREAK; return; } if (nf_ip_checksum(skb, nft_hook(pkt), thoff, IPPROTO_TCP)) { regs->verdict.code = NF_DROP; return; } tcp = skb_header_pointer(skb, thoff, sizeof(struct tcphdr), &_tcph); if (!tcp) { regs->verdict.code = NF_DROP; return; } if (!synproxy_parse_options(skb, thoff, tcp, &opts)) { regs->verdict.code = NF_DROP; return; } switch (skb->protocol) { case htons(ETH_P_IP): nft_synproxy_eval_v4(priv, regs, pkt, tcp, &_tcph, &opts); return; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case htons(ETH_P_IPV6): nft_synproxy_eval_v6(priv, regs, pkt, tcp, &_tcph, &opts); return; #endif } regs->verdict.code = NFT_BREAK; } static int nft_synproxy_do_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_synproxy *priv) { struct synproxy_net *snet = synproxy_pernet(ctx->net); u32 flags; int err; if (tb[NFTA_SYNPROXY_MSS]) priv->info.mss = ntohs(nla_get_be16(tb[NFTA_SYNPROXY_MSS])); if (tb[NFTA_SYNPROXY_WSCALE]) priv->info.wscale = nla_get_u8(tb[NFTA_SYNPROXY_WSCALE]); if (tb[NFTA_SYNPROXY_FLAGS]) { flags = ntohl(nla_get_be32(tb[NFTA_SYNPROXY_FLAGS])); if (flags & ~NF_SYNPROXY_OPT_MASK) return -EOPNOTSUPP; priv->info.options = flags; } err = nf_ct_netns_get(ctx->net, ctx->family); if (err) return err; switch (ctx->family) { case NFPROTO_IPV4: err = nf_synproxy_ipv4_init(snet, ctx->net); if (err) goto nf_ct_failure; break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: err = nf_synproxy_ipv6_init(snet, ctx->net); if (err) goto nf_ct_failure; break; #endif case NFPROTO_INET: err = nf_synproxy_ipv4_init(snet, ctx->net); if (err) goto nf_ct_failure; err = nf_synproxy_ipv6_init(snet, ctx->net); if (err) { nf_synproxy_ipv4_fini(snet, ctx->net); goto nf_ct_failure; } break; } return 0; nf_ct_failure: nf_ct_netns_put(ctx->net, ctx->family); return err; } static void nft_synproxy_do_destroy(const struct nft_ctx *ctx) { struct synproxy_net *snet = synproxy_pernet(ctx->net); switch (ctx->family) { case NFPROTO_IPV4: nf_synproxy_ipv4_fini(snet, ctx->net); break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: nf_synproxy_ipv6_fini(snet, ctx->net); break; #endif case NFPROTO_INET: nf_synproxy_ipv4_fini(snet, ctx->net); nf_synproxy_ipv6_fini(snet, ctx->net); break; } nf_ct_netns_put(ctx->net, ctx->family); } static int nft_synproxy_do_dump(struct sk_buff *skb, struct nft_synproxy *priv) { if (nla_put_be16(skb, NFTA_SYNPROXY_MSS, htons(priv->info.mss)) || nla_put_u8(skb, NFTA_SYNPROXY_WSCALE, priv->info.wscale) || nla_put_be32(skb, NFTA_SYNPROXY_FLAGS, htonl(priv->info.options))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static void nft_synproxy_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_synproxy *priv = nft_expr_priv(expr); nft_synproxy_do_eval(priv, regs, pkt); } static int nft_synproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET) return -EOPNOTSUPP; return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD)); } static int nft_synproxy_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_synproxy *priv = nft_expr_priv(expr); return nft_synproxy_do_init(ctx, tb, priv); } static void nft_synproxy_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nft_synproxy_do_destroy(ctx); } static int nft_synproxy_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { struct nft_synproxy *priv = nft_expr_priv(expr); return nft_synproxy_do_dump(skb, priv); } static struct nft_expr_type nft_synproxy_type; static const struct nft_expr_ops nft_synproxy_ops = { .eval = nft_synproxy_eval, .size = NFT_EXPR_SIZE(sizeof(struct nft_synproxy)), .init = nft_synproxy_init, .destroy = nft_synproxy_destroy, .dump = nft_synproxy_dump, .type = &nft_synproxy_type, .validate = nft_synproxy_validate, .reduce = NFT_REDUCE_READONLY, }; static struct nft_expr_type nft_synproxy_type __read_mostly = { .ops = &nft_synproxy_ops, .name = "synproxy", .owner = THIS_MODULE, .policy = nft_synproxy_policy, .maxattr = NFTA_SYNPROXY_MAX, }; static int nft_synproxy_obj_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_object *obj) { struct nft_synproxy *priv = nft_obj_data(obj); return nft_synproxy_do_init(ctx, tb, priv); } static void nft_synproxy_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { nft_synproxy_do_destroy(ctx); } static int nft_synproxy_obj_dump(struct sk_buff *skb, struct nft_object *obj, bool reset) { struct nft_synproxy *priv = nft_obj_data(obj); return nft_synproxy_do_dump(skb, priv); } static void nft_synproxy_obj_eval(struct nft_object *obj, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_synproxy *priv = nft_obj_data(obj); nft_synproxy_do_eval(priv, regs, pkt); } static void nft_synproxy_obj_update(struct nft_object *obj, struct nft_object *newobj) { struct nft_synproxy *newpriv = nft_obj_data(newobj); struct nft_synproxy *priv = nft_obj_data(obj); priv->info = newpriv->info; } static struct nft_object_type nft_synproxy_obj_type; static const struct nft_object_ops nft_synproxy_obj_ops = { .type = &nft_synproxy_obj_type, .size = sizeof(struct nft_synproxy), .init = nft_synproxy_obj_init, .destroy = nft_synproxy_obj_destroy, .dump = nft_synproxy_obj_dump, .eval = nft_synproxy_obj_eval, .update = nft_synproxy_obj_update, }; static struct nft_object_type nft_synproxy_obj_type __read_mostly = { .type = NFT_OBJECT_SYNPROXY, .ops = &nft_synproxy_obj_ops, .maxattr = NFTA_SYNPROXY_MAX, .policy = nft_synproxy_policy, .owner = THIS_MODULE, }; static int __init nft_synproxy_module_init(void) { int err; err = nft_register_obj(&nft_synproxy_obj_type); if (err < 0) return err; err = nft_register_expr(&nft_synproxy_type); if (err < 0) goto err; return 0; err: nft_unregister_obj(&nft_synproxy_obj_type); return err; } static void __exit nft_synproxy_module_exit(void) { nft_unregister_expr(&nft_synproxy_type); nft_unregister_obj(&nft_synproxy_obj_type); } module_init(nft_synproxy_module_init); module_exit(nft_synproxy_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Fernando Fernandez <ffmancera@riseup.net>"); MODULE_ALIAS_NFT_EXPR("synproxy"); MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_SYNPROXY); MODULE_DESCRIPTION("nftables SYNPROXY expression support"); |
| 124 | 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Cryptographic API for algorithms (i.e., low-level API). * * Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au> */ #ifndef _CRYPTO_ALGAPI_H #define _CRYPTO_ALGAPI_H #include <crypto/utils.h> #include <linux/align.h> #include <linux/cache.h> #include <linux/crypto.h> #include <linux/types.h> #include <linux/workqueue.h> /* * Maximum values for blocksize and alignmask, used to allocate * static buffers that are big enough for any combination of * algs and architectures. Ciphers have a lower maximum size. */ #define MAX_ALGAPI_BLOCKSIZE 160 #define MAX_ALGAPI_ALIGNMASK 127 #define MAX_CIPHER_BLOCKSIZE 16 #define MAX_CIPHER_ALIGNMASK 15 #ifdef ARCH_DMA_MINALIGN #define CRYPTO_DMA_ALIGN ARCH_DMA_MINALIGN #else #define CRYPTO_DMA_ALIGN CRYPTO_MINALIGN #endif #define CRYPTO_DMA_PADDING ((CRYPTO_DMA_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1)) /* * Autoloaded crypto modules should only use a prefixed name to avoid allowing * arbitrary modules to be loaded. Loading from userspace may still need the * unprefixed names, so retains those aliases as well. * This uses __MODULE_INFO directly instead of MODULE_ALIAS because pre-4.3 * gcc (e.g. avr32 toolchain) uses __LINE__ for uniqueness, and this macro * expands twice on the same line. Instead, use a separate base name for the * alias. */ #define MODULE_ALIAS_CRYPTO(name) \ __MODULE_INFO(alias, alias_userspace, name); \ __MODULE_INFO(alias, alias_crypto, "crypto-" name) struct crypto_aead; struct crypto_instance; struct module; struct notifier_block; struct rtattr; struct scatterlist; struct seq_file; struct sk_buff; struct crypto_type { unsigned int (*ctxsize)(struct crypto_alg *alg, u32 type, u32 mask); unsigned int (*extsize)(struct crypto_alg *alg); int (*init_tfm)(struct crypto_tfm *tfm); void (*show)(struct seq_file *m, struct crypto_alg *alg); int (*report)(struct sk_buff *skb, struct crypto_alg *alg); void (*free)(struct crypto_instance *inst); unsigned int type; unsigned int maskclear; unsigned int maskset; unsigned int tfmsize; }; struct crypto_instance { struct crypto_alg alg; struct crypto_template *tmpl; union { /* Node in list of instances after registration. */ struct hlist_node list; /* List of attached spawns before registration. */ struct crypto_spawn *spawns; }; struct work_struct free_work; void *__ctx[] CRYPTO_MINALIGN_ATTR; }; struct crypto_template { struct list_head list; struct hlist_head instances; struct module *module; int (*create)(struct crypto_template *tmpl, struct rtattr **tb); char name[CRYPTO_MAX_ALG_NAME]; }; struct crypto_spawn { struct list_head list; struct crypto_alg *alg; union { /* Back pointer to instance after registration.*/ struct crypto_instance *inst; /* Spawn list pointer prior to registration. */ struct crypto_spawn *next; }; const struct crypto_type *frontend; u32 mask; bool dead; bool registered; }; struct crypto_queue { struct list_head list; struct list_head *backlog; unsigned int qlen; unsigned int max_qlen; }; struct scatter_walk { struct scatterlist *sg; unsigned int offset; }; struct crypto_attr_alg { char name[CRYPTO_MAX_ALG_NAME]; }; struct crypto_attr_type { u32 type; u32 mask; }; /* * Algorithm registration interface. */ int crypto_register_alg(struct crypto_alg *alg); void crypto_unregister_alg(struct crypto_alg *alg); int crypto_register_algs(struct crypto_alg *algs, int count); void crypto_unregister_algs(struct crypto_alg *algs, int count); void crypto_mod_put(struct crypto_alg *alg); int crypto_register_template(struct crypto_template *tmpl); int crypto_register_templates(struct crypto_template *tmpls, int count); void crypto_unregister_template(struct crypto_template *tmpl); void crypto_unregister_templates(struct crypto_template *tmpls, int count); struct crypto_template *crypto_lookup_template(const char *name); int crypto_register_instance(struct crypto_template *tmpl, struct crypto_instance *inst); void crypto_unregister_instance(struct crypto_instance *inst); int crypto_grab_spawn(struct crypto_spawn *spawn, struct crypto_instance *inst, const char *name, u32 type, u32 mask); void crypto_drop_spawn(struct crypto_spawn *spawn); struct crypto_tfm *crypto_spawn_tfm(struct crypto_spawn *spawn, u32 type, u32 mask); void *crypto_spawn_tfm2(struct crypto_spawn *spawn); struct crypto_attr_type *crypto_get_attr_type(struct rtattr **tb); int crypto_check_attr_type(struct rtattr **tb, u32 type, u32 *mask_ret); const char *crypto_attr_alg_name(struct rtattr *rta); int crypto_inst_setname(struct crypto_instance *inst, const char *name, struct crypto_alg *alg); void crypto_init_queue(struct crypto_queue *queue, unsigned int max_qlen); int crypto_enqueue_request(struct crypto_queue *queue, struct crypto_async_request *request); void crypto_enqueue_request_head(struct crypto_queue *queue, struct crypto_async_request *request); struct crypto_async_request *crypto_dequeue_request(struct crypto_queue *queue); static inline unsigned int crypto_queue_len(struct crypto_queue *queue) { return queue->qlen; } void crypto_inc(u8 *a, unsigned int size); static inline void *crypto_tfm_ctx(struct crypto_tfm *tfm) { return tfm->__crt_ctx; } static inline void *crypto_tfm_ctx_align(struct crypto_tfm *tfm, unsigned int align) { if (align <= crypto_tfm_ctx_alignment()) align = 1; return PTR_ALIGN(crypto_tfm_ctx(tfm), align); } static inline unsigned int crypto_dma_align(void) { return CRYPTO_DMA_ALIGN; } static inline unsigned int crypto_dma_padding(void) { return (crypto_dma_align() - 1) & ~(crypto_tfm_ctx_alignment() - 1); } static inline void *crypto_tfm_ctx_dma(struct crypto_tfm *tfm) { return crypto_tfm_ctx_align(tfm, crypto_dma_align()); } static inline struct crypto_instance *crypto_tfm_alg_instance( struct crypto_tfm *tfm) { return container_of(tfm->__crt_alg, struct crypto_instance, alg); } static inline void *crypto_instance_ctx(struct crypto_instance *inst) { return inst->__ctx; } static inline struct crypto_async_request *crypto_get_backlog( struct crypto_queue *queue) { return queue->backlog == &queue->list ? NULL : container_of(queue->backlog, struct crypto_async_request, list); } static inline u32 crypto_requires_off(struct crypto_attr_type *algt, u32 off) { return (algt->type ^ off) & algt->mask & off; } /* * When an algorithm uses another algorithm (e.g., if it's an instance of a * template), these are the flags that should always be set on the "outer" * algorithm if any "inner" algorithm has them set. */ #define CRYPTO_ALG_INHERITED_FLAGS \ (CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK | \ CRYPTO_ALG_ALLOCATES_MEMORY) /* * Given the type and mask that specify the flags restrictions on a template * instance being created, return the mask that should be passed to * crypto_grab_*() (along with type=0) to honor any request the user made to * have any of the CRYPTO_ALG_INHERITED_FLAGS clear. */ static inline u32 crypto_algt_inherited_mask(struct crypto_attr_type *algt) { return crypto_requires_off(algt, CRYPTO_ALG_INHERITED_FLAGS); } int crypto_register_notifier(struct notifier_block *nb); int crypto_unregister_notifier(struct notifier_block *nb); /* Crypto notification events. */ enum { CRYPTO_MSG_ALG_REQUEST, CRYPTO_MSG_ALG_REGISTER, CRYPTO_MSG_ALG_LOADED, }; static inline void crypto_request_complete(struct crypto_async_request *req, int err) { req->complete(req->data, err); } static inline u32 crypto_tfm_alg_type(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_flags & CRYPTO_ALG_TYPE_MASK; } #endif /* _CRYPTO_ALGAPI_H */ |
| 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2022-2023 NXP */ #include "common.h" #include "netlink.h" struct mm_req_info { struct ethnl_req_info base; }; struct mm_reply_data { struct ethnl_reply_data base; struct ethtool_mm_state state; struct ethtool_mm_stats stats; }; #define MM_REPDATA(__reply_base) \ container_of(__reply_base, struct mm_reply_data, base) #define ETHTOOL_MM_STAT_CNT \ (__ETHTOOL_A_MM_STAT_CNT - (ETHTOOL_A_MM_STAT_PAD + 1)) const struct nla_policy ethnl_mm_get_policy[ETHTOOL_A_MM_HEADER + 1] = { [ETHTOOL_A_MM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static int mm_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct mm_reply_data *data = MM_REPDATA(reply_base); struct net_device *dev = reply_base->dev; const struct ethtool_ops *ops; int ret; ops = dev->ethtool_ops; if (!ops->get_mm) return -EOPNOTSUPP; ethtool_stats_init((u64 *)&data->stats, sizeof(data->stats) / sizeof(u64)); ret = ethnl_ops_begin(dev); if (ret < 0) return ret; ret = ops->get_mm(dev, &data->state); if (ret) goto out_complete; if (ops->get_mm_stats && (req_base->flags & ETHTOOL_FLAG_STATS)) ops->get_mm_stats(dev, &data->stats); out_complete: ethnl_ops_complete(dev); return ret; } static int mm_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { int len = 0; len += nla_total_size(sizeof(u8)); /* _MM_PMAC_ENABLED */ len += nla_total_size(sizeof(u8)); /* _MM_TX_ENABLED */ len += nla_total_size(sizeof(u8)); /* _MM_TX_ACTIVE */ len += nla_total_size(sizeof(u8)); /* _MM_VERIFY_ENABLED */ len += nla_total_size(sizeof(u8)); /* _MM_VERIFY_STATUS */ len += nla_total_size(sizeof(u32)); /* _MM_VERIFY_TIME */ len += nla_total_size(sizeof(u32)); /* _MM_MAX_VERIFY_TIME */ len += nla_total_size(sizeof(u32)); /* _MM_TX_MIN_FRAG_SIZE */ len += nla_total_size(sizeof(u32)); /* _MM_RX_MIN_FRAG_SIZE */ if (req_base->flags & ETHTOOL_FLAG_STATS) len += nla_total_size(0) + /* _MM_STATS */ nla_total_size_64bit(sizeof(u64)) * ETHTOOL_MM_STAT_CNT; return len; } static int mm_put_stat(struct sk_buff *skb, u64 val, u16 attrtype) { if (val == ETHTOOL_STAT_NOT_SET) return 0; if (nla_put_u64_64bit(skb, attrtype, val, ETHTOOL_A_MM_STAT_PAD)) return -EMSGSIZE; return 0; } static int mm_put_stats(struct sk_buff *skb, const struct ethtool_mm_stats *stats) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_MM_STATS); if (!nest) return -EMSGSIZE; if (mm_put_stat(skb, stats->MACMergeFrameAssErrorCount, ETHTOOL_A_MM_STAT_REASSEMBLY_ERRORS) || mm_put_stat(skb, stats->MACMergeFrameSmdErrorCount, ETHTOOL_A_MM_STAT_SMD_ERRORS) || mm_put_stat(skb, stats->MACMergeFrameAssOkCount, ETHTOOL_A_MM_STAT_REASSEMBLY_OK) || mm_put_stat(skb, stats->MACMergeFragCountRx, ETHTOOL_A_MM_STAT_RX_FRAG_COUNT) || mm_put_stat(skb, stats->MACMergeFragCountTx, ETHTOOL_A_MM_STAT_TX_FRAG_COUNT) || mm_put_stat(skb, stats->MACMergeHoldCount, ETHTOOL_A_MM_STAT_HOLD_COUNT)) goto err_cancel; nla_nest_end(skb, nest); return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int mm_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct mm_reply_data *data = MM_REPDATA(reply_base); const struct ethtool_mm_state *state = &data->state; if (nla_put_u8(skb, ETHTOOL_A_MM_TX_ENABLED, state->tx_enabled) || nla_put_u8(skb, ETHTOOL_A_MM_TX_ACTIVE, state->tx_active) || nla_put_u8(skb, ETHTOOL_A_MM_PMAC_ENABLED, state->pmac_enabled) || nla_put_u8(skb, ETHTOOL_A_MM_VERIFY_ENABLED, state->verify_enabled) || nla_put_u8(skb, ETHTOOL_A_MM_VERIFY_STATUS, state->verify_status) || nla_put_u32(skb, ETHTOOL_A_MM_VERIFY_TIME, state->verify_time) || nla_put_u32(skb, ETHTOOL_A_MM_MAX_VERIFY_TIME, state->max_verify_time) || nla_put_u32(skb, ETHTOOL_A_MM_TX_MIN_FRAG_SIZE, state->tx_min_frag_size) || nla_put_u32(skb, ETHTOOL_A_MM_RX_MIN_FRAG_SIZE, state->rx_min_frag_size)) return -EMSGSIZE; if (req_base->flags & ETHTOOL_FLAG_STATS && mm_put_stats(skb, &data->stats)) return -EMSGSIZE; return 0; } const struct nla_policy ethnl_mm_set_policy[ETHTOOL_A_MM_MAX + 1] = { [ETHTOOL_A_MM_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_MM_VERIFY_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_MM_VERIFY_TIME] = NLA_POLICY_RANGE(NLA_U32, 1, 128), [ETHTOOL_A_MM_TX_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_MM_PMAC_ENABLED] = NLA_POLICY_MAX(NLA_U8, 1), [ETHTOOL_A_MM_TX_MIN_FRAG_SIZE] = NLA_POLICY_RANGE(NLA_U32, 60, 252), }; static void mm_state_to_cfg(const struct ethtool_mm_state *state, struct ethtool_mm_cfg *cfg) { /* We could also compare state->verify_status against * ETHTOOL_MM_VERIFY_STATUS_DISABLED, but state->verify_enabled * is more like an administrative state which should be seen in * ETHTOOL_MSG_MM_GET replies. For example, a port with verification * disabled might be in the ETHTOOL_MM_VERIFY_STATUS_INITIAL * if it's down. */ cfg->verify_enabled = state->verify_enabled; cfg->verify_time = state->verify_time; cfg->tx_enabled = state->tx_enabled; cfg->pmac_enabled = state->pmac_enabled; cfg->tx_min_frag_size = state->tx_min_frag_size; } static int ethnl_set_mm_validate(struct ethnl_req_info *req_info, struct genl_info *info) { const struct ethtool_ops *ops = req_info->dev->ethtool_ops; return ops->get_mm && ops->set_mm ? 1 : -EOPNOTSUPP; } static int ethnl_set_mm(struct ethnl_req_info *req_info, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct net_device *dev = req_info->dev; struct ethtool_mm_state state = {}; struct nlattr **tb = info->attrs; struct ethtool_mm_cfg cfg = {}; bool mod = false; int ret; ret = dev->ethtool_ops->get_mm(dev, &state); if (ret) return ret; mm_state_to_cfg(&state, &cfg); ethnl_update_bool(&cfg.verify_enabled, tb[ETHTOOL_A_MM_VERIFY_ENABLED], &mod); ethnl_update_u32(&cfg.verify_time, tb[ETHTOOL_A_MM_VERIFY_TIME], &mod); ethnl_update_bool(&cfg.tx_enabled, tb[ETHTOOL_A_MM_TX_ENABLED], &mod); ethnl_update_bool(&cfg.pmac_enabled, tb[ETHTOOL_A_MM_PMAC_ENABLED], &mod); ethnl_update_u32(&cfg.tx_min_frag_size, tb[ETHTOOL_A_MM_TX_MIN_FRAG_SIZE], &mod); if (!mod) return 0; if (cfg.verify_time > state.max_verify_time) { NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_MM_VERIFY_TIME], "verifyTime exceeds device maximum"); return -ERANGE; } if (cfg.verify_enabled && !cfg.tx_enabled) { NL_SET_ERR_MSG(extack, "Verification requires TX enabled"); return -EINVAL; } if (cfg.tx_enabled && !cfg.pmac_enabled) { NL_SET_ERR_MSG(extack, "TX enabled requires pMAC enabled"); return -EINVAL; } ret = dev->ethtool_ops->set_mm(dev, &cfg, extack); return ret < 0 ? ret : 1; } const struct ethnl_request_ops ethnl_mm_request_ops = { .request_cmd = ETHTOOL_MSG_MM_GET, .reply_cmd = ETHTOOL_MSG_MM_GET_REPLY, .hdr_attr = ETHTOOL_A_MM_HEADER, .req_info_size = sizeof(struct mm_req_info), .reply_data_size = sizeof(struct mm_reply_data), .prepare_data = mm_prepare_data, .reply_size = mm_reply_size, .fill_reply = mm_fill_reply, .set_validate = ethnl_set_mm_validate, .set = ethnl_set_mm, .set_ntf_cmd = ETHTOOL_MSG_MM_NTF, }; /* Returns whether a given device supports the MAC merge layer * (has an eMAC and a pMAC). Must be called under rtnl_lock() and * ethnl_ops_begin(). */ bool __ethtool_dev_mm_supported(struct net_device *dev) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_mm_state state = {}; int ret = -EOPNOTSUPP; if (ops && ops->get_mm) ret = ops->get_mm(dev, &state); return !ret; } bool ethtool_dev_mm_supported(struct net_device *dev) { const struct ethtool_ops *ops = dev->ethtool_ops; bool supported; int ret; ASSERT_RTNL(); if (!ops) return false; ret = ethnl_ops_begin(dev); if (ret < 0) return false; supported = __ethtool_dev_mm_supported(dev); ethnl_ops_complete(dev); return supported; } EXPORT_SYMBOL_GPL(ethtool_dev_mm_supported); |
| 1 3 3 2 3 3 3 1 2 1 2 2 2 2 2 2 2 2 2 3 3 3 3 2 1 1 3 1 2 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 | // SPDX-License-Identifier: GPL-2.0-only /* * TCP Illinois congestion control. * Home page: * http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html * * The algorithm is described in: * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm * for High-Speed Networks" * http://tamerbasar.csl.illinois.edu/LiuBasarSrikantPerfEvalArtJun2008.pdf * * Implemented from description in paper and ns-2 simulation. * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/inet_diag.h> #include <asm/div64.h> #include <net/tcp.h> #define ALPHA_SHIFT 7 #define ALPHA_SCALE (1u<<ALPHA_SHIFT) #define ALPHA_MIN ((3*ALPHA_SCALE)/10) /* ~0.3 */ #define ALPHA_MAX (10*ALPHA_SCALE) /* 10.0 */ #define ALPHA_BASE ALPHA_SCALE /* 1.0 */ #define RTT_MAX (U32_MAX / ALPHA_MAX) /* 3.3 secs */ #define BETA_SHIFT 6 #define BETA_SCALE (1u<<BETA_SHIFT) #define BETA_MIN (BETA_SCALE/8) /* 0.125 */ #define BETA_MAX (BETA_SCALE/2) /* 0.5 */ #define BETA_BASE BETA_MAX static int win_thresh __read_mostly = 15; module_param(win_thresh, int, 0); MODULE_PARM_DESC(win_thresh, "Window threshold for starting adaptive sizing"); static int theta __read_mostly = 5; module_param(theta, int, 0); MODULE_PARM_DESC(theta, "# of fast RTT's before full growth"); /* TCP Illinois Parameters */ struct illinois { u64 sum_rtt; /* sum of rtt's measured within last rtt */ u16 cnt_rtt; /* # of rtts measured within last rtt */ u32 base_rtt; /* min of all rtt in usec */ u32 max_rtt; /* max of all rtt in usec */ u32 end_seq; /* right edge of current RTT */ u32 alpha; /* Additive increase */ u32 beta; /* Muliplicative decrease */ u16 acked; /* # packets acked by current ACK */ u8 rtt_above; /* average rtt has gone above threshold */ u8 rtt_low; /* # of rtts measurements below threshold */ }; static void rtt_reset(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); ca->end_seq = tp->snd_nxt; ca->cnt_rtt = 0; ca->sum_rtt = 0; /* TODO: age max_rtt? */ } static void tcp_illinois_init(struct sock *sk) { struct illinois *ca = inet_csk_ca(sk); ca->alpha = ALPHA_MAX; ca->beta = BETA_BASE; ca->base_rtt = 0x7fffffff; ca->max_rtt = 0; ca->acked = 0; ca->rtt_low = 0; ca->rtt_above = 0; rtt_reset(sk); } /* Measure RTT for each ack. */ static void tcp_illinois_acked(struct sock *sk, const struct ack_sample *sample) { struct illinois *ca = inet_csk_ca(sk); s32 rtt_us = sample->rtt_us; ca->acked = sample->pkts_acked; /* dup ack, no rtt sample */ if (rtt_us < 0) return; /* ignore bogus values, this prevents wraparound in alpha math */ if (rtt_us > RTT_MAX) rtt_us = RTT_MAX; /* keep track of minimum RTT seen so far */ if (ca->base_rtt > rtt_us) ca->base_rtt = rtt_us; /* and max */ if (ca->max_rtt < rtt_us) ca->max_rtt = rtt_us; ++ca->cnt_rtt; ca->sum_rtt += rtt_us; } /* Maximum queuing delay */ static inline u32 max_delay(const struct illinois *ca) { return ca->max_rtt - ca->base_rtt; } /* Average queuing delay */ static inline u32 avg_delay(const struct illinois *ca) { u64 t = ca->sum_rtt; do_div(t, ca->cnt_rtt); return t - ca->base_rtt; } /* * Compute value of alpha used for additive increase. * If small window then use 1.0, equivalent to Reno. * * For larger windows, adjust based on average delay. * A. If average delay is at minimum (we are uncongested), * then use large alpha (10.0) to increase faster. * B. If average delay is at maximum (getting congested) * then use small alpha (0.3) * * The result is a convex window growth curve. */ static u32 alpha(struct illinois *ca, u32 da, u32 dm) { u32 d1 = dm / 100; /* Low threshold */ if (da <= d1) { /* If never got out of low delay zone, then use max */ if (!ca->rtt_above) return ALPHA_MAX; /* Wait for 5 good RTT's before allowing alpha to go alpha max. * This prevents one good RTT from causing sudden window increase. */ if (++ca->rtt_low < theta) return ca->alpha; ca->rtt_low = 0; ca->rtt_above = 0; return ALPHA_MAX; } ca->rtt_above = 1; /* * Based on: * * (dm - d1) amin amax * k1 = ------------------- * amax - amin * * (dm - d1) amin * k2 = ---------------- - d1 * amax - amin * * k1 * alpha = ---------- * k2 + da */ dm -= d1; da -= d1; return (dm * ALPHA_MAX) / (dm + (da * (ALPHA_MAX - ALPHA_MIN)) / ALPHA_MIN); } /* * Beta used for multiplicative decrease. * For small window sizes returns same value as Reno (0.5) * * If delay is small (10% of max) then beta = 1/8 * If delay is up to 80% of max then beta = 1/2 * In between is a linear function */ static u32 beta(u32 da, u32 dm) { u32 d2, d3; d2 = dm / 10; if (da <= d2) return BETA_MIN; d3 = (8 * dm) / 10; if (da >= d3 || d3 <= d2) return BETA_MAX; /* * Based on: * * bmin d3 - bmax d2 * k3 = ------------------- * d3 - d2 * * bmax - bmin * k4 = ------------- * d3 - d2 * * b = k3 + k4 da */ return (BETA_MIN * d3 - BETA_MAX * d2 + (BETA_MAX - BETA_MIN) * da) / (d3 - d2); } /* Update alpha and beta values once per RTT */ static void update_params(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); if (tcp_snd_cwnd(tp) < win_thresh) { ca->alpha = ALPHA_BASE; ca->beta = BETA_BASE; } else if (ca->cnt_rtt > 0) { u32 dm = max_delay(ca); u32 da = avg_delay(ca); ca->alpha = alpha(ca, da, dm); ca->beta = beta(da, dm); } rtt_reset(sk); } /* * In case of loss, reset to default values */ static void tcp_illinois_state(struct sock *sk, u8 new_state) { struct illinois *ca = inet_csk_ca(sk); if (new_state == TCP_CA_Loss) { ca->alpha = ALPHA_BASE; ca->beta = BETA_BASE; ca->rtt_low = 0; ca->rtt_above = 0; rtt_reset(sk); } } /* * Increase window in response to successful acknowledgment. */ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); if (after(ack, ca->end_seq)) update_params(sk); /* RFC2861 only increase cwnd if fully utilized */ if (!tcp_is_cwnd_limited(sk)) return; /* In slow start */ if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { u32 delta; /* snd_cwnd_cnt is # of packets since last cwnd increment */ tp->snd_cwnd_cnt += ca->acked; ca->acked = 1; /* This is close approximation of: * tp->snd_cwnd += alpha/tp->snd_cwnd */ delta = (tp->snd_cwnd_cnt * ca->alpha) >> ALPHA_SHIFT; if (delta >= tcp_snd_cwnd(tp)) { tcp_snd_cwnd_set(tp, min(tcp_snd_cwnd(tp) + delta / tcp_snd_cwnd(tp), (u32)tp->snd_cwnd_clamp)); tp->snd_cwnd_cnt = 0; } } } static u32 tcp_illinois_ssthresh(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct illinois *ca = inet_csk_ca(sk); u32 decr; /* Multiplicative decrease */ decr = (tcp_snd_cwnd(tp) * ca->beta) >> BETA_SHIFT; return max(tcp_snd_cwnd(tp) - decr, 2U); } /* Extract info for Tcp socket info provided via netlink. */ static size_t tcp_illinois_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { const struct illinois *ca = inet_csk_ca(sk); if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) { info->vegas.tcpv_enabled = 1; info->vegas.tcpv_rttcnt = ca->cnt_rtt; info->vegas.tcpv_minrtt = ca->base_rtt; info->vegas.tcpv_rtt = 0; if (info->vegas.tcpv_rttcnt > 0) { u64 t = ca->sum_rtt; do_div(t, info->vegas.tcpv_rttcnt); info->vegas.tcpv_rtt = t; } *attr = INET_DIAG_VEGASINFO; return sizeof(struct tcpvegas_info); } return 0; } static struct tcp_congestion_ops tcp_illinois __read_mostly = { .init = tcp_illinois_init, .ssthresh = tcp_illinois_ssthresh, .undo_cwnd = tcp_reno_undo_cwnd, .cong_avoid = tcp_illinois_cong_avoid, .set_state = tcp_illinois_state, .get_info = tcp_illinois_info, .pkts_acked = tcp_illinois_acked, .owner = THIS_MODULE, .name = "illinois", }; static int __init tcp_illinois_register(void) { BUILD_BUG_ON(sizeof(struct illinois) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&tcp_illinois); } static void __exit tcp_illinois_unregister(void) { tcp_unregister_congestion_control(&tcp_illinois); } module_init(tcp_illinois_register); module_exit(tcp_illinois_unregister); MODULE_AUTHOR("Stephen Hemminger, Shao Liu"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("TCP Illinois"); MODULE_VERSION("1.0"); |
| 2 4 2 2 2 2 1 1 1 1 1 1 1 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 | // SPDX-License-Identifier: GPL-2.0-only /* * vhost transport for vsock * * Copyright (C) 2013-2015 Red Hat, Inc. * Author: Asias He <asias@redhat.com> * Stefan Hajnoczi <stefanha@redhat.com> */ #include <linux/miscdevice.h> #include <linux/atomic.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/vmalloc.h> #include <net/sock.h> #include <linux/virtio_vsock.h> #include <linux/vhost.h> #include <linux/hashtable.h> #include <net/af_vsock.h> #include "vhost.h" #define VHOST_VSOCK_DEFAULT_HOST_CID 2 /* Max number of bytes transferred before requeueing the job. * Using this limit prevents one virtqueue from starving others. */ #define VHOST_VSOCK_WEIGHT 0x80000 /* Max number of packets transferred before requeueing the job. * Using this limit prevents one virtqueue from starving others with * small pkts. */ #define VHOST_VSOCK_PKT_WEIGHT 256 enum { VHOST_VSOCK_FEATURES = VHOST_FEATURES | (1ULL << VIRTIO_F_ACCESS_PLATFORM) | (1ULL << VIRTIO_VSOCK_F_SEQPACKET) }; enum { VHOST_VSOCK_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) }; /* Used to track all the vhost_vsock instances on the system. */ static DEFINE_MUTEX(vhost_vsock_mutex); static DEFINE_READ_MOSTLY_HASHTABLE(vhost_vsock_hash, 8); struct vhost_vsock { struct vhost_dev dev; struct vhost_virtqueue vqs[2]; /* Link to global vhost_vsock_hash, writes use vhost_vsock_mutex */ struct hlist_node hash; struct vhost_work send_pkt_work; struct sk_buff_head send_pkt_queue; /* host->guest pending packets */ atomic_t queued_replies; u32 guest_cid; bool seqpacket_allow; }; static u32 vhost_transport_get_local_cid(void) { return VHOST_VSOCK_DEFAULT_HOST_CID; } /* Callers that dereference the return value must hold vhost_vsock_mutex or the * RCU read lock. */ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid) { struct vhost_vsock *vsock; hash_for_each_possible_rcu(vhost_vsock_hash, vsock, hash, guest_cid) { u32 other_cid = vsock->guest_cid; /* Skip instances that have no CID yet */ if (other_cid == 0) continue; if (other_cid == guest_cid) return vsock; } return NULL; } static void vhost_transport_do_send_pkt(struct vhost_vsock *vsock, struct vhost_virtqueue *vq) { struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX]; int pkts = 0, total_len = 0; bool added = false; bool restart_tx = false; mutex_lock(&vq->mutex); if (!vhost_vq_get_backend(vq)) goto out; if (!vq_meta_prefetch(vq)) goto out; /* Avoid further vmexits, we're already processing the virtqueue */ vhost_disable_notify(&vsock->dev, vq); do { struct virtio_vsock_hdr *hdr; size_t iov_len, payload_len; struct iov_iter iov_iter; u32 flags_to_restore = 0; struct sk_buff *skb; unsigned out, in; size_t nbytes; u32 offset; int head; skb = virtio_vsock_skb_dequeue(&vsock->send_pkt_queue); if (!skb) { vhost_enable_notify(&vsock->dev, vq); break; } head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov), &out, &in, NULL, NULL); if (head < 0) { virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); break; } if (head == vq->num) { virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); /* We cannot finish yet if more buffers snuck in while * re-enabling notify. */ if (unlikely(vhost_enable_notify(&vsock->dev, vq))) { vhost_disable_notify(&vsock->dev, vq); continue; } break; } if (out) { kfree_skb(skb); vq_err(vq, "Expected 0 output buffers, got %u\n", out); break; } iov_len = iov_length(&vq->iov[out], in); if (iov_len < sizeof(*hdr)) { kfree_skb(skb); vq_err(vq, "Buffer len [%zu] too small\n", iov_len); break; } iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[out], in, iov_len); offset = VIRTIO_VSOCK_SKB_CB(skb)->offset; payload_len = skb->len - offset; hdr = virtio_vsock_hdr(skb); /* If the packet is greater than the space available in the * buffer, we split it using multiple buffers. */ if (payload_len > iov_len - sizeof(*hdr)) { payload_len = iov_len - sizeof(*hdr); /* As we are copying pieces of large packet's buffer to * small rx buffers, headers of packets in rx queue are * created dynamically and are initialized with header * of current packet(except length). But in case of * SOCK_SEQPACKET, we also must clear message delimeter * bit (VIRTIO_VSOCK_SEQ_EOM) and MSG_EOR bit * (VIRTIO_VSOCK_SEQ_EOR) if set. Otherwise, * there will be sequence of packets with these * bits set. After initialized header will be copied to * rx buffer, these required bits will be restored. */ if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) { hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM); flags_to_restore |= VIRTIO_VSOCK_SEQ_EOM; if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOR) { hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); flags_to_restore |= VIRTIO_VSOCK_SEQ_EOR; } } } /* Set the correct length in the header */ hdr->len = cpu_to_le32(payload_len); nbytes = copy_to_iter(hdr, sizeof(*hdr), &iov_iter); if (nbytes != sizeof(*hdr)) { kfree_skb(skb); vq_err(vq, "Faulted on copying pkt hdr\n"); break; } if (skb_copy_datagram_iter(skb, offset, &iov_iter, payload_len)) { kfree_skb(skb); vq_err(vq, "Faulted on copying pkt buf\n"); break; } /* Deliver to monitoring devices all packets that we * will transmit. */ virtio_transport_deliver_tap_pkt(skb); vhost_add_used(vq, head, sizeof(*hdr) + payload_len); added = true; VIRTIO_VSOCK_SKB_CB(skb)->offset += payload_len; total_len += payload_len; /* If we didn't send all the payload we can requeue the packet * to send it with the next available buffer. */ if (VIRTIO_VSOCK_SKB_CB(skb)->offset < skb->len) { hdr->flags |= cpu_to_le32(flags_to_restore); /* We are queueing the same skb to handle * the remaining bytes, and we want to deliver it * to monitoring devices in the next iteration. */ virtio_vsock_skb_clear_tap_delivered(skb); virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb); } else { if (virtio_vsock_skb_reply(skb)) { int val; val = atomic_dec_return(&vsock->queued_replies); /* Do we have resources to resume tx * processing? */ if (val + 1 == tx_vq->num) restart_tx = true; } consume_skb(skb); } } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); if (added) vhost_signal(&vsock->dev, vq); out: mutex_unlock(&vq->mutex); if (restart_tx) vhost_poll_queue(&tx_vq->poll); } static void vhost_transport_send_pkt_work(struct vhost_work *work) { struct vhost_virtqueue *vq; struct vhost_vsock *vsock; vsock = container_of(work, struct vhost_vsock, send_pkt_work); vq = &vsock->vqs[VSOCK_VQ_RX]; vhost_transport_do_send_pkt(vsock, vq); } static int vhost_transport_send_pkt(struct sk_buff *skb) { struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb); struct vhost_vsock *vsock; int len = skb->len; rcu_read_lock(); /* Find the vhost_vsock according to guest context id */ vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid)); if (!vsock) { rcu_read_unlock(); kfree_skb(skb); return -ENODEV; } if (virtio_vsock_skb_reply(skb)) atomic_inc(&vsock->queued_replies); virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb); vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work); rcu_read_unlock(); return len; } static int vhost_transport_cancel_pkt(struct vsock_sock *vsk) { struct vhost_vsock *vsock; int cnt = 0; int ret = -ENODEV; rcu_read_lock(); /* Find the vhost_vsock according to guest context id */ vsock = vhost_vsock_get(vsk->remote_addr.svm_cid); if (!vsock) goto out; cnt = virtio_transport_purge_skbs(vsk, &vsock->send_pkt_queue); if (cnt) { struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX]; int new_cnt; new_cnt = atomic_sub_return(cnt, &vsock->queued_replies); if (new_cnt + cnt >= tx_vq->num && new_cnt < tx_vq->num) vhost_poll_queue(&tx_vq->poll); } ret = 0; out: rcu_read_unlock(); return ret; } static struct sk_buff * vhost_vsock_alloc_skb(struct vhost_virtqueue *vq, unsigned int out, unsigned int in) { struct virtio_vsock_hdr *hdr; struct iov_iter iov_iter; struct sk_buff *skb; size_t payload_len; size_t nbytes; size_t len; if (in != 0) { vq_err(vq, "Expected 0 input buffers, got %u\n", in); return NULL; } len = iov_length(vq->iov, out); /* len contains both payload and hdr */ skb = virtio_vsock_alloc_skb(len, GFP_KERNEL); if (!skb) return NULL; iov_iter_init(&iov_iter, ITER_SOURCE, vq->iov, out, len); hdr = virtio_vsock_hdr(skb); nbytes = copy_from_iter(hdr, sizeof(*hdr), &iov_iter); if (nbytes != sizeof(*hdr)) { vq_err(vq, "Expected %zu bytes for pkt->hdr, got %zu bytes\n", sizeof(*hdr), nbytes); kfree_skb(skb); return NULL; } payload_len = le32_to_cpu(hdr->len); /* No payload */ if (!payload_len) return skb; /* The pkt is too big or the length in the header is invalid */ if (payload_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE || payload_len + sizeof(*hdr) > len) { kfree_skb(skb); return NULL; } virtio_vsock_skb_rx_put(skb); nbytes = copy_from_iter(skb->data, payload_len, &iov_iter); if (nbytes != payload_len) { vq_err(vq, "Expected %zu byte payload, got %zu bytes\n", payload_len, nbytes); kfree_skb(skb); return NULL; } return skb; } /* Is there space left for replies to rx packets? */ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock) { struct vhost_virtqueue *vq = &vsock->vqs[VSOCK_VQ_TX]; int val; smp_rmb(); /* paired with atomic_inc() and atomic_dec_return() */ val = atomic_read(&vsock->queued_replies); return val < vq->num; } static bool vhost_transport_msgzerocopy_allow(void) { return true; } static bool vhost_transport_seqpacket_allow(u32 remote_cid); static struct virtio_transport vhost_transport = { .transport = { .module = THIS_MODULE, .get_local_cid = vhost_transport_get_local_cid, .init = virtio_transport_do_socket_init, .destruct = virtio_transport_destruct, .release = virtio_transport_release, .connect = virtio_transport_connect, .shutdown = virtio_transport_shutdown, .cancel_pkt = vhost_transport_cancel_pkt, .dgram_enqueue = virtio_transport_dgram_enqueue, .dgram_dequeue = virtio_transport_dgram_dequeue, .dgram_bind = virtio_transport_dgram_bind, .dgram_allow = virtio_transport_dgram_allow, .stream_enqueue = virtio_transport_stream_enqueue, .stream_dequeue = virtio_transport_stream_dequeue, .stream_has_data = virtio_transport_stream_has_data, .stream_has_space = virtio_transport_stream_has_space, .stream_rcvhiwat = virtio_transport_stream_rcvhiwat, .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, .seqpacket_allow = vhost_transport_seqpacket_allow, .seqpacket_has_data = virtio_transport_seqpacket_has_data, .msgzerocopy_allow = vhost_transport_msgzerocopy_allow, .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, .notify_recv_pre_block = virtio_transport_notify_recv_pre_block, .notify_recv_pre_dequeue = virtio_transport_notify_recv_pre_dequeue, .notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue, .notify_send_init = virtio_transport_notify_send_init, .notify_send_pre_block = virtio_transport_notify_send_pre_block, .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue, .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue, .notify_buffer_size = virtio_transport_notify_buffer_size, .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat, .read_skb = virtio_transport_read_skb, }, .send_pkt = vhost_transport_send_pkt, }; static bool vhost_transport_seqpacket_allow(u32 remote_cid) { struct vhost_vsock *vsock; bool seqpacket_allow = false; rcu_read_lock(); vsock = vhost_vsock_get(remote_cid); if (vsock) seqpacket_allow = vsock->seqpacket_allow; rcu_read_unlock(); return seqpacket_allow; } static void vhost_vsock_handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock, dev); int head, pkts = 0, total_len = 0; unsigned int out, in; struct sk_buff *skb; bool added = false; mutex_lock(&vq->mutex); if (!vhost_vq_get_backend(vq)) goto out; if (!vq_meta_prefetch(vq)) goto out; vhost_disable_notify(&vsock->dev, vq); do { struct virtio_vsock_hdr *hdr; if (!vhost_vsock_more_replies(vsock)) { /* Stop tx until the device processes already * pending replies. Leave tx virtqueue * callbacks disabled. */ goto no_more_replies; } head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov), &out, &in, NULL, NULL); if (head < 0) break; if (head == vq->num) { if (unlikely(vhost_enable_notify(&vsock->dev, vq))) { vhost_disable_notify(&vsock->dev, vq); continue; } break; } skb = vhost_vsock_alloc_skb(vq, out, in); if (!skb) { vq_err(vq, "Faulted on pkt\n"); continue; } total_len += sizeof(*hdr) + skb->len; /* Deliver to monitoring devices all received packets */ virtio_transport_deliver_tap_pkt(skb); hdr = virtio_vsock_hdr(skb); /* Only accept correctly addressed packets */ if (le64_to_cpu(hdr->src_cid) == vsock->guest_cid && le64_to_cpu(hdr->dst_cid) == vhost_transport_get_local_cid()) virtio_transport_recv_pkt(&vhost_transport, skb); else kfree_skb(skb); vhost_add_used(vq, head, 0); added = true; } while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len))); no_more_replies: if (added) vhost_signal(&vsock->dev, vq); out: mutex_unlock(&vq->mutex); } static void vhost_vsock_handle_rx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work); struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock, dev); vhost_transport_do_send_pkt(vsock, vq); } static int vhost_vsock_start(struct vhost_vsock *vsock) { struct vhost_virtqueue *vq; size_t i; int ret; mutex_lock(&vsock->dev.mutex); ret = vhost_dev_check_owner(&vsock->dev); if (ret) goto err; for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); if (!vhost_vq_access_ok(vq)) { ret = -EFAULT; goto err_vq; } if (!vhost_vq_get_backend(vq)) { vhost_vq_set_backend(vq, vsock); ret = vhost_vq_init_access(vq); if (ret) goto err_vq; } mutex_unlock(&vq->mutex); } /* Some packets may have been queued before the device was started, * let's kick the send worker to send them. */ vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work); mutex_unlock(&vsock->dev.mutex); return 0; err_vq: vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); } err: mutex_unlock(&vsock->dev.mutex); return ret; } static int vhost_vsock_stop(struct vhost_vsock *vsock, bool check_owner) { size_t i; int ret = 0; mutex_lock(&vsock->dev.mutex); if (check_owner) { ret = vhost_dev_check_owner(&vsock->dev); if (ret) goto err; } for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { struct vhost_virtqueue *vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); vhost_vq_set_backend(vq, NULL); mutex_unlock(&vq->mutex); } err: mutex_unlock(&vsock->dev.mutex); return ret; } static void vhost_vsock_free(struct vhost_vsock *vsock) { kvfree(vsock); } static int vhost_vsock_dev_open(struct inode *inode, struct file *file) { struct vhost_virtqueue **vqs; struct vhost_vsock *vsock; int ret; /* This struct is large and allocation could fail, fall back to vmalloc * if there is no other way. */ vsock = kvmalloc(sizeof(*vsock), GFP_KERNEL | __GFP_RETRY_MAYFAIL); if (!vsock) return -ENOMEM; vqs = kmalloc_array(ARRAY_SIZE(vsock->vqs), sizeof(*vqs), GFP_KERNEL); if (!vqs) { ret = -ENOMEM; goto out; } vsock->guest_cid = 0; /* no CID assigned yet */ vsock->seqpacket_allow = false; atomic_set(&vsock->queued_replies, 0); vqs[VSOCK_VQ_TX] = &vsock->vqs[VSOCK_VQ_TX]; vqs[VSOCK_VQ_RX] = &vsock->vqs[VSOCK_VQ_RX]; vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick; vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick; vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV, VHOST_VSOCK_PKT_WEIGHT, VHOST_VSOCK_WEIGHT, true, NULL); file->private_data = vsock; skb_queue_head_init(&vsock->send_pkt_queue); vhost_work_init(&vsock->send_pkt_work, vhost_transport_send_pkt_work); return 0; out: vhost_vsock_free(vsock); return ret; } static void vhost_vsock_flush(struct vhost_vsock *vsock) { vhost_dev_flush(&vsock->dev); } static void vhost_vsock_reset_orphans(struct sock *sk) { struct vsock_sock *vsk = vsock_sk(sk); /* vmci_transport.c doesn't take sk_lock here either. At least we're * under vsock_table_lock so the sock cannot disappear while we're * executing. */ /* If the peer is still valid, no need to reset connection */ if (vhost_vsock_get(vsk->remote_addr.svm_cid)) return; /* If the close timeout is pending, let it expire. This avoids races * with the timeout callback. */ if (vsk->close_work_scheduled) return; sock_set_flag(sk, SOCK_DONE); vsk->peer_shutdown = SHUTDOWN_MASK; sk->sk_state = SS_UNCONNECTED; sk->sk_err = ECONNRESET; sk_error_report(sk); } static int vhost_vsock_dev_release(struct inode *inode, struct file *file) { struct vhost_vsock *vsock = file->private_data; mutex_lock(&vhost_vsock_mutex); if (vsock->guest_cid) hash_del_rcu(&vsock->hash); mutex_unlock(&vhost_vsock_mutex); /* Wait for other CPUs to finish using vsock */ synchronize_rcu(); /* Iterating over all connections for all CIDs to find orphans is * inefficient. Room for improvement here. */ vsock_for_each_connected_socket(&vhost_transport.transport, vhost_vsock_reset_orphans); /* Don't check the owner, because we are in the release path, so we * need to stop the vsock device in any case. * vhost_vsock_stop() can not fail in this case, so we don't need to * check the return code. */ vhost_vsock_stop(vsock, false); vhost_vsock_flush(vsock); vhost_dev_stop(&vsock->dev); virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue); vhost_dev_cleanup(&vsock->dev); kfree(vsock->dev.vqs); vhost_vsock_free(vsock); return 0; } static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid) { struct vhost_vsock *other; /* Refuse reserved CIDs */ if (guest_cid <= VMADDR_CID_HOST || guest_cid == U32_MAX) return -EINVAL; /* 64-bit CIDs are not yet supported */ if (guest_cid > U32_MAX) return -EINVAL; /* Refuse if CID is assigned to the guest->host transport (i.e. nested * VM), to make the loopback work. */ if (vsock_find_cid(guest_cid)) return -EADDRINUSE; /* Refuse if CID is already in use */ mutex_lock(&vhost_vsock_mutex); other = vhost_vsock_get(guest_cid); if (other && other != vsock) { mutex_unlock(&vhost_vsock_mutex); return -EADDRINUSE; } if (vsock->guest_cid) hash_del_rcu(&vsock->hash); vsock->guest_cid = guest_cid; hash_add_rcu(vhost_vsock_hash, &vsock->hash, vsock->guest_cid); mutex_unlock(&vhost_vsock_mutex); return 0; } static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features) { struct vhost_virtqueue *vq; int i; if (features & ~VHOST_VSOCK_FEATURES) return -EOPNOTSUPP; mutex_lock(&vsock->dev.mutex); if ((features & (1 << VHOST_F_LOG_ALL)) && !vhost_log_access_ok(&vsock->dev)) { goto err; } if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) { if (vhost_init_device_iotlb(&vsock->dev)) goto err; } vsock->seqpacket_allow = features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET); for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); vq->acked_features = features; mutex_unlock(&vq->mutex); } mutex_unlock(&vsock->dev.mutex); return 0; err: mutex_unlock(&vsock->dev.mutex); return -EFAULT; } static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl, unsigned long arg) { struct vhost_vsock *vsock = f->private_data; void __user *argp = (void __user *)arg; u64 guest_cid; u64 features; int start; int r; switch (ioctl) { case VHOST_VSOCK_SET_GUEST_CID: if (copy_from_user(&guest_cid, argp, sizeof(guest_cid))) return -EFAULT; return vhost_vsock_set_cid(vsock, guest_cid); case VHOST_VSOCK_SET_RUNNING: if (copy_from_user(&start, argp, sizeof(start))) return -EFAULT; if (start) return vhost_vsock_start(vsock); else return vhost_vsock_stop(vsock, true); case VHOST_GET_FEATURES: features = VHOST_VSOCK_FEATURES; if (copy_to_user(argp, &features, sizeof(features))) return -EFAULT; return 0; case VHOST_SET_FEATURES: if (copy_from_user(&features, argp, sizeof(features))) return -EFAULT; return vhost_vsock_set_features(vsock, features); case VHOST_GET_BACKEND_FEATURES: features = VHOST_VSOCK_BACKEND_FEATURES; if (copy_to_user(argp, &features, sizeof(features))) return -EFAULT; return 0; case VHOST_SET_BACKEND_FEATURES: if (copy_from_user(&features, argp, sizeof(features))) return -EFAULT; if (features & ~VHOST_VSOCK_BACKEND_FEATURES) return -EOPNOTSUPP; vhost_set_backend_features(&vsock->dev, features); return 0; default: mutex_lock(&vsock->dev.mutex); r = vhost_dev_ioctl(&vsock->dev, ioctl, argp); if (r == -ENOIOCTLCMD) r = vhost_vring_ioctl(&vsock->dev, ioctl, argp); else vhost_vsock_flush(vsock); mutex_unlock(&vsock->dev.mutex); return r; } } static ssize_t vhost_vsock_chr_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct vhost_vsock *vsock = file->private_data; struct vhost_dev *dev = &vsock->dev; int noblock = file->f_flags & O_NONBLOCK; return vhost_chr_read_iter(dev, to, noblock); } static ssize_t vhost_vsock_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct vhost_vsock *vsock = file->private_data; struct vhost_dev *dev = &vsock->dev; return vhost_chr_write_iter(dev, from); } static __poll_t vhost_vsock_chr_poll(struct file *file, poll_table *wait) { struct vhost_vsock *vsock = file->private_data; struct vhost_dev *dev = &vsock->dev; return vhost_chr_poll(file, dev, wait); } static const struct file_operations vhost_vsock_fops = { .owner = THIS_MODULE, .open = vhost_vsock_dev_open, .release = vhost_vsock_dev_release, .llseek = noop_llseek, .unlocked_ioctl = vhost_vsock_dev_ioctl, .compat_ioctl = compat_ptr_ioctl, .read_iter = vhost_vsock_chr_read_iter, .write_iter = vhost_vsock_chr_write_iter, .poll = vhost_vsock_chr_poll, }; static struct miscdevice vhost_vsock_misc = { .minor = VHOST_VSOCK_MINOR, .name = "vhost-vsock", .fops = &vhost_vsock_fops, }; static int __init vhost_vsock_init(void) { int ret; ret = vsock_core_register(&vhost_transport.transport, VSOCK_TRANSPORT_F_H2G); if (ret < 0) return ret; ret = misc_register(&vhost_vsock_misc); if (ret) { vsock_core_unregister(&vhost_transport.transport); return ret; } return 0; }; static void __exit vhost_vsock_exit(void) { misc_deregister(&vhost_vsock_misc); vsock_core_unregister(&vhost_transport.transport); }; module_init(vhost_vsock_init); module_exit(vhost_vsock_exit); MODULE_LICENSE("GPL v2"); MODULE_AUTHOR("Asias He"); MODULE_DESCRIPTION("vhost transport for vsock "); MODULE_ALIAS_MISCDEV(VHOST_VSOCK_MINOR); MODULE_ALIAS("devname:vhost-vsock"); |
| 2176 1 635 1 1556 3 2199 43 43 20 21 4 4 4 4 4 56 1 1 1 1 8 43 28 22 1579 1586 703 1047 1605 1 1 1 1 1598 16 1601 397 1413 1588 43 2 23 19 27 16 41 43 1596 14 421 1176 700 1061 1607 1596 1 1 1 14 16 16 1 2 1 7 9 9 279 277 279 279 180 77 20 7 18 21 68 1 1 1 1 56 8 61 55 243 1 1 1 2 236 219 18 47 191 227 33 1 18 15 21 10 31 13 19 222 4 180 37 189 27 207 46 175 1 1 1 39 15 24 1 1 26 10 18 33 216 41 41 27 27 125 2 1 110 15 1 1 1 115 1 1 4 40 77 77 113 118 129 1 111 1 20 1 6 13 19 19 20 1 19 5 1 1 1 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/read_write.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .mmap = generic_file_readonly_mmap, .splice_read = filemap_splice_read, }; EXPORT_SYMBOL(generic_ro_fops); static inline bool unsigned_offsets(struct file *file) { return file->f_mode & FMODE_UNSIGNED_OFFSET; } /** * vfs_setpos - update the file offset for lseek * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * * This is a low-level filesystem helper for updating the file offset to * the value specified by @offset if the given offset is valid and it is * not equal to the current file offset. * * Return the specified offset on success and -EINVAL on invalid offset. */ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) { if (offset < 0 && !unsigned_offsets(file)) return -EINVAL; if (offset > maxsize) return -EINVAL; if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; } return offset; } EXPORT_SYMBOL(vfs_setpos); /** * generic_file_llseek_size - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @maxsize: max size of this file in file system * @eof: offset used for SEEK_END position * * This is a variant of generic_file_llseek that allows passing in a custom * maximum file size and a custom EOF position, for e.g. hashed directories * * Synchronization: * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. * read/writes behave like SEEK_SET against seeks. */ loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof) { switch (whence) { case SEEK_END: offset += eof; break; case SEEK_CUR: /* * Here we special-case the lseek(fd, 0, SEEK_CUR) * position-querying operation. Avoid rewriting the "same" * f_pos value back to the file because a concurrent read(), * write() or lseek() might have altered it */ if (offset == 0) return file->f_pos; /* * f_lock protects against read/modify/write race with other * SEEK_CURs. Note that parallel writes and reads behave * like SEEK_SET. */ spin_lock(&file->f_lock); offset = vfs_setpos(file, file->f_pos + offset, maxsize); spin_unlock(&file->f_lock); return offset; case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ if ((unsigned long long)offset >= eof) return -ENXIO; break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ if ((unsigned long long)offset >= eof) return -ENXIO; offset = eof; break; } return vfs_setpos(file, offset, maxsize); } EXPORT_SYMBOL(generic_file_llseek_size); /** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is a generic implemenation of ->llseek useable for all normal local * filesystems. It just updates the file offset to the value specified by * @offset and @whence. */ loff_t generic_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; return generic_file_llseek_size(file, offset, whence, inode->i_sb->s_maxbytes, i_size_read(inode)); } EXPORT_SYMBOL(generic_file_llseek); /** * fixed_size_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: size of the file * */ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: case SEEK_END: return generic_file_llseek_size(file, offset, whence, size, size); default: return -EINVAL; } } EXPORT_SYMBOL(fixed_size_llseek); /** * no_seek_end_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * */ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, OFFSET_MAX, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek); /** * no_seek_end_llseek_size - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: maximal offset allowed * */ loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, size, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek_size); /** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is an implementation of ->llseek useable for the rare special case when * userspace expects the seek to succeed but the (device) file is actually not * able to perform the seek. In this case you use noop_llseek() instead of * falling back to the default implementation of ->llseek. */ loff_t noop_llseek(struct file *file, loff_t offset, int whence) { return file->f_pos; } EXPORT_SYMBOL(noop_llseek); loff_t default_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); loff_t retval; inode_lock(inode); switch (whence) { case SEEK_END: offset += i_size_read(inode); break; case SEEK_CUR: if (offset == 0) { retval = file->f_pos; goto out; } offset += file->f_pos; break; case SEEK_DATA: /* * In the generic case the entire file is data, so as * long as offset isn't at the end of the file then the * offset is data. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so * as long as offset isn't i_size or larger, return * i_size. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } offset = inode->i_size; break; } retval = -EINVAL; if (offset >= 0 || unsigned_offsets(file)) { if (offset != file->f_pos) { file->f_pos = offset; file->f_version = 0; } retval = offset; } out: inode_unlock(inode); return retval; } EXPORT_SYMBOL(default_llseek); loff_t vfs_llseek(struct file *file, loff_t offset, int whence) { if (!(file->f_mode & FMODE_LSEEK)) return -ESPIPE; return file->f_op->llseek(file, offset, whence); } EXPORT_SYMBOL(vfs_llseek); static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; struct fd f = fdget_pos(fd); if (!f.file) return -EBADF; retval = -EINVAL; if (whence <= SEEK_MAX) { loff_t res = vfs_llseek(f.file, offset, whence); retval = res; if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } fdput_pos(f); return retval; } SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #endif #if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \ defined(__ARCH_WANT_SYS_LLSEEK) SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned long, offset_low, loff_t __user *, result, unsigned int, whence) { int retval; struct fd f = fdget_pos(fd); loff_t offset; if (!f.file) return -EBADF; retval = -EINVAL; if (whence > SEEK_MAX) goto out_putf; offset = vfs_llseek(f.file, ((loff_t) offset_high << 32) | offset_low, whence); retval = (int)offset; if (offset >= 0) { retval = -EFAULT; if (!copy_to_user(result, &offset, sizeof(offset))) retval = 0; } out_putf: fdput_pos(f); return retval; } #endif int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { int mask = read_write == READ ? MAY_READ : MAY_WRITE; int ret; if (unlikely((ssize_t) count < 0)) return -EINVAL; if (ppos) { loff_t pos = *ppos; if (unlikely(pos < 0)) { if (!unsigned_offsets(file)) return -EINVAL; if (count >= -pos) /* both values are in 0..LLONG_MAX */ return -EOVERFLOW; } else if (unlikely((loff_t) (pos + count) < 0)) { if (!unsigned_offsets(file)) return -EINVAL; } } ret = security_file_permission(file, mask); if (ret) return ret; return fsnotify_file_area_perm(file, mask, ppos, count); } EXPORT_SYMBOL(rw_verify_area); static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_DEST, buf, len); ret = filp->f_op->read_iter(&kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } static int warn_unsupported(struct file *file, const char *op) { pr_warn_ratelimited( "kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n", op, file, current->pid, current->comm); return -EINVAL; } ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) return -EINVAL; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; /* * Also fail if ->read_iter and ->read are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->read_iter || file->f_op->read)) return warn_unsupported(file, "read"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; iov_iter_kvec(&iter, ITER_DEST, &iov, 1, iov.iov_len); ret = file->f_op->read_iter(&kiocb, &iter); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; if (file->f_op->read) ret = file->f_op->read(file, buf, count, pos); else if (file->f_op->read_iter) ret = new_sync_read(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_SOURCE, (void __user *)buf, len); ret = filp->f_op->write_iter(&kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0 && ppos) *ppos = kiocb.ki_pos; return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos) { struct kiocb kiocb; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; /* * Also fail if ->write_iter and ->write are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->write_iter || file->f_op->write)) return warn_unsupported(file, "write"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; ret = file->f_op->write_iter(&kiocb, from); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = (void *)buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct iov_iter iter; iov_iter_kvec(&iter, ITER_SOURCE, &iov, 1, iov.iov_len); return __kernel_write_iter(file, &iter, pos); } /* * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", * but autofs is one of the few internal kernel users that actually * wants this _and_ can be built as a module. So we need to export * this symbol for autofs, even though it really isn't appropriate * for any other kernel modules. */ EXPORT_SYMBOL_GPL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; file_start_write(file); ret = __kernel_write(file, buf, count, pos); file_end_write(file); return ret; } EXPORT_SYMBOL(kernel_write); ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; file_start_write(file); if (file->f_op->write) ret = file->f_op->write(file, buf, count, pos); else if (file->f_op->write_iter) ret = new_sync_write(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); file_end_write(file); return ret; } /* file_ppos returns &file->f_pos or NULL if file is stream */ static inline loff_t *file_ppos(struct file *file) { return file->f_mode & FMODE_STREAM ? NULL : &file->f_pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_read(f.file, buf, count, ppos); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } return ret; } SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { return ksys_read(fd, buf, count); } ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_write(f.file, buf, count, ppos); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } return ret; } SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) { return ksys_write(fd, buf, count); } ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) ret = vfs_read(f.file, buf, count, &pos); fdput(f); } return ret; } SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, size_t, count, loff_t, pos) { return ksys_pread64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PREAD64) COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pread64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) ret = vfs_write(f.file, buf, count, &pos); fdput(f); } return ret; } SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, loff_t, pos) { return ksys_pwrite64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PWRITE64) COMPAT_SYSCALL_DEFINE5(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pwrite64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); ret = kiocb_set_rw_flags(&kiocb, flags, type); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); if (type == READ) ret = filp->f_op->read_iter(&kiocb, iter); else ret = filp->f_op->write_iter(&kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; if (flags & ~RWF_HIPRI) return -EOPNOTSUPP; while (iov_iter_count(iter)) { ssize_t nr; if (type == READ) { nr = filp->f_op->read(filp, iter_iov_addr(iter), iter_iov_len(iter), ppos); } else { nr = filp->f_op->write(filp, iter_iov_addr(iter), iter_iov_len(iter), ppos); } if (nr < 0) { if (!ret) ret = nr; break; } ret += nr; if (nr != iter_iov_len(iter)) break; iov_iter_advance(iter, nr); } return ret; } ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = file->f_op->read_iter(iocb, iter); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_read); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, ppos, tot_len); if (ret < 0) return ret; ret = do_iter_readv_writev(file, iter, ppos, READ, flags); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iter_read); /* * Caller is responsible for calling kiocb_end_write() on completion * if async iocb was queued. */ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->write_iter) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; kiocb_start_write(iocb); ret = file->f_op->write_iter(iocb, iter); if (ret != -EIOCBQUEUED) kiocb_end_write(iocb); if (ret > 0) fsnotify_modify(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_write); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { size_t tot_len; ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (!file->f_op->write_iter) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, ppos, tot_len); if (ret < 0) return ret; file_start_write(file); ret = do_iter_readv_writev(file, iter, ppos, WRITE, flags); if (ret > 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL(vfs_iter_write); static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) return ret; tot_len = iov_iter_count(&iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, pos, tot_len); if (ret < 0) goto out; if (file->f_op->read_iter) ret = do_iter_readv_writev(file, &iter, pos, READ, flags); else ret = do_loop_readv_writev(file, &iter, pos, READ, flags); out: if (ret >= 0) fsnotify_access(file); kfree(iov); return ret; } static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) return ret; tot_len = iov_iter_count(&iter); if (!tot_len) goto out; ret = rw_verify_area(WRITE, file, pos, tot_len); if (ret < 0) goto out; file_start_write(file); if (file->f_op->write_iter) ret = do_iter_readv_writev(file, &iter, pos, WRITE, flags); else ret = do_loop_readv_writev(file, &iter, pos, WRITE, flags); if (ret > 0) fsnotify_modify(file); file_end_write(file); out: kfree(iov); return ret; } static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_readv(f.file, vec, vlen, ppos, flags); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { struct fd f = fdget_pos(fd); ssize_t ret = -EBADF; if (f.file) { loff_t pos, *ppos = file_ppos(f.file); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_writev(f.file, vec, vlen, ppos, flags); if (ret >= 0 && ppos) f.file->f_pos = pos; fdput_pos(f); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) { #define HALF_LONG_BITS (BITS_PER_LONG / 2) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PREAD) ret = vfs_readv(f.file, vec, vlen, &pos, flags); fdput(f); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { struct fd f; ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; f = fdget(fd); if (f.file) { ret = -ESPIPE; if (f.file->f_mode & FMODE_PWRITE) ret = vfs_writev(f.file, vec, vlen, &pos, flags); fdput(f); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_readv(fd, vec, vlen, 0); } SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_writev(fd, vec, vlen, 0); } SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_preadv(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_pwritev(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } /* * Various compat syscalls. Note that they all pretend to take a native * iovec - import_iovec will properly treat those as compat_iovecs based on * in_compat_syscall(). */ #ifdef CONFIG_COMPAT #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_preadv(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_preadv(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_pwritev(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_pwritev(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif /* CONFIG_COMPAT */ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { struct fd in, out; struct inode *in_inode, *out_inode; struct pipe_inode_info *opipe; loff_t pos; loff_t out_pos; ssize_t retval; int fl; /* * Get input file, and verify that it is ok.. */ retval = -EBADF; in = fdget(in_fd); if (!in.file) goto out; if (!(in.file->f_mode & FMODE_READ)) goto fput_in; retval = -ESPIPE; if (!ppos) { pos = in.file->f_pos; } else { pos = *ppos; if (!(in.file->f_mode & FMODE_PREAD)) goto fput_in; } retval = rw_verify_area(READ, in.file, &pos, count); if (retval < 0) goto fput_in; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; /* * Get output file, and verify that it is ok.. */ retval = -EBADF; out = fdget(out_fd); if (!out.file) goto fput_in; if (!(out.file->f_mode & FMODE_WRITE)) goto fput_out; in_inode = file_inode(in.file); out_inode = file_inode(out.file); out_pos = out.file->f_pos; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); if (unlikely(pos + count > max)) { retval = -EOVERFLOW; if (pos >= max) goto fput_out; count = max - pos; } fl = 0; #if 0 /* * We need to debate whether we can enable this or not. The * man page documents EAGAIN return for the output at least, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ if (in.file->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif opipe = get_pipe_info(out.file, true); if (!opipe) { retval = rw_verify_area(WRITE, out.file, &out_pos, count); if (retval < 0) goto fput_out; retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl); } else { if (out.file->f_flags & O_NONBLOCK) fl |= SPLICE_F_NONBLOCK; retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl); } if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); fsnotify_access(in.file); fsnotify_modify(out.file); out.file->f_pos = out_pos; if (ppos) *ppos = pos; else in.file->f_pos = pos; } inc_syscr(current); inc_syscw(current); if (pos > max) retval = -EOVERFLOW; fput_out: fdput(out); fput_in: fdput(in); out: return retval; } SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, compat_off_t __user *, offset, compat_size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, compat_loff_t __user *, offset, compat_size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif /* * Performs necessary checks before doing a file copy * * Can adjust amount of bytes to copy via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the copy should be allowed. */ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *req_count, unsigned int flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); uint64_t count = *req_count; loff_t size_in; int ret; ret = generic_file_rw_checks(file_in, file_out); if (ret) return ret; /* * We allow some filesystems to handle cross sb copy, but passing * a file of the wrong filesystem type to filesystem driver can result * in an attempt to dereference the wrong type of ->private_data, so * avoid doing that until we really have a good reason. * * nfs and cifs define several different file_system_type structures * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ if (flags & COPY_FILE_SPLICE) { /* cross sb splice is allowed */ } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; } else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) { return -EXDEV; } /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EOVERFLOW; /* Shorten the copy to EOF */ size_in = i_size_read(inode_in); if (pos_in >= size_in) count = 0; else count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* Don't allow overlapped copying within the same file. */ if (inode_in == inode_out && pos_out + count > pos_in && pos_out < pos_in + count) return -EINVAL; *req_count = count; return 0; } /* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to * the copy_file_range method. */ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { ssize_t ret; bool splice = flags & COPY_FILE_SPLICE; bool samesb = file_inode(file_in)->i_sb == file_inode(file_out)->i_sb; if (flags & ~COPY_FILE_SPLICE) return -EINVAL; ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, flags); if (unlikely(ret)) return ret; ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) return ret; ret = rw_verify_area(WRITE, file_out, &pos_out, len); if (unlikely(ret)) return ret; if (len == 0) return 0; file_start_write(file_out); /* * Cloning is supported by more file systems, so we implement copy on * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); } else if (!splice && file_in->f_op->remap_file_range && samesb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, min_t(loff_t, MAX_RW_COUNT, len), REMAP_FILE_CAN_SHORTEN); /* fallback to splice */ if (ret <= 0) splice = true; } else if (samesb) { /* Fallback to splice for same sb copy for backward compat */ splice = true; } file_end_write(file_out); if (!splice) goto done; /* * We can get here for same sb copy of filesystems that do not implement * ->copy_file_range() in case filesystem does not support clone or in * case filesystem supports clone but rejected the clone request (e.g. * because it was not block aligned). * * In both cases, fall back to kernel copy so we are able to maintain a * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). * * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE * for server-side-copy between any two sb. * * In any case, we call do_splice_direct() and not splice_file_range(), * without file_start_write() held, to avoid possible deadlocks related * to splicing from input file, while file_start_write() is held on * the output file on a different sb. */ ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, min_t(size_t, len, MAX_RW_COUNT), 0); done: if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); fsnotify_modify(file_out); add_wchar(current, ret); } inc_syscr(current); inc_syscw(current); return ret; } EXPORT_SYMBOL(vfs_copy_file_range); SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { loff_t pos_in; loff_t pos_out; struct fd f_in; struct fd f_out; ssize_t ret = -EBADF; f_in = fdget(fd_in); if (!f_in.file) goto out2; f_out = fdget(fd_out); if (!f_out.file) goto out1; ret = -EFAULT; if (off_in) { if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) goto out; } else { pos_in = f_in.file->f_pos; } if (off_out) { if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) goto out; } else { pos_out = f_out.file->f_pos; } ret = -EINVAL; if (flags != 0) goto out; ret = vfs_copy_file_range(f_in.file, pos_in, f_out.file, pos_out, len, flags); if (ret > 0) { pos_in += ret; pos_out += ret; if (off_in) { if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) ret = -EFAULT; } else { f_in.file->f_pos = pos_in; } if (off_out) { if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) ret = -EFAULT; } else { f_out.file->f_pos = pos_out; } } out: fdput(f_out); out1: fdput(f_in); out2: return ret; } /* * Don't operate on ranges the page cache doesn't support, and don't exceed the * LFS limits. If pos is under the limit it becomes a short access. If it * exceeds the limit we return -EFBIG. */ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count) { struct inode *inode = file->f_mapping->host; loff_t max_size = inode->i_sb->s_maxbytes; loff_t limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY) { if (pos >= limit) { send_sig(SIGXFSZ, current, 0); return -EFBIG; } *count = min(*count, limit - pos); } if (!(file->f_flags & O_LARGEFILE)) max_size = MAX_NON_LFS; if (unlikely(pos >= max_size)) return -EFBIG; *count = min(*count, max_size - pos); return 0; } EXPORT_SYMBOL_GPL(generic_write_check_limits); /* Like generic_write_checks(), but takes size of write instead of iter. */ int generic_write_checks_count(struct kiocb *iocb, loff_t *count) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; if (IS_SWAPFILE(inode)) return -ETXTBSY; if (!*count) return 0; if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); if ((iocb->ki_flags & IOCB_NOWAIT) && !((iocb->ki_flags & IOCB_DIRECT) || (file->f_op->fop_flags & FOP_BUFFER_WASYNC))) return -EINVAL; return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count); } EXPORT_SYMBOL(generic_write_checks_count); /* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { loff_t count = iov_iter_count(from); int ret; ret = generic_write_checks_count(iocb, &count); if (ret) return ret; iov_iter_truncate(from, count); return iov_iter_count(from); } EXPORT_SYMBOL(generic_write_checks); /* * Performs common checks before doing a file copy/clone * from @file_in to @file_out. */ int generic_file_rw_checks(struct file *file_in, struct file *file_out) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); /* Don't copy dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || (file_out->f_flags & O_APPEND)) return -EBADF; return 0; } bool generic_atomic_write_valid(struct iov_iter *iter, loff_t pos) { size_t len = iov_iter_count(iter); if (!iter_is_ubuf(iter)) return false; if (!is_power_of_2(len)) return false; if (!IS_ALIGNED(pos, len)) return false; return true; } |
| 6 6 6 6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_ftp.c: IPVS ftp application module * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * Changes: * * Most code here is taken from ip_masq_ftp.c in kernel 2.2. The difference * is that ip_vs_ftp module handles the reverse direction to ip_masq_ftp. * * IP_MASQ_FTP ftp masquerading module * * Version: @(#)ip_masq_ftp.c 0.04 02/05/96 * * Author: Wouter Gadeyne */ #define KMSG_COMPONENT "IPVS" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/ctype.h> #include <linux/inet.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/netfilter.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_helper.h> #include <linux/gfp.h> #include <net/protocol.h> #include <net/tcp.h> #include <asm/unaligned.h> #include <net/ip_vs.h> #define SERVER_STRING_PASV "227 " #define CLIENT_STRING_PORT "PORT" #define SERVER_STRING_EPSV "229 " #define CLIENT_STRING_EPRT "EPRT" enum { IP_VS_FTP_ACTIVE = 0, IP_VS_FTP_PORT = 0, IP_VS_FTP_PASV, IP_VS_FTP_EPRT, IP_VS_FTP_EPSV, }; /* * List of ports (up to IP_VS_APP_MAX_PORTS) to be handled by helper * First port is set to the default port. */ static unsigned int ports_count = 1; static unsigned short ports[IP_VS_APP_MAX_PORTS] = {21, 0}; module_param_array(ports, ushort, &ports_count, 0444); MODULE_PARM_DESC(ports, "Ports to monitor for FTP control commands"); static char *ip_vs_ftp_data_ptr(struct sk_buff *skb, struct ip_vs_iphdr *ipvsh) { struct tcphdr *th = (struct tcphdr *)((char *)skb->data + ipvsh->len); if ((th->doff << 2) < sizeof(struct tcphdr)) return NULL; return (char *)th + (th->doff << 2); } static int ip_vs_ftp_init_conn(struct ip_vs_app *app, struct ip_vs_conn *cp) { /* We use connection tracking for the command connection */ cp->flags |= IP_VS_CONN_F_NFCT; return 0; } static int ip_vs_ftp_done_conn(struct ip_vs_app *app, struct ip_vs_conn *cp) { return 0; } /* Get <addr,port> from the string "xxx.xxx.xxx.xxx,ppp,ppp", started * with the "pattern". <addr,port> is in network order. * Parse extended format depending on ext. In this case addr can be pre-set. */ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, const char *pattern, size_t plen, char skip, bool ext, int mode, union nf_inet_addr *addr, __be16 *port, __u16 af, char **start, char **end) { char *s, c; unsigned char p[6]; char edelim; __u16 hport; int i = 0; if (data_limit - data < plen) { /* check if there is partial match */ if (strncasecmp(data, pattern, data_limit - data) == 0) return -1; else return 0; } if (strncasecmp(data, pattern, plen) != 0) { return 0; } s = data + plen; if (skip) { bool found = false; for (;; s++) { if (s == data_limit) return -1; if (!found) { /* "(" is optional for non-extended format, * so catch the start of IPv4 address */ if (!ext && isdigit(*s)) break; if (*s == skip) found = true; } else if (*s != skip) { break; } } } /* Old IPv4-only format? */ if (!ext) { p[0] = 0; for (data = s; ; data++) { if (data == data_limit) return -1; c = *data; if (isdigit(c)) { p[i] = p[i]*10 + c - '0'; } else if (c == ',' && i < 5) { i++; p[i] = 0; } else { /* unexpected character or terminator */ break; } } if (i != 5) return -1; *start = s; *end = data; addr->ip = get_unaligned((__be32 *) p); *port = get_unaligned((__be16 *) (p + 4)); return 1; } if (s == data_limit) return -1; *start = s; edelim = *s++; if (edelim < 33 || edelim > 126) return -1; if (s == data_limit) return -1; if (*s == edelim) { /* Address family is usually missing for EPSV response */ if (mode != IP_VS_FTP_EPSV) return -1; s++; if (s == data_limit) return -1; /* Then address should be missing too */ if (*s != edelim) return -1; /* Caller can pre-set addr, if needed */ s++; } else { const char *ep; /* We allow address only from same family */ if (af == AF_INET6 && *s != '2') return -1; if (af == AF_INET && *s != '1') return -1; s++; if (s == data_limit) return -1; if (*s != edelim) return -1; s++; if (s == data_limit) return -1; if (af == AF_INET6) { if (in6_pton(s, data_limit - s, (u8 *)addr, edelim, &ep) <= 0) return -1; } else { if (in4_pton(s, data_limit - s, (u8 *)addr, edelim, &ep) <= 0) return -1; } s = (char *) ep; if (s == data_limit) return -1; if (*s != edelim) return -1; s++; } for (hport = 0; ; s++) { if (s == data_limit) return -1; if (!isdigit(*s)) break; hport = hport * 10 + *s - '0'; } if (s == data_limit || !hport || *s != edelim) return -1; s++; *end = s; *port = htons(hport); return 1; } /* Look at outgoing ftp packets to catch the response to a PASV/EPSV command * from the server (inside-to-outside). * When we see one, we build a connection entry with the client address, * client port 0 (unknown at the moment), the server address and the * server port. Mark the current connection entry as a control channel * of the new entry. All this work is just to make the data connection * can be scheduled to the right server later. * * The outgoing packet should be something like * "227 Entering Passive Mode (xxx,xxx,xxx,xxx,ppp,ppp)". * xxx,xxx,xxx,xxx is the server address, ppp,ppp is the server port number. * The extended format for EPSV response provides usually only port: * "229 Entering Extended Passive Mode (|||ppp|)" */ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, struct sk_buff *skb, int *diff, struct ip_vs_iphdr *ipvsh) { char *data, *data_limit; char *start, *end; union nf_inet_addr from; __be16 port; struct ip_vs_conn *n_cp; char buf[24]; /* xxx.xxx.xxx.xxx,ppp,ppp\000 */ unsigned int buf_len; int ret = 0; enum ip_conntrack_info ctinfo; struct nf_conn *ct; *diff = 0; /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; /* Linear packets are much easier to deal with. */ if (skb_ensure_writable(skb, skb->len)) return 0; if (cp->app_data == (void *) IP_VS_FTP_PASV) { data = ip_vs_ftp_data_ptr(skb, ipvsh); data_limit = skb_tail_pointer(skb); if (!data || data >= data_limit) return 1; if (ip_vs_ftp_get_addrport(data, data_limit, SERVER_STRING_PASV, sizeof(SERVER_STRING_PASV)-1, '(', false, IP_VS_FTP_PASV, &from, &port, cp->af, &start, &end) != 1) return 1; IP_VS_DBG(7, "PASV response (%pI4:%u) -> %pI4:%u detected\n", &from.ip, ntohs(port), &cp->caddr.ip, 0); } else if (cp->app_data == (void *) IP_VS_FTP_EPSV) { data = ip_vs_ftp_data_ptr(skb, ipvsh); data_limit = skb_tail_pointer(skb); if (!data || data >= data_limit) return 1; /* Usually, data address is not specified but * we support different address, so pre-set it. */ from = cp->daddr; if (ip_vs_ftp_get_addrport(data, data_limit, SERVER_STRING_EPSV, sizeof(SERVER_STRING_EPSV)-1, '(', true, IP_VS_FTP_EPSV, &from, &port, cp->af, &start, &end) != 1) return 1; IP_VS_DBG_BUF(7, "EPSV response (%s:%u) -> %s:%u detected\n", IP_VS_DBG_ADDR(cp->af, &from), ntohs(port), IP_VS_DBG_ADDR(cp->af, &cp->caddr), 0); } else { return 1; } /* Now update or create a connection entry for it */ { struct ip_vs_conn_param p; ip_vs_conn_fill_param(cp->ipvs, cp->af, ipvsh->protocol, &from, port, &cp->caddr, 0, &p); n_cp = ip_vs_conn_out_get(&p); } if (!n_cp) { struct ip_vs_conn_param p; ip_vs_conn_fill_param(cp->ipvs, cp->af, ipvsh->protocol, &cp->caddr, 0, &cp->vaddr, port, &p); n_cp = ip_vs_conn_new(&p, cp->af, &from, port, IP_VS_CONN_F_NO_CPORT | IP_VS_CONN_F_NFCT, cp->dest, skb->mark); if (!n_cp) return 0; /* add its controller */ ip_vs_control_add(n_cp, cp); } /* Replace the old passive address with the new one */ if (cp->app_data == (void *) IP_VS_FTP_PASV) { from.ip = n_cp->vaddr.ip; port = n_cp->vport; snprintf(buf, sizeof(buf), "%u,%u,%u,%u,%u,%u", ((unsigned char *)&from.ip)[0], ((unsigned char *)&from.ip)[1], ((unsigned char *)&from.ip)[2], ((unsigned char *)&from.ip)[3], ntohs(port) >> 8, ntohs(port) & 0xFF); } else if (cp->app_data == (void *) IP_VS_FTP_EPSV) { from = n_cp->vaddr; port = n_cp->vport; /* Only port, client will use VIP for the data connection */ snprintf(buf, sizeof(buf), "|||%u|", ntohs(port)); } else { *buf = 0; } buf_len = strlen(buf); ct = nf_ct_get(skb, &ctinfo); if (ct) { bool mangled; /* If mangling fails this function will return 0 * which will cause the packet to be dropped. * Mangling can only fail under memory pressure, * hopefully it will succeed on the retransmitted * packet. */ mangled = nf_nat_mangle_tcp_packet(skb, ct, ctinfo, ipvsh->len, start - data, end - start, buf, buf_len); if (mangled) { ip_vs_nfct_expect_related(skb, ct, n_cp, ipvsh->protocol, 0, 0); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = CHECKSUM_UNNECESSARY; /* csum is updated */ ret = 1; } } /* Not setting 'diff' is intentional, otherwise the sequence * would be adjusted twice. */ cp->app_data = (void *) IP_VS_FTP_ACTIVE; ip_vs_tcp_conn_listen(n_cp); ip_vs_conn_put(n_cp); return ret; } /* Look at incoming ftp packets to catch the PASV/PORT/EPRT/EPSV command * (outside-to-inside). * * The incoming packet having the PORT command should be something like * "PORT xxx,xxx,xxx,xxx,ppp,ppp\n". * xxx,xxx,xxx,xxx is the client address, ppp,ppp is the client port number. * In this case, we create a connection entry using the client address and * port, so that the active ftp data connection from the server can reach * the client. * Extended format: * "EPSV\r\n" when client requests server address from same family * "EPSV 1\r\n" when client requests IPv4 server address * "EPSV 2\r\n" when client requests IPv6 server address * "EPSV ALL\r\n" - not supported * EPRT with specified delimiter (ASCII 33..126), "|" by default: * "EPRT |1|IPv4ADDR|PORT|\r\n" when client provides IPv4 addrport * "EPRT |2|IPv6ADDR|PORT|\r\n" when client provides IPv6 addrport */ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, struct sk_buff *skb, int *diff, struct ip_vs_iphdr *ipvsh) { char *data, *data_start, *data_limit; char *start, *end; union nf_inet_addr to; __be16 port; struct ip_vs_conn *n_cp; /* no diff required for incoming packets */ *diff = 0; /* Only useful for established sessions */ if (cp->state != IP_VS_TCP_S_ESTABLISHED) return 1; /* Linear packets are much easier to deal with. */ if (skb_ensure_writable(skb, skb->len)) return 0; data = data_start = ip_vs_ftp_data_ptr(skb, ipvsh); data_limit = skb_tail_pointer(skb); if (!data || data >= data_limit) return 1; while (data <= data_limit - 6) { if (cp->af == AF_INET && strncasecmp(data, "PASV\r\n", 6) == 0) { /* Passive mode on */ IP_VS_DBG(7, "got PASV at %td of %td\n", data - data_start, data_limit - data_start); cp->app_data = (void *) IP_VS_FTP_PASV; return 1; } /* EPSV or EPSV<space><net-prt> */ if (strncasecmp(data, "EPSV", 4) == 0 && (data[4] == ' ' || data[4] == '\r')) { if (data[4] == ' ') { char proto = data[5]; if (data > data_limit - 7 || data[6] != '\r') return 1; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && proto == '2') { } else #endif if (cp->af == AF_INET && proto == '1') { } else { return 1; } } /* Extended Passive mode on */ IP_VS_DBG(7, "got EPSV at %td of %td\n", data - data_start, data_limit - data_start); cp->app_data = (void *) IP_VS_FTP_EPSV; return 1; } data++; } /* * To support virtual FTP server, the scenerio is as follows: * FTP client ----> Load Balancer ----> FTP server * First detect the port number in the application data, * then create a new connection entry for the coming data * connection. */ if (cp->af == AF_INET && ip_vs_ftp_get_addrport(data_start, data_limit, CLIENT_STRING_PORT, sizeof(CLIENT_STRING_PORT)-1, ' ', false, IP_VS_FTP_PORT, &to, &port, cp->af, &start, &end) == 1) { IP_VS_DBG(7, "PORT %pI4:%u detected\n", &to.ip, ntohs(port)); /* Now update or create a connection entry for it */ IP_VS_DBG(7, "protocol %s %pI4:%u %pI4:%u\n", ip_vs_proto_name(ipvsh->protocol), &to.ip, ntohs(port), &cp->vaddr.ip, ntohs(cp->vport)-1); } else if (ip_vs_ftp_get_addrport(data_start, data_limit, CLIENT_STRING_EPRT, sizeof(CLIENT_STRING_EPRT)-1, ' ', true, IP_VS_FTP_EPRT, &to, &port, cp->af, &start, &end) == 1) { IP_VS_DBG_BUF(7, "EPRT %s:%u detected\n", IP_VS_DBG_ADDR(cp->af, &to), ntohs(port)); /* Now update or create a connection entry for it */ IP_VS_DBG_BUF(7, "protocol %s %s:%u %s:%u\n", ip_vs_proto_name(ipvsh->protocol), IP_VS_DBG_ADDR(cp->af, &to), ntohs(port), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport)-1); } else { return 1; } /* Passive mode off */ cp->app_data = (void *) IP_VS_FTP_ACTIVE; { struct ip_vs_conn_param p; ip_vs_conn_fill_param(cp->ipvs, cp->af, ipvsh->protocol, &to, port, &cp->vaddr, htons(ntohs(cp->vport)-1), &p); n_cp = ip_vs_conn_in_get(&p); if (!n_cp) { n_cp = ip_vs_conn_new(&p, cp->af, &cp->daddr, htons(ntohs(cp->dport)-1), IP_VS_CONN_F_NFCT, cp->dest, skb->mark); if (!n_cp) return 0; /* add its controller */ ip_vs_control_add(n_cp, cp); } } /* * Move tunnel to listen state */ ip_vs_tcp_conn_listen(n_cp); ip_vs_conn_put(n_cp); return 1; } static struct ip_vs_app ip_vs_ftp = { .name = "ftp", .type = IP_VS_APP_TYPE_FTP, .protocol = IPPROTO_TCP, .module = THIS_MODULE, .incs_list = LIST_HEAD_INIT(ip_vs_ftp.incs_list), .init_conn = ip_vs_ftp_init_conn, .done_conn = ip_vs_ftp_done_conn, .bind_conn = NULL, .unbind_conn = NULL, .pkt_out = ip_vs_ftp_out, .pkt_in = ip_vs_ftp_in, }; /* * per netns ip_vs_ftp initialization */ static int __net_init __ip_vs_ftp_init(struct net *net) { int i, ret; struct ip_vs_app *app; struct netns_ipvs *ipvs = net_ipvs(net); if (!ipvs) return -ENOENT; app = register_ip_vs_app(ipvs, &ip_vs_ftp); if (IS_ERR(app)) return PTR_ERR(app); for (i = 0; i < ports_count; i++) { if (!ports[i]) continue; ret = register_ip_vs_app_inc(ipvs, app, app->protocol, ports[i]); if (ret) goto err_unreg; } return 0; err_unreg: unregister_ip_vs_app(ipvs, &ip_vs_ftp); return ret; } /* * netns exit */ static void __ip_vs_ftp_exit(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); if (!ipvs) return; unregister_ip_vs_app(ipvs, &ip_vs_ftp); } static struct pernet_operations ip_vs_ftp_ops = { .init = __ip_vs_ftp_init, .exit = __ip_vs_ftp_exit, }; static int __init ip_vs_ftp_init(void) { /* rcu_barrier() is called by netns on error */ return register_pernet_subsys(&ip_vs_ftp_ops); } /* * ip_vs_ftp finish. */ static void __exit ip_vs_ftp_exit(void) { unregister_pernet_subsys(&ip_vs_ftp_ops); /* rcu_barrier() is called by netns */ } module_init(ip_vs_ftp_init); module_exit(ip_vs_ftp_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("ipvs ftp helper"); |
| 19 135 1 312 306 149 7 149 8 8 17 113 128 129 129 123 7 118 117 19 20 8 6 7 406 1 1 1 1 1 1 1 242 1 1 1 878 872 4 5 5 2 1 1 16 16 2 2 1 31 30 31 30 1 32 1 12 18 18 816 55 53 4 33 27 33 7 55 55 29 55 858 822 439 840 55 859 868 863 36 830 100 845 3 862 867 861 861 15 857 860 864 875 370 859 864 858 860 7 9 1 8 1 1 6 7 1 2 2 3 2 2 4 283 146 146 16 16 1 15 16 149 147 171 420 421 423 427 422 403 28 421 406 402 78 79 4 79 9 8 50 50 49 63 62 61 63 4 42 2 46 62 17 44 31 15 36 17 36 23 24 24 11 12 1 12 366 363 362 363 358 359 2 815 1 1 366 360 359 74 73 5 5 5 870 866 861 69 69 6 6 6 6 229 884 6 6 6 5 4 5 210 210 210 2 2 2 2 1 196 1 197 863 863 866 1 865 2 2 2 2 2 25 25 1 1 74 68 17 17 17 17 17 74 74 877 884 847 75 372 856 859 854 1 815 18 815 366 846 846 842 434 437 238 91 7 91 51 188 10 239 242 3 435 439 180 433 432 439 532 264 532 119 365 25 340 533 530 534 529 529 12 12 246 233 242 247 251 2 248 249 250 247 250 1 1 66 66 66 2 64 21 46 46 66 4 4 4 4 4 4 4 4 4 9 8 9 5 4 4 4 4 4 3 1 4 10 10 5 9 4 1 3 4 4 3 2 1 1 32 32 32 3 3 2 7 7 7 7 5 7 1 2 7 4 7 2 5 5 1 99 100 496 499 117 118 117 9 12 1 10 7 8 3 6 4 1 2 5 3 4 33 2 15 2 18 10 9 18 18 2 1 25 2 9 200 251 2 1 234 2 2 14 16 7 8 1 1 9 9 227 34 221 5 219 3 221 220 238 247 46 46 13 13 13 13 13 13 11 2 2 243 1 2 2 2 2 231 2 3 198 31 5 204 2 221 12 218 17 181 51 1 2 33 204 1 1 202 33 208 42 175 186 1 187 186 186 6 2 5 1 1 1 1 1 1 1 6 5 1 1 18 1 17 4 14 12 1 1 1 12 11 10 9 8 8 2 6 9 7 7 7 1 1 3 2 4 2 1 1 2 2 2 2 2 2 3 3 3 1 3 3 3 3 21 21 21 20 3 12 20 6 6 23 6 13 5 37 37 37 37 25 10 25 37 12 25 25 147 147 6 6 6 6 6 6 3 2 2 3 6 2 6 1 6 6 1 6 1 6 6 6 6 263 259 6 6 6 260 260 250 258 214 143 1 10 11 1 2 2 2 2 1 1 1 1 1 341 335 171 1 206 12 1 1 34 21 34 341 313 314 312 60 59 25 25 25 60 59 2 60 60 76 1 1 1 65 8 70 2 67 5 63 3 1 4 6 56 13 1 59 1 5 62 1 4 64 1 47 19 61 4 63 3 64 2 46 19 63 2 50 15 41 24 61 1 1 6 2 6 2 3 3 3 3 3 3 1 3 2 14 7 3 10 7 3 3 4 1 5 1 1 1 6 1 1 3 3 3 3 2 13 6 6 5 4 4 4 3 2 19 6 13 1 5 8 56 6 3 47 14 37 3 10 341 337 7 7 7 3 3 354 1 356 1 358 6 52 321 6 350 1 350 6 354 356 1 6 6 6 7 7 3 3 6 344 345 21 345 326 171 347 10 354 8 1 2 8 8 8 1 1 15 14 15 9 8 6 3 11 2 9 3 7 8 8 8 1 10 20 19 3 6 1 1 12 8 2 6 10 9 4 30 31 11 13 2 10 2 1 7 4 9 2 9 2 2 9 8 2 9 2 7 4 3 1 2 2 6 1 8 8 2 5 1 7 337 341 338 905 874 47 6 6 6 6 6 6 5 6 6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux INET6 implementation * FIB front-end. * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ /* Changes: * * YOSHIFUJI Hideaki @USAGI * reworked default router selection. * - respect outgoing interface * - select from (probably) reachable routers (i.e. * routers in REACHABLE, STALE, DELAY or PROBE states). * - always select the same router if it is (probably) * reachable. otherwise, round-robin the list. * Ville Nuorvala * Fixed routing subtrees. */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/capability.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/types.h> #include <linux/times.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/route.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/mroute6.h> #include <linux/init.h> #include <linux/if_arp.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/jhash.h> #include <linux/siphash.h> #include <net/net_namespace.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> #include <net/ndisc.h> #include <net/addrconf.h> #include <net/tcp.h> #include <linux/rtnetlink.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/xfrm.h> #include <net/netevent.h> #include <net/netlink.h> #include <net/rtnh.h> #include <net/lwtunnel.h> #include <net/ip_tunnels.h> #include <net/l3mdev.h> #include <net/ip.h> #include <linux/uaccess.h> #include <linux/btf_ids.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif static int ip6_rt_type_to_error(u8 fib6_type); #define CREATE_TRACE_POINTS #include <trace/events/fib6.h> EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup); #undef CREATE_TRACE_POINTS enum rt6_nud_state { RT6_NUD_FAIL_HARD = -3, RT6_NUD_FAIL_PROBE = -2, RT6_NUD_FAIL_DO_RR = -1, RT6_NUD_SUCCEED = 1 }; INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst); static void ip6_negative_advice(struct sock *sk, struct dst_entry *dst); static void ip6_dst_destroy(struct dst_entry *); static void ip6_dst_ifdown(struct dst_entry *, struct net_device *dev); static void ip6_dst_gc(struct dst_ops *ops); static int ip6_pkt_discard(struct sk_buff *skb); static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb); static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, int strict); static size_t rt6_nlmsg_size(struct fib6_info *f6i); static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref); static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev); #endif struct uncached_list { spinlock_t lock; struct list_head head; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list); void rt6_uncached_list_add(struct rt6_info *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list); rt->dst.rt_uncached_list = ul; spin_lock_bh(&ul->lock); list_add_tail(&rt->dst.rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt6_uncached_list_del(struct rt6_info *rt) { if (!list_empty(&rt->dst.rt_uncached)) { struct uncached_list *ul = rt->dst.rt_uncached_list; spin_lock_bh(&ul->lock); list_del_init(&rt->dst.rt_uncached); spin_unlock_bh(&ul->lock); } } static void rt6_uncached_list_flush_dev(struct net_device *dev) { int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); struct rt6_info *rt, *safe; if (list_empty(&ul->head)) continue; spin_lock_bh(&ul->lock); list_for_each_entry_safe(rt, safe, &ul->head, dst.rt_uncached) { struct inet6_dev *rt_idev = rt->rt6i_idev; struct net_device *rt_dev = rt->dst.dev; bool handled = false; if (rt_idev->dev == dev) { rt->rt6i_idev = in6_dev_get(blackhole_netdev); in6_dev_put(rt_idev); handled = true; } if (rt_dev == dev) { rt->dst.dev = blackhole_netdev; netdev_ref_replace(rt_dev, blackhole_netdev, &rt->dst.dev_tracker, GFP_ATOMIC); handled = true; } if (handled) list_del_init(&rt->dst.rt_uncached); } spin_unlock_bh(&ul->lock); } } static inline const void *choose_neigh_daddr(const struct in6_addr *p, struct sk_buff *skb, const void *daddr) { if (!ipv6_addr_any(p)) return (const void *) p; else if (skb) return &ipv6_hdr(skb)->daddr; return daddr; } struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, struct net_device *dev, struct sk_buff *skb, const void *daddr) { struct neighbour *n; daddr = choose_neigh_daddr(gw, skb, daddr); n = __ipv6_neigh_lookup(dev, daddr); if (n) return n; n = neigh_create(&nd_tbl, daddr, dev); return IS_ERR(n) ? NULL : n; } static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); return ip6_neigh_lookup(rt6_nexthop(rt, &in6addr_any), dst->dev, skb, daddr); } static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rt6_info *rt = dst_rt6_info(dst); struct net_device *dev = dst->dev; daddr = choose_neigh_daddr(rt6_nexthop(rt, &in6addr_any), NULL, daddr); if (!daddr) return; if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) return; if (ipv6_addr_is_multicast((const struct in6_addr *)daddr)) return; __ipv6_confirm_neigh(dev, daddr); } static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .gc = ip6_dst_gc, .gc_thresh = 1024, .check = ip6_dst_check, .default_advmss = ip6_default_advmss, .mtu = ip6_mtu, .cow_metrics = dst_cow_metrics_generic, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .redirect = rt6_do_redirect, .local_out = __ip6_local_out, .neigh_lookup = ip6_dst_neigh_lookup, .confirm_neigh = ip6_confirm_neigh, }; static struct dst_ops ip6_dst_blackhole_ops = { .family = AF_INET6, .default_advmss = ip6_default_advmss, .neigh_lookup = ip6_dst_neigh_lookup, .check = ip6_dst_check, .destroy = ip6_dst_destroy, .cow_metrics = dst_cow_metrics_generic, .update_pmtu = dst_blackhole_update_pmtu, .redirect = dst_blackhole_redirect, .mtu = dst_blackhole_mtu, }; static const u32 ip6_template_metrics[RTAX_MAX] = { [RTAX_HOPLIMIT - 1] = 0, }; static const struct fib6_info fib6_null_entry_template = { .fib6_flags = (RTF_REJECT | RTF_NONEXTHOP), .fib6_protocol = RTPROT_KERNEL, .fib6_metric = ~(u32)0, .fib6_ref = REFCOUNT_INIT(1), .fib6_type = RTN_UNREACHABLE, .fib6_metrics = (struct dst_metrics *)&dst_default_metrics, }; static const struct rt6_info ip6_null_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -ENETUNREACH, .input = ip6_pkt_discard, .output = ip6_pkt_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; #ifdef CONFIG_IPV6_MULTIPLE_TABLES static const struct rt6_info ip6_prohibit_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EACCES, .input = ip6_pkt_prohibit, .output = ip6_pkt_prohibit_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; static const struct rt6_info ip6_blk_hole_entry_template = { .dst = { .__rcuref = RCUREF_INIT(1), .__use = 1, .obsolete = DST_OBSOLETE_FORCE_CHK, .error = -EINVAL, .input = dst_discard, .output = dst_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), }; #endif static void rt6_info_init(struct rt6_info *rt) { memset_after(rt, 0, dst); } /* allocate dst with ip6_dst_ops */ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, DST_OBSOLETE_FORCE_CHK, flags); if (rt) { rt6_info_init(rt); atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); } return rt; } EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); struct fib6_info *from; struct inet6_dev *idev; ip_dst_metrics_put(dst); rt6_uncached_list_del(rt); idev = rt->rt6i_idev; if (idev) { rt->rt6i_idev = NULL; in6_dev_put(idev); } from = unrcu_pointer(xchg(&rt->from, NULL)); fib6_info_release(from); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { struct rt6_info *rt = dst_rt6_info(dst); struct inet6_dev *idev = rt->rt6i_idev; if (idev && idev->dev != blackhole_netdev) { struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev); if (blackhole_idev) { rt->rt6i_idev = blackhole_idev; in6_dev_put(idev); } } } static bool __rt6_check_expired(const struct rt6_info *rt) { if (rt->rt6i_flags & RTF_EXPIRES) return time_after(jiffies, rt->dst.expires); else return false; } static bool rt6_check_expired(const struct rt6_info *rt) { struct fib6_info *from; from = rcu_dereference(rt->from); if (rt->rt6i_flags & RTF_EXPIRES) { if (time_after(jiffies, rt->dst.expires)) return true; } else if (from) { return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK || fib6_check_expired(from); } return false; } void fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { struct fib6_info *sibling, *next_sibling; struct fib6_info *match = res->f6i; if (!match->nh && (!match->fib6_nsiblings || have_oif_match)) goto out; if (match->nh && have_oif_match && res->nh) return; if (skb) IP6CB(skb)->flags |= IP6SKB_MULTIPATH; /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. */ if (!fl6->mp_hash && (!match->nh || nexthop_is_multipath(match->nh))) fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL); if (unlikely(match->nh)) { nexthop_path_fib6_result(res, fl6->mp_hash); return; } if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound)) goto out; list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings, fib6_siblings) { const struct fib6_nh *nh = sibling->fib6_nh; int nh_upper_bound; nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound); if (fl6->mp_hash > nh_upper_bound) continue; if (rt6_score_route(nh, sibling->fib6_flags, oif, strict) < 0) break; match = sibling; break; } out: res->f6i = match; res->nh = match->fib6_nh; } /* * Route lookup. rcu_read_lock() should be held. */ static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh, const struct in6_addr *saddr, int oif, int flags) { const struct net_device *dev; if (nh->fib_nh_flags & RTNH_F_DEAD) return false; dev = nh->fib_nh_dev; if (oif) { if (dev->ifindex == oif) return true; } else { if (ipv6_chk_addr(net, saddr, dev, flags & RT6_LOOKUP_F_IFACE)) return true; } return false; } struct fib6_nh_dm_arg { struct net *net; const struct in6_addr *saddr; int oif; int flags; struct fib6_nh *nh; }; static int __rt6_nh_dev_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_dm_arg *arg = _arg; arg->nh = nh; return __rt6_device_match(arg->net, nh, arg->saddr, arg->oif, arg->flags); } /* returns fib6_nh from nexthop or NULL */ static struct fib6_nh *rt6_nh_dev_match(struct net *net, struct nexthop *nh, struct fib6_result *res, const struct in6_addr *saddr, int oif, int flags) { struct fib6_nh_dm_arg arg = { .net = net, .saddr = saddr, .oif = oif, .flags = flags, }; if (nexthop_is_blackhole(nh)) return NULL; if (nexthop_for_each_fib6_nh(nh, __rt6_nh_dev_match, &arg)) return arg.nh; return NULL; } static void rt6_device_match(struct net *net, struct fib6_result *res, const struct in6_addr *saddr, int oif, int flags) { struct fib6_info *f6i = res->f6i; struct fib6_info *spf6i; struct fib6_nh *nh; if (!oif && ipv6_addr_any(saddr)) { if (unlikely(f6i->nh)) { nh = nexthop_fib6_nh(f6i->nh); if (nexthop_is_blackhole(f6i->nh)) goto out_blackhole; } else { nh = f6i->fib6_nh; } if (!(nh->fib_nh_flags & RTNH_F_DEAD)) goto out; } for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) { bool matched = false; if (unlikely(spf6i->nh)) { nh = rt6_nh_dev_match(net, spf6i->nh, res, saddr, oif, flags); if (nh) matched = true; } else { nh = spf6i->fib6_nh; if (__rt6_device_match(net, nh, saddr, oif, flags)) matched = true; } if (matched) { res->f6i = spf6i; goto out; } } if (oif && flags & RT6_LOOKUP_F_IFACE) { res->f6i = net->ipv6.fib6_null_entry; nh = res->f6i->fib6_nh; goto out; } if (unlikely(f6i->nh)) { nh = nexthop_fib6_nh(f6i->nh); if (nexthop_is_blackhole(f6i->nh)) goto out_blackhole; } else { nh = f6i->fib6_nh; } if (nh->fib_nh_flags & RTNH_F_DEAD) { res->f6i = net->ipv6.fib6_null_entry; nh = res->f6i->fib6_nh; } out: res->nh = nh; res->fib6_type = res->f6i->fib6_type; res->fib6_flags = res->f6i->fib6_flags; return; out_blackhole: res->fib6_flags |= RTF_REJECT; res->fib6_type = RTN_BLACKHOLE; res->nh = nh; } #ifdef CONFIG_IPV6_ROUTER_PREF struct __rt6_probe_work { struct work_struct work; struct in6_addr target; struct net_device *dev; netdevice_tracker dev_tracker; }; static void rt6_probe_deferred(struct work_struct *w) { struct in6_addr mcaddr; struct __rt6_probe_work *work = container_of(w, struct __rt6_probe_work, work); addrconf_addr_solict_mult(&work->target, &mcaddr); ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, 0); netdev_put(work->dev, &work->dev_tracker); kfree(work); } static void rt6_probe(struct fib6_nh *fib6_nh) { struct __rt6_probe_work *work = NULL; const struct in6_addr *nh_gw; unsigned long last_probe; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; /* * Okay, this does not seem to be appropriate * for now, however, we need to check if it * is really so; aka Router Reachability Probing. * * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ if (!fib6_nh->fib_nh_gw_family) return; nh_gw = &fib6_nh->fib_nh_gw6; dev = fib6_nh->fib_nh_dev; rcu_read_lock(); last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); if (!idev) goto out; neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { if (READ_ONCE(neigh->nud_state) & NUD_VALID) goto out; write_lock_bh(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, neigh->updated + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) __neigh_set_probe_once(neigh); } write_unlock_bh(&neigh->lock); } else if (time_after(jiffies, last_probe + READ_ONCE(idev->cnf.rtr_probe_interval))) { work = kmalloc(sizeof(*work), GFP_ATOMIC); } if (!work || cmpxchg(&fib6_nh->last_probe, last_probe, jiffies) != last_probe) { kfree(work); } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; netdev_hold(dev, &work->dev_tracker, GFP_ATOMIC); work->dev = dev; schedule_work(&work->work); } out: rcu_read_unlock(); } #else static inline void rt6_probe(struct fib6_nh *fib6_nh) { } #endif /* * Default Router Selection (RFC 2461 6.3.6) */ static enum rt6_nud_state rt6_check_neigh(const struct fib6_nh *fib6_nh) { enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; struct neighbour *neigh; rcu_read_lock(); neigh = __ipv6_neigh_lookup_noref(fib6_nh->fib_nh_dev, &fib6_nh->fib_nh_gw6); if (neigh) { u8 nud_state = READ_ONCE(neigh->nud_state); if (nud_state & NUD_VALID) ret = RT6_NUD_SUCCEED; #ifdef CONFIG_IPV6_ROUTER_PREF else if (!(nud_state & NUD_FAILED)) ret = RT6_NUD_SUCCEED; else ret = RT6_NUD_FAIL_PROBE; #endif } else { ret = IS_ENABLED(CONFIG_IPV6_ROUTER_PREF) ? RT6_NUD_SUCCEED : RT6_NUD_FAIL_DO_RR; } rcu_read_unlock(); return ret; } static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, int strict) { int m = 0; if (!oif || nh->fib_nh_dev->ifindex == oif) m = 2; if (!m && (strict & RT6_LOOKUP_F_IFACE)) return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(fib6_flags)) << 2; #endif if ((strict & RT6_LOOKUP_F_REACHABLE) && !(fib6_flags & RTF_NONEXTHOP) && nh->fib_nh_gw_family) { int n = rt6_check_neigh(nh); if (n < 0) return n; } return m; } static bool find_match(struct fib6_nh *nh, u32 fib6_flags, int oif, int strict, int *mpri, bool *do_rr) { bool match_do_rr = false; bool rc = false; int m; if (nh->fib_nh_flags & RTNH_F_DEAD) goto out; if (ip6_ignore_linkdown(nh->fib_nh_dev) && nh->fib_nh_flags & RTNH_F_LINKDOWN && !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE)) goto out; m = rt6_score_route(nh, fib6_flags, oif, strict); if (m == RT6_NUD_FAIL_DO_RR) { match_do_rr = true; m = 0; /* lowest valid score */ } else if (m == RT6_NUD_FAIL_HARD) { goto out; } if (strict & RT6_LOOKUP_F_REACHABLE) rt6_probe(nh); /* note that m can be RT6_NUD_FAIL_PROBE at this point */ if (m > *mpri) { *do_rr = match_do_rr; *mpri = m; rc = true; } out: return rc; } struct fib6_nh_frl_arg { u32 flags; int oif; int strict; int *mpri; bool *do_rr; struct fib6_nh *nh; }; static int rt6_nh_find_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_frl_arg *arg = _arg; arg->nh = nh; return find_match(nh, arg->flags, arg->oif, arg->strict, arg->mpri, arg->do_rr); } static void __find_rr_leaf(struct fib6_info *f6i_start, struct fib6_info *nomatch, u32 metric, struct fib6_result *res, struct fib6_info **cont, int oif, int strict, bool *do_rr, int *mpri) { struct fib6_info *f6i; for (f6i = f6i_start; f6i && f6i != nomatch; f6i = rcu_dereference(f6i->fib6_next)) { bool matched = false; struct fib6_nh *nh; if (cont && f6i->fib6_metric != metric) { *cont = f6i; return; } if (fib6_check_expired(f6i)) continue; if (unlikely(f6i->nh)) { struct fib6_nh_frl_arg arg = { .flags = f6i->fib6_flags, .oif = oif, .strict = strict, .mpri = mpri, .do_rr = do_rr }; if (nexthop_is_blackhole(f6i->nh)) { res->fib6_flags = RTF_REJECT; res->fib6_type = RTN_BLACKHOLE; res->f6i = f6i; res->nh = nexthop_fib6_nh(f6i->nh); return; } if (nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match, &arg)) { matched = true; nh = arg.nh; } } else { nh = f6i->fib6_nh; if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) matched = true; } if (matched) { res->f6i = f6i; res->nh = nh; res->fib6_flags = f6i->fib6_flags; res->fib6_type = f6i->fib6_type; } } } static void find_rr_leaf(struct fib6_node *fn, struct fib6_info *leaf, struct fib6_info *rr_head, int oif, int strict, bool *do_rr, struct fib6_result *res) { u32 metric = rr_head->fib6_metric; struct fib6_info *cont = NULL; int mpri = -1; __find_rr_leaf(rr_head, NULL, metric, res, &cont, oif, strict, do_rr, &mpri); __find_rr_leaf(leaf, rr_head, metric, res, &cont, oif, strict, do_rr, &mpri); if (res->f6i || !cont) return; __find_rr_leaf(cont, NULL, metric, res, NULL, oif, strict, do_rr, &mpri); } static void rt6_select(struct net *net, struct fib6_node *fn, int oif, struct fib6_result *res, int strict) { struct fib6_info *leaf = rcu_dereference(fn->leaf); struct fib6_info *rt0; bool do_rr = false; int key_plen; /* make sure this function or its helpers sets f6i */ res->f6i = NULL; if (!leaf || leaf == net->ipv6.fib6_null_entry) goto out; rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) rt0 = leaf; /* Double check to make sure fn is not an intermediate node * and fn->leaf does not points to its child's leaf * (This might happen if all routes under fn are deleted from * the tree and fib6_repair_tree() is called on the node.) */ key_plen = rt0->fib6_dst.plen; #ifdef CONFIG_IPV6_SUBTREES if (rt0->fib6_src.plen) key_plen = rt0->fib6_src.plen; #endif if (fn->fn_bit != key_plen) goto out; find_rr_leaf(fn, leaf, rt0, oif, strict, &do_rr, res); if (do_rr) { struct fib6_info *next = rcu_dereference(rt0->fib6_next); /* no entries matched; do round-robin */ if (!next || next->fib6_metric != rt0->fib6_metric) next = leaf; if (next != rt0) { spin_lock_bh(&leaf->fib6_table->tb6_lock); /* make sure next is not being deleted from the tree */ if (next->fib6_node) rcu_assign_pointer(fn->rr_ptr, next); spin_unlock_bh(&leaf->fib6_table->tb6_lock); } } out: if (!res->f6i) { res->f6i = net->ipv6.fib6_null_entry; res->nh = res->f6i->fib6_nh; res->fib6_flags = res->f6i->fib6_flags; res->fib6_type = res->f6i->fib6_type; } } static bool rt6_is_gw_or_nonexthop(const struct fib6_result *res) { return (res->f6i->fib6_flags & RTF_NONEXTHOP) || res->nh->fib_nh_gw_family; } #ifdef CONFIG_IPV6_ROUTE_INFO int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, const struct in6_addr *gwaddr) { struct net *net = dev_net(dev); struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; struct fib6_table *table; unsigned int pref; unsigned long lifetime; struct fib6_info *rt; if (len < sizeof(struct route_info)) { return -EINVAL; } /* Sanity check for prefix_len and length */ if (rinfo->length > 3) { return -EINVAL; } else if (rinfo->prefix_len > 128) { return -EINVAL; } else if (rinfo->prefix_len > 64) { if (rinfo->length < 2) { return -EINVAL; } } else if (rinfo->prefix_len > 0) { if (rinfo->length < 1) { return -EINVAL; } } pref = rinfo->route_pref; if (pref == ICMPV6_ROUTER_PREF_INVALID) return -EINVAL; lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); if (rinfo->length == 3) prefix = (struct in6_addr *)rinfo->prefix; else { /* this function is safe */ ipv6_addr_prefix(&prefix_buf, (struct in6_addr *)rinfo->prefix, rinfo->prefix_len); prefix = &prefix_buf; } if (rinfo->prefix_len == 0) rt = rt6_get_dflt_router(net, gwaddr, dev); else rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev); if (rt && !lifetime) { ip6_del_rt(net, rt, false); rt = NULL; } if (!rt && lifetime) rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev, pref); else if (rt) rt->fib6_flags = RTF_ROUTEINFO | (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (!addrconf_finite_timeout(lifetime)) { fib6_clean_expires(rt); fib6_remove_gc_list(rt); } else { fib6_set_expires(rt, jiffies + HZ * lifetime); fib6_add_gc_list(rt); } spin_unlock_bh(&table->tb6_lock); fib6_info_release(rt); } return 0; } #endif /* * Misc support functions */ /* called with rcu_lock held */ static struct net_device *ip6_rt_get_dev_rcu(const struct fib6_result *res) { struct net_device *dev = res->nh->fib_nh_dev; if (res->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) { /* for copies of local routes, dst->dev needs to be the * device if it is a master device, the master device if * device is enslaved, and the loopback as the default */ if (netif_is_l3_slave(dev) && !rt6_need_strict(&res->f6i->fib6_dst.addr)) dev = l3mdev_master_dev_rcu(dev); else if (!netif_is_l3_master(dev)) dev = dev_net(dev)->loopback_dev; /* last case is netif_is_l3_master(dev) is true in which * case we want dev returned to be dev */ } return dev; } static const int fib6_prop[RTN_MAX + 1] = { [RTN_UNSPEC] = 0, [RTN_UNICAST] = 0, [RTN_LOCAL] = 0, [RTN_BROADCAST] = 0, [RTN_ANYCAST] = 0, [RTN_MULTICAST] = 0, [RTN_BLACKHOLE] = -EINVAL, [RTN_UNREACHABLE] = -EHOSTUNREACH, [RTN_PROHIBIT] = -EACCES, [RTN_THROW] = -EAGAIN, [RTN_NAT] = -EINVAL, [RTN_XRESOLVE] = -EINVAL, }; static int ip6_rt_type_to_error(u8 fib6_type) { return fib6_prop[fib6_type]; } static unsigned short fib6_info_dst_flags(struct fib6_info *rt) { unsigned short flags = 0; if (rt->dst_nocount) flags |= DST_NOCOUNT; if (rt->dst_nopolicy) flags |= DST_NOPOLICY; return flags; } static void ip6_rt_init_dst_reject(struct rt6_info *rt, u8 fib6_type) { rt->dst.error = ip6_rt_type_to_error(fib6_type); switch (fib6_type) { case RTN_BLACKHOLE: rt->dst.output = dst_discard_out; rt->dst.input = dst_discard; break; case RTN_PROHIBIT: rt->dst.output = ip6_pkt_prohibit_out; rt->dst.input = ip6_pkt_prohibit; break; case RTN_THROW: case RTN_UNREACHABLE: default: rt->dst.output = ip6_pkt_discard_out; rt->dst.input = ip6_pkt_discard; break; } } static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res) { struct fib6_info *f6i = res->f6i; if (res->fib6_flags & RTF_REJECT) { ip6_rt_init_dst_reject(rt, res->fib6_type); return; } rt->dst.error = 0; rt->dst.output = ip6_output; if (res->fib6_type == RTN_LOCAL || res->fib6_type == RTN_ANYCAST) { rt->dst.input = ip6_input; } else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { rt->dst.input = ip6_mc_input; } else { rt->dst.input = ip6_forward; } if (res->nh->fib_nh_lws) { rt->dst.lwtstate = lwtstate_get(res->nh->fib_nh_lws); lwtunnel_set_redirect(&rt->dst); } rt->dst.lastuse = jiffies; } /* Caller must already hold reference to @from */ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; rcu_assign_pointer(rt->from, from); ip_dst_init_metrics(&rt->dst, from->fib6_metrics); } /* Caller must already hold reference to f6i in result */ static void ip6_rt_copy_init(struct rt6_info *rt, const struct fib6_result *res) { const struct fib6_nh *nh = res->nh; const struct net_device *dev = nh->fib_nh_dev; struct fib6_info *f6i = res->f6i; ip6_rt_init_dst(rt, res); rt->rt6i_dst = f6i->fib6_dst; rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL; rt->rt6i_flags = res->fib6_flags; if (nh->fib_nh_gw_family) { rt->rt6i_gateway = nh->fib_nh_gw6; rt->rt6i_flags |= RTF_GATEWAY; } rt6_set_from(rt, f6i); #ifdef CONFIG_IPV6_SUBTREES rt->rt6i_src = f6i->fib6_src; #endif } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { struct fib6_node *pn, *sn; while (1) { if (fn->fn_flags & RTN_TL_ROOT) return NULL; pn = rcu_dereference(fn->parent); sn = FIB6_SUBTREE(pn); if (sn && sn != fn) fn = fib6_node_lookup(sn, NULL, saddr); else fn = pn; if (fn->fn_flags & RTN_RTINFO) return fn; } } static bool ip6_hold_safe(struct net *net, struct rt6_info **prt) { struct rt6_info *rt = *prt; if (dst_hold_safe(&rt->dst)) return true; if (net) { rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); } else { rt = NULL; } *prt = rt; return false; } /* called with rcu_lock held */ static struct rt6_info *ip6_create_rt_rcu(const struct fib6_result *res) { struct net_device *dev = res->nh->fib_nh_dev; struct fib6_info *f6i = res->f6i; unsigned short flags; struct rt6_info *nrt; if (!fib6_info_hold_safe(f6i)) goto fallback; flags = fib6_info_dst_flags(f6i); nrt = ip6_dst_alloc(dev_net(dev), dev, flags); if (!nrt) { fib6_info_release(f6i); goto fallback; } ip6_rt_copy_init(nrt, res); return nrt; fallback: nrt = dev_net(dev)->ipv6.ip6_null_entry; dst_hold(&nrt->dst); return nrt; } INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct fib6_result res = {}; struct fib6_node *fn; struct rt6_info *rt; rcu_read_lock(); fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: res.f6i = rcu_dereference(fn->leaf); if (!res.f6i) res.f6i = net->ipv6.fib6_null_entry; else rt6_device_match(net, &res, &fl6->saddr, fl6->flowi6_oif, flags); if (res.f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; rt = net->ipv6.ip6_null_entry; dst_hold(&rt->dst); goto out; } else if (res.fib6_flags & RTF_REJECT) { goto do_create; } fib6_select_path(net, &res, fl6, fl6->flowi6_oif, fl6->flowi6_oif != 0, skb, flags); /* Search through exception table */ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr); if (rt) { if (ip6_hold_safe(net, &rt)) dst_use_noref(&rt->dst, jiffies); } else { do_create: rt = ip6_create_rt_rcu(&res); } out: trace_fib6_table_lookup(net, &res, table, fl6); rcu_read_unlock(); return rt; } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_lookup); } EXPORT_SYMBOL_GPL(ip6_route_lookup); struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr, int oif, const struct sk_buff *skb, int strict) { struct flowi6 fl6 = { .flowi6_oif = oif, .daddr = *daddr, }; struct dst_entry *dst; int flags = strict ? RT6_LOOKUP_F_IFACE : 0; if (saddr) { memcpy(&fl6.saddr, saddr, sizeof(*saddr)); flags |= RT6_LOOKUP_F_HAS_SADDR; } dst = fib6_rule_lookup(net, &fl6, skb, flags, ip6_pol_route_lookup); if (dst->error == 0) return dst_rt6_info(dst); dst_release(dst); return NULL; } EXPORT_SYMBOL(rt6_lookup); /* ip6_ins_rt is called with FREE table->tb6_lock. * It takes new route entry, the addition fails by any reason the * route is released. * Caller must hold dst before calling it. */ static int __ip6_ins_rt(struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { int err; struct fib6_table *table; table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_add(&table->tb6_root, rt, info, extack); spin_unlock_bh(&table->tb6_lock); return err; } int ip6_ins_rt(struct net *net, struct fib6_info *rt) { struct nl_info info = { .nl_net = net, }; return __ip6_ins_rt(rt, &info, NULL); } static struct rt6_info *ip6_rt_cache_alloc(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct fib6_info *f6i = res->f6i; struct net_device *dev; struct rt6_info *rt; /* * Clone the route. */ if (!fib6_info_hold_safe(f6i)) return NULL; dev = ip6_rt_get_dev_rcu(res); rt = ip6_dst_alloc(dev_net(dev), dev, 0); if (!rt) { fib6_info_release(f6i); return NULL; } ip6_rt_copy_init(rt, res); rt->rt6i_flags |= RTF_CACHE; rt->rt6i_dst.addr = *daddr; rt->rt6i_dst.plen = 128; if (!rt6_is_gw_or_nonexthop(res)) { if (f6i->fib6_dst.plen != 128 && ipv6_addr_equal(&f6i->fib6_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { rt->rt6i_src.addr = *saddr; rt->rt6i_src.plen = 128; } #endif } return rt; } static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res) { struct fib6_info *f6i = res->f6i; unsigned short flags = fib6_info_dst_flags(f6i); struct net_device *dev; struct rt6_info *pcpu_rt; if (!fib6_info_hold_safe(f6i)) return NULL; rcu_read_lock(); dev = ip6_rt_get_dev_rcu(res); pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags | DST_NOCOUNT); rcu_read_unlock(); if (!pcpu_rt) { fib6_info_release(f6i); return NULL; } ip6_rt_copy_init(pcpu_rt, res); pcpu_rt->rt6i_flags |= RTF_PCPU; if (f6i->nh) pcpu_rt->sernum = rt_genid_ipv6(dev_net(dev)); return pcpu_rt; } static bool rt6_is_valid(const struct rt6_info *rt6) { return rt6->sernum == rt_genid_ipv6(dev_net(rt6->dst.dev)); } /* It should be called with rcu_read_lock() acquired */ static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res) { struct rt6_info *pcpu_rt; pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu); if (pcpu_rt && pcpu_rt->sernum && !rt6_is_valid(pcpu_rt)) { struct rt6_info *prev, **p; p = this_cpu_ptr(res->nh->rt6i_pcpu); /* Paired with READ_ONCE() in __fib6_drop_pcpu_from() */ prev = xchg(p, NULL); if (prev) { dst_dev_put(&prev->dst); dst_release(&prev->dst); } pcpu_rt = NULL; } return pcpu_rt; } static struct rt6_info *rt6_make_pcpu_route(struct net *net, const struct fib6_result *res) { struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(res); if (!pcpu_rt) return NULL; p = this_cpu_ptr(res->nh->rt6i_pcpu); prev = cmpxchg(p, NULL, pcpu_rt); BUG_ON(prev); if (res->f6i->fib6_destroying) { struct fib6_info *from; from = unrcu_pointer(xchg(&pcpu_rt->from, NULL)); fib6_info_release(from); } return pcpu_rt; } /* exception hash table implementation */ static DEFINE_SPINLOCK(rt6_exception_lock); /* Remove rt6_ex from hash table and free the memory * Caller must hold rt6_exception_lock */ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex) { struct fib6_info *from; struct net *net; if (!bucket || !rt6_ex) return; net = dev_net(rt6_ex->rt6i->dst.dev); net->ipv6.rt6_stats->fib_rt_cache--; /* purge completely the exception to allow releasing the held resources: * some [sk] cache may keep the dst around for unlimited time */ from = unrcu_pointer(xchg(&rt6_ex->rt6i->from, NULL)); fib6_info_release(from); dst_dev_put(&rt6_ex->rt6i->dst); hlist_del_rcu(&rt6_ex->hlist); dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; } /* Remove oldest rt6_ex in bucket and free the memory * Caller must hold rt6_exception_lock */ static void rt6_exception_remove_oldest(struct rt6_exception_bucket *bucket) { struct rt6_exception *rt6_ex, *oldest = NULL; if (!bucket) return; hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { if (!oldest || time_before(rt6_ex->stamp, oldest->stamp)) oldest = rt6_ex; } rt6_remove_exception(bucket, oldest); } static u32 rt6_exception_hash(const struct in6_addr *dst, const struct in6_addr *src) { static siphash_aligned_key_t rt6_exception_key; struct { struct in6_addr dst; struct in6_addr src; } __aligned(SIPHASH_ALIGNMENT) combined = { .dst = *dst, }; u64 val; net_get_random_once(&rt6_exception_key, sizeof(rt6_exception_key)); #ifdef CONFIG_IPV6_SUBTREES if (src) combined.src = *src; #endif val = siphash(&combined, sizeof(combined), &rt6_exception_key); return hash_64(val, FIB6_EXCEPTION_BUCKET_SIZE_SHIFT); } /* Helper function to find the cached rt in the hash table * and update bucket pointer to point to the bucket for this * (daddr, saddr) pair * Caller must hold rt6_exception_lock */ static struct rt6_exception * __rt6_find_exception_spinlock(struct rt6_exception_bucket **bucket, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_exception *rt6_ex; u32 hval; if (!(*bucket) || !daddr) return NULL; hval = rt6_exception_hash(daddr, saddr); *bucket += hval; hlist_for_each_entry(rt6_ex, &(*bucket)->chain, hlist) { struct rt6_info *rt6 = rt6_ex->rt6i; bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (matched && saddr) matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); #endif if (matched) return rt6_ex; } return NULL; } /* Helper function to find the cached rt in the hash table * and update bucket pointer to point to the bucket for this * (daddr, saddr) pair * Caller must hold rcu_read_lock() */ static struct rt6_exception * __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_exception *rt6_ex; u32 hval; WARN_ON_ONCE(!rcu_read_lock_held()); if (!(*bucket) || !daddr) return NULL; hval = rt6_exception_hash(daddr, saddr); *bucket += hval; hlist_for_each_entry_rcu(rt6_ex, &(*bucket)->chain, hlist) { struct rt6_info *rt6 = rt6_ex->rt6i; bool matched = ipv6_addr_equal(daddr, &rt6->rt6i_dst.addr); #ifdef CONFIG_IPV6_SUBTREES if (matched && saddr) matched = ipv6_addr_equal(saddr, &rt6->rt6i_src.addr); #endif if (matched) return rt6_ex; } return NULL; } static unsigned int fib6_mtu(const struct fib6_result *res) { const struct fib6_nh *nh = res->nh; unsigned int mtu; if (res->f6i->fib6_pmtu) { mtu = res->f6i->fib6_pmtu; } else { struct net_device *dev = nh->fib_nh_dev; struct inet6_dev *idev; rcu_read_lock(); idev = __in6_dev_get(dev); mtu = READ_ONCE(idev->cnf.mtu6); rcu_read_unlock(); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } #define FIB6_EXCEPTION_BUCKET_FLUSHED 0x1UL /* used when the flushed bit is not relevant, only access to the bucket * (ie., all bucket users except rt6_insert_exception); * * called under rcu lock; sometimes called with rt6_exception_lock held */ static struct rt6_exception_bucket *fib6_nh_get_excptn_bucket(const struct fib6_nh *nh, spinlock_t *lock) { struct rt6_exception_bucket *bucket; if (lock) bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(lock)); else bucket = rcu_dereference(nh->rt6i_exception_bucket); /* remove bucket flushed bit if set */ if (bucket) { unsigned long p = (unsigned long)bucket; p &= ~FIB6_EXCEPTION_BUCKET_FLUSHED; bucket = (struct rt6_exception_bucket *)p; } return bucket; } static bool fib6_nh_excptn_bucket_flushed(struct rt6_exception_bucket *bucket) { unsigned long p = (unsigned long)bucket; return !!(p & FIB6_EXCEPTION_BUCKET_FLUSHED); } /* called with rt6_exception_lock held */ static void fib6_nh_excptn_bucket_set_flushed(struct fib6_nh *nh, spinlock_t *lock) { struct rt6_exception_bucket *bucket; unsigned long p; bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(lock)); p = (unsigned long)bucket; p |= FIB6_EXCEPTION_BUCKET_FLUSHED; bucket = (struct rt6_exception_bucket *)p; rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); } static int rt6_insert_exception(struct rt6_info *nrt, const struct fib6_result *res) { struct net *net = dev_net(nrt->dst.dev); struct rt6_exception_bucket *bucket; struct fib6_info *f6i = res->f6i; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; struct fib6_nh *nh = res->nh; int max_depth; int err = 0; spin_lock_bh(&rt6_exception_lock); bucket = rcu_dereference_protected(nh->rt6i_exception_bucket, lockdep_is_held(&rt6_exception_lock)); if (!bucket) { bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket), GFP_ATOMIC); if (!bucket) { err = -ENOMEM; goto out; } rcu_assign_pointer(nh->rt6i_exception_bucket, bucket); } else if (fib6_nh_excptn_bucket_flushed(bucket)) { err = -EINVAL; goto out; } #ifdef CONFIG_IPV6_SUBTREES /* fib6_src.plen != 0 indicates f6i is in subtree * and exception table is indexed by a hash of * both fib6_dst and fib6_src. * Otherwise, the exception table is indexed by * a hash of only fib6_dst. */ if (f6i->fib6_src.plen) src_key = &nrt->rt6i_src.addr; #endif /* rt6_mtu_change() might lower mtu on f6i. * Only insert this exception route if its mtu * is less than f6i's mtu value. */ if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(res)) { err = -EINVAL; goto out; } rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_remove_exception(bucket, rt6_ex); rt6_ex = kzalloc(sizeof(*rt6_ex), GFP_ATOMIC); if (!rt6_ex) { err = -ENOMEM; goto out; } rt6_ex->rt6i = nrt; rt6_ex->stamp = jiffies; hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); bucket->depth++; net->ipv6.rt6_stats->fib_rt_cache++; /* Randomize max depth to avoid some side channels attacks. */ max_depth = FIB6_MAX_DEPTH + get_random_u32_below(FIB6_MAX_DEPTH); while (bucket->depth > max_depth) rt6_exception_remove_oldest(bucket); out: spin_unlock_bh(&rt6_exception_lock); /* Update fn->fn_sernum to invalidate all cached dst */ if (!err) { spin_lock_bh(&f6i->fib6_table->tb6_lock); fib6_update_sernum(net, f6i); spin_unlock_bh(&f6i->fib6_table->tb6_lock); fib6_force_start_gc(net); } return err; } static void fib6_nh_flush_exceptions(struct fib6_nh *nh, struct fib6_info *from) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) goto out; /* Prevent rt6_insert_exception() to recreate the bucket list */ if (!from) fib6_nh_excptn_bucket_set_flushed(nh, &rt6_exception_lock); for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { if (!from || rcu_access_pointer(rt6_ex->rt6i->from) == from) rt6_remove_exception(bucket, rt6_ex); } WARN_ON_ONCE(!from && bucket->depth); bucket++; } out: spin_unlock_bh(&rt6_exception_lock); } static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg) { struct fib6_info *f6i = arg; fib6_nh_flush_exceptions(nh, f6i); return 0; } void rt6_flush_exceptions(struct fib6_info *f6i) { if (f6i->nh) nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions, f6i); else fib6_nh_flush_exceptions(f6i->fib6_nh, f6i); } /* Find cached rt in the hash table inside passed in rt * Caller has to hold rcu_read_lock() */ static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct rt6_info *ret = NULL; #ifdef CONFIG_IPV6_SUBTREES /* fib6i_src.plen != 0 indicates f6i is in subtree * and exception table is indexed by a hash of * both fib6_dst and fib6_src. * However, the src addr used to create the hash * might not be exactly the passed in saddr which * is a /128 addr from the flow. * So we need to use f6i->fib6_src to redo lookup * if the passed in saddr does not find anything. * (See the logic in ip6_rt_cache_alloc() on how * rt->rt6i_src is updated.) */ if (res->f6i->fib6_src.plen) src_key = saddr; find_ex: #endif bucket = fib6_nh_get_excptn_bucket(res->nh, NULL); rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i)) ret = rt6_ex->rt6i; #ifdef CONFIG_IPV6_SUBTREES /* Use fib6_src as src_key and redo lookup */ if (!ret && src_key && src_key != &res->f6i->fib6_src.addr) { src_key = &res->f6i->fib6_src.addr; goto find_ex; } #endif return ret; } /* Remove the passed in cached rt from the hash table that contains it */ static int fib6_nh_remove_exception(const struct fib6_nh *nh, int plen, const struct rt6_info *rt) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int err; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return -ENOENT; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_spinlock(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) { rt6_remove_exception(bucket, rt6_ex); err = 0; } else { err = -ENOENT; } spin_unlock_bh(&rt6_exception_lock); return err; } struct fib6_nh_excptn_arg { struct rt6_info *rt; int plen; }; static int rt6_nh_remove_exception_rt(struct fib6_nh *nh, void *_arg) { struct fib6_nh_excptn_arg *arg = _arg; int err; err = fib6_nh_remove_exception(nh, arg->plen, arg->rt); if (err == 0) return 1; return 0; } static int rt6_remove_exception_rt(struct rt6_info *rt) { struct fib6_info *from; from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) return -EINVAL; if (from->nh) { struct fib6_nh_excptn_arg arg = { .rt = rt, .plen = from->fib6_src.plen }; int rc; /* rc = 1 means an entry was found */ rc = nexthop_for_each_fib6_nh(from->nh, rt6_nh_remove_exception_rt, &arg); return rc ? 0 : -ENOENT; } return fib6_nh_remove_exception(from->fib6_nh, from->fib6_src.plen, rt); } /* Find rt6_ex which contains the passed in rt cache and * refresh its stamp */ static void fib6_nh_update_exception(const struct fib6_nh *nh, int plen, const struct rt6_info *rt) { const struct in6_addr *src_key = NULL; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; bucket = fib6_nh_get_excptn_bucket(nh, NULL); #ifdef CONFIG_IPV6_SUBTREES /* rt6i_src.plen != 0 indicates 'from' is in subtree * and exception table is indexed by a hash of * both rt6i_dst and rt6i_src. * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ if (plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_rcu(&bucket, &rt->rt6i_dst.addr, src_key); if (rt6_ex) rt6_ex->stamp = jiffies; } struct fib6_nh_match_arg { const struct net_device *dev; const struct in6_addr *gw; struct fib6_nh *match; }; /* determine if fib6_nh has given device and gateway */ static int fib6_nh_find_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_match_arg *arg = _arg; if (arg->dev != nh->fib_nh_dev || (arg->gw && !nh->fib_nh_gw_family) || (!arg->gw && nh->fib_nh_gw_family) || (arg->gw && !ipv6_addr_equal(arg->gw, &nh->fib_nh_gw6))) return 0; arg->match = nh; /* found a match, break the loop */ return 1; } static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct fib6_info *from; struct fib6_nh *fib6_nh; rcu_read_lock(); from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) goto unlock; if (from->nh) { struct fib6_nh_match_arg arg = { .dev = rt->dst.dev, .gw = &rt->rt6i_gateway, }; nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg); if (!arg.match) goto unlock; fib6_nh = arg.match; } else { fib6_nh = from->fib6_nh; } fib6_nh_update_exception(fib6_nh, from->fib6_src.plen, rt); unlock: rcu_read_unlock(); } static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, struct rt6_info *rt, int mtu) { /* If the new MTU is lower than the route PMTU, this new MTU will be the * lowest MTU in the path: always allow updating the route PMTU to * reflect PMTU decreases. * * If the new MTU is higher, and the route PMTU is equal to the local * MTU, this means the old MTU is the lowest in the path, so allow * updating it: if other nodes now have lower MTUs, PMTU discovery will * handle this. */ if (dst_mtu(&rt->dst) >= mtu) return true; if (dst_mtu(&rt->dst) == idev->cnf.mtu6) return true; return false; } static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, const struct fib6_nh *nh, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i; bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (!bucket) return; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { struct rt6_info *entry = rt6_ex->rt6i; /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected * route), the metrics of its rt->from have already * been updated. */ if (dst_metric_raw(&entry->dst, RTAX_MTU) && rt6_mtu_change_route_allowed(idev, entry, mtu)) dst_metric_set(&entry->dst, RTAX_MTU, mtu); } bucket++; } } #define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) static void fib6_nh_exceptions_clean_tohost(const struct fib6_nh *nh, const struct in6_addr *gateway) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; spin_lock_bh(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { struct rt6_info *entry = rt6_ex->rt6i; if ((entry->rt6i_flags & RTF_CACHE_GATEWAY) == RTF_CACHE_GATEWAY && ipv6_addr_equal(gateway, &entry->rt6i_gateway)) { rt6_remove_exception(bucket, rt6_ex); } } bucket++; } } spin_unlock_bh(&rt6_exception_lock); } static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, struct rt6_exception *rt6_ex, struct fib6_gc_args *gc_args, unsigned long now) { struct rt6_info *rt = rt6_ex->rt6i; /* we are pruning and obsoleting aged-out and non gateway exceptions * even if others have still references to them, so that on next * dst_check() such references can be dropped. * EXPIRES exceptions - e.g. pmtu-generated ones are pruned when * expired, independently from their aging, as per RFC 8201 section 4 */ if (!(rt->rt6i_flags & RTF_EXPIRES)) { if (time_after_eq(now, rt->dst.lastuse + gc_args->timeout)) { pr_debug("aging clone %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } else if (time_after(jiffies, rt->dst.expires)) { pr_debug("purging expired route %p\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } if (rt->rt6i_flags & RTF_GATEWAY) { struct neighbour *neigh; neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); if (!(neigh && (neigh->flags & NTF_ROUTER))) { pr_debug("purging route %p via non-router but gateway\n", rt); rt6_remove_exception(bucket, rt6_ex); return; } } gc_args->more++; } static void fib6_nh_age_exceptions(const struct fib6_nh *nh, struct fib6_gc_args *gc_args, unsigned long now) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; struct hlist_node *tmp; int i; if (!rcu_access_pointer(nh->rt6i_exception_bucket)) return; rcu_read_lock_bh(); spin_lock(&rt6_exception_lock); bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock); if (bucket) { for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) { rt6_age_examine_exception(bucket, rt6_ex, gc_args, now); } bucket++; } } spin_unlock(&rt6_exception_lock); rcu_read_unlock_bh(); } struct fib6_nh_age_excptn_arg { struct fib6_gc_args *gc_args; unsigned long now; }; static int rt6_nh_age_exceptions(struct fib6_nh *nh, void *_arg) { struct fib6_nh_age_excptn_arg *arg = _arg; fib6_nh_age_exceptions(nh, arg->gc_args, arg->now); return 0; } void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, unsigned long now) { if (f6i->nh) { struct fib6_nh_age_excptn_arg arg = { .gc_args = gc_args, .now = now }; nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_age_exceptions, &arg); } else { fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now); } } /* must be called with rcu lock held */ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int strict) { struct fib6_node *fn, *saved_fn; fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); saved_fn = fn; redo_rt6_select: rt6_select(net, fn, oif, res, strict); if (res->f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto redo_rt6_select; else if (strict & RT6_LOOKUP_F_REACHABLE) { /* also consider unreachable route */ strict &= ~RT6_LOOKUP_F_REACHABLE; fn = saved_fn; goto redo_rt6_select; } } trace_fib6_table_lookup(net, res, table, fl6); return 0; } struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct fib6_result res = {}; struct rt6_info *rt = NULL; int strict = 0; WARN_ON_ONCE((flags & RT6_LOOKUP_F_DST_NOREF) && !rcu_read_lock_held()); strict |= flags & RT6_LOOKUP_F_IFACE; strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE; if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0) strict |= RT6_LOOKUP_F_REACHABLE; rcu_read_lock(); fib6_table_lookup(net, table, oif, fl6, &res, strict); if (res.f6i == net->ipv6.fib6_null_entry) goto out; fib6_select_path(net, &res, fl6, oif, false, skb, strict); /*Search through exception table */ rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr); if (rt) { goto out; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && !res.nh->fib_nh_gw_family)) { /* Create a RTF_CACHE clone which will not be * owned by the fib6 tree. It is for the special case where * the daddr in the skb during the neighbor look-up is different * from the fl6->daddr used to look-up route here. */ rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL); if (rt) { /* 1 refcnt is taken during ip6_rt_cache_alloc(). * As rt6_uncached_list_add() does not consume refcnt, * this refcnt is always returned to the caller even * if caller sets RT6_LOOKUP_F_DST_NOREF flag. */ rt6_uncached_list_add(rt); rcu_read_unlock(); return rt; } } else { /* Get a percpu copy */ local_bh_disable(); rt = rt6_get_pcpu_route(&res); if (!rt) rt = rt6_make_pcpu_route(net, &res); local_bh_enable(); } out: if (!rt) rt = net->ipv6.ip6_null_entry; if (!(flags & RT6_LOOKUP_F_DST_NOREF)) ip6_hold_safe(net, &rt); rcu_read_unlock(); return rt; } EXPORT_SYMBOL_GPL(ip6_pol_route); INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, skb, flags); } struct dst_entry *ip6_route_input_lookup(struct net *net, struct net_device *dev, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { if (rt6_need_strict(&fl6->daddr) && dev->type != ARPHRD_PIMREG) flags |= RT6_LOOKUP_F_IFACE; return fib6_rule_lookup(net, fl6, skb, flags, ip6_pol_route_input); } EXPORT_SYMBOL_GPL(ip6_route_input_lookup); static void ip6_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *keys, struct flow_keys *flkeys) { const struct ipv6hdr *outer_iph = ipv6_hdr(skb); const struct ipv6hdr *key_iph = outer_iph; struct flow_keys *_flkeys = flkeys; const struct ipv6hdr *inner_iph; const struct icmp6hdr *icmph; struct ipv6hdr _inner_iph; struct icmp6hdr _icmph; if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6)) goto out; icmph = skb_header_pointer(skb, skb_transport_offset(skb), sizeof(_icmph), &_icmph); if (!icmph) goto out; if (!icmpv6_is_err(icmph->icmp6_type)) goto out; inner_iph = skb_header_pointer(skb, skb_transport_offset(skb) + sizeof(*icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) goto out; key_iph = inner_iph; _flkeys = NULL; out: if (_flkeys) { keys->addrs.v6addrs.src = _flkeys->addrs.v6addrs.src; keys->addrs.v6addrs.dst = _flkeys->addrs.v6addrs.dst; keys->tags.flow_label = _flkeys->tags.flow_label; keys->basic.ip_proto = _flkeys->basic.ip_proto; } else { keys->addrs.v6addrs.src = key_iph->saddr; keys->addrs.v6addrs.dst = key_iph->daddr; keys->tags.flow_label = ip6_flowlabel(key_iph); keys->basic.ip_proto = key_iph->nexthdr; } } static u32 rt6_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_ENCAP); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = keys.ports.dst; *p_has_inner = !!(keys.control.flags & FLOW_DIS_ENCAPSULATION); return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was * encountered during dissection of the outer flow, then there is no * point in calling the flow dissector again. */ if (!has_inner) return 0; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); skb_flow_dissect_flow_keys(skb, &keys, 0); if (!(keys.control.flags & FLOW_DIS_ENCAPSULATION)) return 0; if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_IP) hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_IP) hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_FLOWLABEL) hash_keys.tags.flow_label = keys.tags.flow_label; } if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_IP_PROTO) hash_keys.basic.ip_proto = keys.basic.ip_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_SRC_PORT) hash_keys.ports.src = keys.ports.src; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_INNER_DST_PORT) hash_keys.ports.dst = keys.ports.dst; return fib_multipath_hash_from_keys(net, &hash_keys); } static u32 rt6_multipath_custom_hash_skb(const struct net *net, const struct sk_buff *skb) { u32 mhash, mhash_inner; bool has_inner = true; mhash = rt6_multipath_custom_hash_outer(net, skb, &has_inner); mhash_inner = rt6_multipath_custom_hash_inner(net, skb, has_inner); return jhash_2words(mhash, mhash_inner, 0); } static u32 rt6_multipath_custom_hash_fl6(const struct net *net, const struct flowi6 *fl6) { u32 hash_fields = ip6_multipath_hash_fields(net); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) return 0; memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_IP) hash_keys.addrs.v6addrs.src = fl6->saddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_IP) hash_keys.addrs.v6addrs.dst = fl6->daddr; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_IP_PROTO) hash_keys.basic.ip_proto = fl6->flowi6_proto; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_FLOWLABEL) hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); if (hash_fields & FIB_MULTIPATH_HASH_FIELD_SRC_PORT) hash_keys.ports.src = fl6->fl6_sport; if (hash_fields & FIB_MULTIPATH_HASH_FIELD_DST_PORT) hash_keys.ports.dst = fl6->fl6_dport; return fib_multipath_hash_from_keys(net, &hash_keys); } /* if skb is set it will be used and fl6 can be NULL */ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, struct flow_keys *flkeys) { struct flow_keys hash_keys; u32 mhash = 0; switch (ip6_multipath_hash_policy(net)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (skb) { ip6_multipath_l3_keys(skb, &hash_keys, flkeys); } else { hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 1: if (skb) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; struct flow_keys keys; /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; hash_keys.ports.src = flkeys->ports.src; hash_keys.ports.dst = flkeys->ports.dst; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.ports.src = fl6->fl6_sport; hash_keys.ports.dst = fl6->fl6_dport; hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; if (skb) { struct flow_keys keys; if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, 0); flkeys = &keys; } /* Inner can be v4 or v6 */ if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; } else if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst; hash_keys.tags.flow_label = flkeys->tags.flow_label; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; ip6_multipath_l3_keys(skb, &hash_keys, flkeys); } } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = fl6->saddr; hash_keys.addrs.v6addrs.dst = fl6->daddr; hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6); hash_keys.basic.ip_proto = fl6->flowi6_proto; } mhash = fib_multipath_hash_from_keys(net, &hash_keys); break; case 3: if (skb) mhash = rt6_multipath_custom_hash_skb(net, skb); else mhash = rt6_multipath_custom_hash_fl6(net, fl6); break; } return mhash >> 1; } /* Called with rcu held */ void ip6_route_input(struct sk_buff *skb) { const struct ipv6hdr *iph = ipv6_hdr(skb); struct net *net = dev_net(skb->dev); int flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_DST_NOREF; struct ip_tunnel_info *tun_info; struct flowi6 fl6 = { .flowi6_iif = skb->dev->ifindex, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_mark = skb->mark, .flowi6_proto = iph->nexthdr, }; struct flow_keys *flkeys = NULL, _flkeys; tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id; if (fib6_rules_early_flow_dissect(net, skb, &fl6, &_flkeys)) flkeys = &_flkeys; if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6)) fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys); skb_dst_drop(skb); skb_dst_set_noref(skb, ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags)); } INDIRECT_CALLABLE_SCOPE struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags); } static struct dst_entry *ip6_route_output_flags_noref(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { bool any_src; if (ipv6_addr_type(&fl6->daddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) { struct dst_entry *dst; /* This function does not take refcnt on the dst */ dst = l3mdev_link_scope_lookup(net, fl6); if (dst) return dst; } fl6->flowi6_iif = LOOPBACK_IFINDEX; flags |= RT6_LOOKUP_F_DST_NOREF; any_src = ipv6_addr_any(&fl6->saddr); if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || (fl6->flowi6_oif && any_src)) flags |= RT6_LOOKUP_F_IFACE; if (!any_src) flags |= RT6_LOOKUP_F_HAS_SADDR; else if (sk) flags |= rt6_srcprefs2flags(READ_ONCE(inet6_sk(sk)->srcprefs)); return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output); } struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk, struct flowi6 *fl6, int flags) { struct dst_entry *dst; struct rt6_info *rt6; rcu_read_lock(); dst = ip6_route_output_flags_noref(net, sk, fl6, flags); rt6 = dst_rt6_info(dst); /* For dst cached in uncached_list, refcnt is already taken. */ if (list_empty(&rt6->dst.rt_uncached) && !dst_hold_safe(dst)) { dst = &net->ipv6.ip6_null_entry->dst; dst_hold(dst); } rcu_read_unlock(); return dst; } EXPORT_SYMBOL_GPL(ip6_route_output_flags); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rt6_info *rt, *ort = dst_rt6_info(dst_orig); struct net_device *loopback_dev = net->loopback_dev; struct dst_entry *new = NULL; rt = dst_alloc(&ip6_dst_blackhole_ops, loopback_dev, DST_OBSOLETE_DEAD, 0); if (rt) { rt6_info_init(rt); atomic_inc(&net->ipv6.rt6_stats->fib_rt_alloc); new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; dst_copy_metrics(new, &ort->dst); rt->rt6i_idev = in6_dev_get(loopback_dev); rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif } dst_release(dst_orig); return new ? new : ERR_PTR(-ENOMEM); } /* * Destination cache support functions */ static bool fib6_check(struct fib6_info *f6i, u32 cookie) { u32 rt_cookie = 0; if (!fib6_get_cookie_safe(f6i, &rt_cookie) || rt_cookie != cookie) return false; if (fib6_check_expired(f6i)) return false; return true; } static struct dst_entry *rt6_check(struct rt6_info *rt, struct fib6_info *from, u32 cookie) { u32 rt_cookie = 0; if (!from || !fib6_get_cookie_safe(from, &rt_cookie) || rt_cookie != cookie) return NULL; if (rt6_check_expired(rt)) return NULL; return &rt->dst; } static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, struct fib6_info *from, u32 cookie) { if (!__rt6_check_expired(rt) && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && fib6_check(from, cookie)) return &rt->dst; else return NULL; } INDIRECT_CALLABLE_SCOPE struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) { struct dst_entry *dst_ret; struct fib6_info *from; struct rt6_info *rt; rt = dst_rt6_info(dst); if (rt->sernum) return rt6_is_valid(rt) ? dst : NULL; rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ from = rcu_dereference(rt->from); if (from && (rt->rt6i_flags & RTF_PCPU || unlikely(!list_empty(&rt->dst.rt_uncached)))) dst_ret = rt6_dst_from_check(rt, from, cookie); else dst_ret = rt6_check(rt, from, cookie); rcu_read_unlock(); return dst_ret; } EXPORT_INDIRECT_CALLABLE(ip6_dst_check); static void ip6_negative_advice(struct sock *sk, struct dst_entry *dst) { struct rt6_info *rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_CACHE) { rcu_read_lock(); if (rt6_check_expired(rt)) { /* counteract the dst_release() in sk_dst_reset() */ dst_hold(dst); sk_dst_reset(sk); rt6_remove_exception_rt(rt); } rcu_read_unlock(); return; } sk_dst_reset(sk); } static void ip6_link_failure(struct sk_buff *skb) { struct rt6_info *rt; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); rt = dst_rt6_info(skb_dst(skb)); if (rt) { rcu_read_lock(); if (rt->rt6i_flags & RTF_CACHE) { rt6_remove_exception_rt(rt); } else { struct fib6_info *from; struct fib6_node *fn; from = rcu_dereference(rt->from); if (from) { fn = rcu_dereference(from->fib6_node); if (fn && (rt->rt6i_flags & RTF_DEFAULT)) WRITE_ONCE(fn->fn_sernum, -1); } } rcu_read_unlock(); } } static void rt6_update_expires(struct rt6_info *rt0, int timeout) { if (!(rt0->rt6i_flags & RTF_EXPIRES)) { struct fib6_info *from; rcu_read_lock(); from = rcu_dereference(rt0->from); if (from) rt0->dst.expires = from->expires; rcu_read_unlock(); } dst_set_expires(&rt0->dst, timeout); rt0->rt6i_flags |= RTF_EXPIRES; } static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) { struct net *net = dev_net(rt->dst.dev); dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt->rt6i_flags |= RTF_MODIFIED; rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); } static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) { return !(rt->rt6i_flags & RTF_CACHE) && (rt->rt6i_flags & RTF_PCPU || rcu_access_pointer(rt->from)); } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, const struct ipv6hdr *iph, u32 mtu, bool confirm_neigh) { const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = dst_rt6_info(dst); /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. * [see also comment in rt6_mtu_change_route()] */ if (iph) { daddr = &iph->daddr; saddr = &iph->saddr; } else if (sk) { daddr = &sk->sk_v6_daddr; saddr = &inet6_sk(sk)->saddr; } else { daddr = NULL; saddr = NULL; } if (confirm_neigh) dst_confirm_neigh(dst, daddr); if (mtu < IPV6_MIN_MTU) return; if (mtu >= dst_mtu(dst)) return; if (!rt6_cache_allowed_for_pmtu(rt6)) { rt6_do_update_pmtu(rt6, mtu); /* update rt6_ex->stamp for cache */ if (rt6->rt6i_flags & RTF_CACHE) rt6_update_exception_stamp_rt(rt6); } else if (daddr) { struct fib6_result res = {}; struct rt6_info *nrt6; rcu_read_lock(); res.f6i = rcu_dereference(rt6->from); if (!res.f6i) goto out_unlock; res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; if (res.f6i->nh) { struct fib6_nh_match_arg arg = { .dev = dst->dev, .gw = &rt6->rt6i_gateway, }; nexthop_for_each_fib6_nh(res.f6i->nh, fib6_nh_find_match, &arg); /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev + gw. Should be impossible. */ if (!arg.match) goto out_unlock; res.nh = arg.match; } else { res.nh = res.f6i->fib6_nh; } nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); if (rt6_insert_exception(nrt6, &res)) dst_release_immediate(&nrt6->dst); } out_unlock: rcu_read_unlock(); } } static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu, confirm_neigh); } void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, int oif, u32 mark, kuid_t uid) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_oif = oif, .flowi6_mark = mark ? mark : IP6_REPLY_MARK(net, skb->mark), .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_uid = uid, }; dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu) { int oif = sk->sk_bound_dev_if; struct dst_entry *dst; if (!oif && skb->dev) oif = l3mdev_master_ifindex(skb->dev); ip6_update_pmtu(skb, sock_net(sk), mtu, oif, READ_ONCE(sk->sk_mark), sk->sk_uid); dst = __sk_dst_get(sk); if (!dst || !dst->obsolete || dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) return; bh_lock_sock(sk); if (!sock_owned_by_user(sk) && !ipv6_addr_v4mapped(&sk->sk_v6_daddr)) ip6_datagram_dst_update(sk, false); bh_unlock_sock(sk); } EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu); void ip6_sk_dst_store_flow(struct sock *sk, struct dst_entry *dst, const struct flowi6 *fl6) { #ifdef CONFIG_IPV6_SUBTREES struct ipv6_pinfo *np = inet6_sk(sk); #endif ip6_dst_store(sk, dst, ipv6_addr_equal(&fl6->daddr, &sk->sk_v6_daddr) ? &sk->sk_v6_daddr : NULL, #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_equal(&fl6->saddr, &np->saddr) ? &np->saddr : #endif NULL); } static bool ip6_redirect_nh_match(const struct fib6_result *res, struct flowi6 *fl6, const struct in6_addr *gw, struct rt6_info **ret) { const struct fib6_nh *nh = res->nh; if (nh->fib_nh_flags & RTNH_F_DEAD || !nh->fib_nh_gw_family || fl6->flowi6_oif != nh->fib_nh_dev->ifindex) return false; /* rt_cache's gateway might be different from its 'parent' * in the case of an ip redirect. * So we keep searching in the exception table if the gateway * is different. */ if (!ipv6_addr_equal(gw, &nh->fib_nh_gw6)) { struct rt6_info *rt_cache; rt_cache = rt6_find_cached_rt(res, &fl6->daddr, &fl6->saddr); if (rt_cache && ipv6_addr_equal(gw, &rt_cache->rt6i_gateway)) { *ret = rt_cache; return true; } return false; } return true; } struct fib6_nh_rd_arg { struct fib6_result *res; struct flowi6 *fl6; const struct in6_addr *gw; struct rt6_info **ret; }; static int fib6_nh_redirect_match(struct fib6_nh *nh, void *_arg) { struct fib6_nh_rd_arg *arg = _arg; arg->res->nh = nh; return ip6_redirect_nh_match(arg->res, arg->fl6, arg->gw, arg->ret); } /* Handle redirects */ struct ip6rd_flowi { struct flowi6 fl6; struct in6_addr gateway; }; INDIRECT_CALLABLE_SCOPE struct rt6_info *__ip6_route_redirect(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; struct rt6_info *ret = NULL; struct fib6_result res = {}; struct fib6_nh_rd_arg arg = { .res = &res, .fl6 = fl6, .gw = &rdfl->gateway, .ret = &ret }; struct fib6_info *rt; struct fib6_node *fn; /* Get the "current" route for this destination and * check if the redirect has come from appropriate router. * * RFC 4861 specifies that redirects should only be * accepted if they come from the nexthop to the target. * Due to the way the routes are chosen, this notion * is a bit fuzzy and one might need to check all possible * routes. */ rcu_read_lock(); fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: for_each_fib6_node_rt_rcu(fn) { res.f6i = rt; if (fib6_check_expired(rt)) continue; if (rt->fib6_flags & RTF_REJECT) break; if (unlikely(rt->nh)) { if (nexthop_is_blackhole(rt->nh)) continue; /* on match, res->nh is filled in and potentially ret */ if (nexthop_for_each_fib6_nh(rt->nh, fib6_nh_redirect_match, &arg)) goto out; } else { res.nh = rt->fib6_nh; if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway, &ret)) goto out; } } if (!rt) rt = net->ipv6.fib6_null_entry; else if (rt->fib6_flags & RTF_REJECT) { ret = net->ipv6.ip6_null_entry; goto out; } if (rt == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } res.f6i = rt; res.nh = rt->fib6_nh; out: if (ret) { ip6_hold_safe(net, &ret); } else { res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; ret = ip6_create_rt_rcu(&res); } rcu_read_unlock(); trace_fib6_table_lookup(net, &res, table, fl6); return ret; }; static struct dst_entry *ip6_route_redirect(struct net *net, const struct flowi6 *fl6, const struct sk_buff *skb, const struct in6_addr *gateway) { int flags = RT6_LOOKUP_F_HAS_SADDR; struct ip6rd_flowi rdfl; rdfl.fl6 = *fl6; rdfl.gateway = *gateway; return fib6_rule_lookup(net, &rdfl.fl6, skb, flags, __ip6_route_redirect); } void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark, kuid_t uid) { const struct ipv6hdr *iph = (struct ipv6hdr *) skb->data; struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_oif = oif, .flowi6_mark = mark, .daddr = iph->daddr, .saddr = iph->saddr, .flowlabel = ip6_flowinfo(iph), .flowi6_uid = uid, }; dst = ip6_route_redirect(net, &fl6, skb, &ipv6_hdr(skb)->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_redirect); void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct rd_msg *msg = (struct rd_msg *)icmp6_hdr(skb); struct dst_entry *dst; struct flowi6 fl6 = { .flowi6_iif = LOOPBACK_IFINDEX, .flowi6_oif = oif, .daddr = msg->dest, .saddr = iph->daddr, .flowi6_uid = sock_net_uid(net, NULL), }; dst = ip6_route_redirect(net, &fl6, skb, &iph->saddr); rt6_do_redirect(dst, NULL, skb); dst_release(dst); } void ip6_sk_redirect(struct sk_buff *skb, struct sock *sk) { ip6_redirect(skb, sock_net(sk), sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark), sk->sk_uid); } EXPORT_SYMBOL_GPL(ip6_sk_redirect); static unsigned int ip6_default_advmss(const struct dst_entry *dst) { struct net_device *dev = dst->dev; unsigned int mtu = dst_mtu(dst); struct net *net = dev_net(dev); mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr); if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss) mtu = net->ipv6.sysctl.ip6_rt_min_advmss; /* * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. * IPV6_MAXPLEN is also valid and means: "any MSS, * rely only on pmtu discovery" */ if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr)) mtu = IPV6_MAXPLEN; return mtu; } INDIRECT_CALLABLE_SCOPE unsigned int ip6_mtu(const struct dst_entry *dst) { return ip6_dst_mtu_maybe_forward(dst, false); } EXPORT_INDIRECT_CALLABLE(ip6_mtu); /* MTU selection: * 1. mtu on route is locked - use it * 2. mtu from nexthop exception * 3. mtu from egress device * * based on ip6_dst_mtu_forward and exception logic of * rt6_find_cached_rt; called with rcu_read_lock */ u32 ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { const struct fib6_nh *nh = res->nh; struct fib6_info *f6i = res->f6i; struct inet6_dev *idev; struct rt6_info *rt; u32 mtu = 0; if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) { mtu = f6i->fib6_pmtu; if (mtu) goto out; } rt = rt6_find_cached_rt(res, daddr, saddr); if (unlikely(rt)) { mtu = dst_metric_raw(&rt->dst, RTAX_MTU); } else { struct net_device *dev = nh->fib_nh_dev; mtu = IPV6_MIN_MTU; idev = __in6_dev_get(dev); if (idev) mtu = max_t(u32, mtu, READ_ONCE(idev->cnf.mtu6)); } mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); out: return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu); } struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6) { struct dst_entry *dst; struct rt6_info *rt; struct inet6_dev *idev = in6_dev_get(dev); struct net *net = dev_net(dev); if (unlikely(!idev)) return ERR_PTR(-ENODEV); rt = ip6_dst_alloc(net, dev, 0); if (unlikely(!rt)) { in6_dev_put(idev); dst = ERR_PTR(-ENOMEM); goto out; } rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; rt->rt6i_dst.plen = 128; rt->rt6i_idev = idev; dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 0); /* Add this dst into uncached_list so that rt6_disable_ip() can * do proper release of the net_device */ rt6_uncached_list_add(rt); dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0); out: return dst; } static void ip6_dst_gc(struct dst_ops *ops) { struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops); int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval; int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity; int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout; unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc; unsigned int val; int entries; if (time_after(rt_last_gc + rt_min_interval, jiffies)) goto out; fib6_run_gc(atomic_inc_return(&net->ipv6.ip6_rt_gc_expire), net, true); entries = dst_entries_get_slow(ops); if (entries < ops->gc_thresh) atomic_set(&net->ipv6.ip6_rt_gc_expire, rt_gc_timeout >> 1); out: val = atomic_read(&net->ipv6.ip6_rt_gc_expire); atomic_set(&net->ipv6.ip6_rt_gc_expire, val - (val >> rt_elasticity)); } static int ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg, const struct in6_addr *gw_addr, u32 tbid, int flags, struct fib6_result *res) { struct flowi6 fl6 = { .flowi6_oif = cfg->fc_ifindex, .daddr = *gw_addr, .saddr = cfg->fc_prefsrc, }; struct fib6_table *table; int err; table = fib6_get_table(net, tbid); if (!table) return -EINVAL; if (!ipv6_addr_any(&cfg->fc_prefsrc)) flags |= RT6_LOOKUP_F_HAS_SADDR; flags |= RT6_LOOKUP_F_IGNORE_LINKSTATE; err = fib6_table_lookup(net, table, cfg->fc_ifindex, &fl6, res, flags); if (!err && res->f6i != net->ipv6.fib6_null_entry) fib6_select_path(net, res, &fl6, cfg->fc_ifindex, cfg->fc_ifindex != 0, NULL, flags); return err; } static int ip6_route_check_nh_onlink(struct net *net, struct fib6_config *cfg, const struct net_device *dev, struct netlink_ext_ack *extack) { u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN; const struct in6_addr *gw_addr = &cfg->fc_gateway; struct fib6_result res = {}; int err; err = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0, &res); if (!err && !(res.fib6_flags & RTF_REJECT) && /* ignore match if it is the default route */ !ipv6_addr_any(&res.f6i->fib6_dst.addr) && (res.fib6_type != RTN_UNICAST || dev != res.nh->fib_nh_dev)) { NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway or device mismatch"); err = -EINVAL; } return err; } static int ip6_route_check_nh(struct net *net, struct fib6_config *cfg, struct net_device **_dev, netdevice_tracker *dev_tracker, struct inet6_dev **idev) { const struct in6_addr *gw_addr = &cfg->fc_gateway; struct net_device *dev = _dev ? *_dev : NULL; int flags = RT6_LOOKUP_F_IFACE; struct fib6_result res = {}; int err = -EHOSTUNREACH; if (cfg->fc_table) { err = ip6_nh_lookup_table(net, cfg, gw_addr, cfg->fc_table, flags, &res); /* gw_addr can not require a gateway or resolve to a reject * route. If a device is given, it must match the result. */ if (err || res.fib6_flags & RTF_REJECT || res.nh->fib_nh_gw_family || (dev && dev != res.nh->fib_nh_dev)) err = -EHOSTUNREACH; } if (err < 0) { struct flowi6 fl6 = { .flowi6_oif = cfg->fc_ifindex, .daddr = *gw_addr, }; err = fib6_lookup(net, cfg->fc_ifindex, &fl6, &res, flags); if (err || res.fib6_flags & RTF_REJECT || res.nh->fib_nh_gw_family) err = -EHOSTUNREACH; if (err) return err; fib6_select_path(net, &res, &fl6, cfg->fc_ifindex, cfg->fc_ifindex != 0, NULL, flags); } err = 0; if (dev) { if (dev != res.nh->fib_nh_dev) err = -EHOSTUNREACH; } else { *_dev = dev = res.nh->fib_nh_dev; netdev_hold(dev, dev_tracker, GFP_ATOMIC); *idev = in6_dev_get(dev); } return err; } static int ip6_validate_gw(struct net *net, struct fib6_config *cfg, struct net_device **_dev, netdevice_tracker *dev_tracker, struct inet6_dev **idev, struct netlink_ext_ack *extack) { const struct in6_addr *gw_addr = &cfg->fc_gateway; int gwa_type = ipv6_addr_type(gw_addr); bool skip_dev = gwa_type & IPV6_ADDR_LINKLOCAL ? false : true; const struct net_device *dev = *_dev; bool need_addr_check = !dev; int err = -EINVAL; /* if gw_addr is local we will fail to detect this in case * address is still TENTATIVE (DAD in progress). rt6_lookup() * will return already-added prefix route via interface that * prefix route was assigned to, which might be non-loopback. */ if (dev && ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); goto out; } if (gwa_type != (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST)) { /* IPv6 strictly inhibits using not link-local * addresses as nexthop address. * Otherwise, router will not able to send redirects. * It is very good, but in some (rare!) circumstances * (SIT, PtP, NBMA NOARP links) it is handy to allow * some exceptions. --ANK * We allow IPv4-mapped nexthops to support RFC4798-type * addressing */ if (!(gwa_type & (IPV6_ADDR_UNICAST | IPV6_ADDR_MAPPED))) { NL_SET_ERR_MSG(extack, "Invalid gateway address"); goto out; } rcu_read_lock(); if (cfg->fc_flags & RTNH_F_ONLINK) err = ip6_route_check_nh_onlink(net, cfg, dev, extack); else err = ip6_route_check_nh(net, cfg, _dev, dev_tracker, idev); rcu_read_unlock(); if (err) goto out; } /* reload in case device was changed */ dev = *_dev; err = -EINVAL; if (!dev) { NL_SET_ERR_MSG(extack, "Egress device not specified"); goto out; } else if (dev->flags & IFF_LOOPBACK) { NL_SET_ERR_MSG(extack, "Egress device can not be loopback device for this route"); goto out; } /* if we did not check gw_addr above, do so now that the * egress device has been resolved. */ if (need_addr_check && ipv6_chk_addr_and_flags(net, gw_addr, dev, skip_dev, 0, 0)) { NL_SET_ERR_MSG(extack, "Gateway can not be a local address"); goto out; } err = 0; out: return err; } static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type) { if ((flags & RTF_REJECT) || (dev && (dev->flags & IFF_LOOPBACK) && !(addr_type & IPV6_ADDR_LOOPBACK) && !(flags & (RTF_ANYCAST | RTF_LOCAL)))) return true; return false; } int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { netdevice_tracker *dev_tracker = &fib6_nh->fib_nh_dev_tracker; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; int addr_type; int err; fib6_nh->fib_nh_family = AF_INET6; #ifdef CONFIG_IPV6_ROUTER_PREF fib6_nh->last_probe = jiffies; #endif if (cfg->fc_is_fdb) { fib6_nh->fib_nh_gw6 = cfg->fc_gateway; fib6_nh->fib_nh_gw_family = AF_INET6; return 0; } err = -ENODEV; if (cfg->fc_ifindex) { dev = netdev_get_by_index(net, cfg->fc_ifindex, dev_tracker, gfp_flags); if (!dev) goto out; idev = in6_dev_get(dev); if (!idev) goto out; } if (cfg->fc_flags & RTNH_F_ONLINK) { if (!dev) { NL_SET_ERR_MSG(extack, "Nexthop device required for onlink"); goto out; } if (!(dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } fib6_nh->fib_nh_flags |= RTNH_F_ONLINK; } fib6_nh->fib_nh_weight = 1; /* We cannot add true routes via loopback here, * they would result in kernel looping; promote them to reject routes */ addr_type = ipv6_addr_type(&cfg->fc_dst); if (fib6_is_reject(cfg->fc_flags, dev, addr_type)) { /* hold loopback dev/idev if we haven't done so. */ if (dev != net->loopback_dev) { if (dev) { netdev_put(dev, dev_tracker); in6_dev_put(idev); } dev = net->loopback_dev; netdev_hold(dev, dev_tracker, gfp_flags); idev = in6_dev_get(dev); if (!idev) { err = -ENODEV; goto out; } } goto pcpu_alloc; } if (cfg->fc_flags & RTF_GATEWAY) { err = ip6_validate_gw(net, cfg, &dev, dev_tracker, &idev, extack); if (err) goto out; fib6_nh->fib_nh_gw6 = cfg->fc_gateway; fib6_nh->fib_nh_gw_family = AF_INET6; } err = -ENODEV; if (!dev) goto out; if (!idev || idev->cnf.disable_ipv6) { NL_SET_ERR_MSG(extack, "IPv6 is disabled on nexthop device"); err = -EACCES; goto out; } if (!(dev->flags & IFF_UP) && !cfg->fc_ignore_dev_down) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); err = -ENETDOWN; goto out; } if (!(cfg->fc_flags & (RTF_LOCAL | RTF_ANYCAST)) && !netif_carrier_ok(dev)) fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = fib_nh_common_init(net, &fib6_nh->nh_common, cfg->fc_encap, cfg->fc_encap_type, cfg, gfp_flags, extack); if (err) goto out; pcpu_alloc: fib6_nh->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags); if (!fib6_nh->rt6i_pcpu) { err = -ENOMEM; goto out; } fib6_nh->fib_nh_dev = dev; fib6_nh->fib_nh_oif = dev->ifindex; err = 0; out: if (idev) in6_dev_put(idev); if (err) { lwtstate_put(fib6_nh->fib_nh_lws); fib6_nh->fib_nh_lws = NULL; netdev_put(dev, dev_tracker); } return err; } void fib6_nh_release(struct fib6_nh *fib6_nh) { struct rt6_exception_bucket *bucket; rcu_read_lock(); fib6_nh_flush_exceptions(fib6_nh, NULL); bucket = fib6_nh_get_excptn_bucket(fib6_nh, NULL); if (bucket) { rcu_assign_pointer(fib6_nh->rt6i_exception_bucket, NULL); kfree(bucket); } rcu_read_unlock(); fib6_nh_release_dsts(fib6_nh); free_percpu(fib6_nh->rt6i_pcpu); fib_nh_common_release(&fib6_nh->nh_common); } void fib6_nh_release_dsts(struct fib6_nh *fib6_nh) { int cpu; if (!fib6_nh->rt6i_pcpu) return; for_each_possible_cpu(cpu) { struct rt6_info *pcpu_rt, **ppcpu_rt; ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu); pcpu_rt = xchg(ppcpu_rt, NULL); if (pcpu_rt) { dst_dev_put(&pcpu_rt->dst); dst_release(&pcpu_rt->dst); } } } static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; struct fib6_info *rt = NULL; struct nexthop *nh = NULL; struct fib6_table *table; struct fib6_nh *fib6_nh; int err = -EINVAL; int addr_type; /* RTF_PCPU is an internal flag; can not be set by userspace */ if (cfg->fc_flags & RTF_PCPU) { NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU"); goto out; } /* RTF_CACHE is an internal flag; can not be set by userspace */ if (cfg->fc_flags & RTF_CACHE) { NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE"); goto out; } if (cfg->fc_type > RTN_MAX) { NL_SET_ERR_MSG(extack, "Invalid route type"); goto out; } if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto out; } if (cfg->fc_src_len > 128) { NL_SET_ERR_MSG(extack, "Invalid source address length"); goto out; } #ifndef CONFIG_IPV6_SUBTREES if (cfg->fc_src_len) { NL_SET_ERR_MSG(extack, "Specifying source address requires IPV6_SUBTREES to be enabled"); goto out; } #endif if (cfg->fc_nh_id) { nh = nexthop_find_by_id(net, cfg->fc_nh_id); if (!nh) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); goto out; } err = fib6_check_nexthop(nh, cfg, extack); if (err) goto out; } err = -ENOBUFS; if (cfg->fc_nlinfo.nlh && !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) { table = fib6_get_table(net, cfg->fc_table); if (!table) { pr_warn("NLM_F_CREATE should be specified when creating new route\n"); table = fib6_new_table(net, cfg->fc_table); } } else { table = fib6_new_table(net, cfg->fc_table); } if (!table) goto out; err = -ENOMEM; rt = fib6_info_alloc(gfp_flags, !nh); if (!rt) goto out; rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack); if (IS_ERR(rt->fib6_metrics)) { err = PTR_ERR(rt->fib6_metrics); /* Do not leave garbage there. */ rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics; goto out_free; } if (cfg->fc_flags & RTF_ADDRCONF) rt->dst_nocount = true; if (cfg->fc_flags & RTF_EXPIRES) fib6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; rt->fib6_protocol = cfg->fc_protocol; rt->fib6_table = table; rt->fib6_metric = cfg->fc_metric; rt->fib6_type = cfg->fc_type ? : RTN_UNICAST; rt->fib6_flags = cfg->fc_flags & ~RTF_GATEWAY; ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->fib6_dst.plen = cfg->fc_dst_len; #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len); rt->fib6_src.plen = cfg->fc_src_len; #endif if (nh) { if (rt->fib6_src.plen) { NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing"); goto out_free; } if (!nexthop_get(nh)) { NL_SET_ERR_MSG(extack, "Nexthop has been deleted"); goto out_free; } rt->nh = nh; fib6_nh = nexthop_fib6_nh(rt->nh); } else { err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack); if (err) goto out; fib6_nh = rt->fib6_nh; /* We cannot add true routes via loopback here, they would * result in kernel looping; promote them to reject routes */ addr_type = ipv6_addr_type(&cfg->fc_dst); if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh->fib_nh_dev, addr_type)) rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP; } if (!ipv6_addr_any(&cfg->fc_prefsrc)) { struct net_device *dev = fib6_nh->fib_nh_dev; if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) { NL_SET_ERR_MSG(extack, "Invalid source address"); err = -EINVAL; goto out; } rt->fib6_prefsrc.addr = cfg->fc_prefsrc; rt->fib6_prefsrc.plen = 128; } else rt->fib6_prefsrc.plen = 0; return rt; out: fib6_info_release(rt); return ERR_PTR(err); out_free: ip_fib_metrics_put(rt->fib6_metrics); kfree(rt); return ERR_PTR(err); } int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct fib6_info *rt; int err; rt = ip6_route_info_create(cfg, gfp_flags, extack); if (IS_ERR(rt)) return PTR_ERR(rt); err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack); fib6_info_release(rt); return err; } static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info) { struct net *net = info->nl_net; struct fib6_table *table; int err; if (rt == net->ipv6.fib6_null_entry) { err = -ENOENT; goto out; } table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); spin_unlock_bh(&table->tb6_lock); out: fib6_info_release(rt); return err; } int ip6_del_rt(struct net *net, struct fib6_info *rt, bool skip_notify) { struct nl_info info = { .nl_net = net, .skip_notify = skip_notify }; return __ip6_del_rt(rt, &info); } static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) { struct nl_info *info = &cfg->fc_nlinfo; struct net *net = info->nl_net; struct sk_buff *skb = NULL; struct fib6_table *table; int err = -ENOENT; if (rt == net->ipv6.fib6_null_entry) goto out_put; table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { struct fib6_info *sibling, *next_sibling; struct fib6_node *fn; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (skb) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; if (rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_DELROUTE, info->portid, seq, 0) < 0) { kfree_skb(skb); skb = NULL; } else info->skip_notify = 1; } /* 'rt' points to the first sibling route. If it is not the * leaf, then we do not need to send a notification. Otherwise, * we need to check if the last sibling has a next route or not * and emit a replace or delete notification, respectively. */ info->skip_notify_kernel = 1; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&table->tb6_lock)); if (rcu_access_pointer(fn->leaf) == rt) { struct fib6_info *last_sibling, *replace_rt; last_sibling = list_last_entry(&rt->fib6_siblings, struct fib6_info, fib6_siblings); replace_rt = rcu_dereference_protected( last_sibling->fib6_next, lockdep_is_held(&table->tb6_lock)); if (replace_rt) call_fib6_entry_notifiers_replace(net, replace_rt); else call_fib6_multipath_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, rt->fib6_nsiblings, NULL); } list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { err = fib6_del(sibling, info); if (err) goto out_unlock; } } err = fib6_del(rt, info); out_unlock: spin_unlock_bh(&table->tb6_lock); out_put: fib6_info_release(rt); if (skb) { rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); } return err; } static int __ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg) { int rc = -ESRCH; if (cfg->fc_ifindex && rt->dst.dev->ifindex != cfg->fc_ifindex) goto out; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) goto out; rc = rt6_remove_exception_rt(rt); out: return rc; } static int ip6_del_cached_rt(struct fib6_config *cfg, struct fib6_info *rt, struct fib6_nh *nh) { struct fib6_result res = { .f6i = rt, .nh = nh, }; struct rt6_info *rt_cache; rt_cache = rt6_find_cached_rt(&res, &cfg->fc_dst, &cfg->fc_src); if (rt_cache) return __ip6_del_cached_rt(rt_cache, cfg); return 0; } struct fib6_nh_del_cached_rt_arg { struct fib6_config *cfg; struct fib6_info *f6i; }; static int fib6_nh_del_cached_rt(struct fib6_nh *nh, void *_arg) { struct fib6_nh_del_cached_rt_arg *arg = _arg; int rc; rc = ip6_del_cached_rt(arg->cfg, arg->f6i, nh); return rc != -ESRCH ? rc : 0; } static int ip6_del_cached_rt_nh(struct fib6_config *cfg, struct fib6_info *f6i) { struct fib6_nh_del_cached_rt_arg arg = { .cfg = cfg, .f6i = f6i }; return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_del_cached_rt, &arg); } static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_table *table; struct fib6_info *rt; struct fib6_node *fn; int err = -ESRCH; table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table); if (!table) { NL_SET_ERR_MSG(extack, "FIB table does not exist"); return err; } rcu_read_lock(); fn = fib6_locate(&table->tb6_root, &cfg->fc_dst, cfg->fc_dst_len, &cfg->fc_src, cfg->fc_src_len, !(cfg->fc_flags & RTF_CACHE)); if (fn) { for_each_fib6_node_rt_rcu(fn) { struct fib6_nh *nh; if (rt->nh && cfg->fc_nh_id && rt->nh->id != cfg->fc_nh_id) continue; if (cfg->fc_flags & RTF_CACHE) { int rc = 0; if (rt->nh) { rc = ip6_del_cached_rt_nh(cfg, rt); } else if (cfg->fc_nh_id) { continue; } else { nh = rt->fib6_nh; rc = ip6_del_cached_rt(cfg, rt, nh); } if (rc != -ESRCH) { rcu_read_unlock(); return rc; } continue; } if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric) continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; if (rt->nh) { if (!fib6_info_hold_safe(rt)) continue; rcu_read_unlock(); return __ip6_del_rt(rt, &cfg->fc_nlinfo); } if (cfg->fc_nh_id) continue; nh = rt->fib6_nh; if (cfg->fc_ifindex && (!nh->fib_nh_dev || nh->fib_nh_dev->ifindex != cfg->fc_ifindex)) continue; if (cfg->fc_flags & RTF_GATEWAY && !ipv6_addr_equal(&cfg->fc_gateway, &nh->fib_nh_gw6)) continue; if (!fib6_info_hold_safe(rt)) continue; rcu_read_unlock(); /* if gateway was specified only delete the one hop */ if (cfg->fc_flags & RTF_GATEWAY) return __ip6_del_rt(rt, &cfg->fc_nlinfo); return __ip6_del_rt_siblings(rt, cfg); } } rcu_read_unlock(); return err; } static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct netevent_redirect netevent; struct rt6_info *rt, *nrt = NULL; struct fib6_result res = {}; struct ndisc_options ndopts; struct inet6_dev *in6_dev; struct neighbour *neigh; struct rd_msg *msg; int optlen, on_link; u8 *lladdr; optlen = skb_tail_pointer(skb) - skb_transport_header(skb); optlen -= sizeof(*msg); if (optlen < 0) { net_dbg_ratelimited("rt6_do_redirect: packet too short\n"); return; } msg = (struct rd_msg *)icmp6_hdr(skb); if (ipv6_addr_is_multicast(&msg->dest)) { net_dbg_ratelimited("rt6_do_redirect: destination address is multicast\n"); return; } on_link = 0; if (ipv6_addr_equal(&msg->dest, &msg->target)) { on_link = 1; } else if (ipv6_addr_type(&msg->target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) { net_dbg_ratelimited("rt6_do_redirect: target address is not link-local unicast\n"); return; } in6_dev = __in6_dev_get(skb->dev); if (!in6_dev) return; if (READ_ONCE(in6_dev->cnf.forwarding) || !READ_ONCE(in6_dev->cnf.accept_redirects)) return; /* RFC2461 8.1: * The IP source address of the Redirect MUST be the same as the current * first-hop router for the specified ICMP Destination Address. */ if (!ndisc_parse_options(skb->dev, msg->opt, optlen, &ndopts)) { net_dbg_ratelimited("rt6_redirect: invalid ND options\n"); return; } lladdr = NULL; if (ndopts.nd_opts_tgt_lladdr) { lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, skb->dev); if (!lladdr) { net_dbg_ratelimited("rt6_redirect: invalid link-layer address length\n"); return; } } rt = dst_rt6_info(dst); if (rt->rt6i_flags & RTF_REJECT) { net_dbg_ratelimited("rt6_redirect: source isn't a valid nexthop for redirect target\n"); return; } /* Redirect received -> path was valid. * Look, redirects are sent only in response to data packets, * so that this nexthop apparently is reachable. --ANK */ dst_confirm_neigh(&rt->dst, &ipv6_hdr(skb)->saddr); neigh = __neigh_lookup(&nd_tbl, &msg->target, skb->dev, 1); if (!neigh) return; /* * We have finally decided to accept it. */ ndisc_update(skb->dev, neigh, lladdr, NUD_STALE, NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE| (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER| NEIGH_UPDATE_F_ISROUTER)), NDISC_REDIRECT, &ndopts); rcu_read_lock(); res.f6i = rcu_dereference(rt->from); if (!res.f6i) goto out; if (res.f6i->nh) { struct fib6_nh_match_arg arg = { .dev = dst->dev, .gw = &rt->rt6i_gateway, }; nexthop_for_each_fib6_nh(res.f6i->nh, fib6_nh_find_match, &arg); /* fib6_info uses a nexthop that does not have fib6_nh * using the dst->dev. Should be impossible */ if (!arg.match) goto out; res.nh = arg.match; } else { res.nh = res.f6i->fib6_nh; } res.fib6_flags = res.f6i->fib6_flags; res.fib6_type = res.f6i->fib6_type; nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL); if (!nrt) goto out; nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE; if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; /* rt6_insert_exception() will take care of duplicated exceptions */ if (rt6_insert_exception(nrt, &res)) { dst_release_immediate(&nrt->dst); goto out; } netevent.old = &rt->dst; netevent.new = &nrt->dst; netevent.daddr = &msg->dest; netevent.neigh = neigh; call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); out: rcu_read_unlock(); neigh_release(neigh); } #ifdef CONFIG_IPV6_ROUTE_INFO static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; int ifindex = dev->ifindex; struct fib6_node *fn; struct fib6_info *rt = NULL; struct fib6_table *table; table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); fn = fib6_locate(&table->tb6_root, prefix, prefixlen, NULL, 0, true); if (!fn) goto out; for_each_fib6_node_rt_rcu(fn) { /* these routes do not use nexthops */ if (rt->nh) continue; if (rt->fib6_nh->fib_nh_dev->ifindex != ifindex) continue; if (!(rt->fib6_flags & RTF_ROUTEINFO) || !rt->fib6_nh->fib_nh_gw_family) continue; if (!ipv6_addr_equal(&rt->fib6_nh->fib_nh_gw6, gwaddr)) continue; if (!fib6_info_hold_safe(rt)) continue; break; } out: rcu_read_unlock(); return rt; } static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { struct fib6_config cfg = { .fc_metric = IP6_RT_PRIO_USER, .fc_ifindex = dev->ifindex, .fc_dst_len = prefixlen, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), .fc_protocol = RTPROT_RA, .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, }; cfg.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; cfg.fc_dst = *prefix; cfg.fc_gateway = *gwaddr; /* We should treat it as a default route if prefix length is 0. */ if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; ip6_route_add(&cfg, GFP_ATOMIC, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } #endif struct fib6_info *rt6_get_dflt_router(struct net *net, const struct in6_addr *addr, struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT; struct fib6_info *rt; struct fib6_table *table; table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { struct fib6_nh *nh; /* RA routes do not use nexthops */ if (rt->nh) continue; nh = rt->fib6_nh; if (dev == nh->fib_nh_dev && ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && ipv6_addr_equal(&nh->fib_nh_gw6, addr)) break; } if (rt && !fib6_info_hold_safe(rt)) rt = NULL; rcu_read_unlock(); return rt; } struct fib6_info *rt6_add_dflt_router(struct net *net, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref, u32 defrtr_usr_metric, int lifetime) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT, .fc_metric = defrtr_usr_metric, .fc_ifindex = dev->ifindex, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), .fc_protocol = RTPROT_RA, .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, .fc_expires = jiffies_to_clock_t(lifetime * HZ), }; cfg.fc_gateway = *gwaddr; if (!ip6_route_add(&cfg, GFP_ATOMIC, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); if (table) table->flags |= RT6_TABLE_HAS_DFLT_ROUTER; } return rt6_get_dflt_router(net, gwaddr, dev); } static void __rt6_purge_dflt_routers(struct net *net, struct fib6_table *table) { struct fib6_info *rt; restart: rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { struct net_device *dev = fib6_info_nh_dev(rt); struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && (!idev || idev->cnf.accept_ra != 2) && fib6_info_hold_safe(rt)) { rcu_read_unlock(); ip6_del_rt(net, rt, false); goto restart; } } rcu_read_unlock(); table->flags &= ~RT6_TABLE_HAS_DFLT_ROUTER; } void rt6_purge_dflt_routers(struct net *net) { struct fib6_table *table; struct hlist_head *head; unsigned int h; rcu_read_lock(); for (h = 0; h < FIB6_TABLE_HASHSZ; h++) { head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER) __rt6_purge_dflt_routers(net, table); } } rcu_read_unlock(); } static void rtmsg_to_fib6_config(struct net *net, struct in6_rtmsg *rtmsg, struct fib6_config *cfg) { *cfg = (struct fib6_config){ .fc_table = l3mdev_fib_table_by_index(net, rtmsg->rtmsg_ifindex) ? : RT6_TABLE_MAIN, .fc_ifindex = rtmsg->rtmsg_ifindex, .fc_metric = rtmsg->rtmsg_metric, .fc_expires = rtmsg->rtmsg_info, .fc_dst_len = rtmsg->rtmsg_dst_len, .fc_src_len = rtmsg->rtmsg_src_len, .fc_flags = rtmsg->rtmsg_flags, .fc_type = rtmsg->rtmsg_type, .fc_nlinfo.nl_net = net, .fc_dst = rtmsg->rtmsg_dst, .fc_src = rtmsg->rtmsg_src, .fc_gateway = rtmsg->rtmsg_gateway, }; } int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg) { struct fib6_config cfg; int err; if (cmd != SIOCADDRT && cmd != SIOCDELRT) return -EINVAL; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; rtmsg_to_fib6_config(net, rtmsg, &cfg); rtnl_lock(); switch (cmd) { case SIOCADDRT: /* Only do the default setting of fc_metric in route adding */ if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; err = ip6_route_add(&cfg, GFP_KERNEL, NULL); break; case SIOCDELRT: err = ip6_route_del(&cfg, NULL); break; } rtnl_unlock(); return err; } /* * Drop the packet on the floor */ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) { struct dst_entry *dst = skb_dst(skb); struct net *net = dev_net(dst->dev); struct inet6_dev *idev; SKB_DR(reason); int type; if (netif_is_l3_master(skb->dev) || dst->dev == net->loopback_dev) idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif)); else idev = ip6_dst_idev(dst); switch (ipstats_mib_noroutes) { case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); if (type == IPV6_ADDR_ANY) { SKB_DR_SET(reason, IP_INADDRERRORS); IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); break; } SKB_DR_SET(reason, IP_INNOROUTES); fallthrough; case IPSTATS_MIB_OUTNOROUTES: SKB_DR_OR(reason, IP_OUTNOROUTES); IP6_INC_STATS(net, idev, ipstats_mib_noroutes); break; } /* Start over by dropping the dst for l3mdev case */ if (netif_is_l3_master(skb->dev)) skb_dst_drop(skb); icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0); kfree_skb_reason(skb, reason); return 0; } static int ip6_pkt_discard(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES); } static int ip6_pkt_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES); } static int ip6_pkt_prohibit(struct sk_buff *skb) { return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES); } static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb) { skb->dev = skb_dst(skb)->dev; return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES); } /* * Allocate a dst for local (unicast / anycast) address. */ struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, const struct in6_addr *addr, bool anycast, gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL, .fc_ifindex = idev->dev->ifindex, .fc_flags = RTF_UP | RTF_NONEXTHOP, .fc_dst = *addr, .fc_dst_len = 128, .fc_protocol = RTPROT_KERNEL, .fc_nlinfo.nl_net = net, .fc_ignore_dev_down = true, }; struct fib6_info *f6i; if (anycast) { cfg.fc_type = RTN_ANYCAST; cfg.fc_flags |= RTF_ANYCAST; } else { cfg.fc_type = RTN_LOCAL; cfg.fc_flags |= RTF_LOCAL; } f6i = ip6_route_info_create(&cfg, gfp_flags, extack); if (!IS_ERR(f6i)) { f6i->dst_nocount = true; if (!anycast && (READ_ONCE(net->ipv6.devconf_all->disable_policy) || READ_ONCE(idev->cnf.disable_policy))) f6i->dst_nopolicy = true; } return f6i; } /* remove deleted ip from prefsrc entries */ struct arg_dev_net_ip { struct net *net; struct in6_addr *addr; }; static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) { struct net *net = ((struct arg_dev_net_ip *)arg)->net; struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; if (!rt->nh && rt != net->ipv6.fib6_null_entry && ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr) && !ipv6_chk_addr(net, addr, rt->fib6_nh->fib_nh_dev, 0)) { spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->fib6_prefsrc.plen = 0; spin_unlock_bh(&rt6_exception_lock); } return 0; } void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) { struct net *net = dev_net(ifp->idev->dev); struct arg_dev_net_ip adni = { .net = net, .addr = &ifp->addr, }; fib6_clean_all(net, fib6_remove_prefsrc, &adni); } #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT) /* Remove routers and update dst entries when gateway turn into host. */ static int fib6_clean_tohost(struct fib6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; struct fib6_nh *nh; /* RA routes do not use nexthops */ if (rt->nh) return 0; nh = rt->fib6_nh; if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && nh->fib_nh_gw_family && ipv6_addr_equal(gateway, &nh->fib_nh_gw6)) return -1; /* Further clean up cached routes in exception table. * This is needed because cached route may have a different * gateway than its 'parent' in the case of an ip redirect. */ fib6_nh_exceptions_clean_tohost(nh, gateway); return 0; } void rt6_clean_tohost(struct net *net, struct in6_addr *gateway) { fib6_clean_all(net, fib6_clean_tohost, gateway); } struct arg_netdev_event { const struct net_device *dev; union { unsigned char nh_flags; unsigned long event; }; }; static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) { struct fib6_info *iter; struct fib6_node *fn; fn = rcu_dereference_protected(rt->fib6_node, lockdep_is_held(&rt->fib6_table->tb6_lock)); iter = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(iter)) return iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); } return NULL; } /* only called for fib entries with builtin fib6_nh */ static bool rt6_is_dead(const struct fib6_info *rt) { if (rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD || (rt->fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN && ip6_ignore_linkdown(rt->fib6_nh->fib_nh_dev))) return true; return false; } static int rt6_multipath_total_weight(const struct fib6_info *rt) { struct fib6_info *iter; int total = 0; if (!rt6_is_dead(rt)) total += rt->fib6_nh->fib_nh_weight; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { if (!rt6_is_dead(iter)) total += iter->fib6_nh->fib_nh_weight; } return total; } static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total) { int upper_bound = -1; if (!rt6_is_dead(rt)) { *weight += rt->fib6_nh->fib_nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31, total) - 1; } atomic_set(&rt->fib6_nh->fib_nh_upper_bound, upper_bound); } static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total) { struct fib6_info *iter; int weight = 0; rt6_upper_bound_set(rt, &weight, total); list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) rt6_upper_bound_set(iter, &weight, total); } void rt6_multipath_rebalance(struct fib6_info *rt) { struct fib6_info *first; int total; /* In case the entire multipath route was marked for flushing, * then there is no need to rebalance upon the removal of every * sibling route. */ if (!rt->fib6_nsiblings || rt->should_flush) return; /* During lookup routes are evaluated in order, so we need to * make sure upper bounds are assigned from the first sibling * onwards. */ first = rt6_multipath_first_sibling(rt); if (WARN_ON_ONCE(!first)) return; total = rt6_multipath_total_weight(first); rt6_multipath_upper_bound_set(first, total); } static int fib6_ifup(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; struct net *net = dev_net(arg->dev); if (rt != net->ipv6.fib6_null_entry && !rt->nh && rt->fib6_nh->fib_nh_dev == arg->dev) { rt->fib6_nh->fib_nh_flags &= ~arg->nh_flags; fib6_update_sernum_upto_root(net, rt); rt6_multipath_rebalance(rt); } return 0; } void rt6_sync_up(struct net_device *dev, unsigned char nh_flags) { struct arg_netdev_event arg = { .dev = dev, { .nh_flags = nh_flags, }, }; if (nh_flags & RTNH_F_DEAD && netif_carrier_ok(dev)) arg.nh_flags |= RTNH_F_LINKDOWN; fib6_clean_all(dev_net(dev), fib6_ifup, &arg); } /* only called for fib entries with inline fib6_nh */ static bool rt6_multipath_uses_dev(const struct fib6_info *rt, const struct net_device *dev) { struct fib6_info *iter; if (rt->fib6_nh->fib_nh_dev == dev) return true; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == dev) return true; return false; } static void rt6_multipath_flush(struct fib6_info *rt) { struct fib6_info *iter; rt->should_flush = 1; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) iter->should_flush = 1; } static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt, const struct net_device *down_dev) { struct fib6_info *iter; unsigned int dead = 0; if (rt->fib6_nh->fib_nh_dev == down_dev || rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == down_dev || iter->fib6_nh->fib_nh_flags & RTNH_F_DEAD) dead++; return dead; } static void rt6_multipath_nh_flags_set(struct fib6_info *rt, const struct net_device *dev, unsigned char nh_flags) { struct fib6_info *iter; if (rt->fib6_nh->fib_nh_dev == dev) rt->fib6_nh->fib_nh_flags |= nh_flags; list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) if (iter->fib6_nh->fib_nh_dev == dev) iter->fib6_nh->fib_nh_flags |= nh_flags; } /* called with write lock held for table with rt */ static int fib6_ifdown(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; const struct net_device *dev = arg->dev; struct net *net = dev_net(dev); if (rt == net->ipv6.fib6_null_entry || rt->nh) return 0; switch (arg->event) { case NETDEV_UNREGISTER: return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; case NETDEV_DOWN: if (rt->should_flush) return -1; if (!rt->fib6_nsiblings) return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0; if (rt6_multipath_uses_dev(rt, dev)) { unsigned int count; count = rt6_multipath_dead_count(rt, dev); if (rt->fib6_nsiblings + 1 == count) { rt6_multipath_flush(rt); return -1; } rt6_multipath_nh_flags_set(rt, dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); fib6_update_sernum(net, rt); rt6_multipath_rebalance(rt); } return -2; case NETDEV_CHANGE: if (rt->fib6_nh->fib_nh_dev != dev || rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) break; rt->fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN; rt6_multipath_rebalance(rt); break; } return 0; } void rt6_sync_down_dev(struct net_device *dev, unsigned long event) { struct arg_netdev_event arg = { .dev = dev, { .event = event, }, }; struct net *net = dev_net(dev); if (net->ipv6.sysctl.skip_notify_on_dev_down) fib6_clean_all_skip_notify(net, fib6_ifdown, &arg); else fib6_clean_all(net, fib6_ifdown, &arg); } void rt6_disable_ip(struct net_device *dev, unsigned long event) { rt6_sync_down_dev(dev, event); rt6_uncached_list_flush_dev(dev); neigh_ifdown(&nd_tbl, dev); } struct rt6_mtu_change_arg { struct net_device *dev; unsigned int mtu; struct fib6_info *f6i; }; static int fib6_nh_mtu_change(struct fib6_nh *nh, void *_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *)_arg; struct fib6_info *f6i = arg->f6i; /* For administrative MTU increase, there is no way to discover * IPv6 PMTU increase, so PMTU increase should be updated here. * Since RFC 1981 doesn't include administrative MTU increase * update PMTU increase is a MUST. (i.e. jumbo frame) */ if (nh->fib_nh_dev == arg->dev) { struct inet6_dev *idev = __in6_dev_get(arg->dev); u32 mtu = f6i->fib6_pmtu; if (mtu >= arg->mtu || (mtu < arg->mtu && mtu == idev->cnf.mtu6)) fib6_metric_set(f6i, RTAX_MTU, arg->mtu); spin_lock_bh(&rt6_exception_lock); rt6_exceptions_update_pmtu(idev, nh, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } return 0; } static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; /* In IPv6 pmtu discovery is not optional, so that RTAX_MTU lock cannot disable it. We still use this lock to block changes caused by addrconf/ndisc. */ idev = __in6_dev_get(arg->dev); if (!idev) return 0; if (fib6_metric_locked(f6i, RTAX_MTU)) return 0; arg->f6i = f6i; if (f6i->nh) { /* fib6_nh_mtu_change only returns 0, so this is safe */ return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_mtu_change, arg); } return fib6_nh_mtu_change(f6i->fib6_nh, arg); } void rt6_mtu_change(struct net_device *dev, unsigned int mtu) { struct rt6_mtu_change_arg arg = { .dev = dev, .mtu = mtu, }; fib6_clean_all(dev_net(dev), rt6_mtu_change_route, &arg); } static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 }, [RTA_GATEWAY] = { .len = sizeof(struct in6_addr) }, [RTA_PREFSRC] = { .len = sizeof(struct in6_addr) }, [RTA_OIF] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, [RTA_PRIORITY] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_PREF] = { .type = NLA_U8 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, [RTA_EXPIRES] = { .type = NLA_U32 }, [RTA_UID] = { .type = NLA_U32 }, [RTA_MARK] = { .type = NLA_U32 }, [RTA_TABLE] = { .type = NLA_U32 }, [RTA_IP_PROTO] = { .type = NLA_U8 }, [RTA_SPORT] = { .type = NLA_U16 }, [RTA_DPORT] = { .type = NLA_U16 }, [RTA_NH_ID] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; unsigned int pref; int err; err = nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); if (rtm->rtm_tos) { NL_SET_ERR_MSG(extack, "Invalid dsfield (tos): option not available for IPv6"); goto errout; } *cfg = (struct fib6_config){ .fc_table = rtm->rtm_table, .fc_dst_len = rtm->rtm_dst_len, .fc_src_len = rtm->rtm_src_len, .fc_flags = RTF_UP, .fc_protocol = rtm->rtm_protocol, .fc_type = rtm->rtm_type, .fc_nlinfo.portid = NETLINK_CB(skb).portid, .fc_nlinfo.nlh = nlh, .fc_nlinfo.nl_net = sock_net(skb->sk), }; if (rtm->rtm_type == RTN_UNREACHABLE || rtm->rtm_type == RTN_BLACKHOLE || rtm->rtm_type == RTN_PROHIBIT || rtm->rtm_type == RTN_THROW) cfg->fc_flags |= RTF_REJECT; if (rtm->rtm_type == RTN_LOCAL) cfg->fc_flags |= RTF_LOCAL; if (rtm->rtm_flags & RTM_F_CLONED) cfg->fc_flags |= RTF_CACHE; cfg->fc_flags |= (rtm->rtm_flags & RTNH_F_ONLINK); if (tb[RTA_NH_ID]) { if (tb[RTA_GATEWAY] || tb[RTA_OIF] || tb[RTA_MULTIPATH] || tb[RTA_ENCAP]) { NL_SET_ERR_MSG(extack, "Nexthop specification and nexthop id are mutually exclusive"); goto errout; } cfg->fc_nh_id = nla_get_u32(tb[RTA_NH_ID]); } if (tb[RTA_GATEWAY]) { cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]); cfg->fc_flags |= RTF_GATEWAY; } if (tb[RTA_VIA]) { NL_SET_ERR_MSG(extack, "IPv6 does not support RTA_VIA attribute"); goto errout; } if (tb[RTA_DST]) { int plen = (rtm->rtm_dst_len + 7) >> 3; if (nla_len(tb[RTA_DST]) < plen) goto errout; nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen); } if (tb[RTA_SRC]) { int plen = (rtm->rtm_src_len + 7) >> 3; if (nla_len(tb[RTA_SRC]) < plen) goto errout; nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen); } if (tb[RTA_PREFSRC]) cfg->fc_prefsrc = nla_get_in6_addr(tb[RTA_PREFSRC]); if (tb[RTA_OIF]) cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); if (tb[RTA_PRIORITY]) cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]); if (tb[RTA_METRICS]) { cfg->fc_mx = nla_data(tb[RTA_METRICS]); cfg->fc_mx_len = nla_len(tb[RTA_METRICS]); } if (tb[RTA_TABLE]) cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); if (tb[RTA_MULTIPATH]) { cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]); cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]); err = lwtunnel_valid_encap_type_attr(cfg->fc_mp, cfg->fc_mp_len, extack); if (err < 0) goto errout; } if (tb[RTA_PREF]) { pref = nla_get_u8(tb[RTA_PREF]); if (pref != ICMPV6_ROUTER_PREF_LOW && pref != ICMPV6_ROUTER_PREF_HIGH) pref = ICMPV6_ROUTER_PREF_MEDIUM; cfg->fc_flags |= RTF_PREF(pref); } if (tb[RTA_ENCAP]) cfg->fc_encap = tb[RTA_ENCAP]; if (tb[RTA_ENCAP_TYPE]) { cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack); if (err < 0) goto errout; } if (tb[RTA_EXPIRES]) { unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ); if (addrconf_finite_timeout(timeout)) { cfg->fc_expires = jiffies_to_clock_t(timeout * HZ); cfg->fc_flags |= RTF_EXPIRES; } } err = 0; errout: return err; } struct rt6_nh { struct fib6_info *fib6_info; struct fib6_config r_cfg; struct list_head next; }; static int ip6_route_info_append(struct net *net, struct list_head *rt6_nh_list, struct fib6_info *rt, struct fib6_config *r_cfg) { struct rt6_nh *nh; int err = -EEXIST; list_for_each_entry(nh, rt6_nh_list, next) { /* check if fib6_info already exists */ if (rt6_duplicate_nexthop(nh->fib6_info, rt)) return err; } nh = kzalloc(sizeof(*nh), GFP_KERNEL); if (!nh) return -ENOMEM; nh->fib6_info = rt; memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg)); list_add_tail(&nh->next, rt6_nh_list); return 0; } static void ip6_route_mpath_notify(struct fib6_info *rt, struct fib6_info *rt_last, struct nl_info *info, __u16 nlflags) { /* if this is an APPEND route, then rt points to the first route * inserted and rt_last points to last route inserted. Userspace * wants a consistent dump of the route which starts at the first * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { rt = list_first_entry(&rt_last->fib6_siblings, struct fib6_info, fib6_siblings); } if (rt) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); } static bool ip6_route_mpath_should_notify(const struct fib6_info *rt) { bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); bool should_notify = false; struct fib6_info *leaf; struct fib6_node *fn; rcu_read_lock(); fn = rcu_dereference(rt->fib6_node); if (!fn) goto out; leaf = rcu_dereference(fn->leaf); if (!leaf) goto out; if (rt == leaf || (rt_can_ecmp && rt->fib6_metric == leaf->fib6_metric && rt6_qualify_for_ecmp(leaf))) should_notify = true; out: rcu_read_unlock(); return should_notify; } static int fib6_gw_from_attr(struct in6_addr *gw, struct nlattr *nla, struct netlink_ext_ack *extack) { if (nla_len(nla) < sizeof(*gw)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_GATEWAY"); return -EINVAL; } *gw = nla_get_in6_addr(nla); return 0; } static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; struct fib6_config r_cfg; struct rtnexthop *rtnh; struct fib6_info *rt; struct rt6_nh *err_nh; struct rt6_nh *nh, *nh_safe; __u16 nlflags; int remaining; int attrlen; int err = 1; int nhn = 0; int replace = (cfg->fc_nlinfo.nlh && (cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE)); LIST_HEAD(rt6_nh_list); nlflags = replace ? NLM_F_REPLACE : NLM_F_CREATE; if (info->nlh && info->nlh->nlmsg_flags & NLM_F_APPEND) nlflags |= NLM_F_APPEND; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry and build a list (rt6_nh_list) of * fib6_info structs per nexthop */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) r_cfg.fc_ifindex = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, extack); if (err) goto cleanup; r_cfg.fc_flags |= RTF_GATEWAY; } r_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP); /* RTA_ENCAP_TYPE length checked in * lwtunnel_valid_encap_type_attr */ nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE); if (nla) r_cfg.fc_encap_type = nla_get_u16(nla); } r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); rt = ip6_route_info_create(&r_cfg, GFP_KERNEL, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto cleanup; } if (!rt6_qualify_for_ecmp(rt)) { err = -EINVAL; NL_SET_ERR_MSG(extack, "Device only routes can not be added for IPv6 using the multipath API."); fib6_info_release(rt); goto cleanup; } rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1; err = ip6_route_info_append(info->nl_net, &rt6_nh_list, rt, &r_cfg); if (err) { fib6_info_release(rt); goto cleanup; } rtnh = rtnh_next(rtnh, &remaining); } if (list_empty(&rt6_nh_list)) { NL_SET_ERR_MSG(extack, "Invalid nexthop configuration - no valid nexthops"); return -EINVAL; } /* for add and replace send one notification with all nexthops. * Skip the notification in fib6_add_rt2node and send one with * the full route when done */ info->skip_notify = 1; /* For add and replace, send one notification with all nexthops. For * append, send one notification with all appended nexthops. */ info->skip_notify_kernel = 1; err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { err = __ip6_ins_rt(nh->fib6_info, info, extack); if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, "multipath route replace failed (check consistency of installed routes)"); err_nh = nh; goto add_errout; } /* save reference to last route successfully inserted */ rt_last = nh->fib6_info; /* save reference to first route for notification */ if (!rt_notif) rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, * we have already failed to add the first nexthop: * fib6_add_rt2node() has rejected it; when replacing, old * nexthops have been replaced by first new, the rest should * be added to it. */ if (cfg->fc_nlinfo.nlh) { cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; } nhn++; } /* An in-kernel notification should only be sent in case the new * multipath route is added as the first route in the node, or if * it was appended to it. We pass 'rt_notif' since it is the first * sibling and might allow us to skip some checks in the replace case. */ if (ip6_route_mpath_should_notify(rt_notif)) { enum fib_event_type fib_event; if (rt_notif->fib6_nsiblings != nhn - 1) fib_event = FIB_EVENT_ENTRY_APPEND; else fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib6_multipath_entry_notifiers(info->nl_net, fib_event, rt_notif, nhn - 1, extack); if (err) { /* Delete all the siblings that were just added */ err_nh = NULL; goto add_errout; } } /* success ... tell user about new route */ ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags); goto cleanup; add_errout: /* send notification for routes that were added so that * the delete notifications sent by ip6_route_del are * coherent */ if (rt_notif) ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags); /* Delete routes that were already added */ list_for_each_entry(nh, &rt6_nh_list, next) { if (err_nh == nh) break; ip6_route_del(&nh->r_cfg, extack); } cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } return err; } static int ip6_route_multipath_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { struct fib6_config r_cfg; struct rtnexthop *rtnh; int last_err = 0; int remaining; int attrlen; int err; remaining = cfg->fc_mp_len; rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); if (rtnh->rtnh_ifindex) r_cfg.fc_ifindex = rtnh->rtnh_ifindex; attrlen = rtnh_attrlen(rtnh); if (attrlen > 0) { struct nlattr *nla, *attrs = rtnh_attrs(rtnh); nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla) { err = fib6_gw_from_attr(&r_cfg.fc_gateway, nla, extack); if (err) { last_err = err; goto next_rtnh; } r_cfg.fc_flags |= RTF_GATEWAY; } } err = ip6_route_del(&r_cfg, extack); if (err) last_err = err; next_rtnh: rtnh = rtnh_next(rtnh, &remaining); } return last_err; } static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib6_config cfg; int err; err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_nh_id && !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id)) { NL_SET_ERR_MSG(extack, "Nexthop id does not exist"); return -EINVAL; } if (cfg.fc_mp) return ip6_route_multipath_del(&cfg, extack); else { cfg.fc_delete_all_nh = 1; return ip6_route_del(&cfg, extack); } } static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct fib6_config cfg; int err; err = rtm_to_fib6_config(skb, nlh, &cfg, extack); if (err < 0) return err; if (cfg.fc_metric == 0) cfg.fc_metric = IP6_RT_PRIO_USER; if (cfg.fc_mp) return ip6_route_multipath_add(&cfg, extack); else return ip6_route_add(&cfg, GFP_KERNEL, extack); } /* add the overhead of this fib6_nh to nexthop_len */ static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg) { int *nexthop_len = arg; *nexthop_len += nla_total_size(0) /* RTA_MULTIPATH */ + NLA_ALIGN(sizeof(struct rtnexthop)) + nla_total_size(16); /* RTA_GATEWAY */ if (nh->fib_nh_lws) { /* RTA_ENCAP_TYPE */ *nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); /* RTA_ENCAP */ *nexthop_len += nla_total_size(2); } return 0; } static size_t rt6_nlmsg_size(struct fib6_info *f6i) { int nexthop_len; if (f6i->nh) { nexthop_len = nla_total_size(4); /* RTA_NH_ID */ nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); } else { struct fib6_info *sibling, *next_sibling; struct fib6_nh *nh = f6i->fib6_nh; nexthop_len = 0; if (f6i->fib6_nsiblings) { rt6_nh_nlmsg_size(nh, &nexthop_len); list_for_each_entry_safe(sibling, next_sibling, &f6i->fib6_siblings, fib6_siblings) { rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); } } nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } return NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(16) /* RTA_SRC */ + nla_total_size(16) /* RTA_DST */ + nla_total_size(16) /* RTA_GATEWAY */ + nla_total_size(16) /* RTA_PREFSRC */ + nla_total_size(4) /* RTA_TABLE */ + nla_total_size(4) /* RTA_IIF */ + nla_total_size(4) /* RTA_OIF */ + nla_total_size(4) /* RTA_PRIORITY */ + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */ + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ + nla_total_size(1) /* RTA_PREF */ + nexthop_len; } static int rt6_fill_node_nexthop(struct sk_buff *skb, struct nexthop *nh, unsigned char *flags) { if (nexthop_is_multipath(nh)) { struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (nexthop_mpath_fill_node(skb, nh, AF_INET6)) goto nla_put_failure; nla_nest_end(skb, mp); } else { struct fib6_nh *fib6_nh; fib6_nh = nexthop_fib6_nh(nh); if (fib_nexthop_info(skb, &fib6_nh->nh_common, AF_INET6, flags, false) < 0) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int rt6_fill_node(struct net *net, struct sk_buff *skb, struct fib6_info *rt, struct dst_entry *dst, struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags) { struct rt6_info *rt6 = dst_rt6_info(dst); struct rt6key *rt6_dst, *rt6_src; u32 *pmetrics, table, rt6_flags; unsigned char nh_flags = 0; struct nlmsghdr *nlh; struct rtmsg *rtm; long expires = 0; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; if (rt6) { rt6_dst = &rt6->rt6i_dst; rt6_src = &rt6->rt6i_src; rt6_flags = rt6->rt6i_flags; } else { rt6_dst = &rt->fib6_dst; rt6_src = &rt->fib6_src; rt6_flags = rt->fib6_flags; } rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; rtm->rtm_dst_len = rt6_dst->plen; rtm->rtm_src_len = rt6_src->plen; rtm->rtm_tos = 0; if (rt->fib6_table) table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; rtm->rtm_table = table < 256 ? table : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; rtm->rtm_type = rt->fib6_type; rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->fib6_protocol; if (rt6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dest) { if (nla_put_in6_addr(skb, RTA_DST, dest)) goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { if (nla_put_in6_addr(skb, RTA_SRC, src)) goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE if (ipv6_addr_is_multicast(&rt6_dst->addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) return 0; if (err < 0) goto nla_put_failure; } else #endif if (nla_put_u32(skb, RTA_IIF, iif)) goto nla_put_failure; } else if (dest) { struct in6_addr saddr_buf; if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 && nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } if (rt->fib6_prefsrc.plen) { struct in6_addr saddr_buf; saddr_buf = rt->fib6_prefsrc.addr; if (nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } pmetrics = dst ? dst_metrics_ptr(dst) : rt->fib6_metrics->metrics; if (rtnetlink_put_metrics(skb, pmetrics) < 0) goto nla_put_failure; if (nla_put_u32(skb, RTA_PRIORITY, rt->fib6_metric)) goto nla_put_failure; /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ if (rt6) { if (rt6_flags & RTF_GATEWAY && nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) goto nla_put_failure; if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex)) goto nla_put_failure; if (dst->lwtstate && lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0) goto nla_put_failure; } else if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; struct nlattr *mp; mp = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp) goto nla_put_failure; if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common, rt->fib6_nh->fib_nh_weight, AF_INET6, 0) < 0) goto nla_put_failure; list_for_each_entry_safe(sibling, next_sibling, &rt->fib6_siblings, fib6_siblings) { if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common, sibling->fib6_nh->fib_nh_weight, AF_INET6, 0) < 0) goto nla_put_failure; } nla_nest_end(skb, mp); } else if (rt->nh) { if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id)) goto nla_put_failure; if (nexthop_is_blackhole(rt->nh)) rtm->rtm_type = RTN_BLACKHOLE; if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) && rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0) goto nla_put_failure; rtm->rtm_flags |= nh_flags; } else { if (fib_nexthop_info(skb, &rt->fib6_nh->nh_common, AF_INET6, &nh_flags, false) < 0) goto nla_put_failure; rtm->rtm_flags |= nh_flags; } if (rt6_flags & RTF_EXPIRES) { expires = dst ? dst->expires : rt->expires; expires -= jiffies; } if (!dst) { if (READ_ONCE(rt->offload)) rtm->rtm_flags |= RTM_F_OFFLOAD; if (READ_ONCE(rt->trap)) rtm->rtm_flags |= RTM_F_TRAP; if (READ_ONCE(rt->offload_failed)) rtm->rtm_flags |= RTM_F_OFFLOAD_FAILED; } if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags))) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int fib6_info_nh_uses_dev(struct fib6_nh *nh, void *arg) { const struct net_device *dev = arg; if (nh->fib_nh_dev == dev) return 1; return 0; } static bool fib6_info_uses_dev(const struct fib6_info *f6i, const struct net_device *dev) { if (f6i->nh) { struct net_device *_dev = (struct net_device *)dev; return !!nexthop_for_each_fib6_nh(f6i->nh, fib6_info_nh_uses_dev, _dev); } if (f6i->fib6_nh->fib_nh_dev == dev) return true; if (f6i->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; list_for_each_entry_safe(sibling, next_sibling, &f6i->fib6_siblings, fib6_siblings) { if (sibling->fib6_nh->fib_nh_dev == dev) return true; } } return false; } struct fib6_nh_exception_dump_walker { struct rt6_rtnl_dump_arg *dump; struct fib6_info *rt; unsigned int flags; unsigned int skip; unsigned int count; }; static int rt6_nh_dump_exceptions(struct fib6_nh *nh, void *arg) { struct fib6_nh_exception_dump_walker *w = arg; struct rt6_rtnl_dump_arg *dump = w->dump; struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; int i, err; bucket = fib6_nh_get_excptn_bucket(nh, NULL); if (!bucket) return 0; for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { if (w->skip) { w->skip--; continue; } /* Expiration of entries doesn't bump sernum, insertion * does. Removal is triggered by insertion, so we can * rely on the fact that if entries change between two * partial dumps, this node is scanned again completely, * see rt6_insert_exception() and fib6_dump_table(). * * Count expired entries we go through as handled * entries that we'll skip next time, in case of partial * node dump. Otherwise, if entries expire meanwhile, * we'll skip the wrong amount. */ if (rt6_check_expired(rt6_ex->rt6i)) { w->count++; continue; } err = rt6_fill_node(dump->net, dump->skb, w->rt, &rt6_ex->rt6i->dst, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(dump->cb->skb).portid, dump->cb->nlh->nlmsg_seq, w->flags); if (err) return err; w->count++; } bucket++; } return 0; } /* Return -1 if done with node, number of handled routes on partial dump */ int rt6_dump_route(struct fib6_info *rt, void *p_arg, unsigned int skip) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; struct fib_dump_filter *filter = &arg->filter; unsigned int flags = NLM_F_MULTI; struct net *net = arg->net; int count = 0; if (rt == net->ipv6.fib6_null_entry) return -1; if ((filter->flags & RTM_F_PREFIX) && !(rt->fib6_flags & RTF_PREFIX_RT)) { /* success since this is not a prefix route */ return -1; } if (filter->filter_set && ((filter->rt_type && rt->fib6_type != filter->rt_type) || (filter->dev && !fib6_info_uses_dev(rt, filter->dev)) || (filter->protocol && rt->fib6_protocol != filter->protocol))) { return -1; } if (filter->filter_set || !filter->dump_routes || !filter->dump_exceptions) { flags |= NLM_F_DUMP_FILTERED; } if (filter->dump_routes) { if (skip) { skip--; } else { if (rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq, flags)) { return 0; } count++; } } if (filter->dump_exceptions) { struct fib6_nh_exception_dump_walker w = { .dump = arg, .rt = rt, .flags = flags, .skip = skip, .count = 0 }; int err; rcu_read_lock(); if (rt->nh) { err = nexthop_for_each_fib6_nh(rt->nh, rt6_nh_dump_exceptions, &w); } else { err = rt6_nh_dump_exceptions(rt->fib6_nh, &w); } rcu_read_unlock(); if (err) return count + w.count; } return -1; } static int inet6_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG_MOD(extack, "Invalid header for get route request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request"); return -EINVAL; } if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) { NL_SET_ERR_MSG_MOD(extack, "Invalid flags for get route request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_SRC: case RTA_DST: case RTA_IIF: case RTA_OIF: case RTA_MARK: case RTA_UID: case RTA_SPORT: case RTA_DPORT: case RTA_IP_PROTO: break; default: NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); return -EINVAL; } } return 0; } static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; int err, iif = 0, oif = 0; struct fib6_info *from; struct dst_entry *dst; struct rt6_info *rt; struct sk_buff *skb; struct rtmsg *rtm; struct flowi6 fl6 = {}; bool fibmatch; err = inet6_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; err = -EINVAL; rtm = nlmsg_data(nlh); fl6.flowlabel = ip6_make_flowinfo(rtm->rtm_tos, 0); fibmatch = !!(rtm->rtm_flags & RTM_F_FIB_MATCH); if (tb[RTA_SRC]) { if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr)) goto errout; fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]); } if (tb[RTA_DST]) { if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr)) goto errout; fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]); } if (tb[RTA_IIF]) iif = nla_get_u32(tb[RTA_IIF]); if (tb[RTA_OIF]) oif = nla_get_u32(tb[RTA_OIF]); if (tb[RTA_MARK]) fl6.flowi6_mark = nla_get_u32(tb[RTA_MARK]); if (tb[RTA_UID]) fl6.flowi6_uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else fl6.flowi6_uid = iif ? INVALID_UID : current_uid(); if (tb[RTA_SPORT]) fl6.fl6_sport = nla_get_be16(tb[RTA_SPORT]); if (tb[RTA_DPORT]) fl6.fl6_dport = nla_get_be16(tb[RTA_DPORT]); if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], &fl6.flowi6_proto, AF_INET6, extack); if (err) goto errout; } if (iif) { struct net_device *dev; int flags = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(net, iif); if (!dev) { rcu_read_unlock(); err = -ENODEV; goto errout; } fl6.flowi6_iif = iif; if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; dst = ip6_route_input_lookup(net, dev, &fl6, NULL, flags); rcu_read_unlock(); } else { fl6.flowi6_oif = oif; dst = ip6_route_output(net, NULL, &fl6); } rt = dst_rt6_info(dst); if (rt->dst.error) { err = rt->dst.error; ip6_rt_put(rt); goto errout; } if (rt == net->ipv6.ip6_null_entry) { err = rt->dst.error; ip6_rt_put(rt); goto errout; } skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); err = -ENOBUFS; goto errout; } skb_dst_set(skb, &rt->dst); rcu_read_lock(); from = rcu_dereference(rt->from); if (from) { if (fibmatch) err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); else err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, &fl6.saddr, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } else { err = -ENETUNREACH; } rcu_read_unlock(); if (err < 0) { kfree_skb(skb); goto errout; } err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout: return err; } void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int nlm_flags) { struct sk_buff *skb; struct net *net = info->nl_net; u32 seq; int err; err = -ENOBUFS; seq = info->nlh ? info->nlh->nlmsg_seq : 0; skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, event, info->portid, seq, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_rt_update(struct net *net, struct fib6_info *rt, struct nl_info *info) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; struct sk_buff *skb; int err = -ENOBUFS; skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (!skb) goto errout; err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_NEWROUTE, info->portid, seq, NLM_F_REPLACE); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, info->nlh, gfp_any()); return; errout: if (err < 0) rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i, bool offload, bool trap, bool offload_failed) { struct sk_buff *skb; int err; if (READ_ONCE(f6i->offload) == offload && READ_ONCE(f6i->trap) == trap && READ_ONCE(f6i->offload_failed) == offload_failed) return; WRITE_ONCE(f6i->offload, offload); WRITE_ONCE(f6i->trap, trap); /* 2 means send notifications only if offload_failed was changed. */ if (net->ipv6.sysctl.fib_notify_on_flag_change == 2 && READ_ONCE(f6i->offload_failed) == offload_failed) return; WRITE_ONCE(f6i->offload_failed, offload_failed); if (!rcu_access_pointer(f6i->fib6_node)) /* The route was removed from the tree, do not send * notification. */ return; if (!net->ipv6.sysctl.fib_notify_on_flag_change) return; skb = nlmsg_new(rt6_nlmsg_size(f6i), GFP_KERNEL); if (!skb) { err = -ENOBUFS; goto errout; } err = rt6_fill_node(net, skb, f6i, NULL, NULL, NULL, 0, RTM_NEWROUTE, 0, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ROUTE, NULL, GFP_KERNEL); return; errout: rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err); } EXPORT_SYMBOL(fib6_info_hw_flags_set); static int ip6_route_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); if (!(dev->flags & IFF_LOOPBACK)) return NOTIFY_OK; if (event == NETDEV_REGISTER) { net->ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = dev; net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry->dst.dev = dev; net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev); net->ipv6.ip6_blk_hole_entry->dst.dev = dev; net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev); #endif } else if (event == NETDEV_UNREGISTER && dev->reg_state != NETREG_UNREGISTERED) { /* NETDEV_UNREGISTER could be fired for multiple times by * netdev_wait_allrefs(). Make sure we only call this once. */ in6_dev_put_clear(&net->ipv6.ip6_null_entry->rt6i_idev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES in6_dev_put_clear(&net->ipv6.ip6_prohibit_entry->rt6i_idev); in6_dev_put_clear(&net->ipv6.ip6_blk_hole_entry->rt6i_idev); #endif } return NOTIFY_OK; } /* * /proc */ #ifdef CONFIG_PROC_FS static int rt6_stats_seq_show(struct seq_file *seq, void *v) { struct net *net = (struct net *)seq->private; seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n", net->ipv6.rt6_stats->fib_nodes, net->ipv6.rt6_stats->fib_route_nodes, atomic_read(&net->ipv6.rt6_stats->fib_rt_alloc), net->ipv6.rt6_stats->fib_rt_entries, net->ipv6.rt6_stats->fib_rt_cache, dst_entries_get_slow(&net->ipv6.ip6_dst_ops), net->ipv6.rt6_stats->fib_discarded_routes); return 0; } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL static int ipv6_sysctl_rtcache_flush(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct net *net; int delay; int ret; if (!write) return -EINVAL; ret = proc_dointvec(ctl, write, buffer, lenp, ppos); if (ret) return ret; net = (struct net *)ctl->extra1; delay = net->ipv6.sysctl.flush_delay; fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0); return 0; } static struct ctl_table ipv6_route_table_template[] = { { .procname = "max_size", .data = &init_net.ipv6.sysctl.ip6_rt_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_thresh", .data = &ip6_dst_ops_template.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "flush", .data = &init_net.ipv6.sysctl.flush_delay, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv6_sysctl_rtcache_flush }, { .procname = "gc_min_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_timeout", .data = &init_net.ipv6.sysctl.ip6_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_interval", .data = &init_net.ipv6.sysctl.ip6_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_elasticity", .data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "mtu_expires", .data = &init_net.ipv6.sysctl.ip6_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "min_adv_mss", .data = &init_net.ipv6.sysctl.ip6_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_min_interval_ms", .data = &init_net.ipv6.sysctl.ip6_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "skip_notify_on_dev_down", .data = &init_net.ipv6.sysctl.skip_notify_on_dev_down, .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net) { struct ctl_table *table; table = kmemdup(ipv6_route_table_template, sizeof(ipv6_route_table_template), GFP_KERNEL); if (table) { table[0].data = &net->ipv6.sysctl.ip6_rt_max_size; table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh; table[2].data = &net->ipv6.sysctl.flush_delay; table[2].extra1 = net; table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout; table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval; table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity; table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires; table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss; table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval; table[10].data = &net->ipv6.sysctl.skip_notify_on_dev_down; } return table; } size_t ipv6_route_sysctl_table_size(struct net *net) { /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) return 1; return ARRAY_SIZE(ipv6_route_table_template); } #endif static int __net_init ip6_route_net_init(struct net *net) { int ret = -ENOMEM; memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template, sizeof(net->ipv6.ip6_dst_ops)); if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) goto out_ip6_dst_ops; net->ipv6.fib6_null_entry = fib6_info_alloc(GFP_KERNEL, true); if (!net->ipv6.fib6_null_entry) goto out_ip6_dst_entries; memcpy(net->ipv6.fib6_null_entry, &fib6_null_entry_template, sizeof(*net->ipv6.fib6_null_entry)); net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), GFP_KERNEL); if (!net->ipv6.ip6_null_entry) goto out_fib6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_null_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.fib6_has_custom_rules = false; net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, sizeof(*net->ipv6.ip6_prohibit_entry), GFP_KERNEL); if (!net->ipv6.ip6_prohibit_entry) goto out_ip6_null_entry; net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->dst.rt_uncached); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), GFP_KERNEL); if (!net->ipv6.ip6_blk_hole_entry) goto out_ip6_prohibit_entry; net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst, ip6_template_metrics, true); INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->dst.rt_uncached); #ifdef CONFIG_IPV6_SUBTREES net->ipv6.fib6_routes_require_src = 0; #endif #endif net->ipv6.sysctl.flush_delay = 0; net->ipv6.sysctl.ip6_rt_max_size = INT_MAX; net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2; net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ; net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ; net->ipv6.sysctl.ip6_rt_gc_elasticity = 9; net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ; net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40; net->ipv6.sysctl.skip_notify_on_dev_down = 0; atomic_set(&net->ipv6.ip6_rt_gc_expire, 30*HZ); ret = 0; out: return ret; #ifdef CONFIG_IPV6_MULTIPLE_TABLES out_ip6_prohibit_entry: kfree(net->ipv6.ip6_prohibit_entry); out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif out_fib6_null_entry: kfree(net->ipv6.fib6_null_entry); out_ip6_dst_entries: dst_entries_destroy(&net->ipv6.ip6_dst_ops); out_ip6_dst_ops: goto out; } static void __net_exit ip6_route_net_exit(struct net *net) { kfree(net->ipv6.fib6_null_entry); kfree(net->ipv6.ip6_null_entry); #ifdef CONFIG_IPV6_MULTIPLE_TABLES kfree(net->ipv6.ip6_prohibit_entry); kfree(net->ipv6.ip6_blk_hole_entry); #endif dst_entries_destroy(&net->ipv6.ip6_dst_ops); } static int __net_init ip6_route_net_init_late(struct net *net) { #ifdef CONFIG_PROC_FS if (!proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops, sizeof(struct ipv6_route_iter))) return -ENOMEM; if (!proc_create_net_single("rt6_stats", 0444, net->proc_net, rt6_stats_seq_show, NULL)) { remove_proc_entry("ipv6_route", net->proc_net); return -ENOMEM; } #endif return 0; } static void __net_exit ip6_route_net_exit_late(struct net *net) { #ifdef CONFIG_PROC_FS remove_proc_entry("ipv6_route", net->proc_net); remove_proc_entry("rt6_stats", net->proc_net); #endif } static struct pernet_operations ip6_route_net_ops = { .init = ip6_route_net_init, .exit = ip6_route_net_exit, }; static int __net_init ipv6_inetpeer_init(struct net *net) { struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); if (!bp) return -ENOMEM; inet_peer_base_init(bp); net->ipv6.peers = bp; return 0; } static void __net_exit ipv6_inetpeer_exit(struct net *net) { struct inet_peer_base *bp = net->ipv6.peers; net->ipv6.peers = NULL; inetpeer_invalidate_tree(bp); kfree(bp); } static struct pernet_operations ipv6_inetpeer_ops = { .init = ipv6_inetpeer_init, .exit = ipv6_inetpeer_exit, }; static struct pernet_operations ip6_route_net_late_ops = { .init = ip6_route_net_init_late, .exit = ip6_route_net_exit_late, }; static struct notifier_block ip6_route_dev_notifier = { .notifier_call = ip6_route_dev_notify, .priority = ADDRCONF_NOTIFY_PRIORITY - 10, }; void __init ip6_route_init_special_entries(void) { /* Registering of the loopback is done before this portion of code, * the loopback reference in rt6_info will not be taken, do it * manually for init_net */ init_net.ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #endif } #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *rt) BTF_ID_LIST(btf_fib6_info_id) BTF_ID(struct, fib6_info) static const struct bpf_iter_seq_info ipv6_route_seq_info = { .seq_ops = &ipv6_route_seq_ops, .init_seq_private = bpf_iter_init_seq_net, .fini_seq_private = bpf_iter_fini_seq_net, .seq_priv_size = sizeof(struct ipv6_route_iter), }; static struct bpf_iter_reg ipv6_route_reg_info = { .target = "ipv6_route", .ctx_arg_info_size = 1, .ctx_arg_info = { { offsetof(struct bpf_iter__ipv6_route, rt), PTR_TO_BTF_ID_OR_NULL }, }, .seq_info = &ipv6_route_seq_info, }; static int __init bpf_iter_register(void) { ipv6_route_reg_info.ctx_arg_info[0].btf_id = *btf_fib6_info_id; return bpf_iter_reg_target(&ipv6_route_reg_info); } static void bpf_iter_unregister(void) { bpf_iter_unreg_target(&ipv6_route_reg_info); } #endif #endif int __init ip6_route_init(void) { int ret; int cpu; ret = -ENOMEM; ip6_dst_ops_template.kmem_cachep = kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0, SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!ip6_dst_ops_template.kmem_cachep) goto out; ret = dst_entries_init(&ip6_dst_blackhole_ops); if (ret) goto out_kmem_cache; ret = register_pernet_subsys(&ipv6_inetpeer_ops); if (ret) goto out_dst_entries; ret = register_pernet_subsys(&ip6_route_net_ops); if (ret) goto out_register_inetpeer; ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep; ret = fib6_init(); if (ret) goto out_register_subsys; ret = xfrm6_init(); if (ret) goto out_fib6_init; ret = fib6_rules_init(); if (ret) goto xfrm6_init; ret = register_pernet_subsys(&ip6_route_net_late_ops); if (ret) goto fib6_rules_init; ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, 0); if (ret < 0) goto out_register_late_subsys; ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, 0); if (ret < 0) goto out_register_late_subsys; ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL, RTNL_FLAG_DOIT_UNLOCKED); if (ret < 0) goto out_register_late_subsys; ret = register_netdevice_notifier(&ip6_route_dev_notifier); if (ret) goto out_register_late_subsys; #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) ret = bpf_iter_register(); if (ret) goto out_register_late_subsys; #endif #endif for_each_possible_cpu(cpu) { struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); spin_lock_init(&ul->lock); } out: return ret; out_register_late_subsys: rtnl_unregister_all(PF_INET6); unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_init: fib6_rules_cleanup(); xfrm6_init: xfrm6_fini(); out_fib6_init: fib6_gc_cleanup(); out_register_subsys: unregister_pernet_subsys(&ip6_route_net_ops); out_register_inetpeer: unregister_pernet_subsys(&ipv6_inetpeer_ops); out_dst_entries: dst_entries_destroy(&ip6_dst_blackhole_ops); out_kmem_cache: kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); goto out; } void ip6_route_cleanup(void) { #if IS_BUILTIN(CONFIG_IPV6) #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) bpf_iter_unregister(); #endif #endif unregister_netdevice_notifier(&ip6_route_dev_notifier); unregister_pernet_subsys(&ip6_route_net_late_ops); fib6_rules_cleanup(); xfrm6_fini(); fib6_gc_cleanup(); unregister_pernet_subsys(&ipv6_inetpeer_ops); unregister_pernet_subsys(&ip6_route_net_ops); dst_entries_destroy(&ip6_dst_blackhole_ops); kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep); } |
| 3637 680 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM percpu #if !defined(_TRACE_PERCPU_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PERCPU_H #include <linux/tracepoint.h> #include <trace/events/mmflags.h> TRACE_EVENT(percpu_alloc_percpu, TP_PROTO(unsigned long call_site, bool reserved, bool is_atomic, size_t size, size_t align, void *base_addr, int off, void __percpu *ptr, size_t bytes_alloc, gfp_t gfp_flags), TP_ARGS(call_site, reserved, is_atomic, size, align, base_addr, off, ptr, bytes_alloc, gfp_flags), TP_STRUCT__entry( __field( unsigned long, call_site ) __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) __field( size_t, bytes_alloc ) __field( unsigned long, gfp_flags ) ), TP_fast_assign( __entry->call_site = call_site; __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; __entry->bytes_alloc = bytes_alloc; __entry->gfp_flags = (__force unsigned long)gfp_flags; ), TP_printk("call_site=%pS reserved=%d is_atomic=%d size=%zu align=%zu base_addr=%p off=%d ptr=%p bytes_alloc=%zu gfp_flags=%s", (void *)__entry->call_site, __entry->reserved, __entry->is_atomic, __entry->size, __entry->align, __entry->base_addr, __entry->off, __entry->ptr, __entry->bytes_alloc, show_gfp_flags(__entry->gfp_flags)) ); TRACE_EVENT(percpu_free_percpu, TP_PROTO(void *base_addr, int off, void __percpu *ptr), TP_ARGS(base_addr, off, ptr), TP_STRUCT__entry( __field( void *, base_addr ) __field( int, off ) __field( void __percpu *, ptr ) ), TP_fast_assign( __entry->base_addr = base_addr; __entry->off = off; __entry->ptr = ptr; ), TP_printk("base_addr=%p off=%d ptr=%p", __entry->base_addr, __entry->off, __entry->ptr) ); TRACE_EVENT(percpu_alloc_percpu_fail, TP_PROTO(bool reserved, bool is_atomic, size_t size, size_t align), TP_ARGS(reserved, is_atomic, size, align), TP_STRUCT__entry( __field( bool, reserved ) __field( bool, is_atomic ) __field( size_t, size ) __field( size_t, align ) ), TP_fast_assign( __entry->reserved = reserved; __entry->is_atomic = is_atomic; __entry->size = size; __entry->align = align; ), TP_printk("reserved=%d is_atomic=%d size=%zu align=%zu", __entry->reserved, __entry->is_atomic, __entry->size, __entry->align) ); TRACE_EVENT(percpu_create_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); TRACE_EVENT(percpu_destroy_chunk, TP_PROTO(void *base_addr), TP_ARGS(base_addr), TP_STRUCT__entry( __field( void *, base_addr ) ), TP_fast_assign( __entry->base_addr = base_addr; ), TP_printk("base_addr=%p", __entry->base_addr) ); #endif /* _TRACE_PERCPU_H */ #include <trace/define_trace.h> |
| 112 3 1724 880 221 510 180 1713 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. NET is implemented using the BSD Socket * interface as the means of communication with the user level. * * Definitions for the Ethernet handlers. * * Version: @(#)eth.h 1.0.4 05/13/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Relocated to include/linux where it belongs by Alan Cox * <gw4pts@gw4pts.ampr.org> */ #ifndef _LINUX_ETHERDEVICE_H #define _LINUX_ETHERDEVICE_H #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/random.h> #include <linux/crc32.h> #include <asm/unaligned.h> #include <asm/bitsperlong.h> #ifdef __KERNEL__ struct device; struct fwnode_handle; int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr); int platform_get_ethdev_address(struct device *dev, struct net_device *netdev); unsigned char *arch_get_platform_mac_address(void); int nvmem_get_mac_address(struct device *dev, void *addrbuf); int device_get_mac_address(struct device *dev, char *addr); int device_get_ethdev_address(struct device *dev, struct net_device *netdev); int fwnode_get_mac_address(struct fwnode_handle *fwnode, char *addr); u32 eth_get_headlen(const struct net_device *dev, const void *data, u32 len); __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev); extern const struct header_ops eth_header_ops; int eth_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned len); int eth_header_parse(const struct sk_buff *skb, unsigned char *haddr); int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void eth_header_cache_update(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); __be16 eth_header_parse_protocol(const struct sk_buff *skb); int eth_prepare_mac_addr_change(struct net_device *dev, void *p); void eth_commit_mac_addr_change(struct net_device *dev, void *p); int eth_mac_addr(struct net_device *dev, void *p); int eth_validate_addr(struct net_device *dev); struct net_device *alloc_etherdev_mqs(int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1) #define alloc_etherdev_mq(sizeof_priv, count) alloc_etherdev_mqs(sizeof_priv, count, count) struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv, unsigned int txqs, unsigned int rxqs); #define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1) struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb); int eth_gro_complete(struct sk_buff *skb, int nhoff); /* Reserved Ethernet Addresses per IEEE 802.1Q */ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; #define eth_stp_addr eth_reserved_addr_base static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 }; static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 }; /** * is_link_local_ether_addr - Determine if given Ethernet address is link-local * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if address is link local reserved addr (01:80:c2:00:00:0X) per * IEEE 802.1Q 8.6.3 Frame filtering. * * Please note: addr must be aligned to u16. */ static inline bool is_link_local_ether_addr(const u8 *addr) { __be16 *a = (__be16 *)addr; static const __be16 *b = (const __be16 *)eth_reserved_addr_base; static const __be16 m = cpu_to_be16(0xfff0); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return (((*(const u32 *)addr) ^ (*(const u32 *)b)) | (__force int)((a[2] ^ b[2]) & m)) == 0; #else return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | ((a[2] ^ b[2]) & m)) == 0; #endif } /** * is_zero_ether_addr - Determine if give Ethernet address is all zeros. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is all zeroes. * * Please note: addr must be aligned to u16. */ static inline bool is_zero_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ((*(const u32 *)addr) | (*(const u16 *)(addr + 4))) == 0; #else return (*(const u16 *)(addr + 0) | *(const u16 *)(addr + 2) | *(const u16 *)(addr + 4)) == 0; #endif } /** * is_multicast_ether_addr - Determine if the Ethernet address is a multicast. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is a multicast address. * By definition the broadcast address is also a multicast address. */ static inline bool is_multicast_ether_addr(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 a = *(const u32 *)addr; #else u16 a = *(const u16 *)addr; #endif #ifdef __BIG_ENDIAN return 0x01 & (a >> ((sizeof(a) * 8) - 8)); #else return 0x01 & a; #endif } static inline bool is_multicast_ether_addr_64bits(const u8 *addr) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #ifdef __BIG_ENDIAN return 0x01 & ((*(const u64 *)addr) >> 56); #else return 0x01 & (*(const u64 *)addr); #endif #else return is_multicast_ether_addr(addr); #endif } /** * is_local_ether_addr - Determine if the Ethernet address is locally-assigned one (IEEE 802). * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is a local address. */ static inline bool is_local_ether_addr(const u8 *addr) { return 0x02 & addr[0]; } /** * is_broadcast_ether_addr - Determine if the Ethernet address is broadcast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is the broadcast address. * * Please note: addr must be aligned to u16. */ static inline bool is_broadcast_ether_addr(const u8 *addr) { return (*(const u16 *)(addr + 0) & *(const u16 *)(addr + 2) & *(const u16 *)(addr + 4)) == 0xffff; } /** * is_unicast_ether_addr - Determine if the Ethernet address is unicast * @addr: Pointer to a six-byte array containing the Ethernet address * * Return true if the address is a unicast address. */ static inline bool is_unicast_ether_addr(const u8 *addr) { return !is_multicast_ether_addr(addr); } /** * is_valid_ether_addr - Determine if the given Ethernet address is valid * @addr: Pointer to a six-byte array containing the Ethernet address * * Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not * a multicast address, and is not FF:FF:FF:FF:FF:FF. * * Return true if the address is valid. * * Please note: addr must be aligned to u16. */ static inline bool is_valid_ether_addr(const u8 *addr) { /* FF:FF:FF:FF:FF:FF is a multicast address so we don't need to * explicitly check for it here. */ return !is_multicast_ether_addr(addr) && !is_zero_ether_addr(addr); } /** * eth_proto_is_802_3 - Determine if a given Ethertype/length is a protocol * @proto: Ethertype/length value to be tested * * Check that the value from the Ethertype/length field is a valid Ethertype. * * Return true if the valid is an 802.3 supported Ethertype. */ static inline bool eth_proto_is_802_3(__be16 proto) { #ifndef __BIG_ENDIAN /* if CPU is little endian mask off bits representing LSB */ proto &= htons(0xFF00); #endif /* cast both to u16 and compare since LSB can be ignored */ return (__force u16)proto >= (__force u16)htons(ETH_P_802_3_MIN); } /** * eth_random_addr - Generate software assigned random Ethernet address * @addr: Pointer to a six-byte array containing the Ethernet address * * Generate a random Ethernet address (MAC) that is not multicast * and has the local assigned bit set. */ static inline void eth_random_addr(u8 *addr) { get_random_bytes(addr, ETH_ALEN); addr[0] &= 0xfe; /* clear multicast bit */ addr[0] |= 0x02; /* set local assignment bit (IEEE802) */ } /** * eth_broadcast_addr - Assign broadcast address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the broadcast address to the given address array. */ static inline void eth_broadcast_addr(u8 *addr) { memset(addr, 0xff, ETH_ALEN); } /** * eth_zero_addr - Assign zero address * @addr: Pointer to a six-byte array containing the Ethernet address * * Assign the zero address to the given address array. */ static inline void eth_zero_addr(u8 *addr) { memset(addr, 0x00, ETH_ALEN); } /** * eth_hw_addr_random - Generate software assigned random Ethernet and * set device flag * @dev: pointer to net_device structure * * Generate a random Ethernet address (MAC) to be used by a net device * and set addr_assign_type so the state can be read by sysfs and be * used by userspace. */ static inline void eth_hw_addr_random(struct net_device *dev) { u8 addr[ETH_ALEN]; eth_random_addr(addr); __dev_addr_set(dev, addr, ETH_ALEN); dev->addr_assign_type = NET_ADDR_RANDOM; } /** * eth_hw_addr_crc - Calculate CRC from netdev_hw_addr * @ha: pointer to hardware address * * Calculate CRC from a hardware address as basis for filter hashes. */ static inline u32 eth_hw_addr_crc(struct netdev_hw_addr *ha) { return ether_crc(ETH_ALEN, ha->addr); } /** * ether_addr_copy - Copy an Ethernet address * @dst: Pointer to a six-byte array Ethernet address destination * @src: Pointer to a six-byte array Ethernet address source * * Please note: dst & src must both be aligned to u16. */ static inline void ether_addr_copy(u8 *dst, const u8 *src) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) *(u32 *)dst = *(const u32 *)src; *(u16 *)(dst + 4) = *(const u16 *)(src + 4); #else u16 *a = (u16 *)dst; const u16 *b = (const u16 *)src; a[0] = b[0]; a[1] = b[1]; a[2] = b[2]; #endif } /** * eth_hw_addr_set - Assign Ethernet address to a net_device * @dev: pointer to net_device structure * @addr: address to assign * * Assign given address to the net_device, addr_assign_type is not changed. */ static inline void eth_hw_addr_set(struct net_device *dev, const u8 *addr) { __dev_addr_set(dev, addr, ETH_ALEN); } /** * eth_hw_addr_inherit - Copy dev_addr from another net_device * @dst: pointer to net_device to copy dev_addr to * @src: pointer to net_device to copy dev_addr from * * Copy the Ethernet address from one net_device to another along with * the address attributes (addr_assign_type). */ static inline void eth_hw_addr_inherit(struct net_device *dst, struct net_device *src) { dst->addr_assign_type = src->addr_assign_type; eth_hw_addr_set(dst, src->dev_addr); } /** * ether_addr_equal - Compare two Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: addr1 & addr2 must both be aligned to u16. */ static inline bool ether_addr_equal(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) u32 fold = ((*(const u32 *)addr1) ^ (*(const u32 *)addr2)) | ((*(const u16 *)(addr1 + 4)) ^ (*(const u16 *)(addr2 + 4))); return fold == 0; #else const u16 *a = (const u16 *)addr1; const u16 *b = (const u16 *)addr2; return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) == 0; #endif } /** * ether_addr_equal_64bits - Compare two Ethernet addresses * @addr1: Pointer to an array of 8 bytes * @addr2: Pointer to an other array of 8 bytes * * Compare two Ethernet addresses, returns true if equal, false otherwise. * * The function doesn't need any conditional branches and possibly uses * word memory accesses on CPU allowing cheap unaligned memory reads. * arrays = { byte1, byte2, byte3, byte4, byte5, byte6, pad1, pad2 } * * Please note that alignment of addr1 & addr2 are only guaranteed to be 16 bits. */ static inline bool ether_addr_equal_64bits(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 u64 fold = (*(const u64 *)addr1) ^ (*(const u64 *)addr2); #ifdef __BIG_ENDIAN return (fold >> 16) == 0; #else return (fold << 16) == 0; #endif #else return ether_addr_equal(addr1, addr2); #endif } /** * ether_addr_equal_unaligned - Compare two not u16 aligned Ethernet addresses * @addr1: Pointer to a six-byte array containing the Ethernet address * @addr2: Pointer other six-byte array containing the Ethernet address * * Compare two Ethernet addresses, returns true if equal * * Please note: Use only when any Ethernet address may not be u16 aligned. */ static inline bool ether_addr_equal_unaligned(const u8 *addr1, const u8 *addr2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) return ether_addr_equal(addr1, addr2); #else return memcmp(addr1, addr2, ETH_ALEN) == 0; #endif } /** * ether_addr_equal_masked - Compare two Ethernet addresses with a mask * @addr1: Pointer to a six-byte array containing the 1st Ethernet address * @addr2: Pointer to a six-byte array containing the 2nd Ethernet address * @mask: Pointer to a six-byte array containing the Ethernet address bitmask * * Compare two Ethernet addresses with a mask, returns true if for every bit * set in the bitmask the equivalent bits in the ethernet addresses are equal. * Using a mask with all bits set is a slower ether_addr_equal. */ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2, const u8 *mask) { int i; for (i = 0; i < ETH_ALEN; i++) { if ((addr1[i] ^ addr2[i]) & mask[i]) return false; } return true; } static inline bool ether_addr_is_ipv4_mcast(const u8 *addr) { u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 }; return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask); } static inline bool ether_addr_is_ipv6_mcast(const u8 *addr) { u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 }; return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask); } static inline bool ether_addr_is_ip_mcast(const u8 *addr) { return ether_addr_is_ipv4_mcast(addr) || ether_addr_is_ipv6_mcast(addr); } /** * ether_addr_to_u64 - Convert an Ethernet address into a u64 value. * @addr: Pointer to a six-byte array containing the Ethernet address * * Return a u64 value of the address */ static inline u64 ether_addr_to_u64(const u8 *addr) { u64 u = 0; int i; for (i = 0; i < ETH_ALEN; i++) u = u << 8 | addr[i]; return u; } /** * u64_to_ether_addr - Convert a u64 to an Ethernet address. * @u: u64 to convert to an Ethernet MAC address * @addr: Pointer to a six-byte array to contain the Ethernet address */ static inline void u64_to_ether_addr(u64 u, u8 *addr) { int i; for (i = ETH_ALEN - 1; i >= 0; i--) { addr[i] = u & 0xff; u = u >> 8; } } /** * eth_addr_dec - Decrement the given MAC address * * @addr: Pointer to a six-byte array containing Ethernet address to decrement */ static inline void eth_addr_dec(u8 *addr) { u64 u = ether_addr_to_u64(addr); u--; u64_to_ether_addr(u, addr); } /** * eth_addr_inc() - Increment the given MAC address. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_inc(u8 *addr) { u64 u = ether_addr_to_u64(addr); u++; u64_to_ether_addr(u, addr); } /** * eth_addr_add() - Add (or subtract) an offset to/from the given MAC address. * * @offset: Offset to add. * @addr: Pointer to a six-byte array containing Ethernet address to increment. */ static inline void eth_addr_add(u8 *addr, long offset) { u64 u = ether_addr_to_u64(addr); u += offset; u64_to_ether_addr(u, addr); } /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure * @addr: Pointer to a six-byte array containing the Ethernet address * * Compare passed address with all addresses of the device. Return true if the * address if one of the device addresses. * * Note that this function calls ether_addr_equal_64bits() so take care of * the right padding. */ static inline bool is_etherdev_addr(const struct net_device *dev, const u8 addr[6 + 2]) { struct netdev_hw_addr *ha; bool res = false; rcu_read_lock(); for_each_dev_addr(dev, ha) { res = ether_addr_equal_64bits(addr, ha->addr); if (res) break; } rcu_read_unlock(); return res; } #endif /* __KERNEL__ */ /** * compare_ether_header - Compare two Ethernet headers * @a: Pointer to Ethernet header * @b: Pointer to Ethernet header * * Compare two Ethernet headers, returns 0 if equal. * This assumes that the network header (i.e., IP header) is 4-byte * aligned OR the platform can handle unaligned access. This is the * case for all packets coming into netif_receive_skb or similar * entry points. */ static inline unsigned long compare_ether_header(const void *a, const void *b) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 unsigned long fold; /* * We want to compare 14 bytes: * [a0 ... a13] ^ [b0 ... b13] * Use two long XOR, ORed together, with an overlap of two bytes. * [a0 a1 a2 a3 a4 a5 a6 a7 ] ^ [b0 b1 b2 b3 b4 b5 b6 b7 ] | * [a6 a7 a8 a9 a10 a11 a12 a13] ^ [b6 b7 b8 b9 b10 b11 b12 b13] * This means the [a6 a7] ^ [b6 b7] part is done two times. */ fold = *(unsigned long *)a ^ *(unsigned long *)b; fold |= *(unsigned long *)(a + 6) ^ *(unsigned long *)(b + 6); return fold; #else u32 *a32 = (u32 *)((u8 *)a + 2); u32 *b32 = (u32 *)((u8 *)b + 2); return (*(u16 *)a ^ *(u16 *)b) | (a32[0] ^ b32[0]) | (a32[1] ^ b32[1]) | (a32[2] ^ b32[2]); #endif } /** * eth_hw_addr_gen - Generate and assign Ethernet address to a port * @dev: pointer to port's net_device structure * @base_addr: base Ethernet address * @id: offset to add to the base address * * Generate a MAC address using a base address and an offset and assign it * to a net_device. Commonly used by switch drivers which need to compute * addresses for all their ports. addr_assign_type is not changed. */ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr, unsigned int id) { u64 u = ether_addr_to_u64(base_addr); u8 addr[ETH_ALEN]; u += id; u64_to_ether_addr(u, addr); eth_hw_addr_set(dev, addr); } /** * eth_skb_pkt_type - Assign packet type if destination address does not match * @skb: Assigned a packet type if address does not match @dev address * @dev: Network device used to compare packet address against * * If the destination MAC address of the packet does not match the network * device address, assign an appropriate packet type. */ static inline void eth_skb_pkt_type(struct sk_buff *skb, const struct net_device *dev) { const struct ethhdr *eth = eth_hdr(skb); if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) { if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) skb->pkt_type = PACKET_BROADCAST; else skb->pkt_type = PACKET_MULTICAST; } else { skb->pkt_type = PACKET_OTHERHOST; } } } static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb) { struct ethhdr *eth = (struct ethhdr *)skb->data; skb_pull_inline(skb, ETH_HLEN); return eth; } /** * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame * @skb: Buffer to pad * * An Ethernet frame should have a minimum size of 60 bytes. This function * takes short frames and pads them with zeros up to the 60 byte limit. */ static inline int eth_skb_pad(struct sk_buff *skb) { return skb_put_padto(skb, ETH_ZLEN); } #endif /* _LINUX_ETHERDEVICE_H */ |
| 14 14 1 14 12 6 1 6 1 6 6 2 2 5 6 6 2 4 4 1 6 1 2 1 6 5 6 6 6 6 7 1 8 6 2 2 6 6 3 5 6 6 6 3 6 2 6 6 6 6 6 6 6 8 8 3 1 2 7 2 2 2 2 2 2 14 13 1 14 14 14 43 40 5 12 16 13 4 2 36 2 35 22 3 6 10 2 2 2 19 3 2 1 1 49 1 6 14 1 64 64 59 5 1 1 1 3 35 1 8 1 4 6 3 9 4 8 1 36 2 1 1 49 1 1 42 1 1 7 1 30 6 36 33 34 3 18 16 1 14 2 5 12 1 14 14 1 1 14 50 51 29 22 4 4 4 1 4 4 4 3 4 3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 | /* * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. * */ #include <linux/kernel.h> #include <linux/moduleparam.h> #include <linux/gfp.h> #include <net/sock.h> #include <linux/in.h> #include <linux/list.h> #include <linux/ratelimit.h> #include <linux/export.h> #include <linux/sizes.h> #include "rds.h" /* When transmitting messages in rds_send_xmit, we need to emerge from * time to time and briefly release the CPU. Otherwise the softlock watchdog * will kick our shin. * Also, it seems fairer to not let one busy connection stall all the * others. * * send_batch_count is the number of times we'll loop in send_xmit. Setting * it to 0 will restore the old behavior (where we looped until we had * drained the queue). */ static int send_batch_count = SZ_1K; module_param(send_batch_count, int, 0444); MODULE_PARM_DESC(send_batch_count, " batch factor when working the send queue"); static void rds_send_remove_from_sock(struct list_head *messages, int status); /* * Reset the send state. Callers must ensure that this doesn't race with * rds_send_xmit(). */ void rds_send_path_reset(struct rds_conn_path *cp) { struct rds_message *rm, *tmp; unsigned long flags; if (cp->cp_xmit_rm) { rm = cp->cp_xmit_rm; cp->cp_xmit_rm = NULL; /* Tell the user the RDMA op is no longer mapped by the * transport. This isn't entirely true (it's flushed out * independently) but as the connection is down, there's * no ongoing RDMA to/from that memory */ rds_message_unmapped(rm); rds_message_put(rm); } cp->cp_xmit_sg = 0; cp->cp_xmit_hdr_off = 0; cp->cp_xmit_data_off = 0; cp->cp_xmit_atomic_sent = 0; cp->cp_xmit_rdma_sent = 0; cp->cp_xmit_data_sent = 0; cp->cp_conn->c_map_queued = 0; cp->cp_unacked_packets = rds_sysctl_max_unacked_packets; cp->cp_unacked_bytes = rds_sysctl_max_unacked_bytes; /* Mark messages as retransmissions, and move them to the send q */ spin_lock_irqsave(&cp->cp_lock, flags); list_for_each_entry_safe(rm, tmp, &cp->cp_retrans, m_conn_item) { set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags); set_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags); } list_splice_init(&cp->cp_retrans, &cp->cp_send_queue); spin_unlock_irqrestore(&cp->cp_lock, flags); } EXPORT_SYMBOL_GPL(rds_send_path_reset); static int acquire_in_xmit(struct rds_conn_path *cp) { return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0; } static void release_in_xmit(struct rds_conn_path *cp) { clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); /* * We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk * the system-wide hashed waitqueue buckets in the fast path only to * almost never find waiters. */ if (waitqueue_active(&cp->cp_waitq)) wake_up_all(&cp->cp_waitq); } /* * We're making the conscious trade-off here to only send one message * down the connection at a time. * Pro: * - tx queueing is a simple fifo list * - reassembly is optional and easily done by transports per conn * - no per flow rx lookup at all, straight to the socket * - less per-frag memory and wire overhead * Con: * - queued acks can be delayed behind large messages * Depends: * - small message latency is higher behind queued large messages * - large message latency isn't starved by intervening small sends */ int rds_send_xmit(struct rds_conn_path *cp) { struct rds_connection *conn = cp->cp_conn; struct rds_message *rm; unsigned long flags; unsigned int tmp; struct scatterlist *sg; int ret = 0; LIST_HEAD(to_be_dropped); int batch_count; unsigned long send_gen = 0; int same_rm = 0; restart: batch_count = 0; /* * sendmsg calls here after having queued its message on the send * queue. We only have one task feeding the connection at a time. If * another thread is already feeding the queue then we back off. This * avoids blocking the caller and trading per-connection data between * caches per message. */ if (!acquire_in_xmit(cp)) { rds_stats_inc(s_send_lock_contention); ret = -ENOMEM; goto out; } if (rds_destroy_pending(cp->cp_conn)) { release_in_xmit(cp); ret = -ENETUNREACH; /* dont requeue send work */ goto out; } /* * we record the send generation after doing the xmit acquire. * if someone else manages to jump in and do some work, we'll use * this to avoid a goto restart farther down. * * The acquire_in_xmit() check above ensures that only one * caller can increment c_send_gen at any time. */ send_gen = READ_ONCE(cp->cp_send_gen) + 1; WRITE_ONCE(cp->cp_send_gen, send_gen); /* * rds_conn_shutdown() sets the conn state and then tests RDS_IN_XMIT, * we do the opposite to avoid races. */ if (!rds_conn_path_up(cp)) { release_in_xmit(cp); ret = 0; goto out; } if (conn->c_trans->xmit_path_prepare) conn->c_trans->xmit_path_prepare(cp); /* * spin trying to push headers and data down the connection until * the connection doesn't make forward progress. */ while (1) { rm = cp->cp_xmit_rm; if (!rm) { same_rm = 0; } else { same_rm++; if (same_rm >= 4096) { rds_stats_inc(s_send_stuck_rm); ret = -EAGAIN; break; } } /* * If between sending messages, we can send a pending congestion * map update. */ if (!rm && test_and_clear_bit(0, &conn->c_map_queued)) { rm = rds_cong_update_alloc(conn); if (IS_ERR(rm)) { ret = PTR_ERR(rm); break; } rm->data.op_active = 1; rm->m_inc.i_conn_path = cp; rm->m_inc.i_conn = cp->cp_conn; cp->cp_xmit_rm = rm; } /* * If not already working on one, grab the next message. * * cp_xmit_rm holds a ref while we're sending this message down * the connction. We can use this ref while holding the * send_sem.. rds_send_reset() is serialized with it. */ if (!rm) { unsigned int len; batch_count++; /* we want to process as big a batch as we can, but * we also want to avoid softlockups. If we've been * through a lot of messages, lets back off and see * if anyone else jumps in */ if (batch_count >= send_batch_count) goto over_batch; spin_lock_irqsave(&cp->cp_lock, flags); if (!list_empty(&cp->cp_send_queue)) { rm = list_entry(cp->cp_send_queue.next, struct rds_message, m_conn_item); rds_message_addref(rm); /* * Move the message from the send queue to the retransmit * list right away. */ list_move_tail(&rm->m_conn_item, &cp->cp_retrans); } spin_unlock_irqrestore(&cp->cp_lock, flags); if (!rm) break; /* Unfortunately, the way Infiniband deals with * RDMA to a bad MR key is by moving the entire * queue pair to error state. We could possibly * recover from that, but right now we drop the * connection. * Therefore, we never retransmit messages with RDMA ops. */ if (test_bit(RDS_MSG_FLUSH, &rm->m_flags) || (rm->rdma.op_active && test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags))) { spin_lock_irqsave(&cp->cp_lock, flags); if (test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) list_move(&rm->m_conn_item, &to_be_dropped); spin_unlock_irqrestore(&cp->cp_lock, flags); continue; } /* Require an ACK every once in a while */ len = ntohl(rm->m_inc.i_hdr.h_len); if (cp->cp_unacked_packets == 0 || cp->cp_unacked_bytes < len) { set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags); cp->cp_unacked_packets = rds_sysctl_max_unacked_packets; cp->cp_unacked_bytes = rds_sysctl_max_unacked_bytes; rds_stats_inc(s_send_ack_required); } else { cp->cp_unacked_bytes -= len; cp->cp_unacked_packets--; } cp->cp_xmit_rm = rm; } /* The transport either sends the whole rdma or none of it */ if (rm->rdma.op_active && !cp->cp_xmit_rdma_sent) { rm->m_final_op = &rm->rdma; /* The transport owns the mapped memory for now. * You can't unmap it while it's on the send queue */ set_bit(RDS_MSG_MAPPED, &rm->m_flags); ret = conn->c_trans->xmit_rdma(conn, &rm->rdma); if (ret) { clear_bit(RDS_MSG_MAPPED, &rm->m_flags); wake_up_interruptible(&rm->m_flush_wait); break; } cp->cp_xmit_rdma_sent = 1; } if (rm->atomic.op_active && !cp->cp_xmit_atomic_sent) { rm->m_final_op = &rm->atomic; /* The transport owns the mapped memory for now. * You can't unmap it while it's on the send queue */ set_bit(RDS_MSG_MAPPED, &rm->m_flags); ret = conn->c_trans->xmit_atomic(conn, &rm->atomic); if (ret) { clear_bit(RDS_MSG_MAPPED, &rm->m_flags); wake_up_interruptible(&rm->m_flush_wait); break; } cp->cp_xmit_atomic_sent = 1; } /* * A number of cases require an RDS header to be sent * even if there is no data. * We permit 0-byte sends; rds-ping depends on this. * However, if there are exclusively attached silent ops, * we skip the hdr/data send, to enable silent operation. */ if (rm->data.op_nents == 0) { int ops_present; int all_ops_are_silent = 1; ops_present = (rm->atomic.op_active || rm->rdma.op_active); if (rm->atomic.op_active && !rm->atomic.op_silent) all_ops_are_silent = 0; if (rm->rdma.op_active && !rm->rdma.op_silent) all_ops_are_silent = 0; if (ops_present && all_ops_are_silent && !rm->m_rdma_cookie) rm->data.op_active = 0; } if (rm->data.op_active && !cp->cp_xmit_data_sent) { rm->m_final_op = &rm->data; ret = conn->c_trans->xmit(conn, rm, cp->cp_xmit_hdr_off, cp->cp_xmit_sg, cp->cp_xmit_data_off); if (ret <= 0) break; if (cp->cp_xmit_hdr_off < sizeof(struct rds_header)) { tmp = min_t(int, ret, sizeof(struct rds_header) - cp->cp_xmit_hdr_off); cp->cp_xmit_hdr_off += tmp; ret -= tmp; } sg = &rm->data.op_sg[cp->cp_xmit_sg]; while (ret) { tmp = min_t(int, ret, sg->length - cp->cp_xmit_data_off); cp->cp_xmit_data_off += tmp; ret -= tmp; if (cp->cp_xmit_data_off == sg->length) { cp->cp_xmit_data_off = 0; sg++; cp->cp_xmit_sg++; BUG_ON(ret != 0 && cp->cp_xmit_sg == rm->data.op_nents); } } if (cp->cp_xmit_hdr_off == sizeof(struct rds_header) && (cp->cp_xmit_sg == rm->data.op_nents)) cp->cp_xmit_data_sent = 1; } /* * A rm will only take multiple times through this loop * if there is a data op. Thus, if the data is sent (or there was * none), then we're done with the rm. */ if (!rm->data.op_active || cp->cp_xmit_data_sent) { cp->cp_xmit_rm = NULL; cp->cp_xmit_sg = 0; cp->cp_xmit_hdr_off = 0; cp->cp_xmit_data_off = 0; cp->cp_xmit_rdma_sent = 0; cp->cp_xmit_atomic_sent = 0; cp->cp_xmit_data_sent = 0; rds_message_put(rm); } } over_batch: if (conn->c_trans->xmit_path_complete) conn->c_trans->xmit_path_complete(cp); release_in_xmit(cp); /* Nuke any messages we decided not to retransmit. */ if (!list_empty(&to_be_dropped)) { /* irqs on here, so we can put(), unlike above */ list_for_each_entry(rm, &to_be_dropped, m_conn_item) rds_message_put(rm); rds_send_remove_from_sock(&to_be_dropped, RDS_RDMA_DROPPED); } /* * Other senders can queue a message after we last test the send queue * but before we clear RDS_IN_XMIT. In that case they'd back off and * not try and send their newly queued message. We need to check the * send queue after having cleared RDS_IN_XMIT so that their message * doesn't get stuck on the send queue. * * If the transport cannot continue (i.e ret != 0), then it must * call us when more room is available, such as from the tx * completion handler. * * We have an extra generation check here so that if someone manages * to jump in after our release_in_xmit, we'll see that they have done * some work and we will skip our goto */ if (ret == 0) { bool raced; smp_mb(); raced = send_gen != READ_ONCE(cp->cp_send_gen); if ((test_bit(0, &conn->c_map_queued) || !list_empty(&cp->cp_send_queue)) && !raced) { if (batch_count < send_batch_count) goto restart; rcu_read_lock(); if (rds_destroy_pending(cp->cp_conn)) ret = -ENETUNREACH; else queue_delayed_work(rds_wq, &cp->cp_send_w, 1); rcu_read_unlock(); } else if (raced) { rds_stats_inc(s_send_lock_queue_raced); } } out: return ret; } EXPORT_SYMBOL_GPL(rds_send_xmit); static void rds_send_sndbuf_remove(struct rds_sock *rs, struct rds_message *rm) { u32 len = be32_to_cpu(rm->m_inc.i_hdr.h_len); assert_spin_locked(&rs->rs_lock); BUG_ON(rs->rs_snd_bytes < len); rs->rs_snd_bytes -= len; if (rs->rs_snd_bytes == 0) rds_stats_inc(s_send_queue_empty); } static inline int rds_send_is_acked(struct rds_message *rm, u64 ack, is_acked_func is_acked) { if (is_acked) return is_acked(rm, ack); return be64_to_cpu(rm->m_inc.i_hdr.h_sequence) <= ack; } /* * This is pretty similar to what happens below in the ACK * handling code - except that we call here as soon as we get * the IB send completion on the RDMA op and the accompanying * message. */ void rds_rdma_send_complete(struct rds_message *rm, int status) { struct rds_sock *rs = NULL; struct rm_rdma_op *ro; struct rds_notifier *notifier; unsigned long flags; spin_lock_irqsave(&rm->m_rs_lock, flags); ro = &rm->rdma; if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) && ro->op_active && ro->op_notify && ro->op_notifier) { notifier = ro->op_notifier; rs = rm->m_rs; sock_hold(rds_rs_to_sk(rs)); notifier->n_status = status; spin_lock(&rs->rs_lock); list_add_tail(¬ifier->n_list, &rs->rs_notify_queue); spin_unlock(&rs->rs_lock); ro->op_notifier = NULL; } spin_unlock_irqrestore(&rm->m_rs_lock, flags); if (rs) { rds_wake_sk_sleep(rs); sock_put(rds_rs_to_sk(rs)); } } EXPORT_SYMBOL_GPL(rds_rdma_send_complete); /* * Just like above, except looks at atomic op */ void rds_atomic_send_complete(struct rds_message *rm, int status) { struct rds_sock *rs = NULL; struct rm_atomic_op *ao; struct rds_notifier *notifier; unsigned long flags; spin_lock_irqsave(&rm->m_rs_lock, flags); ao = &rm->atomic; if (test_bit(RDS_MSG_ON_SOCK, &rm->m_flags) && ao->op_active && ao->op_notify && ao->op_notifier) { notifier = ao->op_notifier; rs = rm->m_rs; sock_hold(rds_rs_to_sk(rs)); notifier->n_status = status; spin_lock(&rs->rs_lock); list_add_tail(¬ifier->n_list, &rs->rs_notify_queue); spin_unlock(&rs->rs_lock); ao->op_notifier = NULL; } spin_unlock_irqrestore(&rm->m_rs_lock, flags); if (rs) { rds_wake_sk_sleep(rs); sock_put(rds_rs_to_sk(rs)); } } EXPORT_SYMBOL_GPL(rds_atomic_send_complete); /* * This is the same as rds_rdma_send_complete except we * don't do any locking - we have all the ingredients (message, * socket, socket lock) and can just move the notifier. */ static inline void __rds_send_complete(struct rds_sock *rs, struct rds_message *rm, int status) { struct rm_rdma_op *ro; struct rm_atomic_op *ao; ro = &rm->rdma; if (ro->op_active && ro->op_notify && ro->op_notifier) { ro->op_notifier->n_status = status; list_add_tail(&ro->op_notifier->n_list, &rs->rs_notify_queue); ro->op_notifier = NULL; } ao = &rm->atomic; if (ao->op_active && ao->op_notify && ao->op_notifier) { ao->op_notifier->n_status = status; list_add_tail(&ao->op_notifier->n_list, &rs->rs_notify_queue); ao->op_notifier = NULL; } /* No need to wake the app - caller does this */ } /* * This removes messages from the socket's list if they're on it. The list * argument must be private to the caller, we must be able to modify it * without locks. The messages must have a reference held for their * position on the list. This function will drop that reference after * removing the messages from the 'messages' list regardless of if it found * the messages on the socket list or not. */ static void rds_send_remove_from_sock(struct list_head *messages, int status) { unsigned long flags; struct rds_sock *rs = NULL; struct rds_message *rm; while (!list_empty(messages)) { int was_on_sock = 0; rm = list_entry(messages->next, struct rds_message, m_conn_item); list_del_init(&rm->m_conn_item); /* * If we see this flag cleared then we're *sure* that someone * else beat us to removing it from the sock. If we race * with their flag update we'll get the lock and then really * see that the flag has been cleared. * * The message spinlock makes sure nobody clears rm->m_rs * while we're messing with it. It does not prevent the * message from being removed from the socket, though. */ spin_lock_irqsave(&rm->m_rs_lock, flags); if (!test_bit(RDS_MSG_ON_SOCK, &rm->m_flags)) goto unlock_and_drop; if (rs != rm->m_rs) { if (rs) { rds_wake_sk_sleep(rs); sock_put(rds_rs_to_sk(rs)); } rs = rm->m_rs; if (rs) sock_hold(rds_rs_to_sk(rs)); } if (!rs) goto unlock_and_drop; spin_lock(&rs->rs_lock); if (test_and_clear_bit(RDS_MSG_ON_SOCK, &rm->m_flags)) { struct rm_rdma_op *ro = &rm->rdma; struct rds_notifier *notifier; list_del_init(&rm->m_sock_item); rds_send_sndbuf_remove(rs, rm); if (ro->op_active && ro->op_notifier && (ro->op_notify || (ro->op_recverr && status))) { notifier = ro->op_notifier; list_add_tail(¬ifier->n_list, &rs->rs_notify_queue); if (!notifier->n_status) notifier->n_status = status; rm->rdma.op_notifier = NULL; } was_on_sock = 1; } spin_unlock(&rs->rs_lock); unlock_and_drop: spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); if (was_on_sock) rds_message_put(rm); } if (rs) { rds_wake_sk_sleep(rs); sock_put(rds_rs_to_sk(rs)); } } /* * Transports call here when they've determined that the receiver queued * messages up to, and including, the given sequence number. Messages are * moved to the retrans queue when rds_send_xmit picks them off the send * queue. This means that in the TCP case, the message may not have been * assigned the m_ack_seq yet - but that's fine as long as tcp_is_acked * checks the RDS_MSG_HAS_ACK_SEQ bit. */ void rds_send_path_drop_acked(struct rds_conn_path *cp, u64 ack, is_acked_func is_acked) { struct rds_message *rm, *tmp; unsigned long flags; LIST_HEAD(list); spin_lock_irqsave(&cp->cp_lock, flags); list_for_each_entry_safe(rm, tmp, &cp->cp_retrans, m_conn_item) { if (!rds_send_is_acked(rm, ack, is_acked)) break; list_move(&rm->m_conn_item, &list); clear_bit(RDS_MSG_ON_CONN, &rm->m_flags); } /* order flag updates with spin locks */ if (!list_empty(&list)) smp_mb__after_atomic(); spin_unlock_irqrestore(&cp->cp_lock, flags); /* now remove the messages from the sock list as needed */ rds_send_remove_from_sock(&list, RDS_RDMA_SUCCESS); } EXPORT_SYMBOL_GPL(rds_send_path_drop_acked); void rds_send_drop_acked(struct rds_connection *conn, u64 ack, is_acked_func is_acked) { WARN_ON(conn->c_trans->t_mp_capable); rds_send_path_drop_acked(&conn->c_path[0], ack, is_acked); } EXPORT_SYMBOL_GPL(rds_send_drop_acked); void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in6 *dest) { struct rds_message *rm, *tmp; struct rds_connection *conn; struct rds_conn_path *cp; unsigned long flags; LIST_HEAD(list); /* get all the messages we're dropping under the rs lock */ spin_lock_irqsave(&rs->rs_lock, flags); list_for_each_entry_safe(rm, tmp, &rs->rs_send_queue, m_sock_item) { if (dest && (!ipv6_addr_equal(&dest->sin6_addr, &rm->m_daddr) || dest->sin6_port != rm->m_inc.i_hdr.h_dport)) continue; list_move(&rm->m_sock_item, &list); rds_send_sndbuf_remove(rs, rm); clear_bit(RDS_MSG_ON_SOCK, &rm->m_flags); } /* order flag updates with the rs lock */ smp_mb__after_atomic(); spin_unlock_irqrestore(&rs->rs_lock, flags); if (list_empty(&list)) return; /* Remove the messages from the conn */ list_for_each_entry(rm, &list, m_sock_item) { conn = rm->m_inc.i_conn; if (conn->c_trans->t_mp_capable) cp = rm->m_inc.i_conn_path; else cp = &conn->c_path[0]; spin_lock_irqsave(&cp->cp_lock, flags); /* * Maybe someone else beat us to removing rm from the conn. * If we race with their flag update we'll get the lock and * then really see that the flag has been cleared. */ if (!test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags)) { spin_unlock_irqrestore(&cp->cp_lock, flags); continue; } list_del_init(&rm->m_conn_item); spin_unlock_irqrestore(&cp->cp_lock, flags); /* * Couldn't grab m_rs_lock in top loop (lock ordering), * but we can now. */ spin_lock_irqsave(&rm->m_rs_lock, flags); spin_lock(&rs->rs_lock); __rds_send_complete(rs, rm, RDS_RDMA_CANCELED); spin_unlock(&rs->rs_lock); spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); } rds_wake_sk_sleep(rs); while (!list_empty(&list)) { rm = list_entry(list.next, struct rds_message, m_sock_item); list_del_init(&rm->m_sock_item); rds_message_wait(rm); /* just in case the code above skipped this message * because RDS_MSG_ON_CONN wasn't set, run it again here * taking m_rs_lock is the only thing that keeps us * from racing with ack processing. */ spin_lock_irqsave(&rm->m_rs_lock, flags); spin_lock(&rs->rs_lock); __rds_send_complete(rs, rm, RDS_RDMA_CANCELED); spin_unlock(&rs->rs_lock); spin_unlock_irqrestore(&rm->m_rs_lock, flags); rds_message_put(rm); } } /* * we only want this to fire once so we use the callers 'queued'. It's * possible that another thread can race with us and remove the * message from the flow with RDS_CANCEL_SENT_TO. */ static int rds_send_queue_rm(struct rds_sock *rs, struct rds_connection *conn, struct rds_conn_path *cp, struct rds_message *rm, __be16 sport, __be16 dport, int *queued) { unsigned long flags; u32 len; if (*queued) goto out; len = be32_to_cpu(rm->m_inc.i_hdr.h_len); /* this is the only place which holds both the socket's rs_lock * and the connection's c_lock */ spin_lock_irqsave(&rs->rs_lock, flags); /* * If there is a little space in sndbuf, we don't queue anything, * and userspace gets -EAGAIN. But poll() indicates there's send * room. This can lead to bad behavior (spinning) if snd_bytes isn't * freed up by incoming acks. So we check the *old* value of * rs_snd_bytes here to allow the last msg to exceed the buffer, * and poll() now knows no more data can be sent. */ if (rs->rs_snd_bytes < rds_sk_sndbuf(rs)) { rs->rs_snd_bytes += len; /* let recv side know we are close to send space exhaustion. * This is probably not the optimal way to do it, as this * means we set the flag on *all* messages as soon as our * throughput hits a certain threshold. */ if (rs->rs_snd_bytes >= rds_sk_sndbuf(rs) / 2) set_bit(RDS_MSG_ACK_REQUIRED, &rm->m_flags); list_add_tail(&rm->m_sock_item, &rs->rs_send_queue); set_bit(RDS_MSG_ON_SOCK, &rm->m_flags); rds_message_addref(rm); sock_hold(rds_rs_to_sk(rs)); rm->m_rs = rs; /* The code ordering is a little weird, but we're trying to minimize the time we hold c_lock */ rds_message_populate_header(&rm->m_inc.i_hdr, sport, dport, 0); rm->m_inc.i_conn = conn; rm->m_inc.i_conn_path = cp; rds_message_addref(rm); spin_lock(&cp->cp_lock); rm->m_inc.i_hdr.h_sequence = cpu_to_be64(cp->cp_next_tx_seq++); list_add_tail(&rm->m_conn_item, &cp->cp_send_queue); set_bit(RDS_MSG_ON_CONN, &rm->m_flags); spin_unlock(&cp->cp_lock); rdsdebug("queued msg %p len %d, rs %p bytes %d seq %llu\n", rm, len, rs, rs->rs_snd_bytes, (unsigned long long)be64_to_cpu(rm->m_inc.i_hdr.h_sequence)); *queued = 1; } spin_unlock_irqrestore(&rs->rs_lock, flags); out: return *queued; } /* * rds_message is getting to be quite complicated, and we'd like to allocate * it all in one go. This figures out how big it needs to be up front. */ static int rds_rm_size(struct msghdr *msg, int num_sgs, struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; int size = 0; int cmsg_groups = 0; int retval; bool zcopy_cookie = false; struct rds_iov_vector *iov, *tmp_iov; if (num_sgs < 0) return -EINVAL; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_RDS) continue; switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: if (vct->indx >= vct->len) { vct->len += vct->incr; tmp_iov = krealloc(vct->vec, vct->len * sizeof(struct rds_iov_vector), GFP_KERNEL); if (!tmp_iov) { vct->len -= vct->incr; return -ENOMEM; } vct->vec = tmp_iov; } iov = &vct->vec[vct->indx]; memset(iov, 0, sizeof(struct rds_iov_vector)); vct->indx++; cmsg_groups |= 1; retval = rds_rdma_extra_size(CMSG_DATA(cmsg), iov); if (retval < 0) return retval; size += retval; break; case RDS_CMSG_ZCOPY_COOKIE: zcopy_cookie = true; fallthrough; case RDS_CMSG_RDMA_DEST: case RDS_CMSG_RDMA_MAP: cmsg_groups |= 2; /* these are valid but do no add any size */ break; case RDS_CMSG_ATOMIC_CSWP: case RDS_CMSG_ATOMIC_FADD: case RDS_CMSG_MASKED_ATOMIC_CSWP: case RDS_CMSG_MASKED_ATOMIC_FADD: cmsg_groups |= 1; size += sizeof(struct scatterlist); break; default: return -EINVAL; } } if ((msg->msg_flags & MSG_ZEROCOPY) && !zcopy_cookie) return -EINVAL; size += num_sgs * sizeof(struct scatterlist); /* Ensure (DEST, MAP) are never used with (ARGS, ATOMIC) */ if (cmsg_groups == 3) return -EINVAL; return size; } static int rds_cmsg_zcopy(struct rds_sock *rs, struct rds_message *rm, struct cmsghdr *cmsg) { u32 *cookie; if (cmsg->cmsg_len < CMSG_LEN(sizeof(*cookie)) || !rm->data.op_mmp_znotifier) return -EINVAL; cookie = CMSG_DATA(cmsg); rm->data.op_mmp_znotifier->z_cookie = *cookie; return 0; } static int rds_cmsg_send(struct rds_sock *rs, struct rds_message *rm, struct msghdr *msg, int *allocated_mr, struct rds_iov_vector_arr *vct) { struct cmsghdr *cmsg; int ret = 0, ind = 0; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_RDS) continue; /* As a side effect, RDMA_DEST and RDMA_MAP will set * rm->rdma.m_rdma_cookie and rm->rdma.m_rdma_mr. */ switch (cmsg->cmsg_type) { case RDS_CMSG_RDMA_ARGS: if (ind >= vct->indx) return -ENOMEM; ret = rds_cmsg_rdma_args(rs, rm, cmsg, &vct->vec[ind]); ind++; break; case RDS_CMSG_RDMA_DEST: ret = rds_cmsg_rdma_dest(rs, rm, cmsg); break; case RDS_CMSG_RDMA_MAP: ret = rds_cmsg_rdma_map(rs, rm, cmsg); if (!ret) *allocated_mr = 1; else if (ret == -ENODEV) /* Accommodate the get_mr() case which can fail * if connection isn't established yet. */ ret = -EAGAIN; break; case RDS_CMSG_ATOMIC_CSWP: case RDS_CMSG_ATOMIC_FADD: case RDS_CMSG_MASKED_ATOMIC_CSWP: case RDS_CMSG_MASKED_ATOMIC_FADD: ret = rds_cmsg_atomic(rs, rm, cmsg); break; case RDS_CMSG_ZCOPY_COOKIE: ret = rds_cmsg_zcopy(rs, rm, cmsg); break; default: return -EINVAL; } if (ret) break; } return ret; } static int rds_send_mprds_hash(struct rds_sock *rs, struct rds_connection *conn, int nonblock) { int hash; if (conn->c_npaths == 0) hash = RDS_MPATH_HASH(rs, RDS_MPATH_WORKERS); else hash = RDS_MPATH_HASH(rs, conn->c_npaths); if (conn->c_npaths == 0 && hash != 0) { rds_send_ping(conn, 0); /* The underlying connection is not up yet. Need to wait * until it is up to be sure that the non-zero c_path can be * used. But if we are interrupted, we have to use the zero * c_path in case the connection ends up being non-MP capable. */ if (conn->c_npaths == 0) { /* Cannot wait for the connection be made, so just use * the base c_path. */ if (nonblock) return 0; if (wait_event_interruptible(conn->c_hs_waitq, conn->c_npaths != 0)) hash = 0; } if (conn->c_npaths == 1) hash = 0; } return hash; } static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes) { struct rds_rdma_args *args; struct cmsghdr *cmsg; for_each_cmsghdr(cmsg, msg) { if (!CMSG_OK(msg, cmsg)) return -EINVAL; if (cmsg->cmsg_level != SOL_RDS) continue; if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) { if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args))) return -EINVAL; args = CMSG_DATA(cmsg); *rdma_bytes += args->remote_vec.bytes; } } return 0; } int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); __be16 dport; struct rds_message *rm = NULL; struct rds_connection *conn; int ret = 0; int queued = 0, allocated_mr = 0; int nonblock = msg->msg_flags & MSG_DONTWAIT; long timeo = sock_sndtimeo(sk, nonblock); struct rds_conn_path *cpath; struct in6_addr daddr; __u32 scope_id = 0; size_t rdma_payload_len = 0; bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) && sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY)); int num_sgs = DIV_ROUND_UP(payload_len, PAGE_SIZE); int namelen; struct rds_iov_vector_arr vct; int ind; memset(&vct, 0, sizeof(vct)); /* expect 1 RDMA CMSG per rds_sendmsg. can still grow if more needed. */ vct.incr = 1; /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_CMSG_COMPAT | MSG_ZEROCOPY)) { ret = -EOPNOTSUPP; goto out; } namelen = msg->msg_namelen; if (namelen != 0) { if (namelen < sizeof(*usin)) { ret = -EINVAL; goto out; } switch (usin->sin_family) { case AF_INET: if (usin->sin_addr.s_addr == htonl(INADDR_ANY) || usin->sin_addr.s_addr == htonl(INADDR_BROADCAST) || ipv4_is_multicast(usin->sin_addr.s_addr)) { ret = -EINVAL; goto out; } ipv6_addr_set_v4mapped(usin->sin_addr.s_addr, &daddr); dport = usin->sin_port; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { int addr_type; if (namelen < sizeof(*sin6)) { ret = -EINVAL; goto out; } addr_type = ipv6_addr_type(&sin6->sin6_addr); if (!(addr_type & IPV6_ADDR_UNICAST)) { __be32 addr4; if (!(addr_type & IPV6_ADDR_MAPPED)) { ret = -EINVAL; goto out; } /* It is a mapped address. Need to do some * sanity checks. */ addr4 = sin6->sin6_addr.s6_addr32[3]; if (addr4 == htonl(INADDR_ANY) || addr4 == htonl(INADDR_BROADCAST) || ipv4_is_multicast(addr4)) { ret = -EINVAL; goto out; } } if (addr_type & IPV6_ADDR_LINKLOCAL) { if (sin6->sin6_scope_id == 0) { ret = -EINVAL; goto out; } scope_id = sin6->sin6_scope_id; } daddr = sin6->sin6_addr; dport = sin6->sin6_port; break; } #endif default: ret = -EINVAL; goto out; } } else { /* We only care about consistency with ->connect() */ lock_sock(sk); daddr = rs->rs_conn_addr; dport = rs->rs_conn_port; scope_id = rs->rs_bound_scope_id; release_sock(sk); } lock_sock(sk); if (ipv6_addr_any(&rs->rs_bound_addr) || ipv6_addr_any(&daddr)) { release_sock(sk); ret = -ENOTCONN; goto out; } else if (namelen != 0) { /* Cannot send to an IPv4 address using an IPv6 source * address and cannot send to an IPv6 address using an * IPv4 source address. */ if (ipv6_addr_v4mapped(&daddr) ^ ipv6_addr_v4mapped(&rs->rs_bound_addr)) { release_sock(sk); ret = -EOPNOTSUPP; goto out; } /* If the socket is already bound to a link local address, * it can only send to peers on the same link. But allow * communicating between link local and non-link local address. */ if (scope_id != rs->rs_bound_scope_id) { if (!scope_id) { scope_id = rs->rs_bound_scope_id; } else if (rs->rs_bound_scope_id) { release_sock(sk); ret = -EINVAL; goto out; } } } release_sock(sk); ret = rds_rdma_bytes(msg, &rdma_payload_len); if (ret) goto out; if (max_t(size_t, payload_len, rdma_payload_len) > RDS_MAX_MSG_SIZE) { ret = -EMSGSIZE; goto out; } if (payload_len > rds_sk_sndbuf(rs)) { ret = -EMSGSIZE; goto out; } if (zcopy) { if (rs->rs_transport->t_type != RDS_TRANS_TCP) { ret = -EOPNOTSUPP; goto out; } num_sgs = iov_iter_npages(&msg->msg_iter, INT_MAX); } /* size of rm including all sgs */ ret = rds_rm_size(msg, num_sgs, &vct); if (ret < 0) goto out; rm = rds_message_alloc(ret, GFP_KERNEL); if (!rm) { ret = -ENOMEM; goto out; } /* Attach data to the rm */ if (payload_len) { rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); if (IS_ERR(rm->data.op_sg)) { ret = PTR_ERR(rm->data.op_sg); goto out; } ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy); if (ret) goto out; } rm->data.op_active = 1; rm->m_daddr = daddr; /* rds_conn_create has a spinlock that runs with IRQ off. * Caching the conn in the socket helps a lot. */ if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr) && rs->rs_tos == rs->rs_conn->c_tos) { conn = rs->rs_conn; } else { conn = rds_conn_create_outgoing(sock_net(sock->sk), &rs->rs_bound_addr, &daddr, rs->rs_transport, rs->rs_tos, sock->sk->sk_allocation, scope_id); if (IS_ERR(conn)) { ret = PTR_ERR(conn); goto out; } rs->rs_conn = conn; } if (conn->c_trans->t_mp_capable) cpath = &conn->c_path[rds_send_mprds_hash(rs, conn, nonblock)]; else cpath = &conn->c_path[0]; rm->m_conn_path = cpath; /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); if (ret) goto out; if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) { printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", &rm->rdma, conn->c_trans->xmit_rdma); ret = -EOPNOTSUPP; goto out; } if (rm->atomic.op_active && !conn->c_trans->xmit_atomic) { printk_ratelimited(KERN_NOTICE "atomic_op %p conn xmit_atomic %p\n", &rm->atomic, conn->c_trans->xmit_atomic); ret = -EOPNOTSUPP; goto out; } if (rds_destroy_pending(conn)) { ret = -EAGAIN; goto out; } if (rds_conn_path_down(cpath)) rds_check_all_paths(conn); ret = rds_cong_wait(conn->c_fcong, dport, nonblock, rs); if (ret) { rs->rs_seen_congestion = 1; goto out; } while (!rds_send_queue_rm(rs, conn, cpath, rm, rs->rs_bound_port, dport, &queued)) { rds_stats_inc(s_send_queue_full); if (nonblock) { ret = -EAGAIN; goto out; } timeo = wait_event_interruptible_timeout(*sk_sleep(sk), rds_send_queue_rm(rs, conn, cpath, rm, rs->rs_bound_port, dport, &queued), timeo); rdsdebug("sendmsg woke queued %d timeo %ld\n", queued, timeo); if (timeo > 0 || timeo == MAX_SCHEDULE_TIMEOUT) continue; ret = timeo; if (ret == 0) ret = -ETIMEDOUT; goto out; } /* * By now we've committed to the send. We reuse rds_send_worker() * to retry sends in the rds thread if the transport asks us to. */ rds_stats_inc(s_send_queued); ret = rds_send_xmit(cpath); if (ret == -ENOMEM || ret == -EAGAIN) { ret = 0; rcu_read_lock(); if (rds_destroy_pending(cpath->cp_conn)) ret = -ENETUNREACH; else queue_delayed_work(rds_wq, &cpath->cp_send_w, 1); rcu_read_unlock(); } if (ret) goto out; rds_message_put(rm); for (ind = 0; ind < vct.indx; ind++) kfree(vct.vec[ind].iov); kfree(vct.vec); return payload_len; out: for (ind = 0; ind < vct.indx; ind++) kfree(vct.vec[ind].iov); kfree(vct.vec); /* If the user included a RDMA_MAP cmsg, we allocated a MR on the fly. * If the sendmsg goes through, we keep the MR. If it fails with EAGAIN * or in any other way, we need to destroy the MR again */ if (allocated_mr) rds_rdma_unuse(rs, rds_rdma_cookie_key(rm->m_rdma_cookie), 1); if (rm) rds_message_put(rm); return ret; } /* * send out a probe. Can be shared by rds_send_ping, * rds_send_pong, rds_send_hb. * rds_send_hb should use h_flags * RDS_FLAG_HB_PING|RDS_FLAG_ACK_REQUIRED * or * RDS_FLAG_HB_PONG|RDS_FLAG_ACK_REQUIRED */ static int rds_send_probe(struct rds_conn_path *cp, __be16 sport, __be16 dport, u8 h_flags) { struct rds_message *rm; unsigned long flags; int ret = 0; rm = rds_message_alloc(0, GFP_ATOMIC); if (!rm) { ret = -ENOMEM; goto out; } rm->m_daddr = cp->cp_conn->c_faddr; rm->data.op_active = 1; rds_conn_path_connect_if_down(cp); ret = rds_cong_wait(cp->cp_conn->c_fcong, dport, 1, NULL); if (ret) goto out; spin_lock_irqsave(&cp->cp_lock, flags); list_add_tail(&rm->m_conn_item, &cp->cp_send_queue); set_bit(RDS_MSG_ON_CONN, &rm->m_flags); rds_message_addref(rm); rm->m_inc.i_conn = cp->cp_conn; rm->m_inc.i_conn_path = cp; rds_message_populate_header(&rm->m_inc.i_hdr, sport, dport, cp->cp_next_tx_seq); rm->m_inc.i_hdr.h_flags |= h_flags; cp->cp_next_tx_seq++; if (RDS_HS_PROBE(be16_to_cpu(sport), be16_to_cpu(dport)) && cp->cp_conn->c_trans->t_mp_capable) { u16 npaths = cpu_to_be16(RDS_MPATH_WORKERS); u32 my_gen_num = cpu_to_be32(cp->cp_conn->c_my_gen_num); rds_message_add_extension(&rm->m_inc.i_hdr, RDS_EXTHDR_NPATHS, &npaths, sizeof(npaths)); rds_message_add_extension(&rm->m_inc.i_hdr, RDS_EXTHDR_GEN_NUM, &my_gen_num, sizeof(u32)); } spin_unlock_irqrestore(&cp->cp_lock, flags); rds_stats_inc(s_send_queued); rds_stats_inc(s_send_pong); /* schedule the send work on rds_wq */ rcu_read_lock(); if (!rds_destroy_pending(cp->cp_conn)) queue_delayed_work(rds_wq, &cp->cp_send_w, 1); rcu_read_unlock(); rds_message_put(rm); return 0; out: if (rm) rds_message_put(rm); return ret; } int rds_send_pong(struct rds_conn_path *cp, __be16 dport) { return rds_send_probe(cp, 0, dport, 0); } void rds_send_ping(struct rds_connection *conn, int cp_index) { unsigned long flags; struct rds_conn_path *cp = &conn->c_path[cp_index]; spin_lock_irqsave(&cp->cp_lock, flags); if (conn->c_ping_triggered) { spin_unlock_irqrestore(&cp->cp_lock, flags); return; } conn->c_ping_triggered = 1; spin_unlock_irqrestore(&cp->cp_lock, flags); rds_send_probe(cp, cpu_to_be16(RDS_FLAG_PROBE_PORT), 0, 0); } EXPORT_SYMBOL_GPL(rds_send_ping); |
| 5 1 5 4 3 2 2 6 12 6 14 1 13 12 3 8 1 1 5 5 3 5 1 3 2 3 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * ebt_among * * Authors: * Grzegorz Borowiak <grzes@gnu.univ.gda.pl> * * August, 2003 * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ip.h> #include <linux/if_arp.h> #include <linux/module.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_bridge/ebt_among.h> static bool ebt_mac_wormhash_contains(const struct ebt_mac_wormhash *wh, const char *mac, __be32 ip) { /* You may be puzzled as to how this code works. * Some tricks were used, refer to * include/linux/netfilter_bridge/ebt_among.h * as there you can find a solution of this mystery. */ const struct ebt_mac_wormhash_tuple *p; int start, limit, i; uint32_t cmp[2] = { 0, 0 }; int key = ((const unsigned char *)mac)[5]; ether_addr_copy(((char *) cmp) + 2, mac); start = wh->table[key]; limit = wh->table[key + 1]; if (ip) { for (i = start; i < limit; i++) { p = &wh->pool[i]; if (cmp[1] == p->cmp[1] && cmp[0] == p->cmp[0]) if (p->ip == 0 || p->ip == ip) return true; } } else { for (i = start; i < limit; i++) { p = &wh->pool[i]; if (cmp[1] == p->cmp[1] && cmp[0] == p->cmp[0]) if (p->ip == 0) return true; } } return false; } static int ebt_mac_wormhash_check_integrity(const struct ebt_mac_wormhash *wh) { int i; for (i = 0; i < 256; i++) { if (wh->table[i] > wh->table[i + 1]) return -0x100 - i; if (wh->table[i] < 0) return -0x200 - i; if (wh->table[i] > wh->poolsize) return -0x300 - i; } if (wh->table[256] > wh->poolsize) return -0xc00; return 0; } static int get_ip_dst(const struct sk_buff *skb, __be32 *addr) { if (eth_hdr(skb)->h_proto == htons(ETH_P_IP)) { const struct iphdr *ih; struct iphdr _iph; ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph); if (ih == NULL) return -1; *addr = ih->daddr; } else if (eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) { const struct arphdr *ah; struct arphdr _arph; const __be32 *bp; __be32 buf; ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); if (ah == NULL || ah->ar_pln != sizeof(__be32) || ah->ar_hln != ETH_ALEN) return -1; bp = skb_header_pointer(skb, sizeof(struct arphdr) + 2 * ETH_ALEN + sizeof(__be32), sizeof(__be32), &buf); if (bp == NULL) return -1; *addr = *bp; } return 0; } static int get_ip_src(const struct sk_buff *skb, __be32 *addr) { if (eth_hdr(skb)->h_proto == htons(ETH_P_IP)) { const struct iphdr *ih; struct iphdr _iph; ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph); if (ih == NULL) return -1; *addr = ih->saddr; } else if (eth_hdr(skb)->h_proto == htons(ETH_P_ARP)) { const struct arphdr *ah; struct arphdr _arph; const __be32 *bp; __be32 buf; ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); if (ah == NULL || ah->ar_pln != sizeof(__be32) || ah->ar_hln != ETH_ALEN) return -1; bp = skb_header_pointer(skb, sizeof(struct arphdr) + ETH_ALEN, sizeof(__be32), &buf); if (bp == NULL) return -1; *addr = *bp; } return 0; } static bool ebt_among_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct ebt_among_info *info = par->matchinfo; const char *dmac, *smac; const struct ebt_mac_wormhash *wh_dst, *wh_src; __be32 dip = 0, sip = 0; wh_dst = ebt_among_wh_dst(info); wh_src = ebt_among_wh_src(info); if (wh_src) { smac = eth_hdr(skb)->h_source; if (get_ip_src(skb, &sip)) return false; if (!(info->bitmask & EBT_AMONG_SRC_NEG)) { /* we match only if it contains */ if (!ebt_mac_wormhash_contains(wh_src, smac, sip)) return false; } else { /* we match only if it DOES NOT contain */ if (ebt_mac_wormhash_contains(wh_src, smac, sip)) return false; } } if (wh_dst) { dmac = eth_hdr(skb)->h_dest; if (get_ip_dst(skb, &dip)) return false; if (!(info->bitmask & EBT_AMONG_DST_NEG)) { /* we match only if it contains */ if (!ebt_mac_wormhash_contains(wh_dst, dmac, dip)) return false; } else { /* we match only if it DOES NOT contain */ if (ebt_mac_wormhash_contains(wh_dst, dmac, dip)) return false; } } return true; } static bool poolsize_invalid(const struct ebt_mac_wormhash *w) { return w && w->poolsize >= (INT_MAX / sizeof(struct ebt_mac_wormhash_tuple)); } static bool wormhash_offset_invalid(int off, unsigned int len) { if (off == 0) /* not present */ return false; if (off < (int)sizeof(struct ebt_among_info) || off % __alignof__(struct ebt_mac_wormhash)) return true; off += sizeof(struct ebt_mac_wormhash); return off > len; } static bool wormhash_sizes_valid(const struct ebt_mac_wormhash *wh, int a, int b) { if (a == 0) a = sizeof(struct ebt_among_info); return ebt_mac_wormhash_size(wh) + a == b; } static int ebt_among_mt_check(const struct xt_mtchk_param *par) { const struct ebt_among_info *info = par->matchinfo; const struct ebt_entry_match *em = container_of(par->matchinfo, const struct ebt_entry_match, data); unsigned int expected_length = sizeof(struct ebt_among_info); const struct ebt_mac_wormhash *wh_dst, *wh_src; int err; if (expected_length > em->match_size) return -EINVAL; if (wormhash_offset_invalid(info->wh_dst_ofs, em->match_size) || wormhash_offset_invalid(info->wh_src_ofs, em->match_size)) return -EINVAL; wh_dst = ebt_among_wh_dst(info); if (poolsize_invalid(wh_dst)) return -EINVAL; expected_length += ebt_mac_wormhash_size(wh_dst); if (expected_length > em->match_size) return -EINVAL; wh_src = ebt_among_wh_src(info); if (poolsize_invalid(wh_src)) return -EINVAL; if (info->wh_src_ofs < info->wh_dst_ofs) { if (!wormhash_sizes_valid(wh_src, info->wh_src_ofs, info->wh_dst_ofs)) return -EINVAL; } else { if (!wormhash_sizes_valid(wh_dst, info->wh_dst_ofs, info->wh_src_ofs)) return -EINVAL; } expected_length += ebt_mac_wormhash_size(wh_src); if (em->match_size != EBT_ALIGN(expected_length)) { pr_err_ratelimited("wrong size: %d against expected %d, rounded to %zd\n", em->match_size, expected_length, EBT_ALIGN(expected_length)); return -EINVAL; } if (wh_dst && (err = ebt_mac_wormhash_check_integrity(wh_dst))) { pr_err_ratelimited("dst integrity fail: %x\n", -err); return -EINVAL; } if (wh_src && (err = ebt_mac_wormhash_check_integrity(wh_src))) { pr_err_ratelimited("src integrity fail: %x\n", -err); return -EINVAL; } return 0; } static struct xt_match ebt_among_mt_reg __read_mostly = { .name = "among", .revision = 0, .family = NFPROTO_BRIDGE, .match = ebt_among_mt, .checkentry = ebt_among_mt_check, .matchsize = -1, /* special case */ .me = THIS_MODULE, }; static int __init ebt_among_init(void) { return xt_register_match(&ebt_among_mt_reg); } static void __exit ebt_among_fini(void) { xt_unregister_match(&ebt_among_mt_reg); } module_init(ebt_among_init); module_exit(ebt_among_fini); MODULE_DESCRIPTION("Ebtables: Combined MAC/IP address list matching"); MODULE_LICENSE("GPL"); |
| 5 2 3 6 6 1 5 5 6 2 2 1 3 3 3 | 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C)2006 USAGI/WIDE Project * * Author: * Kazunori Miyazawa <miyazawa@linux-ipv6.org> */ #include <crypto/internal/cipher.h> #include <crypto/internal/hash.h> #include <linux/err.h> #include <linux/kernel.h> #include <linux/module.h> static u_int32_t ks[12] = {0x01010101, 0x01010101, 0x01010101, 0x01010101, 0x02020202, 0x02020202, 0x02020202, 0x02020202, 0x03030303, 0x03030303, 0x03030303, 0x03030303}; /* * +------------------------ * | <parent tfm> * +------------------------ * | xcbc_tfm_ctx * +------------------------ * | consts (block size * 2) * +------------------------ */ struct xcbc_tfm_ctx { struct crypto_cipher *child; u8 consts[]; }; /* * +------------------------ * | <shash desc> * +------------------------ * | xcbc_desc_ctx * +------------------------ * | odds (block size) * +------------------------ * | prev (block size) * +------------------------ */ struct xcbc_desc_ctx { unsigned int len; u8 odds[]; }; #define XCBC_BLOCKSIZE 16 static int crypto_xcbc_digest_setkey(struct crypto_shash *parent, const u8 *inkey, unsigned int keylen) { struct xcbc_tfm_ctx *ctx = crypto_shash_ctx(parent); u8 *consts = ctx->consts; int err = 0; u8 key1[XCBC_BLOCKSIZE]; int bs = sizeof(key1); if ((err = crypto_cipher_setkey(ctx->child, inkey, keylen))) return err; crypto_cipher_encrypt_one(ctx->child, consts, (u8 *)ks + bs); crypto_cipher_encrypt_one(ctx->child, consts + bs, (u8 *)ks + bs * 2); crypto_cipher_encrypt_one(ctx->child, key1, (u8 *)ks); return crypto_cipher_setkey(ctx->child, key1, bs); } static int crypto_xcbc_digest_init(struct shash_desc *pdesc) { struct xcbc_desc_ctx *ctx = shash_desc_ctx(pdesc); int bs = crypto_shash_blocksize(pdesc->tfm); u8 *prev = &ctx->odds[bs]; ctx->len = 0; memset(prev, 0, bs); return 0; } static int crypto_xcbc_digest_update(struct shash_desc *pdesc, const u8 *p, unsigned int len) { struct crypto_shash *parent = pdesc->tfm; struct xcbc_tfm_ctx *tctx = crypto_shash_ctx(parent); struct xcbc_desc_ctx *ctx = shash_desc_ctx(pdesc); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_blocksize(parent); u8 *odds = ctx->odds; u8 *prev = odds + bs; /* checking the data can fill the block */ if ((ctx->len + len) <= bs) { memcpy(odds + ctx->len, p, len); ctx->len += len; return 0; } /* filling odds with new data and encrypting it */ memcpy(odds + ctx->len, p, bs - ctx->len); len -= bs - ctx->len; p += bs - ctx->len; crypto_xor(prev, odds, bs); crypto_cipher_encrypt_one(tfm, prev, prev); /* clearing the length */ ctx->len = 0; /* encrypting the rest of data */ while (len > bs) { crypto_xor(prev, p, bs); crypto_cipher_encrypt_one(tfm, prev, prev); p += bs; len -= bs; } /* keeping the surplus of blocksize */ if (len) { memcpy(odds, p, len); ctx->len = len; } return 0; } static int crypto_xcbc_digest_final(struct shash_desc *pdesc, u8 *out) { struct crypto_shash *parent = pdesc->tfm; struct xcbc_tfm_ctx *tctx = crypto_shash_ctx(parent); struct xcbc_desc_ctx *ctx = shash_desc_ctx(pdesc); struct crypto_cipher *tfm = tctx->child; int bs = crypto_shash_blocksize(parent); u8 *odds = ctx->odds; u8 *prev = odds + bs; unsigned int offset = 0; if (ctx->len != bs) { unsigned int rlen; u8 *p = odds + ctx->len; *p = 0x80; p++; rlen = bs - ctx->len -1; if (rlen) memset(p, 0, rlen); offset += bs; } crypto_xor(prev, odds, bs); crypto_xor(prev, &tctx->consts[offset], bs); crypto_cipher_encrypt_one(tfm, out, prev); return 0; } static int xcbc_init_tfm(struct crypto_tfm *tfm) { struct crypto_cipher *cipher; struct crypto_instance *inst = (void *)tfm->__crt_alg; struct crypto_cipher_spawn *spawn = crypto_instance_ctx(inst); struct xcbc_tfm_ctx *ctx = crypto_tfm_ctx(tfm); cipher = crypto_spawn_cipher(spawn); if (IS_ERR(cipher)) return PTR_ERR(cipher); ctx->child = cipher; return 0; }; static void xcbc_exit_tfm(struct crypto_tfm *tfm) { struct xcbc_tfm_ctx *ctx = crypto_tfm_ctx(tfm); crypto_free_cipher(ctx->child); } static int xcbc_create(struct crypto_template *tmpl, struct rtattr **tb) { struct shash_instance *inst; struct crypto_cipher_spawn *spawn; struct crypto_alg *alg; u32 mask; int err; err = crypto_check_attr_type(tb, CRYPTO_ALG_TYPE_SHASH, &mask); if (err) return err; inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL); if (!inst) return -ENOMEM; spawn = shash_instance_ctx(inst); err = crypto_grab_cipher(spawn, shash_crypto_instance(inst), crypto_attr_alg_name(tb[1]), 0, mask); if (err) goto err_free_inst; alg = crypto_spawn_cipher_alg(spawn); err = -EINVAL; if (alg->cra_blocksize != XCBC_BLOCKSIZE) goto err_free_inst; err = crypto_inst_setname(shash_crypto_instance(inst), tmpl->name, alg); if (err) goto err_free_inst; inst->alg.base.cra_priority = alg->cra_priority; inst->alg.base.cra_blocksize = alg->cra_blocksize; inst->alg.base.cra_ctxsize = sizeof(struct xcbc_tfm_ctx) + alg->cra_blocksize * 2; inst->alg.digestsize = alg->cra_blocksize; inst->alg.descsize = sizeof(struct xcbc_desc_ctx) + alg->cra_blocksize * 2; inst->alg.base.cra_init = xcbc_init_tfm; inst->alg.base.cra_exit = xcbc_exit_tfm; inst->alg.init = crypto_xcbc_digest_init; inst->alg.update = crypto_xcbc_digest_update; inst->alg.final = crypto_xcbc_digest_final; inst->alg.setkey = crypto_xcbc_digest_setkey; inst->free = shash_free_singlespawn_instance; err = shash_register_instance(tmpl, inst); if (err) { err_free_inst: shash_free_singlespawn_instance(inst); } return err; } static struct crypto_template crypto_xcbc_tmpl = { .name = "xcbc", .create = xcbc_create, .module = THIS_MODULE, }; static int __init crypto_xcbc_module_init(void) { return crypto_register_template(&crypto_xcbc_tmpl); } static void __exit crypto_xcbc_module_exit(void) { crypto_unregister_template(&crypto_xcbc_tmpl); } subsys_initcall(crypto_xcbc_module_init); module_exit(crypto_xcbc_module_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("XCBC keyed hash algorithm"); MODULE_ALIAS_CRYPTO("xcbc"); MODULE_IMPORT_NS(CRYPTO_INTERNAL); |
| 1 1 1 1 1 645 | 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 | // SPDX-License-Identifier: GPL-2.0 /* * Dynamic byte queue limits. See include/linux/dynamic_queue_limits.h * * Copyright (c) 2011, Tom Herbert <therbert@google.com> */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/dynamic_queue_limits.h> #include <linux/compiler.h> #include <linux/export.h> #include <trace/events/napi.h> #define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0) #define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0) static void dql_check_stall(struct dql *dql, unsigned short stall_thrs) { unsigned long now; if (!stall_thrs) return; now = jiffies; /* Check for a potential stall */ if (time_after_eq(now, dql->last_reap + stall_thrs)) { unsigned long hist_head, t, start, end; /* We are trying to detect a period of at least @stall_thrs * jiffies without any Tx completions, but during first half * of which some Tx was posted. */ dqs_again: hist_head = READ_ONCE(dql->history_head); /* pairs with smp_wmb() in dql_queued() */ smp_rmb(); /* Get the previous entry in the ring buffer, which is the * oldest sample. */ start = (hist_head - DQL_HIST_LEN + 1) * BITS_PER_LONG; /* Advance start to continue from the last reap time */ if (time_before(start, dql->last_reap + 1)) start = dql->last_reap + 1; /* Newest sample we should have already seen a completion for */ end = hist_head * BITS_PER_LONG + (BITS_PER_LONG - 1); /* Shrink the search space to [start, (now - start_thrs/2)] if * `end` is beyond the stall zone */ if (time_before(now, end + stall_thrs / 2)) end = now - stall_thrs / 2; /* Search for the queued time in [t, end] */ for (t = start; time_before_eq(t, end); t++) if (test_bit(t % (DQL_HIST_LEN * BITS_PER_LONG), dql->history)) break; /* Variable t contains the time of the queue */ if (!time_before_eq(t, end)) goto no_stall; /* The ring buffer was modified in the meantime, retry */ if (hist_head != READ_ONCE(dql->history_head)) goto dqs_again; dql->stall_cnt++; dql->stall_max = max_t(unsigned short, dql->stall_max, now - t); trace_dql_stall_detected(dql->stall_thrs, now - t, dql->last_reap, dql->history_head, now, dql->history); } no_stall: dql->last_reap = now; } /* Records completed count and recalculates the queue limit */ void dql_completed(struct dql *dql, unsigned int count) { unsigned int inprogress, prev_inprogress, limit; unsigned int ovlimit, completed, num_queued; unsigned short stall_thrs; bool all_prev_completed; num_queued = READ_ONCE(dql->num_queued); /* Read stall_thrs in advance since it belongs to the same (first) * cache line as ->num_queued. This way, dql_check_stall() does not * need to touch the first cache line again later, reducing the window * of possible false sharing. */ stall_thrs = READ_ONCE(dql->stall_thrs); /* Can't complete more than what's in queue */ BUG_ON(count > num_queued - dql->num_completed); completed = dql->num_completed + count; limit = dql->limit; ovlimit = POSDIFF(num_queued - dql->num_completed, limit); inprogress = num_queued - completed; prev_inprogress = dql->prev_num_queued - dql->num_completed; all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued); if ((ovlimit && !inprogress) || (dql->prev_ovlimit && all_prev_completed)) { /* * Queue considered starved if: * - The queue was over-limit in the last interval, * and there is no more data in the queue. * OR * - The queue was over-limit in the previous interval and * when enqueuing it was possible that all queued data * had been consumed. This covers the case when queue * may have becomes starved between completion processing * running and next time enqueue was scheduled. * * When queue is starved increase the limit by the amount * of bytes both sent and completed in the last interval, * plus any previous over-limit. */ limit += POSDIFF(completed, dql->prev_num_queued) + dql->prev_ovlimit; dql->slack_start_time = jiffies; dql->lowest_slack = UINT_MAX; } else if (inprogress && prev_inprogress && !all_prev_completed) { /* * Queue was not starved, check if the limit can be decreased. * A decrease is only considered if the queue has been busy in * the whole interval (the check above). * * If there is slack, the amount of excess data queued above * the amount needed to prevent starvation, the queue limit * can be decreased. To avoid hysteresis we consider the * minimum amount of slack found over several iterations of the * completion routine. */ unsigned int slack, slack_last_objs; /* * Slack is the maximum of * - The queue limit plus previous over-limit minus twice * the number of objects completed. Note that two times * number of completed bytes is a basis for an upper bound * of the limit. * - Portion of objects in the last queuing operation that * was not part of non-zero previous over-limit. That is * "round down" by non-overlimit portion of the last * queueing operation. */ slack = POSDIFF(limit + dql->prev_ovlimit, 2 * (completed - dql->num_completed)); slack_last_objs = dql->prev_ovlimit ? POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0; slack = max(slack, slack_last_objs); if (slack < dql->lowest_slack) dql->lowest_slack = slack; if (time_after(jiffies, dql->slack_start_time + dql->slack_hold_time)) { limit = POSDIFF(limit, dql->lowest_slack); dql->slack_start_time = jiffies; dql->lowest_slack = UINT_MAX; } } /* Enforce bounds on limit */ limit = clamp(limit, dql->min_limit, dql->max_limit); if (limit != dql->limit) { dql->limit = limit; ovlimit = 0; } dql->adj_limit = limit + completed; dql->prev_ovlimit = ovlimit; dql->prev_last_obj_cnt = dql->last_obj_cnt; dql->num_completed = completed; dql->prev_num_queued = num_queued; dql_check_stall(dql, stall_thrs); } EXPORT_SYMBOL(dql_completed); void dql_reset(struct dql *dql) { /* Reset all dynamic values */ dql->limit = 0; dql->num_queued = 0; dql->num_completed = 0; dql->last_obj_cnt = 0; dql->prev_num_queued = 0; dql->prev_last_obj_cnt = 0; dql->prev_ovlimit = 0; dql->lowest_slack = UINT_MAX; dql->slack_start_time = jiffies; dql->last_reap = jiffies; dql->history_head = jiffies / BITS_PER_LONG; memset(dql->history, 0, sizeof(dql->history)); } EXPORT_SYMBOL(dql_reset); void dql_init(struct dql *dql, unsigned int hold_time) { dql->max_limit = DQL_MAX_LIMIT; dql->min_limit = 0; dql->slack_hold_time = hold_time; dql->stall_thrs = 0; dql_reset(dql); } EXPORT_SYMBOL(dql_init); |
| 2 2 1 1 1 2 2 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Binary Increase Congestion control for TCP * Home page: * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC * This is from the implementation of BICTCP in * Lison-Xu, Kahaled Harfoush, and Injong Rhee. * "Binary Increase Congestion Control for Fast, Long Distance * Networks" in InfoComm 2004 * Available from: * http://netsrv.csc.ncsu.edu/export/bitcp.pdf * * Unless BIC is enabled and congestion window is large * this behaves the same as the original Reno. */ #include <linux/mm.h> #include <linux/module.h> #include <net/tcp.h> #define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation * max_cwnd = snd_cwnd * beta */ #define BICTCP_B 4 /* * In binary search, * go to point (max+min)/N */ static int fast_convergence = 1; static int max_increment = 16; static int low_window = 14; static int beta = 819; /* = 819/1024 (BICTCP_BETA_SCALE) */ static int initial_ssthresh; static int smooth_part = 20; module_param(fast_convergence, int, 0644); MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence"); module_param(max_increment, int, 0644); MODULE_PARM_DESC(max_increment, "Limit on increment allowed during binary search"); module_param(low_window, int, 0644); MODULE_PARM_DESC(low_window, "lower bound on congestion window (for TCP friendliness)"); module_param(beta, int, 0644); MODULE_PARM_DESC(beta, "beta for multiplicative increase"); module_param(initial_ssthresh, int, 0644); MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold"); module_param(smooth_part, int, 0644); MODULE_PARM_DESC(smooth_part, "log(B/(B*Smin))/log(B/(B-1))+B, # of RTT from Wmax-B to Wmax"); /* BIC TCP Parameters */ struct bictcp { u32 cnt; /* increase cwnd by 1 after ACKs */ u32 last_max_cwnd; /* last maximum snd_cwnd */ u32 last_cwnd; /* the last snd_cwnd */ u32 last_time; /* time when updated last_cwnd */ u32 epoch_start; /* beginning of an epoch */ #define ACK_RATIO_SHIFT 4 u32 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */ }; static inline void bictcp_reset(struct bictcp *ca) { ca->cnt = 0; ca->last_max_cwnd = 0; ca->last_cwnd = 0; ca->last_time = 0; ca->epoch_start = 0; ca->delayed_ack = 2 << ACK_RATIO_SHIFT; } static void bictcp_init(struct sock *sk) { struct bictcp *ca = inet_csk_ca(sk); bictcp_reset(ca); if (initial_ssthresh) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } /* * Compute congestion window to use. */ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) { if (ca->last_cwnd == cwnd && (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) return; ca->last_cwnd = cwnd; ca->last_time = tcp_jiffies32; if (ca->epoch_start == 0) /* record the beginning of an epoch */ ca->epoch_start = tcp_jiffies32; /* start off normal */ if (cwnd <= low_window) { ca->cnt = cwnd; return; } /* binary increase */ if (cwnd < ca->last_max_cwnd) { __u32 dist = (ca->last_max_cwnd - cwnd) / BICTCP_B; if (dist > max_increment) /* linear increase */ ca->cnt = cwnd / max_increment; else if (dist <= 1U) /* binary search increase */ ca->cnt = (cwnd * smooth_part) / BICTCP_B; else /* binary search increase */ ca->cnt = cwnd / dist; } else { /* slow start AMD linear increase */ if (cwnd < ca->last_max_cwnd + BICTCP_B) /* slow start */ ca->cnt = (cwnd * smooth_part) / BICTCP_B; else if (cwnd < ca->last_max_cwnd + max_increment*(BICTCP_B-1)) /* slow start */ ca->cnt = (cwnd * (BICTCP_B-1)) / (cwnd - ca->last_max_cwnd); else /* linear increase */ ca->cnt = cwnd / max_increment; } /* if in slow start or link utilization is very low */ if (ca->last_max_cwnd == 0) { if (ca->cnt > 20) /* increase cwnd 5% per RTT */ ca->cnt = 20; } ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack; if (ca->cnt == 0) /* cannot be zero */ ca->cnt = 1; } static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); if (!tcp_is_cwnd_limited(sk)) return; if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; } bictcp_update(ca, tcp_snd_cwnd(tp)); tcp_cong_avoid_ai(tp, ca->cnt, acked); } /* * behave like Reno until low_window is reached, * then increase congestion window slowly */ static u32 bictcp_recalc_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); ca->epoch_start = 0; /* end of epoch */ /* Wmax and fast convergence */ if (tcp_snd_cwnd(tp) < ca->last_max_cwnd && fast_convergence) ca->last_max_cwnd = (tcp_snd_cwnd(tp) * (BICTCP_BETA_SCALE + beta)) / (2 * BICTCP_BETA_SCALE); else ca->last_max_cwnd = tcp_snd_cwnd(tp); if (tcp_snd_cwnd(tp) <= low_window) return max(tcp_snd_cwnd(tp) >> 1U, 2U); else return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U); } static void bictcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Loss) bictcp_reset(inet_csk_ca(sk)); } /* Track delayed acknowledgment ratio using sliding window * ratio = (15*ratio + sample) / 16 */ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct inet_connection_sock *icsk = inet_csk(sk); if (icsk->icsk_ca_state == TCP_CA_Open) { struct bictcp *ca = inet_csk_ca(sk); ca->delayed_ack += sample->pkts_acked - (ca->delayed_ack >> ACK_RATIO_SHIFT); } } static struct tcp_congestion_ops bictcp __read_mostly = { .init = bictcp_init, .ssthresh = bictcp_recalc_ssthresh, .cong_avoid = bictcp_cong_avoid, .set_state = bictcp_state, .undo_cwnd = tcp_reno_undo_cwnd, .pkts_acked = bictcp_acked, .owner = THIS_MODULE, .name = "bic", }; static int __init bictcp_register(void) { BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); return tcp_register_congestion_control(&bictcp); } static void __exit bictcp_unregister(void) { tcp_unregister_congestion_control(&bictcp); } module_init(bictcp_register); module_exit(bictcp_unregister); MODULE_AUTHOR("Stephen Hemminger"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("BIC TCP"); |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * acpi.h - ACPI Interface * * Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> */ #ifndef _LINUX_ACPI_H #define _LINUX_ACPI_H #include <linux/errno.h> #include <linux/ioport.h> /* for struct resource */ #include <linux/resource_ext.h> #include <linux/device.h> #include <linux/mod_devicetable.h> #include <linux/property.h> #include <linux/uuid.h> #include <linux/node.h> struct irq_domain; struct irq_domain_ops; #ifndef _LINUX #define _LINUX #endif #include <acpi/acpi.h> #include <acpi/acpi_numa.h> #ifdef CONFIG_ACPI #include <linux/list.h> #include <linux/dynamic_debug.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/fw_table.h> #include <acpi/acpi_bus.h> #include <acpi/acpi_drivers.h> #include <acpi/acpi_io.h> #include <asm/acpi.h> #ifdef CONFIG_ACPI_TABLE_LIB #define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI) #define __init_or_acpilib #define __initdata_or_acpilib #else #define EXPORT_SYMBOL_ACPI_LIB(x) #define __init_or_acpilib __init #define __initdata_or_acpilib __initdata #endif static inline acpi_handle acpi_device_handle(struct acpi_device *adev) { return adev ? adev->handle : NULL; } #define ACPI_COMPANION(dev) to_acpi_device_node((dev)->fwnode) #define ACPI_COMPANION_SET(dev, adev) set_primary_fwnode(dev, (adev) ? \ acpi_fwnode_handle(adev) : NULL) #define ACPI_HANDLE(dev) acpi_device_handle(ACPI_COMPANION(dev)) #define ACPI_HANDLE_FWNODE(fwnode) \ acpi_device_handle(to_acpi_device_node(fwnode)) static inline struct fwnode_handle *acpi_alloc_fwnode_static(void) { struct fwnode_handle *fwnode; fwnode = kzalloc(sizeof(struct fwnode_handle), GFP_KERNEL); if (!fwnode) return NULL; fwnode_init(fwnode, &acpi_static_fwnode_ops); return fwnode; } static inline void acpi_free_fwnode_static(struct fwnode_handle *fwnode) { if (WARN_ON(!is_acpi_static_node(fwnode))) return; kfree(fwnode); } static inline bool has_acpi_companion(struct device *dev) { return is_acpi_device_node(dev->fwnode); } static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { ACPI_COMPANION_SET(dev, acpi_find_child_device(parent, addr, false)); } static inline const char *acpi_dev_name(struct acpi_device *adev) { return dev_name(&adev->dev); } struct device *acpi_get_first_physical_node(struct acpi_device *adev); enum acpi_irq_model_id { ACPI_IRQ_MODEL_PIC = 0, ACPI_IRQ_MODEL_IOAPIC, ACPI_IRQ_MODEL_IOSAPIC, ACPI_IRQ_MODEL_PLATFORM, ACPI_IRQ_MODEL_GIC, ACPI_IRQ_MODEL_LPIC, ACPI_IRQ_MODEL_COUNT }; extern enum acpi_irq_model_id acpi_irq_model; enum acpi_interrupt_id { ACPI_INTERRUPT_PMI = 1, ACPI_INTERRUPT_INIT, ACPI_INTERRUPT_CPEI, ACPI_INTERRUPT_COUNT }; #define ACPI_SPACE_MEM 0 enum acpi_address_range_id { ACPI_ADDRESS_RANGE_MEMORY = 1, ACPI_ADDRESS_RANGE_RESERVED = 2, ACPI_ADDRESS_RANGE_ACPI = 3, ACPI_ADDRESS_RANGE_NVS = 4, ACPI_ADDRESS_RANGE_COUNT }; /* Table Handlers */ typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table); /* Debugger support */ struct acpi_debugger_ops { int (*create_thread)(acpi_osd_exec_callback function, void *context); ssize_t (*write_log)(const char *msg); ssize_t (*read_cmd)(char *buffer, size_t length); int (*wait_command_ready)(bool single_step, char *buffer, size_t length); int (*notify_command_complete)(void); }; struct acpi_debugger { const struct acpi_debugger_ops *ops; struct module *owner; struct mutex lock; }; #ifdef CONFIG_ACPI_DEBUGGER int __init acpi_debugger_init(void); int acpi_register_debugger(struct module *owner, const struct acpi_debugger_ops *ops); void acpi_unregister_debugger(const struct acpi_debugger_ops *ops); int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context); ssize_t acpi_debugger_write_log(const char *msg); ssize_t acpi_debugger_read_cmd(char *buffer, size_t buffer_length); int acpi_debugger_wait_command_ready(void); int acpi_debugger_notify_command_complete(void); #else static inline int acpi_debugger_init(void) { return -ENODEV; } static inline int acpi_register_debugger(struct module *owner, const struct acpi_debugger_ops *ops) { return -ENODEV; } static inline void acpi_unregister_debugger(const struct acpi_debugger_ops *ops) { } static inline int acpi_debugger_create_thread(acpi_osd_exec_callback function, void *context) { return -ENODEV; } static inline int acpi_debugger_write_log(const char *msg) { return -ENODEV; } static inline int acpi_debugger_read_cmd(char *buffer, u32 buffer_length) { return -ENODEV; } static inline int acpi_debugger_wait_command_ready(void) { return -ENODEV; } static inline int acpi_debugger_notify_command_complete(void) { return -ENODEV; } #endif #define BAD_MADT_ENTRY(entry, end) ( \ (!entry) || (unsigned long)entry + sizeof(*entry) > end || \ ((struct acpi_subtable_header *)entry)->length < sizeof(*entry)) void __iomem *__acpi_map_table(unsigned long phys, unsigned long size); void __acpi_unmap_table(void __iomem *map, unsigned long size); int early_acpi_boot_init(void); int acpi_boot_init (void); void acpi_boot_table_prepare (void); void acpi_boot_table_init (void); int acpi_mps_check (void); int acpi_numa_init (void); int acpi_locate_initial_tables (void); void acpi_reserve_initial_tables (void); void acpi_table_init_complete (void); int acpi_table_init (void); int acpi_table_parse(char *id, acpi_tbl_table_handler handler); int __init_or_acpilib acpi_table_parse_entries(char *id, unsigned long table_size, int entry_id, acpi_tbl_entry_handler handler, unsigned int max_entries); int __init_or_acpilib acpi_table_parse_entries_array(char *id, unsigned long table_size, struct acpi_subtable_proc *proc, int proc_num, unsigned int max_entries); int acpi_table_parse_madt(enum acpi_madt_type id, acpi_tbl_entry_handler handler, unsigned int max_entries); int __init_or_acpilib acpi_table_parse_cedt(enum acpi_cedt_type id, acpi_tbl_entry_handler_arg handler_arg, void *arg); int acpi_parse_mcfg (struct acpi_table_header *header); void acpi_table_print_madt_entry (struct acpi_subtable_header *madt); #if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH) void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa); #else static inline void acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) { } #endif void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa); #if defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH) void acpi_arch_dma_setup(struct device *dev); #else static inline void acpi_arch_dma_setup(struct device *dev) { } #endif #ifdef CONFIG_ARM64 void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa); #else static inline void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { } #endif #ifdef CONFIG_RISCV void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa); #else static inline void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { } #endif #ifndef PHYS_CPUID_INVALID typedef u32 phys_cpuid_t; #define PHYS_CPUID_INVALID (phys_cpuid_t)(-1) #endif static inline bool invalid_logical_cpuid(u32 cpuid) { return (int)cpuid < 0; } static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id) { return phys_id == PHYS_CPUID_INVALID; } int __init acpi_get_madt_revision(void); /* Validate the processor object's proc_id */ bool acpi_duplicate_processor_id(int proc_id); /* Processor _CTS control */ struct acpi_processor_power; #ifdef CONFIG_ACPI_PROCESSOR_CSTATE bool acpi_processor_claim_cst_control(void); int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, struct acpi_processor_power *info); #else static inline bool acpi_processor_claim_cst_control(void) { return false; } static inline int acpi_processor_evaluate_cst(acpi_handle handle, u32 cpu, struct acpi_processor_power *info) { return -ENODEV; } #endif #ifdef CONFIG_ACPI_HOTPLUG_CPU /* Arch dependent functions for cpu hotplug support */ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu); int acpi_unmap_cpu(int cpu); #endif /* CONFIG_ACPI_HOTPLUG_CPU */ acpi_handle acpi_get_processor_handle(int cpu); #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr); #endif int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base); int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base); int acpi_ioapic_registered(acpi_handle handle, u32 gsi_base); void acpi_irq_stats_init(void); extern u32 acpi_irq_handled; extern u32 acpi_irq_not_handled; extern unsigned int acpi_sci_irq; extern bool acpi_no_s5; #define INVALID_ACPI_IRQ ((unsigned)-1) static inline bool acpi_sci_irq_valid(void) { return acpi_sci_irq != INVALID_ACPI_IRQ; } extern int sbf_port; extern unsigned long acpi_realmode_flags; int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity); int acpi_gsi_to_irq (u32 gsi, unsigned int *irq); int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi); void acpi_set_irq_model(enum acpi_irq_model_id model, struct fwnode_handle *(*)(u32)); void acpi_set_gsi_to_irq_fallback(u32 (*)(u32)); struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags, unsigned int size, struct fwnode_handle *fwnode, const struct irq_domain_ops *ops, void *host_data); #ifdef CONFIG_X86_IO_APIC extern int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity); #else static inline int acpi_get_override_irq(u32 gsi, int *trigger, int *polarity) { return -1; } #endif /* * This function undoes the effect of one call to acpi_register_gsi(). * If this matches the last registration, any IRQ resources for gsi * are freed. */ void acpi_unregister_gsi (u32 gsi); struct pci_dev; int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); bool acpi_isa_irq_available(int irq); #ifdef CONFIG_PCI void acpi_penalize_sci_irq(int irq, int trigger, int polarity); #else static inline void acpi_penalize_sci_irq(int irq, int trigger, int polarity) { } #endif void acpi_pci_irq_disable (struct pci_dev *dev); extern int ec_read(u8 addr, u8 *val); extern int ec_write(u8 addr, u8 val); extern int ec_transaction(u8 command, const u8 *wdata, unsigned wdata_len, u8 *rdata, unsigned rdata_len); extern acpi_handle ec_get_handle(void); extern bool acpi_is_pnp_device(struct acpi_device *); #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE) typedef void (*wmi_notify_handler) (u32 value, void *context); int wmi_instance_count(const char *guid); extern acpi_status wmi_evaluate_method(const char *guid, u8 instance, u32 method_id, const struct acpi_buffer *in, struct acpi_buffer *out); extern acpi_status wmi_query_block(const char *guid, u8 instance, struct acpi_buffer *out); extern acpi_status wmi_set_block(const char *guid, u8 instance, const struct acpi_buffer *in); extern acpi_status wmi_install_notify_handler(const char *guid, wmi_notify_handler handler, void *data); extern acpi_status wmi_remove_notify_handler(const char *guid); extern acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out); extern bool wmi_has_guid(const char *guid); extern char *wmi_get_acpi_device_uid(const char *guid); #endif /* CONFIG_ACPI_WMI */ #define ACPI_VIDEO_OUTPUT_SWITCHING 0x0001 #define ACPI_VIDEO_DEVICE_POSTING 0x0002 #define ACPI_VIDEO_ROM_AVAILABLE 0x0004 #define ACPI_VIDEO_BACKLIGHT 0x0008 #define ACPI_VIDEO_BACKLIGHT_FORCE_VENDOR 0x0010 #define ACPI_VIDEO_BACKLIGHT_FORCE_VIDEO 0x0020 #define ACPI_VIDEO_OUTPUT_SWITCHING_FORCE_VENDOR 0x0040 #define ACPI_VIDEO_OUTPUT_SWITCHING_FORCE_VIDEO 0x0080 #define ACPI_VIDEO_BACKLIGHT_DMI_VENDOR 0x0100 #define ACPI_VIDEO_BACKLIGHT_DMI_VIDEO 0x0200 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VENDOR 0x0400 #define ACPI_VIDEO_OUTPUT_SWITCHING_DMI_VIDEO 0x0800 extern char acpi_video_backlight_string[]; extern long acpi_is_video_device(acpi_handle handle); extern void acpi_osi_setup(char *str); extern bool acpi_osi_is_win8(void); #ifdef CONFIG_ACPI_THERMAL_LIB int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp); int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp); int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp); int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp); #endif #ifdef CONFIG_ACPI_HMAT int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord); #else static inline int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord) { return -EOPNOTSUPP; } #endif #ifdef CONFIG_ACPI_NUMA int acpi_map_pxm_to_node(int pxm); int acpi_get_node(acpi_handle handle); /** * pxm_to_online_node - Map proximity ID to online node * @pxm: ACPI proximity ID * * This is similar to pxm_to_node(), but always returns an online * node. When the mapped node from a given proximity ID is offline, it * looks up the node distance table and returns the nearest online node. * * ACPI device drivers, which are called after the NUMA initialization has * completed in the kernel, can call this interface to obtain their device * NUMA topology from ACPI tables. Such drivers do not have to deal with * offline nodes. A node may be offline when SRAT memory entry does not exist, * or NUMA is disabled, ex. "numa=off" on x86. */ static inline int pxm_to_online_node(int pxm) { int node = pxm_to_node(pxm); return numa_map_to_online_node(node); } #else static inline int pxm_to_online_node(int pxm) { return 0; } static inline int acpi_map_pxm_to_node(int pxm) { return 0; } static inline int acpi_get_node(acpi_handle handle) { return 0; } #endif extern int pnpacpi_disabled; #define PXM_INVAL (-1) bool acpi_dev_resource_memory(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_io(struct acpi_resource *ares, struct resource *res); bool acpi_dev_resource_address_space(struct acpi_resource *ares, struct resource_win *win); bool acpi_dev_resource_ext_address_space(struct acpi_resource *ares, struct resource_win *win); unsigned long acpi_dev_irq_flags(u8 triggering, u8 polarity, u8 shareable, u8 wake_capable); unsigned int acpi_dev_get_irq_type(int triggering, int polarity); bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index, struct resource *res); void acpi_dev_free_resource_list(struct list_head *list); int acpi_dev_get_resources(struct acpi_device *adev, struct list_head *list, int (*preproc)(struct acpi_resource *, void *), void *preproc_data); int acpi_dev_get_dma_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_get_memory_resources(struct acpi_device *adev, struct list_head *list); int acpi_dev_filter_resource_type(struct acpi_resource *ares, unsigned long types); static inline int acpi_dev_filter_resource_type_cb(struct acpi_resource *ares, void *arg) { return acpi_dev_filter_resource_type(ares, (unsigned long)arg); } struct acpi_device *acpi_resource_consumer(struct resource *res); int acpi_check_resource_conflict(const struct resource *res); int acpi_check_region(resource_size_t start, resource_size_t n, const char *name); int acpi_resources_are_enforced(void); #ifdef CONFIG_HIBERNATION extern int acpi_check_s4_hw_signature; #endif #ifdef CONFIG_PM_SLEEP void __init acpi_old_suspend_ordering(void); void __init acpi_nvs_nosave(void); void __init acpi_nvs_nosave_s3(void); void __init acpi_sleep_no_blacklist(void); #endif /* CONFIG_PM_SLEEP */ int acpi_register_wakeup_handler( int wake_irq, bool (*wakeup)(void *context), void *context); void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context); struct acpi_osc_context { char *uuid_str; /* UUID string */ int rev; struct acpi_buffer cap; /* list of DWORD capabilities */ struct acpi_buffer ret; /* free by caller if success */ }; acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context); /* Number of _OSC capability DWORDS depends on bridge type */ #define OSC_PCI_CAPABILITY_DWORDS 3 #define OSC_CXL_CAPABILITY_DWORDS 5 /* Indexes into _OSC Capabilities Buffer (DWORDs 2 to 5 are device-specific) */ #define OSC_QUERY_DWORD 0 /* DWORD 1 */ #define OSC_SUPPORT_DWORD 1 /* DWORD 2 */ #define OSC_CONTROL_DWORD 2 /* DWORD 3 */ #define OSC_EXT_SUPPORT_DWORD 3 /* DWORD 4 */ #define OSC_EXT_CONTROL_DWORD 4 /* DWORD 5 */ /* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */ #define OSC_QUERY_ENABLE 0x00000001 /* input */ #define OSC_REQUEST_ERROR 0x00000002 /* return */ #define OSC_INVALID_UUID_ERROR 0x00000004 /* return */ #define OSC_INVALID_REVISION_ERROR 0x00000008 /* return */ #define OSC_CAPABILITIES_MASK_ERROR 0x00000010 /* return */ /* Platform-Wide Capabilities _OSC: Capabilities DWORD 2: Support Field */ #define OSC_SB_PAD_SUPPORT 0x00000001 #define OSC_SB_PPC_OST_SUPPORT 0x00000002 #define OSC_SB_PR3_SUPPORT 0x00000004 #define OSC_SB_HOTPLUG_OST_SUPPORT 0x00000008 #define OSC_SB_APEI_SUPPORT 0x00000010 #define OSC_SB_CPC_SUPPORT 0x00000020 #define OSC_SB_CPCV2_SUPPORT 0x00000040 #define OSC_SB_PCLPI_SUPPORT 0x00000080 #define OSC_SB_OSLPI_SUPPORT 0x00000100 #define OSC_SB_FAST_THERMAL_SAMPLING_SUPPORT 0x00000200 #define OSC_SB_OVER_16_PSTATES_SUPPORT 0x00000400 #define OSC_SB_GED_SUPPORT 0x00000800 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT 0x00001000 #define OSC_SB_IRQ_RESOURCE_SOURCE_SUPPORT 0x00002000 #define OSC_SB_CPC_FLEXIBLE_ADR_SPACE 0x00004000 #define OSC_SB_GENERIC_INITIATOR_SUPPORT 0x00020000 #define OSC_SB_NATIVE_USB4_SUPPORT 0x00040000 #define OSC_SB_BATTERY_CHARGE_LIMITING_SUPPORT 0x00080000 #define OSC_SB_PRM_SUPPORT 0x00200000 #define OSC_SB_FFH_OPR_SUPPORT 0x00400000 extern bool osc_sb_apei_support_acked; extern bool osc_pc_lpi_support_confirmed; extern bool osc_sb_native_usb4_support_confirmed; extern bool osc_sb_cppc2_support_acked; extern bool osc_cpc_flexible_adr_space_confirmed; /* USB4 Capabilities */ #define OSC_USB_USB3_TUNNELING 0x00000001 #define OSC_USB_DP_TUNNELING 0x00000002 #define OSC_USB_PCIE_TUNNELING 0x00000004 #define OSC_USB_XDOMAIN 0x00000008 extern u32 osc_sb_native_usb4_control; /* PCI Host Bridge _OSC: Capabilities DWORD 2: Support Field */ #define OSC_PCI_EXT_CONFIG_SUPPORT 0x00000001 #define OSC_PCI_ASPM_SUPPORT 0x00000002 #define OSC_PCI_CLOCK_PM_SUPPORT 0x00000004 #define OSC_PCI_SEGMENT_GROUPS_SUPPORT 0x00000008 #define OSC_PCI_MSI_SUPPORT 0x00000010 #define OSC_PCI_EDR_SUPPORT 0x00000080 #define OSC_PCI_HPX_TYPE_3_SUPPORT 0x00000100 /* PCI Host Bridge _OSC: Capabilities DWORD 3: Control Field */ #define OSC_PCI_EXPRESS_NATIVE_HP_CONTROL 0x00000001 #define OSC_PCI_SHPC_NATIVE_HP_CONTROL 0x00000002 #define OSC_PCI_EXPRESS_PME_CONTROL 0x00000004 #define OSC_PCI_EXPRESS_AER_CONTROL 0x00000008 #define OSC_PCI_EXPRESS_CAPABILITY_CONTROL 0x00000010 #define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020 #define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080 /* CXL _OSC: Capabilities DWORD 4: Support Field */ #define OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT 0x00000001 #define OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT 0x00000002 #define OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT 0x00000004 #define OSC_CXL_NATIVE_HP_SUPPORT 0x00000008 /* CXL _OSC: Capabilities DWORD 5: Control Field */ #define OSC_CXL_ERROR_REPORTING_CONTROL 0x00000001 static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) { u32 *ret = context->ret.pointer; return ret[OSC_CONTROL_DWORD]; } static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) { u32 *ret = context->ret.pointer; return ret[OSC_EXT_CONTROL_DWORD]; } #define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002 #define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004 #define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006 #define ACPI_GSB_ACCESS_ATTRIB_WORD 0x00000008 #define ACPI_GSB_ACCESS_ATTRIB_BLOCK 0x0000000A #define ACPI_GSB_ACCESS_ATTRIB_MULTIBYTE 0x0000000B #define ACPI_GSB_ACCESS_ATTRIB_WORD_CALL 0x0000000C #define ACPI_GSB_ACCESS_ATTRIB_BLOCK_CALL 0x0000000D #define ACPI_GSB_ACCESS_ATTRIB_RAW_BYTES 0x0000000E #define ACPI_GSB_ACCESS_ATTRIB_RAW_PROCESS 0x0000000F /* Enable _OST when all relevant hotplug operations are enabled */ #if defined(CONFIG_ACPI_HOTPLUG_CPU) && \ defined(CONFIG_ACPI_HOTPLUG_MEMORY) && \ defined(CONFIG_ACPI_CONTAINER) #define ACPI_HOTPLUG_OST #endif /* _OST Source Event Code (OSPM Action) */ #define ACPI_OST_EC_OSPM_SHUTDOWN 0x100 #define ACPI_OST_EC_OSPM_EJECT 0x103 #define ACPI_OST_EC_OSPM_INSERTION 0x200 /* _OST General Processing Status Code */ #define ACPI_OST_SC_SUCCESS 0x0 #define ACPI_OST_SC_NON_SPECIFIC_FAILURE 0x1 #define ACPI_OST_SC_UNRECOGNIZED_NOTIFY 0x2 /* _OST OS Shutdown Processing (0x100) Status Code */ #define ACPI_OST_SC_OS_SHUTDOWN_DENIED 0x80 #define ACPI_OST_SC_OS_SHUTDOWN_IN_PROGRESS 0x81 #define ACPI_OST_SC_OS_SHUTDOWN_COMPLETED 0x82 #define ACPI_OST_SC_OS_SHUTDOWN_NOT_SUPPORTED 0x83 /* _OST Ejection Request (0x3, 0x103) Status Code */ #define ACPI_OST_SC_EJECT_NOT_SUPPORTED 0x80 #define ACPI_OST_SC_DEVICE_IN_USE 0x81 #define ACPI_OST_SC_DEVICE_BUSY 0x82 #define ACPI_OST_SC_EJECT_DEPENDENCY_BUSY 0x83 #define ACPI_OST_SC_EJECT_IN_PROGRESS 0x84 /* _OST Insertion Request (0x200) Status Code */ #define ACPI_OST_SC_INSERT_IN_PROGRESS 0x80 #define ACPI_OST_SC_DRIVER_LOAD_FAILURE 0x81 #define ACPI_OST_SC_INSERT_NOT_SUPPORTED 0x82 enum acpi_predicate { all_versions, less_than_or_equal, equal, greater_than_or_equal, }; /* Table must be terminted by a NULL entry */ struct acpi_platform_list { char oem_id[ACPI_OEM_ID_SIZE+1]; char oem_table_id[ACPI_OEM_TABLE_ID_SIZE+1]; u32 oem_revision; char *table; enum acpi_predicate pred; char *reason; u32 data; }; int acpi_match_platform_list(const struct acpi_platform_list *plat); extern void acpi_early_init(void); extern void acpi_subsystem_init(void); extern int acpi_nvs_register(__u64 start, __u64 size); extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), void *data); const struct acpi_device_id *acpi_match_acpi_device(const struct acpi_device_id *ids, const struct acpi_device *adev); const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids, const struct device *dev); const void *acpi_device_get_match_data(const struct device *dev); extern bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv); int acpi_device_uevent_modalias(const struct device *, struct kobj_uevent_env *); int acpi_device_modalias(struct device *, char *, int); struct platform_device *acpi_create_platform_device(struct acpi_device *, const struct property_entry *); #define ACPI_PTR(_ptr) (_ptr) static inline void acpi_device_set_enumerated(struct acpi_device *adev) { adev->flags.visited = true; } static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { adev->flags.visited = false; } enum acpi_reconfig_event { ACPI_RECONFIG_DEVICE_ADD = 0, ACPI_RECONFIG_DEVICE_REMOVE, }; int acpi_reconfig_notifier_register(struct notifier_block *nb); int acpi_reconfig_notifier_unregister(struct notifier_block *nb); #ifdef CONFIG_ACPI_GTDT int acpi_gtdt_init(struct acpi_table_header *table, int *platform_timer_count); int acpi_gtdt_map_ppi(int type); bool acpi_gtdt_c3stop(int type); int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count); #endif #ifndef ACPI_HAVE_ARCH_SET_ROOT_POINTER static inline void acpi_arch_set_root_pointer(u64 addr) { } #endif #ifndef ACPI_HAVE_ARCH_GET_ROOT_POINTER static inline u64 acpi_arch_get_root_pointer(void) { return 0; } #endif int acpi_get_local_u64_address(acpi_handle handle, u64 *addr); int acpi_get_local_address(acpi_handle handle, u32 *addr); const char *acpi_get_subsystem_id(acpi_handle handle); #else /* !CONFIG_ACPI */ #define acpi_disabled 1 #define ACPI_COMPANION(dev) (NULL) #define ACPI_COMPANION_SET(dev, adev) do { } while (0) #define ACPI_HANDLE(dev) (NULL) #define ACPI_HANDLE_FWNODE(fwnode) (NULL) /* Get rid of the -Wunused-variable for adev */ #define acpi_dev_uid_match(adev, uid2) (adev && false) #define acpi_dev_hid_uid_match(adev, hid2, uid2) (adev && false) struct fwnode_handle; static inline bool acpi_dev_found(const char *hid) { return false; } static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) { return false; } struct acpi_device; static inline int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer) { return -ENODEV; } static inline struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) { return NULL; } static inline bool acpi_reduced_hardware(void) { return false; } static inline void acpi_dev_put(struct acpi_device *adev) {} static inline bool is_acpi_node(const struct fwnode_handle *fwnode) { return false; } static inline bool is_acpi_device_node(const struct fwnode_handle *fwnode) { return false; } static inline struct acpi_device *to_acpi_device_node(const struct fwnode_handle *fwnode) { return NULL; } static inline bool is_acpi_data_node(const struct fwnode_handle *fwnode) { return false; } static inline struct acpi_data_node *to_acpi_data_node(const struct fwnode_handle *fwnode) { return NULL; } static inline bool acpi_data_node_match(const struct fwnode_handle *fwnode, const char *name) { return false; } static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev) { return NULL; } static inline bool has_acpi_companion(struct device *dev) { return false; } static inline void acpi_preset_companion(struct device *dev, struct acpi_device *parent, u64 addr) { } static inline const char *acpi_dev_name(struct acpi_device *adev) { return NULL; } static inline struct device *acpi_get_first_physical_node(struct acpi_device *adev) { return NULL; } static inline void acpi_early_init(void) { } static inline void acpi_subsystem_init(void) { } static inline int early_acpi_boot_init(void) { return 0; } static inline int acpi_boot_init(void) { return 0; } static inline void acpi_boot_table_prepare(void) { } static inline void acpi_boot_table_init(void) { } static inline int acpi_mps_check(void) { return 0; } static inline int acpi_check_resource_conflict(struct resource *res) { return 0; } static inline int acpi_check_region(resource_size_t start, resource_size_t n, const char *name) { return 0; } struct acpi_table_header; static inline int acpi_table_parse(char *id, int (*handler)(struct acpi_table_header *)) { return -ENODEV; } static inline int acpi_nvs_register(__u64 start, __u64 size) { return 0; } static inline int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *), void *data) { return 0; } struct acpi_device_id; static inline const struct acpi_device_id *acpi_match_acpi_device( const struct acpi_device_id *ids, const struct acpi_device *adev) { return NULL; } static inline const struct acpi_device_id *acpi_match_device( const struct acpi_device_id *ids, const struct device *dev) { return NULL; } static inline const void *acpi_device_get_match_data(const struct device *dev) { return NULL; } static inline bool acpi_driver_match_device(struct device *dev, const struct device_driver *drv) { return false; } static inline bool acpi_check_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 funcs) { return false; } static inline union acpi_object *acpi_evaluate_dsm(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4) { return NULL; } static inline union acpi_object *acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev, u64 func, union acpi_object *argv4, acpi_object_type type) { return NULL; } static inline int acpi_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { return -ENODEV; } static inline int acpi_device_modalias(struct device *dev, char *buf, int size) { return -ENODEV; } static inline struct platform_device * acpi_create_platform_device(struct acpi_device *adev, const struct property_entry *properties) { return NULL; } static inline bool acpi_dma_supported(const struct acpi_device *adev) { return false; } static inline enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev) { return DEV_DMA_NOT_SUPPORTED; } static inline int acpi_dma_get_range(struct device *dev, const struct bus_dma_region **map) { return -ENODEV; } static inline int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr) { return 0; } static inline int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr, const u32 *input_id) { return 0; } #define ACPI_PTR(_ptr) (NULL) static inline void acpi_device_set_enumerated(struct acpi_device *adev) { } static inline void acpi_device_clear_enumerated(struct acpi_device *adev) { } static inline int acpi_reconfig_notifier_register(struct notifier_block *nb) { return -EINVAL; } static inline int acpi_reconfig_notifier_unregister(struct notifier_block *nb) { return -EINVAL; } static inline struct acpi_device *acpi_resource_consumer(struct resource *res) { return NULL; } static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) { return -ENODEV; } static inline const char *acpi_get_subsystem_id(acpi_handle handle) { return ERR_PTR(-ENODEV); } static inline int acpi_register_wakeup_handler(int wake_irq, bool (*wakeup)(void *context), void *context) { return -ENXIO; } static inline void acpi_unregister_wakeup_handler( bool (*wakeup)(void *context), void *context) { } struct acpi_osc_context; static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context) { return 0; } static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context) { return 0; } static inline bool acpi_sleep_state_supported(u8 sleep_state) { return false; } static inline acpi_handle acpi_get_processor_handle(int cpu) { return NULL; } #endif /* !CONFIG_ACPI */ extern void arch_post_acpi_subsys_init(void); #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC int acpi_ioapic_add(acpi_handle root); #else static inline int acpi_ioapic_add(acpi_handle root) { return 0; } #endif #ifdef CONFIG_ACPI void acpi_os_set_prepare_sleep(int (*func)(u8 sleep_state, u32 pm1a_ctrl, u32 pm1b_ctrl)); acpi_status acpi_os_prepare_sleep(u8 sleep_state, u32 pm1a_control, u32 pm1b_control); void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state, u32 val_a, u32 val_b)); acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state, u32 val_a, u32 val_b); #if defined(CONFIG_SUSPEND) && defined(CONFIG_X86) struct acpi_s2idle_dev_ops { struct list_head list_node; void (*prepare)(void); void (*check)(void); void (*restore)(void); }; int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg); void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg); int acpi_get_lps0_constraint(struct acpi_device *adev); #else /* CONFIG_SUSPEND && CONFIG_X86 */ static inline int acpi_get_lps0_constraint(struct device *dev) { return ACPI_STATE_UNKNOWN; } #endif /* CONFIG_SUSPEND && CONFIG_X86 */ void arch_reserve_mem_area(acpi_physical_address addr, size_t size); #else #define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0) #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM) int acpi_dev_suspend(struct device *dev, bool wakeup); int acpi_dev_resume(struct device *dev); int acpi_subsys_runtime_suspend(struct device *dev); int acpi_subsys_runtime_resume(struct device *dev); int acpi_dev_pm_attach(struct device *dev, bool power_on); bool acpi_storage_d3(struct device *dev); bool acpi_dev_state_d0(struct device *dev); #else static inline int acpi_subsys_runtime_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_runtime_resume(struct device *dev) { return 0; } static inline int acpi_dev_pm_attach(struct device *dev, bool power_on) { return 0; } static inline bool acpi_storage_d3(struct device *dev) { return false; } static inline bool acpi_dev_state_d0(struct device *dev) { return true; } #endif #if defined(CONFIG_ACPI) && defined(CONFIG_PM_SLEEP) int acpi_subsys_prepare(struct device *dev); void acpi_subsys_complete(struct device *dev); int acpi_subsys_suspend_late(struct device *dev); int acpi_subsys_suspend_noirq(struct device *dev); int acpi_subsys_suspend(struct device *dev); int acpi_subsys_freeze(struct device *dev); int acpi_subsys_poweroff(struct device *dev); void acpi_ec_mark_gpe_for_wake(void); void acpi_ec_set_gpe_wake_mask(u8 action); int acpi_subsys_restore_early(struct device *dev); #else static inline int acpi_subsys_prepare(struct device *dev) { return 0; } static inline void acpi_subsys_complete(struct device *dev) {} static inline int acpi_subsys_suspend_late(struct device *dev) { return 0; } static inline int acpi_subsys_suspend_noirq(struct device *dev) { return 0; } static inline int acpi_subsys_suspend(struct device *dev) { return 0; } static inline int acpi_subsys_freeze(struct device *dev) { return 0; } static inline int acpi_subsys_poweroff(struct device *dev) { return 0; } static inline int acpi_subsys_restore_early(struct device *dev) { return 0; } static inline void acpi_ec_mark_gpe_for_wake(void) {} static inline void acpi_ec_set_gpe_wake_mask(u8 action) {} #endif #ifdef CONFIG_ACPI char *acpi_handle_path(acpi_handle handle); __printf(3, 4) void acpi_handle_printk(const char *level, acpi_handle handle, const char *fmt, ...); void acpi_evaluation_failure_warn(acpi_handle handle, const char *name, acpi_status status); #else /* !CONFIG_ACPI */ static inline __printf(3, 4) void acpi_handle_printk(const char *level, void *handle, const char *fmt, ...) {} static inline void acpi_evaluation_failure_warn(acpi_handle handle, const char *name, acpi_status status) {} #endif /* !CONFIG_ACPI */ #if defined(CONFIG_ACPI) && defined(CONFIG_DYNAMIC_DEBUG) __printf(3, 4) void __acpi_handle_debug(struct _ddebug *descriptor, acpi_handle handle, const char *fmt, ...); #endif /* * acpi_handle_<level>: Print message with ACPI prefix and object path * * These interfaces acquire the global namespace mutex to obtain an object * path. In interrupt context, it shows the object path as <n/a>. */ #define acpi_handle_emerg(handle, fmt, ...) \ acpi_handle_printk(KERN_EMERG, handle, fmt, ##__VA_ARGS__) #define acpi_handle_alert(handle, fmt, ...) \ acpi_handle_printk(KERN_ALERT, handle, fmt, ##__VA_ARGS__) #define acpi_handle_crit(handle, fmt, ...) \ acpi_handle_printk(KERN_CRIT, handle, fmt, ##__VA_ARGS__) #define acpi_handle_err(handle, fmt, ...) \ acpi_handle_printk(KERN_ERR, handle, fmt, ##__VA_ARGS__) #define acpi_handle_warn(handle, fmt, ...) \ acpi_handle_printk(KERN_WARNING, handle, fmt, ##__VA_ARGS__) #define acpi_handle_notice(handle, fmt, ...) \ acpi_handle_printk(KERN_NOTICE, handle, fmt, ##__VA_ARGS__) #define acpi_handle_info(handle, fmt, ...) \ acpi_handle_printk(KERN_INFO, handle, fmt, ##__VA_ARGS__) #if defined(DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__) #else #if defined(CONFIG_DYNAMIC_DEBUG) #define acpi_handle_debug(handle, fmt, ...) \ _dynamic_func_call(fmt, __acpi_handle_debug, \ handle, pr_fmt(fmt), ##__VA_ARGS__) #else #define acpi_handle_debug(handle, fmt, ...) \ ({ \ if (0) \ acpi_handle_printk(KERN_DEBUG, handle, fmt, ##__VA_ARGS__); \ 0; \ }) #endif #endif #if defined(CONFIG_ACPI) && defined(CONFIG_GPIOLIB) bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio); int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable); #else static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { return false; } static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares, struct acpi_resource_gpio **agpio) { return false; } static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index, bool *wake_capable) { return -ENXIO; } #endif static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index, bool *wake_capable) { return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable); } static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *con_id, int index) { return acpi_dev_gpio_irq_wake_get_by(adev, con_id, index, NULL); } static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index) { return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, NULL); } /* Device properties */ #ifdef CONFIG_ACPI int acpi_dev_get_property(const struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj); int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct fwnode_reference_args *args); static inline int acpi_node_get_property_reference( const struct fwnode_handle *fwnode, const char *name, size_t index, struct fwnode_reference_args *args) { return __acpi_node_get_property_reference(fwnode, name, index, NR_FWNODE_REFERENCE_ARGS, args); } static inline bool acpi_dev_has_props(const struct acpi_device *adev) { return !list_empty(&adev->data.properties); } struct acpi_device_properties * acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid, union acpi_object *properties); int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr); struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child); struct acpi_probe_entry; typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *, struct acpi_probe_entry *); #define ACPI_TABLE_ID_LEN 5 /** * struct acpi_probe_entry - boot-time probing entry * @id: ACPI table name * @type: Optional subtable type to match * (if @id contains subtables) * @subtable_valid: Optional callback to check the validity of * the subtable * @probe_table: Callback to the driver being probed when table * match is successful * @probe_subtbl: Callback to the driver being probed when table and * subtable match (and optional callback is successful) * @driver_data: Sideband data provided back to the driver */ struct acpi_probe_entry { __u8 id[ACPI_TABLE_ID_LEN]; __u8 type; acpi_probe_entry_validate_subtbl subtable_valid; union { acpi_tbl_table_handler probe_table; acpi_tbl_entry_handler probe_subtbl; }; kernel_ulong_t driver_data; }; #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, \ valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ .probe_table = fn, \ .driver_data = data, \ } #define ACPI_DECLARE_SUBTABLE_PROBE_ENTRY(table, name, table_id, \ subtable, valid, data, fn) \ static const struct acpi_probe_entry __acpi_probe_##name \ __used __section("__" #table "_acpi_probe_table") = { \ .id = table_id, \ .type = subtable, \ .subtable_valid = valid, \ .probe_subtbl = fn, \ .driver_data = data, \ } #define ACPI_PROBE_TABLE(name) __##name##_acpi_probe_table #define ACPI_PROBE_TABLE_END(name) __##name##_acpi_probe_table_end int __acpi_probe_device_table(struct acpi_probe_entry *start, int nr); #define acpi_probe_device_table(t) \ ({ \ extern struct acpi_probe_entry ACPI_PROBE_TABLE(t), \ ACPI_PROBE_TABLE_END(t); \ __acpi_probe_device_table(&ACPI_PROBE_TABLE(t), \ (&ACPI_PROBE_TABLE_END(t) - \ &ACPI_PROBE_TABLE(t))); \ }) #else static inline int acpi_dev_get_property(struct acpi_device *adev, const char *name, acpi_object_type type, const union acpi_object **obj) { return -ENXIO; } static inline int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, size_t num_args, struct fwnode_reference_args *args) { return -ENXIO; } static inline int acpi_node_get_property_reference(const struct fwnode_handle *fwnode, const char *name, size_t index, struct fwnode_reference_args *args) { return -ENXIO; } static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname, void **valptr) { return -ENXIO; } static inline struct fwnode_handle * acpi_get_next_subnode(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { return NULL; } static inline struct fwnode_handle * acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle *prev) { return ERR_PTR(-ENXIO); } static inline int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode, struct fwnode_handle **remote, struct fwnode_handle **port, struct fwnode_handle **endpoint) { return -ENXIO; } #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ static const void * __acpi_table_##name[] \ __attribute__((unused)) \ = { (void *) table_id, \ (void *) subtable, \ (void *) valid, \ (void *) fn, \ (void *) data } #define acpi_probe_device_table(t) ({ int __r = 0; __r;}) #endif #ifdef CONFIG_ACPI_TABLE_UPGRADE void acpi_table_upgrade(void); #else static inline void acpi_table_upgrade(void) { } #endif #if defined(CONFIG_ACPI) && defined(CONFIG_ACPI_WATCHDOG) extern bool acpi_has_watchdog(void); #else static inline bool acpi_has_watchdog(void) { return false; } #endif #ifdef CONFIG_ACPI_SPCR_TABLE extern bool qdf2400_e44_present; int acpi_parse_spcr(bool enable_earlycon, bool enable_console); #else static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console) { return 0; } #endif #if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res); #else static inline int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) { return -EINVAL; } #endif #ifdef CONFIG_ACPI_LPIT int lpit_read_residency_count_address(u64 *address); #else static inline int lpit_read_residency_count_address(u64 *address) { return -EINVAL; } #endif #ifdef CONFIG_ACPI_PROCESSOR_IDLE #ifndef arch_get_idle_state_flags static inline unsigned int arch_get_idle_state_flags(u32 arch_flags) { return 0; } #endif #endif /* CONFIG_ACPI_PROCESSOR_IDLE */ #ifdef CONFIG_ACPI_PPTT int acpi_pptt_cpu_is_thread(unsigned int cpu); int find_acpi_cpu_topology(unsigned int cpu, int level); int find_acpi_cpu_topology_cluster(unsigned int cpu); int find_acpi_cpu_topology_package(unsigned int cpu); int find_acpi_cpu_topology_hetero_id(unsigned int cpu); #else static inline int acpi_pptt_cpu_is_thread(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology(unsigned int cpu, int level) { return -EINVAL; } static inline int find_acpi_cpu_topology_cluster(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology_package(unsigned int cpu) { return -EINVAL; } static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu) { return -EINVAL; } #endif #ifdef CONFIG_ARM64 void acpi_arm_init(void); #else static inline void acpi_arm_init(void) { } #endif #ifdef CONFIG_ACPI_PCC void acpi_init_pcc(void); #else static inline void acpi_init_pcc(void) { } #endif #ifdef CONFIG_ACPI_FFH void acpi_init_ffh(void); extern int acpi_ffh_address_space_arch_setup(void *handler_ctxt, void **region_ctxt); extern int acpi_ffh_address_space_arch_handler(acpi_integer *value, void *region_context); #else static inline void acpi_init_ffh(void) { } #endif #ifdef CONFIG_ACPI extern void acpi_device_notify(struct device *dev); extern void acpi_device_notify_remove(struct device *dev); #else static inline void acpi_device_notify(struct device *dev) { } static inline void acpi_device_notify_remove(struct device *dev) { } #endif static inline void acpi_use_parent_companion(struct device *dev) { ACPI_COMPANION_SET(dev, ACPI_COMPANION(dev->parent)); } #ifdef CONFIG_ACPI_HMAT int hmat_update_target_coordinates(int nid, struct access_coordinate *coord, enum access_coordinate_class access); #else static inline int hmat_update_target_coordinates(int nid, struct access_coordinate *coord, enum access_coordinate_class access) { return -EOPNOTSUPP; } #endif #ifdef CONFIG_ACPI_NUMA bool acpi_node_backed_by_real_pxm(int nid); #else static inline bool acpi_node_backed_by_real_pxm(int nid) { return false; } #endif #endif /*_LINUX_ACPI_H*/ |
| 1 1 1 1 | 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 | // SPDX-License-Identifier: GPL-2.0-only /* * OCB mode implementation * * Copyright: (c) 2014 Czech Technical University in Prague * (c) 2014 Volkswagen Group Research * Copyright (C) 2022 - 2023 Intel Corporation * Author: Rostislav Lisovy <rostislav.lisovy@fel.cvut.cz> * Funded by: Volkswagen Group Research */ #include <linux/delay.h> #include <linux/if_ether.h> #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <net/mac80211.h> #include <asm/unaligned.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" #define IEEE80211_OCB_HOUSEKEEPING_INTERVAL (60 * HZ) #define IEEE80211_OCB_PEER_INACTIVITY_LIMIT (240 * HZ) #define IEEE80211_OCB_MAX_STA_ENTRIES 128 /** * enum ocb_deferred_task_flags - mac80211 OCB deferred tasks * @OCB_WORK_HOUSEKEEPING: run the periodic OCB housekeeping tasks * * These flags are used in @wrkq_flags field of &struct ieee80211_if_ocb */ enum ocb_deferred_task_flags { OCB_WORK_HOUSEKEEPING, }; void ieee80211_ocb_rx_no_sta(struct ieee80211_sub_if_data *sdata, const u8 *bssid, const u8 *addr, u32 supp_rates) { struct ieee80211_if_ocb *ifocb = &sdata->u.ocb; struct ieee80211_local *local = sdata->local; struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_supported_band *sband; struct sta_info *sta; int band; /* XXX: Consider removing the least recently used entry and * allow new one to be added. */ if (local->num_sta >= IEEE80211_OCB_MAX_STA_ENTRIES) { net_info_ratelimited("%s: No room for a new OCB STA entry %pM\n", sdata->name, addr); return; } ocb_dbg(sdata, "Adding new OCB station %pM\n", addr); rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf); if (WARN_ON_ONCE(!chanctx_conf)) { rcu_read_unlock(); return; } band = chanctx_conf->def.chan->band; rcu_read_unlock(); sta = sta_info_alloc(sdata, addr, GFP_ATOMIC); if (!sta) return; /* Add only mandatory rates for now */ sband = local->hw.wiphy->bands[band]; sta->sta.deflink.supp_rates[band] = ieee80211_mandatory_rates(sband); spin_lock(&ifocb->incomplete_lock); list_add(&sta->list, &ifocb->incomplete_stations); spin_unlock(&ifocb->incomplete_lock); wiphy_work_queue(local->hw.wiphy, &sdata->work); } static struct sta_info *ieee80211_ocb_finish_sta(struct sta_info *sta) __acquires(RCU) { struct ieee80211_sub_if_data *sdata = sta->sdata; u8 addr[ETH_ALEN]; memcpy(addr, sta->sta.addr, ETH_ALEN); ocb_dbg(sdata, "Adding new IBSS station %pM (dev=%s)\n", addr, sdata->name); sta_info_move_state(sta, IEEE80211_STA_AUTH); sta_info_move_state(sta, IEEE80211_STA_ASSOC); sta_info_move_state(sta, IEEE80211_STA_AUTHORIZED); rate_control_rate_init(sta); /* If it fails, maybe we raced another insertion? */ if (sta_info_insert_rcu(sta)) return sta_info_get(sdata, addr); return sta; } static void ieee80211_ocb_housekeeping(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ocb *ifocb = &sdata->u.ocb; ocb_dbg(sdata, "Running ocb housekeeping\n"); ieee80211_sta_expire(sdata, IEEE80211_OCB_PEER_INACTIVITY_LIMIT); mod_timer(&ifocb->housekeeping_timer, round_jiffies(jiffies + IEEE80211_OCB_HOUSEKEEPING_INTERVAL)); } void ieee80211_ocb_work(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ocb *ifocb = &sdata->u.ocb; struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (ifocb->joined != true) return; spin_lock_bh(&ifocb->incomplete_lock); while (!list_empty(&ifocb->incomplete_stations)) { sta = list_first_entry(&ifocb->incomplete_stations, struct sta_info, list); list_del(&sta->list); spin_unlock_bh(&ifocb->incomplete_lock); ieee80211_ocb_finish_sta(sta); rcu_read_unlock(); spin_lock_bh(&ifocb->incomplete_lock); } spin_unlock_bh(&ifocb->incomplete_lock); if (test_and_clear_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags)) ieee80211_ocb_housekeeping(sdata); } static void ieee80211_ocb_housekeeping_timer(struct timer_list *t) { struct ieee80211_sub_if_data *sdata = from_timer(sdata, t, u.ocb.housekeeping_timer); struct ieee80211_local *local = sdata->local; struct ieee80211_if_ocb *ifocb = &sdata->u.ocb; set_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags); wiphy_work_queue(local->hw.wiphy, &sdata->work); } void ieee80211_ocb_setup_sdata(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ocb *ifocb = &sdata->u.ocb; timer_setup(&ifocb->housekeeping_timer, ieee80211_ocb_housekeeping_timer, 0); INIT_LIST_HEAD(&ifocb->incomplete_stations); spin_lock_init(&ifocb->incomplete_lock); } int ieee80211_ocb_join(struct ieee80211_sub_if_data *sdata, struct ocb_setup *setup) { struct ieee80211_chan_req chanreq = { .oper = setup->chandef }; struct ieee80211_local *local = sdata->local; struct ieee80211_if_ocb *ifocb = &sdata->u.ocb; u64 changed = BSS_CHANGED_OCB | BSS_CHANGED_BSSID; int err; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (ifocb->joined == true) return -EINVAL; sdata->deflink.operating_11g_mode = true; sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; sdata->deflink.needed_rx_chains = sdata->local->rx_chains; err = ieee80211_link_use_channel(&sdata->deflink, &chanreq, IEEE80211_CHANCTX_SHARED); if (err) return err; ieee80211_bss_info_change_notify(sdata, changed); ifocb->joined = true; set_bit(OCB_WORK_HOUSEKEEPING, &ifocb->wrkq_flags); wiphy_work_queue(local->hw.wiphy, &sdata->work); netif_carrier_on(sdata->dev); return 0; } int ieee80211_ocb_leave(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_ocb *ifocb = &sdata->u.ocb; struct ieee80211_local *local = sdata->local; struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); ifocb->joined = false; sta_info_flush(sdata, -1); spin_lock_bh(&ifocb->incomplete_lock); while (!list_empty(&ifocb->incomplete_stations)) { sta = list_first_entry(&ifocb->incomplete_stations, struct sta_info, list); list_del(&sta->list); spin_unlock_bh(&ifocb->incomplete_lock); sta_info_free(local, sta); spin_lock_bh(&ifocb->incomplete_lock); } spin_unlock_bh(&ifocb->incomplete_lock); netif_carrier_off(sdata->dev); clear_bit(SDATA_STATE_OFFCHANNEL, &sdata->state); ieee80211_bss_info_change_notify(sdata, BSS_CHANGED_OCB); ieee80211_link_release_channel(&sdata->deflink); skb_queue_purge(&sdata->skb_queue); del_timer_sync(&sdata->u.ocb.housekeeping_timer); /* If the timer fired while we waited for it, it will have * requeued the work. Now the work will be running again * but will not rearm the timer again because it checks * whether we are connected to the network or not -- at this * point we shouldn't be anymore. */ return 0; } |
| 2 5 12630 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/limits.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #ifdef CONFIG_GENERIC_ENTRY enum syscall_work_bit { SYSCALL_WORK_BIT_SECCOMP, SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT, SYSCALL_WORK_BIT_SYSCALL_TRACE, SYSCALL_WORK_BIT_SYSCALL_EMU, SYSCALL_WORK_BIT_SYSCALL_AUDIT, SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH, SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP, }; #define SYSCALL_WORK_SECCOMP BIT(SYSCALL_WORK_BIT_SECCOMP) #define SYSCALL_WORK_SYSCALL_TRACEPOINT BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT) #define SYSCALL_WORK_SYSCALL_TRACE BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE) #define SYSCALL_WORK_SYSCALL_EMU BIT(SYSCALL_WORK_BIT_SYSCALL_EMU) #define SYSCALL_WORK_SYSCALL_AUDIT BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT) #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH) #define SYSCALL_WORK_SYSCALL_EXIT_TRAP BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP) #endif #include <asm/thread_info.h> #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } /* * This may be used in noinstr code, and needs to be __always_inline to prevent * inadvertent instrumentation. */ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti) { return READ_ONCE(ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define read_thread_flags() \ read_ti_thread_flags(current_thread_info()) #define read_task_thread_flags(t) \ read_ti_thread_flags(task_thread_info(t)) #ifdef CONFIG_GENERIC_ENTRY #define set_syscall_work(fl) \ set_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define test_syscall_work(fl) \ test_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define clear_syscall_work(fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define set_task_syscall_work(t, fl) \ set_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define test_task_syscall_work(t, fl) \ test_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define clear_task_syscall_work(t, fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #else /* CONFIG_GENERIC_ENTRY */ #define set_syscall_work(fl) \ set_ti_thread_flag(current_thread_info(), TIF_##fl) #define test_syscall_work(fl) \ test_ti_thread_flag(current_thread_info(), TIF_##fl) #define clear_syscall_work(fl) \ clear_ti_thread_flag(current_thread_info(), TIF_##fl) #define set_task_syscall_work(t, fl) \ set_ti_thread_flag(task_thread_info(t), TIF_##fl) #define test_task_syscall_work(t, fl) \ test_ti_thread_flag(task_thread_info(t), TIF_##fl) #define clear_task_syscall_work(t, fl) \ clear_ti_thread_flag(task_thread_info(t), TIF_##fl) #endif /* !CONFIG_GENERIC_ENTRY */ #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H static __always_inline bool tif_need_resched(void) { return arch_test_bit(TIF_NEED_RESCHED, (unsigned long *)(¤t_thread_info()->flags)); } #else static __always_inline bool tif_need_resched(void) { return test_bit(TIF_NEED_RESCHED, (unsigned long *)(¤t_thread_info()->flags)); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifdef CONFIG_HARDENED_USERCOPY extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); static __always_inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { } #endif /* CONFIG_HARDENED_USERCOPY */ extern void __compiletime_error("copy source size is too small") __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); void __copy_overflow(int size, unsigned long count); static inline void copy_overflow(int size, unsigned long count) { if (IS_ENABLED(CONFIG_BUG)) __copy_overflow(size, count); } static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __builtin_object_size(addr, 0); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); else if (is_source) __bad_copy_from(); else __bad_copy_to(); return false; } if (WARN_ON_ONCE(bytes > INT_MAX)) return false; check_object_size(addr, bytes, is_source); return true; } #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif void arch_task_cache_init(void); /* for CONFIG_SH */ void arch_release_task_struct(struct task_struct *tsk); int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ |
| 353 40 17 40 28 28 34 17 34 28 1948 53 94 139 1991 1961 185 34 2 8 31 13 61 2183 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 | /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */ #ifndef _LINUX_BPF_H #define _LINUX_BPF_H 1 #include <uapi/linux/bpf.h> #include <uapi/linux/filter.h> #include <linux/workqueue.h> #include <linux/file.h> #include <linux/percpu.h> #include <linux/err.h> #include <linux/rbtree_latch.h> #include <linux/numa.h> #include <linux/mm_types.h> #include <linux/wait.h> #include <linux/refcount.h> #include <linux/mutex.h> #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/capability.h> #include <linux/sched/mm.h> #include <linux/slab.h> #include <linux/percpu-refcount.h> #include <linux/stddef.h> #include <linux/bpfptr.h> #include <linux/btf.h> #include <linux/rcupdate_trace.h> #include <linux/static_call.h> #include <linux/memcontrol.h> #include <linux/cfi.h> struct bpf_verifier_env; struct bpf_verifier_log; struct perf_event; struct bpf_prog; struct bpf_prog_aux; struct bpf_map; struct bpf_arena; struct sock; struct seq_file; struct btf; struct btf_type; struct exception_table_entry; struct seq_operations; struct bpf_iter_aux_info; struct bpf_local_storage; struct bpf_local_storage_map; struct kobject; struct mem_cgroup; struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; struct bpf_token; struct user_namespace; struct super_block; struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma; extern bool bpf_global_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_fini_seq_priv_t)(void *private_data); typedef unsigned int (*bpf_func_t)(const void *, const struct bpf_insn *); struct bpf_iter_seq_info { const struct seq_operations *seq_ops; bpf_iter_init_seq_priv_t init_seq_private; bpf_iter_fini_seq_priv_t fini_seq_private; u32 seq_priv_size; }; /* map is generic key/value storage optionally accessible by eBPF programs */ struct bpf_map_ops { /* funcs callable from userspace (via syscall) */ int (*map_alloc_check)(union bpf_attr *attr); struct bpf_map *(*map_alloc)(union bpf_attr *attr); void (*map_release)(struct bpf_map *map, struct file *map_file); void (*map_free)(struct bpf_map *map); int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key); void (*map_release_uref)(struct bpf_map *map); void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key); int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_lookup_and_delete_elem)(struct bpf_map *map, void *key, void *value, u64 flags); int (*map_lookup_and_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_update_batch)(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr); int (*map_delete_batch)(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); /* funcs callable from userspace and from eBPF programs */ void *(*map_lookup_elem)(struct bpf_map *map, void *key); long (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags); long (*map_delete_elem)(struct bpf_map *map, void *key); long (*map_push_elem)(struct bpf_map *map, void *value, u64 flags); long (*map_pop_elem)(struct bpf_map *map, void *value); long (*map_peek_elem)(struct bpf_map *map, void *value); void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu); /* funcs called by prog_array and perf_event_array map */ void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file, int fd); /* If need_defer is true, the implementation should guarantee that * the to-be-put element is still alive before the bpf program, which * may manipulate it, exists. */ void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer); int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); void (*map_seq_show_elem)(struct bpf_map *map, void *key, struct seq_file *m); int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); /* Prog poke tracking helpers. */ int (*map_poke_track)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_untrack)(struct bpf_map *map, struct bpf_prog_aux *aux); void (*map_poke_run)(struct bpf_map *map, u32 key, struct bpf_prog *old, struct bpf_prog *new); /* Direct value access helpers. */ int (*map_direct_value_addr)(const struct bpf_map *map, u64 *imm, u32 off); int (*map_direct_value_meta)(const struct bpf_map *map, u64 imm, u32 *off); int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma); __poll_t (*map_poll)(struct bpf_map *map, struct file *filp, struct poll_table_struct *pts); unsigned long (*map_get_unmapped_area)(struct file *filep, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* Functions called by bpf_local_storage maps */ int (*map_local_storage_charge)(struct bpf_local_storage_map *smap, void *owner, u32 size); void (*map_local_storage_uncharge)(struct bpf_local_storage_map *smap, void *owner, u32 size); struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ long (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); /* map_meta_equal must be implemented for maps that can be * used as an inner map. It is a runtime check to ensure * an inner map can be inserted to an outer map. * * Some properties of the inner map has been used during the * verification time. When inserting an inner map at the runtime, * map_meta_equal has to ensure the inserting map has the same * properties that the verifier has used earlier. */ bool (*map_meta_equal)(const struct bpf_map *meta0, const struct bpf_map *meta1); int (*map_set_for_each_callback_args)(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); long (*map_for_each_callback)(struct bpf_map *map, bpf_callback_t callback_fn, void *callback_ctx, u64 flags); u64 (*map_mem_usage)(const struct bpf_map *map); /* BTF id of struct allocated by map_alloc */ int *map_btf_id; /* bpf_iter info used to open a seq_file */ const struct bpf_iter_seq_info *iter_seq_info; }; enum { /* Support at most 11 fields in a BTF type */ BTF_FIELDS_MAX = 11, }; enum btf_field_type { BPF_SPIN_LOCK = (1 << 0), BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), BPF_KPTR_PERCPU = (1 << 4), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU, BPF_LIST_HEAD = (1 << 5), BPF_LIST_NODE = (1 << 6), BPF_RB_ROOT = (1 << 7), BPF_RB_NODE = (1 << 8), BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE, BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD, BPF_REFCOUNT = (1 << 9), BPF_WORKQUEUE = (1 << 10), }; typedef void (*btf_dtor_kfunc_t)(void *); struct btf_field_kptr { struct btf *btf; struct module *module; /* dtor used if btf_is_kernel(btf), otherwise the type is * program-allocated, dtor is NULL, and __bpf_obj_drop_impl is used */ btf_dtor_kfunc_t dtor; u32 btf_id; }; struct btf_field_graph_root { struct btf *btf; u32 value_btf_id; u32 node_offset; struct btf_record *value_rec; }; struct btf_field { u32 offset; u32 size; enum btf_field_type type; union { struct btf_field_kptr kptr; struct btf_field_graph_root graph_root; }; }; struct btf_record { u32 cnt; u32 field_mask; int spin_lock_off; int timer_off; int wq_off; int refcount_off; struct btf_field fields[]; }; /* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */ struct bpf_rb_node_kern { struct rb_node rb_node; void *owner; } __attribute__((aligned(8))); /* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */ struct bpf_list_node_kern { struct list_head list_head; void *owner; } __attribute__((aligned(8))); struct bpf_map { const struct bpf_map_ops *ops; struct bpf_map *inner_map_meta; #ifdef CONFIG_SECURITY void *security; #endif enum bpf_map_type map_type; u32 key_size; u32 value_size; u32 max_entries; u64 map_extra; /* any per-map-type extra fields */ u32 map_flags; u32 id; struct btf_record *record; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; u32 btf_vmlinux_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif char name[BPF_OBJ_NAME_LEN]; struct mutex freeze_mutex; atomic64_t refcnt; atomic64_t usercnt; /* rcu is used before freeing and work is only used during freeing */ union { struct work_struct work; struct rcu_head rcu; }; atomic64_t writecnt; /* 'Ownership' of program-containing map is claimed by the first program * that is going to use this map or by the first program which FD is * stored in the map to make sure that all callers and callees have the * same prog type, JITed flag and xdp_has_frags flag. */ struct { spinlock_t lock; enum bpf_prog_type type; bool jited; bool xdp_has_frags; } owner; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ bool free_after_mult_rcu_gp; bool free_after_rcu_gp; atomic64_t sleepable_refcnt; s64 __percpu *elem_count; }; static inline const char *btf_field_type_name(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return "bpf_spin_lock"; case BPF_TIMER: return "bpf_timer"; case BPF_WORKQUEUE: return "bpf_wq"; case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; case BPF_KPTR_PERCPU: return "percpu_kptr"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: return "bpf_list_node"; case BPF_RB_ROOT: return "bpf_rb_root"; case BPF_RB_NODE: return "bpf_rb_node"; case BPF_REFCOUNT: return "bpf_refcount"; default: WARN_ON_ONCE(1); return "unknown"; } } static inline u32 btf_field_type_size(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return sizeof(struct bpf_spin_lock); case BPF_TIMER: return sizeof(struct bpf_timer); case BPF_WORKQUEUE: return sizeof(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); case BPF_LIST_NODE: return sizeof(struct bpf_list_node); case BPF_RB_ROOT: return sizeof(struct bpf_rb_root); case BPF_RB_NODE: return sizeof(struct bpf_rb_node); case BPF_REFCOUNT: return sizeof(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; } } static inline u32 btf_field_type_align(enum btf_field_type type) { switch (type) { case BPF_SPIN_LOCK: return __alignof__(struct bpf_spin_lock); case BPF_TIMER: return __alignof__(struct bpf_timer); case BPF_WORKQUEUE: return __alignof__(struct bpf_wq); case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); case BPF_LIST_NODE: return __alignof__(struct bpf_list_node); case BPF_RB_ROOT: return __alignof__(struct bpf_rb_root); case BPF_RB_NODE: return __alignof__(struct bpf_rb_node); case BPF_REFCOUNT: return __alignof__(struct bpf_refcount); default: WARN_ON_ONCE(1); return 0; } } static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) { memset(addr, 0, field->size); switch (field->type) { case BPF_REFCOUNT: refcount_set((refcount_t *)addr, 1); break; case BPF_RB_NODE: RB_CLEAR_NODE((struct rb_node *)addr); break; case BPF_LIST_HEAD: case BPF_LIST_NODE: INIT_LIST_HEAD((struct list_head *)addr); break; case BPF_RB_ROOT: /* RB_ROOT_CACHED 0-inits, no need to do anything after memset */ case BPF_SPIN_LOCK: case BPF_TIMER: case BPF_WORKQUEUE: case BPF_KPTR_UNREF: case BPF_KPTR_REF: case BPF_KPTR_PERCPU: break; default: WARN_ON_ONCE(1); return; } } static inline bool btf_record_has_field(const struct btf_record *rec, enum btf_field_type type) { if (IS_ERR_OR_NULL(rec)) return false; return rec->field_mask & type; } static inline void bpf_obj_init(const struct btf_record *rec, void *obj) { int i; if (IS_ERR_OR_NULL(rec)) return; for (i = 0; i < rec->cnt; i++) bpf_obj_init_field(&rec->fields[i], obj + rec->fields[i].offset); } /* 'dst' must be a temporary buffer and should not point to memory that is being * used in parallel by a bpf program or bpf syscall, otherwise the access from * the bpf program or bpf syscall may be corrupted by the reinitialization, * leading to weird problems. Even 'dst' is newly-allocated from bpf memory * allocator, it is still possible for 'dst' to be used in parallel by a bpf * program or bpf syscall. */ static inline void check_and_init_map_value(struct bpf_map *map, void *dst) { bpf_obj_init(map->record, dst); } /* memcpy that is used with 8-byte aligned pointers, power-of-8 size and * forced to use 'long' read/writes to try to atomically copy long counters. * Best-effort only. No barriers here, since it _will_ race with concurrent * updates from BPF programs. Called from bpf syscall and mostly used with * size 8 or 16 bytes, so ask compiler to inline it. */ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size) { const long *lsrc = src; long *ldst = dst; size /= sizeof(long); while (size--) data_race(*ldst++ = *lsrc++); } /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */ static inline void bpf_obj_memcpy(struct btf_record *rec, void *dst, void *src, u32 size, bool long_memcpy) { u32 curr_off = 0; int i; if (IS_ERR_OR_NULL(rec)) { if (long_memcpy) bpf_long_memcpy(dst, src, round_up(size, 8)); else memcpy(dst, src, size); return; } for (i = 0; i < rec->cnt; i++) { u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memcpy(dst + curr_off, src + curr_off, sz); curr_off += rec->fields[i].size + sz; } memcpy(dst + curr_off, src + curr_off, size - curr_off); } static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) { bpf_obj_memcpy(map->record, dst, src, map->value_size, false); } static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src) { bpf_obj_memcpy(map->record, dst, src, map->value_size, true); } static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size) { u32 curr_off = 0; int i; if (IS_ERR_OR_NULL(rec)) { memset(dst, 0, size); return; } for (i = 0; i < rec->cnt; i++) { u32 next_off = rec->fields[i].offset; u32 sz = next_off - curr_off; memset(dst + curr_off, 0, sz); curr_off += rec->fields[i].size + sz; } memset(dst + curr_off, 0, size - curr_off); } static inline void zero_map_value(struct bpf_map *map, void *dst) { bpf_obj_memzero(map->record, dst, map->value_size); } void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); void bpf_wq_cancel_and_free(void *timer); void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock); void bpf_rb_root_free(const struct btf_field *field, void *rb_root, struct bpf_spin_lock *spin_lock); u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena); u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena); int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; struct bpf_offloaded_map; struct bpf_map_dev_ops { int (*map_get_next_key)(struct bpf_offloaded_map *map, void *key, void *next_key); int (*map_lookup_elem)(struct bpf_offloaded_map *map, void *key, void *value); int (*map_update_elem)(struct bpf_offloaded_map *map, void *key, void *value, u64 flags); int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key); }; struct bpf_offloaded_map { struct bpf_map map; struct net_device *netdev; const struct bpf_map_dev_ops *dev_ops; void *dev_priv; struct list_head offloads; }; static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) { return container_of(map, struct bpf_offloaded_map, map); } static inline bool bpf_map_offload_neutral(const struct bpf_map *map) { return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; } static inline bool bpf_map_support_seq_show(const struct bpf_map *map) { return (map->btf_value_type_id || map->btf_vmlinux_value_type_id) && map->ops->map_seq_show_elem; } int map_check_no_btf(const struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type); bool bpf_map_meta_equal(const struct bpf_map *meta0, const struct bpf_map *meta1); extern const struct bpf_map_ops bpf_map_offload_ops; /* bpf_type_flag contains a set of flags that are applicable to the values of * arg_type, ret_type and reg_type. For example, a pointer value may be null, * or a memory is read-only. We classify types into two categories: base types * and extended types. Extended types are base types combined with a type flag. * * Currently there are no more than 32 base types in arg_type, ret_type and * reg_types. */ #define BPF_BASE_TYPE_BITS 8 enum bpf_type_flag { /* PTR may be NULL. */ PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS), /* MEM is read-only. When applied on bpf_arg, it indicates the arg is * compatible with both mutable and immutable memory. */ MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), /* MEM points to BPF ring buffer reservation. */ MEM_RINGBUF = BIT(2 + BPF_BASE_TYPE_BITS), /* MEM is in user address space. */ MEM_USER = BIT(3 + BPF_BASE_TYPE_BITS), /* MEM is a percpu memory. MEM_PERCPU tags PTR_TO_BTF_ID. When tagged * with MEM_PERCPU, PTR_TO_BTF_ID _cannot_ be directly accessed. In * order to drop this tag, it must be passed into bpf_per_cpu_ptr() * or bpf_this_cpu_ptr(), which will return the pointer corresponding * to the specified cpu. */ MEM_PERCPU = BIT(4 + BPF_BASE_TYPE_BITS), /* Indicates that the argument will be released. */ OBJ_RELEASE = BIT(5 + BPF_BASE_TYPE_BITS), /* PTR is not trusted. This is only used with PTR_TO_BTF_ID, to mark * unreferenced and referenced kptr loaded from map value using a load * instruction, so that they can only be dereferenced but not escape the * BPF program into the kernel (i.e. cannot be passed as arguments to * kfunc or bpf helpers). */ PTR_UNTRUSTED = BIT(6 + BPF_BASE_TYPE_BITS), MEM_UNINIT = BIT(7 + BPF_BASE_TYPE_BITS), /* DYNPTR points to memory local to the bpf program. */ DYNPTR_TYPE_LOCAL = BIT(8 + BPF_BASE_TYPE_BITS), /* DYNPTR points to a kernel-produced ringbuf record. */ DYNPTR_TYPE_RINGBUF = BIT(9 + BPF_BASE_TYPE_BITS), /* Size is known at compile time. */ MEM_FIXED_SIZE = BIT(10 + BPF_BASE_TYPE_BITS), /* MEM is of an allocated object of type in program BTF. This is used to * tag PTR_TO_BTF_ID allocated using bpf_obj_new. */ MEM_ALLOC = BIT(11 + BPF_BASE_TYPE_BITS), /* PTR was passed from the kernel in a trusted context, and may be * passed to KF_TRUSTED_ARGS kfuncs or BPF helper functions. * Confusingly, this is _not_ the opposite of PTR_UNTRUSTED above. * PTR_UNTRUSTED refers to a kptr that was read directly from a map * without invoking bpf_kptr_xchg(). What we really need to know is * whether a pointer is safe to pass to a kfunc or BPF helper function. * While PTR_UNTRUSTED pointers are unsafe to pass to kfuncs and BPF * helpers, they do not cover all possible instances of unsafe * pointers. For example, a pointer that was obtained from walking a * struct will _not_ get the PTR_UNTRUSTED type modifier, despite the * fact that it may be NULL, invalid, etc. This is due to backwards * compatibility requirements, as this was the behavior that was first * introduced when kptrs were added. The behavior is now considered * deprecated, and PTR_UNTRUSTED will eventually be removed. * * PTR_TRUSTED, on the other hand, is a pointer that the kernel * guarantees to be valid and safe to pass to kfuncs and BPF helpers. * For example, pointers passed to tracepoint arguments are considered * PTR_TRUSTED, as are pointers that are passed to struct_ops * callbacks. As alluded to above, pointers that are obtained from * walking PTR_TRUSTED pointers are _not_ trusted. For example, if a * struct task_struct *task is PTR_TRUSTED, then accessing * task->last_wakee will lose the PTR_TRUSTED modifier when it's stored * in a BPF register. Similarly, pointers passed to certain programs * types such as kretprobes are not guaranteed to be valid, as they may * for example contain an object that was recently freed. */ PTR_TRUSTED = BIT(12 + BPF_BASE_TYPE_BITS), /* MEM is tagged with rcu and memory access needs rcu_read_lock protection. */ MEM_RCU = BIT(13 + BPF_BASE_TYPE_BITS), /* Used to tag PTR_TO_BTF_ID | MEM_ALLOC references which are non-owning. * Currently only valid for linked-list and rbtree nodes. If the nodes * have a bpf_refcount_field, they must be tagged MEM_RCU as well. */ NON_OWN_REF = BIT(14 + BPF_BASE_TYPE_BITS), /* DYNPTR points to sk_buff */ DYNPTR_TYPE_SKB = BIT(15 + BPF_BASE_TYPE_BITS), /* DYNPTR points to xdp_buff */ DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS), __BPF_TYPE_FLAG_MAX, __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1, }; #define DYNPTR_TYPE_FLAG_MASK (DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \ | DYNPTR_TYPE_XDP) /* Max number of base types. */ #define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) /* Max number of all types. */ #define BPF_TYPE_LIMIT (__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1)) /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ /* the following constraints used to prototype * bpf_map_lookup/update/delete_elem() functions */ ARG_CONST_MAP_PTR, /* const argument used as pointer to bpf_map */ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ /* Used to prototype bpf_memcmp() and other functions that access data * on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ ARG_PTR_TO_ARENA, ARG_CONST_SIZE, /* number of bytes accessed from memory */ ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_RINGBUF_MEM, /* pointer to dynamically reserved ringbuf memory */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ ARG_PTR_TO_KPTR, /* pointer to referenced kptr */ ARG_PTR_TO_DYNPTR, /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */ __BPF_ARG_TYPE_MAX, /* Extended arg_types. */ ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE, ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM, ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX, ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, ARG_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID, /* pointer to memory does not need to be initialized, helper function must fill * all bytes or clear them in error case. */ ARG_PTR_TO_UNINIT_MEM = MEM_UNINIT | ARG_PTR_TO_MEM, /* Pointer to valid memory of size known at compile time. */ ARG_PTR_TO_FIXED_SIZE_MEM = MEM_FIXED_SIZE | ARG_PTR_TO_MEM, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_ARG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* type of values returned from helper functions */ enum bpf_return_type { RET_INTEGER, /* function returns integer */ RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_SOCKET, /* returns a pointer to a socket */ RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */ RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */ RET_PTR_TO_MEM, /* returns a pointer to memory */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ __BPF_RET_TYPE_MAX, /* Extended ret_types. */ RET_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE, RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, RET_PTR_TO_RINGBUF_MEM_OR_NULL = PTR_MAYBE_NULL | MEM_RINGBUF | RET_PTR_TO_MEM, RET_PTR_TO_DYNPTR_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MEM, RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, RET_PTR_TO_BTF_ID_TRUSTED = PTR_TRUSTED | RET_PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_RET_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL * instructions after verifying */ struct bpf_func_proto { u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); bool gpl_only; bool pkt_access; bool might_sleep; enum bpf_return_type ret_type; union { struct { enum bpf_arg_type arg1_type; enum bpf_arg_type arg2_type; enum bpf_arg_type arg3_type; enum bpf_arg_type arg4_type; enum bpf_arg_type arg5_type; }; enum bpf_arg_type arg_type[5]; }; union { struct { u32 *arg1_btf_id; u32 *arg2_btf_id; u32 *arg3_btf_id; u32 *arg4_btf_id; u32 *arg5_btf_id; }; u32 *arg_btf_id[5]; struct { size_t arg1_size; size_t arg2_size; size_t arg3_size; size_t arg4_size; size_t arg5_size; }; size_t arg_size[5]; }; int *ret_btf_id; /* return value btf_id */ bool (*allowed)(const struct bpf_prog *prog); }; /* bpf_context is intentionally undefined structure. Pointer to bpf_context is * the first argument to eBPF programs. * For socket filters: 'struct bpf_context *' == 'struct sk_buff *' */ struct bpf_context; enum bpf_access_type { BPF_READ = 1, BPF_WRITE = 2 }; /* types of values stored in eBPF registers */ /* Pointer types represent: * pointer * pointer + imm * pointer + (u16) var * pointer + (u16) var + imm * if (range > 0) then [ptr, ptr + range - off) is safe to access * if (id > 0) means that some 'var' was added * if (off > 0) means that 'imm' was added */ enum bpf_reg_type { NOT_INIT = 0, /* nothing was written into register */ SCALAR_VALUE, /* reg doesn't contain a valid pointer */ PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ PTR_TO_MAP_KEY, /* reg points to a map element key */ PTR_TO_STACK, /* reg == frame_pointer + offset */ PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ PTR_TO_SOCKET, /* reg points to struct bpf_sock */ PTR_TO_SOCK_COMMON, /* reg points to sock_common */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ /* PTR_TO_BTF_ID points to a kernel struct that does not need * to be null checked by the BPF program. This does not imply the * pointer is _not_ null and in practice this can easily be a null * pointer when reading pointer chains. The assumption is program * context will handle null pointer dereference typically via fault * handling. The verifier must keep this in mind and can make no * assumptions about null or non-null when doing branch analysis. * Further, when passed into helpers the helpers can not, without * additional context, assume the value is non-null. */ PTR_TO_BTF_ID, /* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not * been checked for null. Used primarily to inform the verifier * an explicit null check is required for this struct. */ PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_ARENA, PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_FUNC, /* reg points to a bpf program function */ CONST_PTR_TO_DYNPTR, /* reg points to a const struct bpf_dynptr */ __BPF_REG_TYPE_MAX, /* Extended reg_types. */ PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, /* This must be the last entry. Its purpose is to ensure the enum is * wide enough to hold the higher bits reserved for bpf_type_flag. */ __BPF_REG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* The information passed from prog-specific *_is_valid_access * back to the verifier. */ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; union { int ctx_field_size; struct { struct btf *btf; u32 btf_id; }; }; struct bpf_verifier_log *log; /* for verbose logs */ }; static inline void bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size) { aux->ctx_field_size = size; } static bool bpf_is_ldimm64(const struct bpf_insn *insn) { return insn->code == (BPF_LD | BPF_IMM | BPF_DW); } static inline bool bpf_pseudo_func(const struct bpf_insn *insn) { return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC; } struct bpf_prog_ops { int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); }; struct bpf_reg_state; struct bpf_verifier_ops { /* return eBPF function prototype for verification */ const struct bpf_func_proto * (*get_func_proto)(enum bpf_func_id func_id, const struct bpf_prog *prog); /* return true if 'size' wide access at offset 'off' within bpf_context * with 'type' (read or write) is allowed */ bool (*is_valid_access)(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); int (*gen_ld_abs)(const struct bpf_insn *orig, struct bpf_insn *insn_buf); u32 (*convert_ctx_access)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); }; struct bpf_prog_offload_ops { /* verifier basic callbacks */ int (*insn_hook)(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx); int (*finalize)(struct bpf_verifier_env *env); /* verifier optimization callbacks (called after .finalize) */ int (*replace_insn)(struct bpf_verifier_env *env, u32 off, struct bpf_insn *insn); int (*remove_insns)(struct bpf_verifier_env *env, u32 off, u32 cnt); /* program management callbacks */ int (*prepare)(struct bpf_prog *prog); int (*translate)(struct bpf_prog *prog); void (*destroy)(struct bpf_prog *prog); }; struct bpf_prog_offload { struct bpf_prog *prog; struct net_device *netdev; struct bpf_offload_dev *offdev; void *dev_priv; struct list_head offloads; bool dev_state; bool opt_failed; void *jited_image; u32 jited_len; }; enum bpf_cgroup_storage_type { BPF_CGROUP_STORAGE_SHARED, BPF_CGROUP_STORAGE_PERCPU, __BPF_CGROUP_STORAGE_MAX }; #define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX /* The longest tracepoint has 12 args. * See include/trace/bpf_probe.h */ #define MAX_BPF_FUNC_ARGS 12 /* The maximum number of arguments passed through registers * a single function may have. */ #define MAX_BPF_FUNC_REG_ARGS 5 /* The argument is a structure. */ #define BTF_FMODEL_STRUCT_ARG BIT(0) /* The argument is signed. */ #define BTF_FMODEL_SIGNED_ARG BIT(1) struct btf_func_model { u8 ret_size; u8 ret_flags; u8 nr_args; u8 arg_size[MAX_BPF_FUNC_ARGS]; u8 arg_flags[MAX_BPF_FUNC_ARGS]; }; /* Restore arguments before returning from trampoline to let original function * continue executing. This flag is used for fentry progs when there are no * fexit progs. */ #define BPF_TRAMP_F_RESTORE_REGS BIT(0) /* Call original function after fentry progs, but before fexit progs. * Makes sense for fentry/fexit, normal calls and indirect calls. */ #define BPF_TRAMP_F_CALL_ORIG BIT(1) /* Skip current frame and return to parent. Makes sense for fentry/fexit * programs only. Should not be used with normal calls and indirect calls. */ #define BPF_TRAMP_F_SKIP_FRAME BIT(2) /* Store IP address of the caller on the trampoline stack, * so it's available for trampoline's programs. */ #define BPF_TRAMP_F_IP_ARG BIT(3) /* Return the return value of fentry prog. Only used by bpf_struct_ops. */ #define BPF_TRAMP_F_RET_FENTRY_RET BIT(4) /* Get original function from stack instead of from provided direct address. * Makes sense for trampolines with fexit or fmod_ret programs. */ #define BPF_TRAMP_F_ORIG_STACK BIT(5) /* This trampoline is on a function with another ftrace_ops with IPMODIFY, * e.g., a live patch. This flag is set and cleared by ftrace call backs, */ #define BPF_TRAMP_F_SHARE_IPMODIFY BIT(6) /* Indicate that current trampoline is in a tail call context. Then, it has to * cache and restore tail_call_cnt to avoid infinite tail call loop. */ #define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) /* * Indicate the trampoline should be suitable to receive indirect calls; * without this indirectly calling the generated code can result in #UD/#CP, * depending on the CFI options. * * Used by bpf_struct_ops. * * Incompatible with FENTRY usage, overloads @func_addr argument. */ #define BPF_TRAMP_F_INDIRECT BIT(8) /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ enum { #if defined(__s390x__) BPF_MAX_TRAMP_LINKS = 27, #else BPF_MAX_TRAMP_LINKS = 38, #endif }; struct bpf_tramp_links { struct bpf_tramp_link *links[BPF_MAX_TRAMP_LINKS]; int nr_links; }; struct bpf_tramp_run_ctx; /* Different use cases for BPF trampoline: * 1. replace nop at the function entry (kprobe equivalent) * flags = BPF_TRAMP_F_RESTORE_REGS * fentry = a set of programs to run before returning from trampoline * * 2. replace nop at the function entry (kprobe + kretprobe equivalent) * flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME * orig_call = fentry_ip + MCOUNT_INSN_SIZE * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function * * 3. replace direct call instruction anywhere in the function body * or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid) * With flags = 0 * fentry = a set of programs to run before returning from trampoline * With flags = BPF_TRAMP_F_CALL_ORIG * orig_call = original callback addr or direct function addr * fentry = a set of program to run before calling original function * fexit = a set of program to run after original function */ struct bpf_tramp_image; int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); void *arch_alloc_bpf_trampoline(unsigned int size); void arch_free_bpf_trampoline(void *image, unsigned int size); int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size); int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, struct bpf_tramp_links *tlinks, void *func_addr); u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); void notrace __bpf_tramp_enter(struct bpf_tramp_image *tr); void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr); typedef u64 (*bpf_trampoline_enter_t)(struct bpf_prog *prog, struct bpf_tramp_run_ctx *run_ctx); typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start, struct bpf_tramp_run_ctx *run_ctx); bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog); bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog); struct bpf_ksym { unsigned long start; unsigned long end; char name[KSYM_NAME_LEN]; struct list_head lnode; struct latch_tree_node tnode; bool prog; }; enum bpf_tramp_prog_type { BPF_TRAMP_FENTRY, BPF_TRAMP_FEXIT, BPF_TRAMP_MODIFY_RETURN, BPF_TRAMP_MAX, BPF_TRAMP_REPLACE, /* more than MAX */ }; struct bpf_tramp_image { void *image; int size; struct bpf_ksym ksym; struct percpu_ref pcref; void *ip_after_call; void *ip_epilogue; union { struct rcu_head rcu; struct work_struct work; }; }; struct bpf_trampoline { /* hlist for trampoline_table */ struct hlist_node hlist; struct ftrace_ops *fops; /* serializes access to fields of this trampoline */ struct mutex mutex; refcount_t refcnt; u32 flags; u64 key; struct { struct btf_func_model model; void *addr; bool ftrace_managed; } func; /* if !NULL this is BPF_PROG_TYPE_EXT program that extends another BPF * program by replacing one of its functions. func.addr is the address * of the function it replaced. */ struct bpf_prog *extension_prog; /* list of BPF programs using this trampoline */ struct hlist_head progs_hlist[BPF_TRAMP_MAX]; /* Number of attached programs. A counter per kind. */ int progs_cnt[BPF_TRAMP_MAX]; /* Executable image of trampoline */ struct bpf_tramp_image *cur_image; }; struct bpf_attach_target_info { struct btf_func_model fmodel; long tgt_addr; struct module *tgt_mod; const char *tgt_name; const struct btf_type *tgt_type; }; #define BPF_DISPATCHER_MAX 48 /* Fits in 2048B */ struct bpf_dispatcher_prog { struct bpf_prog *prog; refcount_t users; }; struct bpf_dispatcher { /* dispatcher mutex */ struct mutex mutex; void *func; struct bpf_dispatcher_prog progs[BPF_DISPATCHER_MAX]; int num_progs; void *image; void *rw_image; u32 image_off; struct bpf_ksym ksym; #ifdef CONFIG_HAVE_STATIC_CALL struct static_call_key *sc_key; void *sc_tramp; #endif }; #ifndef __bpfcall #define __bpfcall __nocfi #endif static __always_inline __bpfcall unsigned int bpf_dispatcher_nop_func( const void *ctx, const struct bpf_insn *insnsi, bpf_func_t bpf_func) { return bpf_func(ctx, insnsi); } /* the implementation of the opaque uapi struct bpf_dynptr */ struct bpf_dynptr_kern { void *data; /* Size represents the number of usable bytes of dynptr data. * If for example the offset is at 4 for a local dynptr whose data is * of type u64, the number of usable bytes is 4. * * The upper 8 bits are reserved. It is as follows: * Bits 0 - 23 = size * Bits 24 - 30 = dynptr type * Bit 31 = whether dynptr is read-only */ u32 size; u32 offset; } __aligned(8); enum bpf_dynptr_type { BPF_DYNPTR_TYPE_INVALID, /* Points to memory that is local to the bpf program */ BPF_DYNPTR_TYPE_LOCAL, /* Underlying data is a ringbuf record */ BPF_DYNPTR_TYPE_RINGBUF, /* Underlying data is a sk_buff */ BPF_DYNPTR_TYPE_SKB, /* Underlying data is a xdp_buff */ BPF_DYNPTR_TYPE_XDP, }; int bpf_dynptr_check_size(u32 size); u32 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr); const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u32 len); void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u32 len); bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_JIT int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr); struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info); void bpf_trampoline_put(struct bpf_trampoline *tr); int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs); /* * When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn * indirection with a direct call to the bpf program. If the architecture does * not have STATIC_CALL, avoid a double-indirection. */ #ifdef CONFIG_HAVE_STATIC_CALL #define __BPF_DISPATCHER_SC_INIT(_name) \ .sc_key = &STATIC_CALL_KEY(_name), \ .sc_tramp = STATIC_CALL_TRAMP_ADDR(_name), #define __BPF_DISPATCHER_SC(name) \ DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func) #define __BPF_DISPATCHER_CALL(name) \ static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func) #define __BPF_DISPATCHER_UPDATE(_d, _new) \ __static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new)) #else #define __BPF_DISPATCHER_SC_INIT(name) #define __BPF_DISPATCHER_SC(name) #define __BPF_DISPATCHER_CALL(name) bpf_func(ctx, insnsi) #define __BPF_DISPATCHER_UPDATE(_d, _new) #endif #define BPF_DISPATCHER_INIT(_name) { \ .mutex = __MUTEX_INITIALIZER(_name.mutex), \ .func = &_name##_func, \ .progs = {}, \ .num_progs = 0, \ .image = NULL, \ .image_off = 0, \ .ksym = { \ .name = #_name, \ .lnode = LIST_HEAD_INIT(_name.ksym.lnode), \ }, \ __BPF_DISPATCHER_SC_INIT(_name##_call) \ } #define DEFINE_BPF_DISPATCHER(name) \ __BPF_DISPATCHER_SC(name); \ noinline __bpfcall unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func) \ { \ return __BPF_DISPATCHER_CALL(name); \ } \ EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \ struct bpf_dispatcher bpf_dispatcher_##name = \ BPF_DISPATCHER_INIT(bpf_dispatcher_##name); #define DECLARE_BPF_DISPATCHER(name) \ unsigned int bpf_dispatcher_##name##_func( \ const void *ctx, \ const struct bpf_insn *insnsi, \ bpf_func_t bpf_func); \ extern struct bpf_dispatcher bpf_dispatcher_##name; #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name) void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to); /* Called only from JIT-enabled code, so there's no need for stubs. */ void bpf_image_ksym_add(void *data, unsigned int size, struct bpf_ksym *ksym); void bpf_image_ksym_del(struct bpf_ksym *ksym); void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); int bpf_jit_charge_modmem(u32 size); void bpf_jit_uncharge_modmem(u32 size); bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { return -ENOTSUPP; } static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr) { return -ENOTSUPP; } static inline struct bpf_trampoline *bpf_trampoline_get(u64 key, struct bpf_attach_target_info *tgt_info) { return NULL; } static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {} #define DEFINE_BPF_DISPATCHER(name) #define DECLARE_BPF_DISPATCHER(name) #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_nop_func #define BPF_DISPATCHER_PTR(name) NULL static inline void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from, struct bpf_prog *to) {} static inline bool is_bpf_image_address(unsigned long address) { return false; } static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) { return false; } #endif struct bpf_func_info_aux { u16 linkage; bool unreliable; bool called : 1; bool verified : 1; }; enum bpf_jit_poke_reason { BPF_POKE_REASON_TAIL_CALL, }; /* Descriptor of pokes pointing /into/ the JITed image. */ struct bpf_jit_poke_descriptor { void *tailcall_target; void *tailcall_bypass; void *bypass_addr; void *aux; union { struct { struct bpf_map *map; u32 key; } tail_call; }; bool tailcall_target_stable; u8 adj_off; u16 reason; u32 insn_idx; }; /* reg_type info for ctx arguments */ struct bpf_ctx_arg_aux { u32 offset; enum bpf_reg_type reg_type; struct btf *btf; u32 btf_id; }; struct btf_mod_pair { struct btf *btf; struct module *module; }; struct bpf_kfunc_desc_tab; struct bpf_prog_aux { atomic64_t refcnt; u32 used_map_cnt; u32 used_btf_cnt; u32 max_ctx_offset; u32 max_pkt_offset; u32 max_tp_access; u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 ctx_arg_info_size; u32 max_rdonly_access; u32 max_rdwr_access; struct btf *attach_btf; const struct bpf_ctx_arg_aux *ctx_arg_info; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; struct bpf_trampoline *dst_trampoline; enum bpf_prog_type saved_dst_prog_type; enum bpf_attach_type saved_dst_attach_type; bool verifier_zext; /* Zero extensions has been inserted by verifier. */ bool dev_bound; /* Program is bound to the netdev. */ bool offload_requested; /* Program is bound and offloaded to the netdev. */ bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */ bool attach_tracing_prog; /* true if tracing another tracing program */ bool func_proto_unreliable; bool tail_call_reachable; bool xdp_has_frags; bool exception_cb; bool exception_boundary; struct bpf_arena *arena; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ const char *attach_func_name; struct bpf_prog **func; void *jit_data; /* JIT specific data. arch dependent */ struct bpf_jit_poke_descriptor *poke_tab; struct bpf_kfunc_desc_tab *kfunc_tab; struct bpf_kfunc_btf_tab *kfunc_btf_tab; u32 size_poke_tab; #ifdef CONFIG_FINEIBT struct bpf_ksym ksym_prefix; #endif struct bpf_ksym ksym; const struct bpf_prog_ops *ops; struct bpf_map **used_maps; struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */ struct btf_mod_pair *used_btfs; struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ u32 verified_insns; int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64); #ifdef CONFIG_SECURITY void *security; #endif struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; struct bpf_func_info_aux *func_info_aux; /* bpf_line_info loaded from userspace. linfo->insn_off * has the xlated insn offset. * Both the main and sub prog share the same linfo. * The subprog can access its first linfo by * using the linfo_idx. */ struct bpf_line_info *linfo; /* jited_linfo is the jited addr of the linfo. It has a * one to one mapping to linfo: * jited_linfo[i] is the jited addr for the linfo[i]->insn_off. * Both the main and sub prog share the same jited_linfo. * The subprog can access its first jited_linfo by * using the linfo_idx. */ void **jited_linfo; u32 func_info_cnt; u32 nr_linfo; /* subprog can use linfo_idx to access its first linfo and * jited_linfo. * main prog always has linfo_idx == 0 */ u32 linfo_idx; struct module *mod; u32 num_exentries; struct exception_table_entry *extable; union { struct work_struct work; struct rcu_head rcu; }; }; struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ blinding_requested:1, /* needs constant blinding */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ kprobe_override:1, /* Do we override a kprobe? */ has_callchain_buf:1, /* callchain buffer allocated? */ enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */ call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */ call_get_func_ip:1, /* Do we call get_func_ip() */ tstamp_type_access:1, /* Accessed __sk_buff->tstamp_type */ sleepable:1; /* BPF program is sleepable */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ u32 jited_len; /* Size of jited insns in bytes */ u8 tag[BPF_TAG_SIZE]; struct bpf_prog_stats __percpu *stats; int __percpu *active; unsigned int (*bpf_func)(const void *ctx, const struct bpf_insn *insn); struct bpf_prog_aux *aux; /* Auxiliary fields */ struct sock_fprog_kern *orig_prog; /* Original BPF program */ /* Instructions for interpreter */ union { DECLARE_FLEX_ARRAY(struct sock_filter, insns); DECLARE_FLEX_ARRAY(struct bpf_insn, insnsi); }; }; struct bpf_array_aux { /* Programs with direct jumps into programs part of this array. */ struct list_head poke_progs; struct bpf_map *map; struct mutex poke_mutex; struct work_struct work; }; struct bpf_link { atomic64_t refcnt; u32 id; enum bpf_link_type type; const struct bpf_link_ops *ops; struct bpf_prog *prog; /* rcu is used before freeing, work can be used to schedule that * RCU-based freeing before that, so they never overlap */ union { struct rcu_head rcu; struct work_struct work; }; }; struct bpf_link_ops { void (*release)(struct bpf_link *link); /* deallocate link resources callback, called without RCU grace period * waiting */ void (*dealloc)(struct bpf_link *link); /* deallocate link resources callback, called after RCU grace period; * if underlying BPF program is sleepable we go through tasks trace * RCU GP and then "classic" RCU GP */ void (*dealloc_deferred)(struct bpf_link *link); int (*detach)(struct bpf_link *link); int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog); void (*show_fdinfo)(const struct bpf_link *link, struct seq_file *seq); int (*fill_link_info)(const struct bpf_link *link, struct bpf_link_info *info); int (*update_map)(struct bpf_link *link, struct bpf_map *new_map, struct bpf_map *old_map); __poll_t (*poll)(struct file *file, struct poll_table_struct *pts); }; struct bpf_tramp_link { struct bpf_link link; struct hlist_node tramp_hlist; u64 cookie; }; struct bpf_shim_tramp_link { struct bpf_tramp_link link; struct bpf_trampoline *trampoline; }; struct bpf_tracing_link { struct bpf_tramp_link link; enum bpf_attach_type attach_type; struct bpf_trampoline *trampoline; struct bpf_prog *tgt_prog; }; struct bpf_raw_tp_link { struct bpf_link link; struct bpf_raw_event_map *btp; u64 cookie; }; struct bpf_link_primer { struct bpf_link *link; struct file *file; int fd; u32 id; }; struct bpf_mount_opts { kuid_t uid; kgid_t gid; umode_t mode; /* BPF token-related delegation options */ u64 delegate_cmds; u64 delegate_maps; u64 delegate_progs; u64 delegate_attachs; }; struct bpf_token { struct work_struct work; atomic64_t refcnt; struct user_namespace *userns; u64 allowed_cmds; u64 allowed_maps; u64 allowed_progs; u64 allowed_attachs; #ifdef CONFIG_SECURITY void *security; #endif }; struct bpf_struct_ops_value; struct btf_member; #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64 /** * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to * define a BPF_MAP_TYPE_STRUCT_OPS map type composed * of BPF_PROG_TYPE_STRUCT_OPS progs. * @verifier_ops: A structure of callbacks that are invoked by the verifier * when determining whether the struct_ops progs in the * struct_ops map are valid. * @init: A callback that is invoked a single time, and before any other * callback, to initialize the structure. A nonzero return value means * the subsystem could not be initialized. * @check_member: When defined, a callback invoked by the verifier to allow * the subsystem to determine if an entry in the struct_ops map * is valid. A nonzero return value means that the map is * invalid and should be rejected by the verifier. * @init_member: A callback that is invoked for each member of the struct_ops * map to allow the subsystem to initialize the member. A nonzero * value means the member could not be initialized. This callback * is exclusive with the @type, @type_id, @value_type, and * @value_id fields. * @reg: A callback that is invoked when the struct_ops map has been * initialized and is being attached to. Zero means the struct_ops map * has been successfully registered and is live. A nonzero return value * means the struct_ops map could not be registered. * @unreg: A callback that is invoked when the struct_ops map should be * unregistered. * @update: A callback that is invoked when the live struct_ops map is being * updated to contain new values. This callback is only invoked when * the struct_ops map is loaded with BPF_F_LINK. If not defined, the * it is assumed that the struct_ops map cannot be updated. * @validate: A callback that is invoked after all of the members have been * initialized. This callback should perform static checks on the * map, meaning that it should either fail or succeed * deterministically. A struct_ops map that has been validated may * not necessarily succeed in being registered if the call to @reg * fails. For example, a valid struct_ops map may be loaded, but * then fail to be registered due to there being another active * struct_ops map on the system in the subsystem already. For this * reason, if this callback is not defined, the check is skipped as * the struct_ops map will have final verification performed in * @reg. * @type: BTF type. * @value_type: Value type. * @name: The name of the struct bpf_struct_ops object. * @func_models: Func models * @type_id: BTF type id. * @value_id: BTF value id. */ struct bpf_struct_ops { const struct bpf_verifier_ops *verifier_ops; int (*init)(struct btf *btf); int (*check_member)(const struct btf_type *t, const struct btf_member *member, const struct bpf_prog *prog); int (*init_member)(const struct btf_type *t, const struct btf_member *member, void *kdata, const void *udata); int (*reg)(void *kdata, struct bpf_link *link); void (*unreg)(void *kdata, struct bpf_link *link); int (*update)(void *kdata, void *old_kdata, struct bpf_link *link); int (*validate)(void *kdata); void *cfi_stubs; struct module *owner; const char *name; struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS]; }; /* Every member of a struct_ops type has an instance even a member is not * an operator (function pointer). The "info" field will be assigned to * prog->aux->ctx_arg_info of BPF struct_ops programs to provide the * argument information required by the verifier to verify the program. * * btf_ctx_access() will lookup prog->aux->ctx_arg_info to find the * corresponding entry for an given argument. */ struct bpf_struct_ops_arg_info { struct bpf_ctx_arg_aux *info; u32 cnt; }; struct bpf_struct_ops_desc { struct bpf_struct_ops *st_ops; const struct btf_type *type; const struct btf_type *value_type; u32 type_id; u32 value_id; /* Collection of argument information for each member */ struct bpf_struct_ops_arg_info *arg_info; }; enum bpf_struct_ops_state { BPF_STRUCT_OPS_STATE_INIT, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE, BPF_STRUCT_OPS_STATE_READY, }; struct bpf_struct_ops_common_value { refcount_t refcnt; enum bpf_struct_ops_state state; }; #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL) /* This macro helps developer to register a struct_ops type and generate * type information correctly. Developers should use this macro to register * a struct_ops type instead of calling __register_bpf_struct_ops() directly. */ #define register_bpf_struct_ops(st_ops, type) \ ({ \ struct bpf_struct_ops_##type { \ struct bpf_struct_ops_common_value common; \ struct type data ____cacheline_aligned_in_smp; \ }; \ BTF_TYPE_EMIT(struct bpf_struct_ops_##type); \ __register_bpf_struct_ops(st_ops); \ }) #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA)) bool bpf_struct_ops_get(const void *kdata); void bpf_struct_ops_put(const void *kdata); int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, void *stub_func, void **image, u32 *image_off, bool allow_alloc); void bpf_struct_ops_image_free(void *image); static inline bool bpf_try_module_get(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) return bpf_struct_ops_get(data); else return try_module_get(owner); } static inline void bpf_module_put(const void *data, struct module *owner) { if (owner == BPF_MODULE_OWNER) bpf_struct_ops_put(data); else module_put(owner); } int bpf_struct_ops_link_create(union bpf_attr *attr); #ifdef CONFIG_NET /* Define it here to avoid the use of forward declaration */ struct bpf_dummy_ops_state { int val; }; struct bpf_dummy_ops { int (*test_1)(struct bpf_dummy_ops_state *cb); int (*test_2)(struct bpf_dummy_ops_state *cb, int a1, unsigned short a2, char a3, unsigned long a4); int (*test_sleepable)(struct bpf_dummy_ops_state *cb); }; int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); #endif int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, struct btf *btf, struct bpf_verifier_log *log); void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map); void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc); #else #define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; }) static inline bool bpf_try_module_get(const void *data, struct module *owner) { return try_module_get(owner); } static inline void bpf_module_put(const void *data, struct module *owner) { module_put(owner); } static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, void *value) { return -EINVAL; } static inline int bpf_struct_ops_link_create(union bpf_attr *attr) { return -EOPNOTSUPP; } static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) { } static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) { } #endif #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM) int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, int cgroup_atype); void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog); #else static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog, int cgroup_atype) { return -EOPNOTSUPP; } static inline void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog) { } #endif struct bpf_array { struct bpf_map map; u32 elem_size; u32 index_mask; struct bpf_array_aux *aux; union { DECLARE_FLEX_ARRAY(char, value) __aligned(8); DECLARE_FLEX_ARRAY(void *, ptrs) __aligned(8); DECLARE_FLEX_ARRAY(void __percpu *, pptrs) __aligned(8); }; }; #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ #define MAX_TAIL_CALL_CNT 33 /* Maximum number of loops for bpf_loop and bpf_iter_num. * It's enum to expose it (and thus make it discoverable) through BTF. */ enum { BPF_MAX_LOOPS = 8 * 1024 * 1024, }; #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ BPF_F_WRONLY | \ BPF_F_WRONLY_PROG) #define BPF_MAP_CAN_READ BIT(0) #define BPF_MAP_CAN_WRITE BIT(1) /* Maximum number of user-producer ring buffer samples that can be drained in * a call to bpf_user_ringbuf_drain(). */ #define BPF_MAX_USER_RINGBUF_SAMPLES (128 * 1024) static inline u32 bpf_map_flags_to_cap(struct bpf_map *map) { u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); /* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is * not possible. */ if (access_flags & BPF_F_RDONLY_PROG) return BPF_MAP_CAN_READ; else if (access_flags & BPF_F_WRONLY_PROG) return BPF_MAP_CAN_WRITE; else return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE; } static inline bool bpf_map_flags_access_ok(u32 access_flags) { return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) != (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG); } struct bpf_event_entry { struct perf_event *event; struct file *perf_file; struct file *map_file; struct rcu_head rcu; }; static inline bool map_type_contains_progs(struct bpf_map *map) { return map->map_type == BPF_MAP_TYPE_PROG_ARRAY || map->map_type == BPF_MAP_TYPE_DEVMAP || map->map_type == BPF_MAP_TYPE_CPUMAP; } bool bpf_prog_map_compatible(struct bpf_map *map, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy); /* an array of programs to be executed under rcu_lock. * * Typical usage: * ret = bpf_prog_run_array(rcu_dereference(&bpf_prog_array), ctx, bpf_prog_run); * * the structure returned by bpf_prog_array_alloc() should be populated * with program pointers and the last pointer must be NULL. * The user has to keep refcnt on the program and make sure the program * is removed from the array before bpf_prog_put(). * The 'struct bpf_prog_array *' should only be replaced with xchg() * since other cpus are walking the array of pointers in parallel. */ struct bpf_prog_array_item { struct bpf_prog *prog; union { struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; u64 bpf_cookie; }; }; struct bpf_prog_array { struct rcu_head rcu; struct bpf_prog_array_item items[]; }; struct bpf_empty_prog_array { struct bpf_prog_array hdr; struct bpf_prog *null_prog; }; /* to avoid allocating empty bpf_prog_array for cgroups that * don't have bpf program attached use one global 'bpf_empty_prog_array' * It will not be modified the caller of bpf_prog_array_alloc() * (since caller requested prog_cnt == 0) * that pointer should be 'freed' by bpf_prog_array_free() */ extern struct bpf_empty_prog_array bpf_empty_prog_array; struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); /* Use when traversal over the bpf_prog_array uses tasks_trace rcu */ void bpf_prog_array_free_sleepable(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); bool bpf_prog_array_is_empty(struct bpf_prog_array *array); int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, __u32 __user *prog_ids, u32 cnt); void bpf_prog_array_delete_safe(struct bpf_prog_array *progs, struct bpf_prog *old_prog); int bpf_prog_array_delete_safe_at(struct bpf_prog_array *array, int index); int bpf_prog_array_update_at(struct bpf_prog_array *array, int index, struct bpf_prog *prog); int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt); int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, u64 bpf_cookie, struct bpf_prog_array **new_array); struct bpf_run_ctx {}; struct bpf_cg_run_ctx { struct bpf_run_ctx run_ctx; const struct bpf_prog_array_item *prog_item; int retval; }; struct bpf_trace_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; bool is_uprobe; }; struct bpf_tramp_run_ctx { struct bpf_run_ctx run_ctx; u64 bpf_cookie; struct bpf_run_ctx *saved_run_ctx; }; static inline struct bpf_run_ctx *bpf_set_run_ctx(struct bpf_run_ctx *new_ctx) { struct bpf_run_ctx *old_ctx = NULL; #ifdef CONFIG_BPF_SYSCALL old_ctx = current->bpf_ctx; current->bpf_ctx = new_ctx; #endif return old_ctx; } static inline void bpf_reset_run_ctx(struct bpf_run_ctx *old_ctx) { #ifdef CONFIG_BPF_SYSCALL current->bpf_ctx = old_ctx; #endif } /* BPF program asks to bypass CAP_NET_BIND_SERVICE in bind. */ #define BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE (1 << 0) /* BPF program asks to set CN on the packet. */ #define BPF_RET_SET_CN (1 << 0) typedef u32 (*bpf_prog_run_fn)(const struct bpf_prog *prog, const void *ctx); static __always_inline u32 bpf_prog_run_array(const struct bpf_prog_array *array, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu lock held"); if (unlikely(!array)) return ret; run_ctx.is_uprobe = false; migrate_disable(); old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; } bpf_reset_run_ctx(old_run_ctx); migrate_enable(); return ret; } /* Notes on RCU design for bpf_prog_arrays containing sleepable programs: * * We use the tasks_trace rcu flavor read section to protect the bpf_prog_array * overall. As a result, we must use the bpf_prog_array_free_sleepable * in order to use the tasks_trace rcu grace period. * * When a non-sleepable program is inside the array, we take the rcu read * section and disable preemption for that program alone, so it can access * rcu-protected dynamically sized maps. */ static __always_inline u32 bpf_prog_run_array_uprobe(const struct bpf_prog_array __rcu *array_rcu, const void *ctx, bpf_prog_run_fn run_prog) { const struct bpf_prog_array_item *item; const struct bpf_prog *prog; const struct bpf_prog_array *array; struct bpf_run_ctx *old_run_ctx; struct bpf_trace_run_ctx run_ctx; u32 ret = 1; might_fault(); rcu_read_lock_trace(); migrate_disable(); run_ctx.is_uprobe = true; array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held()); if (unlikely(!array)) goto out; old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx); item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { if (!prog->sleepable) rcu_read_lock(); run_ctx.bpf_cookie = item->bpf_cookie; ret &= run_prog(prog, ctx); item++; if (!prog->sleepable) rcu_read_unlock(); } bpf_reset_run_ctx(old_run_ctx); out: migrate_enable(); rcu_read_unlock_trace(); return ret; } #ifdef CONFIG_BPF_SYSCALL DECLARE_PER_CPU(int, bpf_prog_active); extern struct mutex bpf_stats_enabled_mutex; /* * Block execution of BPF programs attached to instrumentation (perf, * kprobes, tracepoints) to prevent deadlocks on map operations as any of * these events can happen inside a region which holds a map bucket lock * and can deadlock on it. */ static inline void bpf_disable_instrumentation(void) { migrate_disable(); this_cpu_inc(bpf_prog_active); } static inline void bpf_enable_instrumentation(void) { this_cpu_dec(bpf_prog_active); migrate_enable(); } extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \ extern const struct bpf_prog_ops _name ## _prog_ops; \ extern const struct bpf_verifier_ops _name ## _verifier_ops; #define BPF_MAP_TYPE(_id, _ops) \ extern const struct bpf_map_ops _ops; #define BPF_LINK_TYPE(_id, _name) #include <linux/bpf_types.h> #undef BPF_PROG_TYPE #undef BPF_MAP_TYPE #undef BPF_LINK_TYPE extern const struct bpf_prog_ops bpf_offload_prog_ops; extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops; extern const struct bpf_verifier_ops xdp_analyzer_ops; struct bpf_prog *bpf_prog_get(u32 ufd); struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv); void bpf_prog_add(struct bpf_prog *prog, int i); void bpf_prog_sub(struct bpf_prog *prog, int i); void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_free_id(struct bpf_prog *prog); void bpf_map_free_id(struct bpf_map *map); struct btf_field *btf_record_find(const struct btf_record *rec, u32 offset, u32 field_mask); void btf_record_free(struct btf_record *rec); void bpf_map_free_record(struct bpf_map *map); struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_inc(struct bpf_map *map); void bpf_map_inc_with_uref(struct bpf_map *map); struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref); struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_update_batch(struct bpf_map *map, struct file *map_file, const union bpf_attr *attr, union bpf_attr __user *uattr); int generic_map_delete_batch(struct bpf_map *map, const union bpf_attr *attr, union bpf_attr __user *uattr); struct bpf_map *bpf_map_get_curr_or_next(u32 *id); struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array); #ifdef CONFIG_MEMCG void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags); void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, gfp_t flags); #else /* * These specialized allocators have to be macros for their allocations to be * accounted separately (to have separate alloc_tag). */ #define bpf_map_kmalloc_node(_map, _size, _flags, _node) \ kmalloc_node(_size, _flags, _node) #define bpf_map_kzalloc(_map, _size, _flags) \ kzalloc(_size, _flags) #define bpf_map_kvcalloc(_map, _n, _size, _flags) \ kvcalloc(_n, _size, _flags) #define bpf_map_alloc_percpu(_map, _size, _align, _flags) \ __alloc_percpu_gfp(_size, _align, _flags) #endif static inline int bpf_map_init_elem_count(struct bpf_map *map) { size_t size = sizeof(*map->elem_count), align = size; gfp_t flags = GFP_USER | __GFP_NOWARN; map->elem_count = bpf_map_alloc_percpu(map, size, align, flags); if (!map->elem_count) return -ENOMEM; return 0; } static inline void bpf_map_free_elem_count(struct bpf_map *map) { free_percpu(map->elem_count); } static inline void bpf_map_inc_elem_count(struct bpf_map *map) { this_cpu_inc(*map->elem_count); } static inline void bpf_map_dec_elem_count(struct bpf_map *map) { this_cpu_dec(*map->elem_count); } extern int sysctl_unprivileged_bpf_disabled; bool bpf_token_capable(const struct bpf_token *token, int cap); static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token) { return bpf_token_capable(token, CAP_PERFMON); } static inline bool bpf_allow_uninit_stack(const struct bpf_token *token) { return bpf_token_capable(token, CAP_PERFMON); } static inline bool bpf_bypass_spec_v1(const struct bpf_token *token) { return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } static inline bool bpf_bypass_spec_v4(const struct bpf_token *token) { return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } int bpf_map_new_fd(struct bpf_map *map, int flags); int bpf_prog_new_fd(struct bpf_prog *prog); void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog); int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer); int bpf_link_settle(struct bpf_link_primer *primer); void bpf_link_cleanup(struct bpf_link_primer *primer); void bpf_link_inc(struct bpf_link *link); struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link); void bpf_link_put(struct bpf_link *link); int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); void bpf_token_inc(struct bpf_token *token); void bpf_token_put(struct bpf_token *token); int bpf_token_create(union bpf_attr *attr); struct bpf_token *bpf_token_get_from_fd(u32 ufd); bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); bool bpf_token_allow_prog_type(const struct bpf_token *token, enum bpf_prog_type prog_type, enum bpf_attach_type attach_type); int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ extern int bpf_iter_ ## target(args); \ int __init bpf_iter_ ## target(args) { return 0; } /* * The task type of iterators. * * For BPF task iterators, they can be parameterized with various * parameters to visit only some of tasks. * * BPF_TASK_ITER_ALL (default) * Iterate over resources of every task. * * BPF_TASK_ITER_TID * Iterate over resources of a task/tid. * * BPF_TASK_ITER_TGID * Iterate over resources of every task of a process / task group. */ enum bpf_iter_task_type { BPF_TASK_ITER_ALL = 0, BPF_TASK_ITER_TID, BPF_TASK_ITER_TGID, }; struct bpf_iter_aux_info { /* for map_elem iter */ struct bpf_map *map; /* for cgroup iter */ struct { struct cgroup *start; /* starting cgroup */ enum bpf_cgroup_iter_order order; } cgroup; struct { enum bpf_iter_task_type type; u32 pid; } task; }; typedef int (*bpf_iter_attach_target_t)(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_detach_target_t)(struct bpf_iter_aux_info *aux); typedef void (*bpf_iter_show_fdinfo_t) (const struct bpf_iter_aux_info *aux, struct seq_file *seq); typedef int (*bpf_iter_fill_link_info_t)(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); typedef const struct bpf_func_proto * (*bpf_iter_get_func_proto_t)(enum bpf_func_id func_id, const struct bpf_prog *prog); enum bpf_iter_feature { BPF_ITER_RESCHED = BIT(0), }; #define BPF_ITER_CTX_ARG_MAX 2 struct bpf_iter_reg { const char *target; bpf_iter_attach_target_t attach_target; bpf_iter_detach_target_t detach_target; bpf_iter_show_fdinfo_t show_fdinfo; bpf_iter_fill_link_info_t fill_link_info; bpf_iter_get_func_proto_t get_func_proto; u32 ctx_arg_info_size; u32 feature; struct bpf_ctx_arg_aux ctx_arg_info[BPF_ITER_CTX_ARG_MAX]; const struct bpf_iter_seq_info *seq_info; }; struct bpf_iter_meta { __bpf_md_ptr(struct seq_file *, seq); u64 session_id; u64 seq_num; }; struct bpf_iter__bpf_map_elem { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(void *, key); __bpf_md_ptr(void *, value); }; int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info); void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info); bool bpf_iter_prog_supported(struct bpf_prog *prog); const struct bpf_func_proto * bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog); int bpf_iter_new_fd(struct bpf_link *link); bool bpf_link_is_iter(struct bpf_link *link); struct bpf_prog *bpf_iter_get_info(struct bpf_iter_meta *meta, bool in_stop); int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx); void bpf_iter_map_show_fdinfo(const struct bpf_iter_aux_info *aux, struct seq_file *seq); int bpf_iter_map_fill_link_info(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info); int map_set_for_each_callback_args(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee); int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value); int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value); int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags); int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value); int bpf_get_file_flag(int flags); int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size, size_t actual_size); /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size); #ifndef CONFIG_BPF_JIT_ALWAYS_ON void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); #endif struct btf *bpf_get_btf_vmlinux(void); /* Map specifics */ struct xdp_frame; struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; void __dev_flush(struct list_head *flush_list); int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx); int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress); void __cpu_map_flush(struct list_head *flush_list); int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb); /* Return map's numa specified by userspace */ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr) { return (attr->map_flags & BPF_F_NUMA_NODE) ? attr->numa_node : NUMA_NO_NODE; } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); int array_map_alloc_check(union bpf_attr *attr); int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int bpf_prog_test_run_nf(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); static inline bool bpf_tracing_ctx_access(int off, int size, enum bpf_access_type type) { if (off < 0 || off >= sizeof(__u64) * MAX_BPF_FUNC_ARGS) return false; if (type != BPF_READ) return false; if (off % size != 0) return false; return true; } static inline bool bpf_tracing_btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { if (!bpf_tracing_ctx_access(off, size, type)) return false; return btf_ctx_access(off, size, type, prog, info); } int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name); bool btf_struct_ids_match(struct bpf_verifier_log *log, const struct btf *btf, u32 id, int off, const struct btf *need_btf, u32 need_type_id, bool strict); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, const struct btf_type *func_proto, const char *func_name, struct btf_func_model *m); struct bpf_reg_state; int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key); int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, int comp_idx, const char *tag_key, int last_id); struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); void bpf_task_storage_free(struct task_struct *task); void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, u16 btf_fd_idx, u8 **func_addr); struct bpf_core_ctx { struct bpf_verifier_log *log; const struct btf *btf; }; bool btf_nested_type_is_trusted(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, const char *field_name, u32 btf_id, const char *suffix); bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, const struct btf *reg_btf, u32 reg_id, const struct btf *arg_btf, u32 arg_id); int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, int relo_idx, void *insn); static inline bool unprivileged_ebpf_enabled(void) { return !sysctl_unprivileged_bpf_disabled; } /* Not all bpf prog type has the bpf_ctx. * For the bpf prog type that has initialized the bpf_ctx, * this function can be used to decide if a kernel function * is called by a bpf program. */ static inline bool has_current_bpf_ctx(void) { return !!current->bpf_ctx; } void notrace bpf_prog_inc_misses_counter(struct bpf_prog *prog); void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size); void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); } static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_prog_add(struct bpf_prog *prog, int i) { } static inline void bpf_prog_sub(struct bpf_prog *prog, int i) { } static inline void bpf_prog_put(struct bpf_prog *prog) { } static inline void bpf_prog_inc(struct bpf_prog *prog) { } static inline struct bpf_prog *__must_check bpf_prog_inc_not_zero(struct bpf_prog *prog) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) { } static inline int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer) { return -EOPNOTSUPP; } static inline int bpf_link_settle(struct bpf_link_primer *primer) { return -EOPNOTSUPP; } static inline void bpf_link_cleanup(struct bpf_link_primer *primer) { } static inline void bpf_link_inc(struct bpf_link *link) { } static inline struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link) { return NULL; } static inline void bpf_link_put(struct bpf_link *link) { } static inline int bpf_obj_get_user(const char __user *pathname, int flags) { return -EOPNOTSUPP; } static inline bool bpf_token_capable(const struct bpf_token *token, int cap) { return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); } static inline void bpf_token_inc(struct bpf_token *token) { } static inline void bpf_token_put(struct bpf_token *token) { } static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) { return ERR_PTR(-EOPNOTSUPP); } static inline void __dev_flush(struct list_head *flush_list) { } struct xdp_frame; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; static inline int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { return 0; } struct sk_buff; static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog) { return 0; } static inline int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, struct bpf_prog *xdp_prog, struct bpf_map *map, bool exclude_ingress) { return 0; } static inline void __cpu_map_flush(struct list_head *flush_list) { } static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb) { return -EOPNOTSUPP; } static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { return ERR_PTR(-EOPNOTSUPP); } static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_tracing(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline int bpf_prog_test_run_sk_lookup(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } static inline void bpf_map_put(struct bpf_map *map) { } static inline struct bpf_prog *bpf_prog_by_id(u32 id) { return ERR_PTR(-ENOTSUPP); } static inline int btf_struct_access(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size, enum bpf_access_type atype, u32 *next_btf_id, enum bpf_type_flag *flag, const char **field_name) { return -EACCES; } static inline const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } static inline void bpf_task_storage_free(struct task_struct *task) { } static inline bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog) { return false; } static inline const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn) { return NULL; } static inline int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id, u16 btf_fd_idx, u8 **func_addr) { return -ENOTSUPP; } static inline bool unprivileged_ebpf_enabled(void) { return false; } static inline bool has_current_bpf_ctx(void) { return false; } static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog) { } static inline void bpf_cgrp_storage_free(struct cgroup *cgroup) { } static inline void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size) { } static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) { } static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr) { } #endif /* CONFIG_BPF_SYSCALL */ static __always_inline int bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr) { int ret = -EFAULT; if (IS_ENABLED(CONFIG_BPF_EVENTS)) ret = copy_from_kernel_nofault(dst, unsafe_ptr, size); if (unlikely(ret < 0)) memset(dst, 0, size); return ret; } void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len); static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, enum bpf_prog_type type) { return bpf_prog_get_type_dev(ufd, type, false); } void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len); bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_dev_bound_destroy(struct bpf_prog *prog); int bpf_prog_offload_info_fill(struct bpf_prog_info *info, struct bpf_prog *prog); int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map); int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_map_offload_update_elem(struct bpf_map *map, void *key, void *value, u64 flags); int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key); bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); struct bpf_offload_dev * bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv); void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev); int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev); bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); void unpriv_ebpf_notify(int new_state); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log, struct bpf_prog_aux *prog_aux); void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id); int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr); int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog); void bpf_dev_bound_netdev_unregister(struct net_device *dev); static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return aux->dev_bound; } static inline bool bpf_prog_is_offloaded(const struct bpf_prog_aux *aux) { return aux->offload_requested; } bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs); static inline bool bpf_map_is_offloaded(struct bpf_map *map) { return unlikely(map->ops == &bpf_map_offload_ops); } struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map); int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags); int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog); void sock_map_unhash(struct sock *sk); void sock_map_destroy(struct sock *sk); void sock_map_close(struct sock *sk, long timeout); #else static inline int bpf_dev_bound_kfunc_check(struct bpf_verifier_log *log, struct bpf_prog_aux *prog_aux) { return -EOPNOTSUPP; } static inline void *bpf_dev_bound_resolve_kfunc(struct bpf_prog *prog, u32 func_id) { return NULL; } static inline int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr) { return -EOPNOTSUPP; } static inline int bpf_prog_dev_bound_inherit(struct bpf_prog *new_prog, struct bpf_prog *old_prog) { return -EOPNOTSUPP; } static inline void bpf_dev_bound_netdev_unregister(struct net_device *dev) { } static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux) { return false; } static inline bool bpf_prog_is_offloaded(struct bpf_prog_aux *aux) { return false; } static inline bool bpf_prog_dev_bound_match(const struct bpf_prog *lhs, const struct bpf_prog *rhs) { return false; } static inline bool bpf_map_is_offloaded(struct bpf_map *map) { return false; } static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) { return ERR_PTR(-EOPNOTSUPP); } static inline void bpf_map_offload_map_free(struct bpf_map *map) { } static inline u64 bpf_map_offload_map_mem_usage(const struct bpf_map *map) { return 0; } static inline int bpf_prog_test_run_syscall(struct bpf_prog *prog, const union bpf_attr *kattr, union bpf_attr __user *uattr) { return -ENOTSUPP; } #ifdef CONFIG_BPF_SYSCALL static inline int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) { return -EINVAL; } static inline int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) { return -EOPNOTSUPP; } static inline int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags) { return -EOPNOTSUPP; } static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { return -EINVAL; } static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog) { return -EOPNOTSUPP; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ static __always_inline void bpf_prog_inc_misses_counters(const struct bpf_prog_array *array) { const struct bpf_prog_array_item *item; struct bpf_prog *prog; if (unlikely(!array)) return; item = &array->items[0]; while ((prog = READ_ONCE(item->prog))) { bpf_prog_inc_misses_counter(prog); item++; } } #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value); int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags); #else static inline void bpf_sk_reuseport_detach(struct sock *sk) { } #ifdef CONFIG_BPF_SYSCALL static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, void *value) { return -EOPNOTSUPP; } static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return -EOPNOTSUPP; } #endif /* CONFIG_BPF_SYSCALL */ #endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */ /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; extern const struct bpf_func_proto bpf_map_delete_elem_proto; extern const struct bpf_func_proto bpf_map_push_elem_proto; extern const struct bpf_func_proto bpf_map_pop_elem_proto; extern const struct bpf_func_proto bpf_map_peek_elem_proto; extern const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto; extern const struct bpf_func_proto bpf_get_prandom_u32_proto; extern const struct bpf_func_proto bpf_get_smp_processor_id_proto; extern const struct bpf_func_proto bpf_get_numa_node_id_proto; extern const struct bpf_func_proto bpf_tail_call_proto; extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_boot_ns_proto; extern const struct bpf_func_proto bpf_ktime_get_tai_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_get_task_stack_proto; extern const struct bpf_func_proto bpf_get_stackid_proto_pe; extern const struct bpf_func_proto bpf_get_stack_proto_pe; extern const struct bpf_func_proto bpf_sock_map_update_proto; extern const struct bpf_func_proto bpf_sock_hash_update_proto; extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto; extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto; extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; extern const struct bpf_func_proto bpf_sk_redirect_map_proto; extern const struct bpf_func_proto bpf_spin_lock_proto; extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; extern const struct bpf_func_proto bpf_tcp_sock_proto; extern const struct bpf_func_proto bpf_jiffies64_proto; extern const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_event_output_data_proto; extern const struct bpf_func_proto bpf_ringbuf_output_proto; extern const struct bpf_func_proto bpf_ringbuf_reserve_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_proto; extern const struct bpf_func_proto bpf_ringbuf_query_proto; extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto; extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto; extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto; extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; extern const struct bpf_func_proto bpf_skc_to_mptcp_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; extern const struct bpf_func_proto bpf_sock_from_file_proto; extern const struct bpf_func_proto bpf_get_socket_ptr_cookie_proto; extern const struct bpf_func_proto bpf_task_storage_get_recur_proto; extern const struct bpf_func_proto bpf_task_storage_get_proto; extern const struct bpf_func_proto bpf_task_storage_delete_recur_proto; extern const struct bpf_func_proto bpf_task_storage_delete_proto; extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_find_vma_proto; extern const struct bpf_func_proto bpf_loop_proto; extern const struct bpf_func_proto bpf_copy_from_user_task_proto; extern const struct bpf_func_proto bpf_set_retval_proto; extern const struct bpf_func_proto bpf_get_retval_proto; extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto; extern const struct bpf_func_proto bpf_cgrp_storage_get_proto; extern const struct bpf_func_proto bpf_cgrp_storage_delete_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); u64 bpf_get_raw_cpu_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #if defined(CONFIG_NET) bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, struct bpf_dynptr *ptr); #else static inline bool bpf_sock_common_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } static inline int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags, struct bpf_dynptr *ptr) { return -EOPNOTSUPP; } #endif #ifdef CONFIG_INET struct sk_reuseport_kern { struct sk_buff *skb; struct sock *sk; struct sock *selected_sk; struct sock *migrating_sk; void *data_end; u32 hash; u32 reuseport_id; bool bind_inany; }; bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size); #else static inline bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } static inline bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { return false; } static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, struct bpf_insn *insn_buf, struct bpf_prog *prog, u32 *target_size) { return 0; } #endif /* CONFIG_INET */ enum bpf_text_poke_type { BPF_MOD_CALL, BPF_MOD_JUMP, }; int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t, void *addr1, void *addr2); void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, struct bpf_prog *new, struct bpf_prog *old); void *bpf_arch_text_copy(void *dst, void *src, size_t len); int bpf_arch_text_invalidate(void *dst, size_t len); struct btf_id_set; bool btf_id_set_contains(const struct btf_id_set *set, u32 id); #define MAX_BPRINTF_VARARGS 12 #define MAX_BPRINTF_BUF 1024 struct bpf_bprintf_data { u32 *bin_args; char *buf; bool get_bin_args; bool get_buf; }; int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args, u32 num_args, struct bpf_bprintf_data *data); void bpf_bprintf_cleanup(struct bpf_bprintf_data *data); #ifdef CONFIG_BPF_LSM void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); void bpf_cgroup_atype_put(int cgroup_atype); #else static inline void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype) {} static inline void bpf_cgroup_atype_put(int cgroup_atype) {} #endif /* CONFIG_BPF_LSM */ struct key; #ifdef CONFIG_KEYS struct bpf_key { struct key *key; bool has_ref; }; #endif /* CONFIG_KEYS */ static inline bool type_is_alloc(u32 type) { return type & MEM_ALLOC; } static inline gfp_t bpf_memcg_flags(gfp_t flags) { if (memcg_bpf_enabled()) return flags | __GFP_ACCOUNT; return flags; } static inline bool bpf_is_subprog(const struct bpf_prog *prog) { return prog->aux->func_idx != 0; } #endif /* _LINUX_BPF_H */ |
| 2 2 2 2 2 2 1 1 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 | // SPDX-License-Identifier: GPL-2.0 /* * Functions related to sysfs handling */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/blktrace_api.h> #include <linux/debugfs.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" #include "blk-wbt.h" #include "blk-cgroup.h" #include "blk-throttle.h" struct queue_sysfs_entry { struct attribute attr; ssize_t (*show)(struct gendisk *disk, char *page); ssize_t (*store)(struct gendisk *disk, const char *page, size_t count); }; static ssize_t queue_var_show(unsigned long var, char *page) { return sprintf(page, "%lu\n", var); } static ssize_t queue_var_store(unsigned long *var, const char *page, size_t count) { int err; unsigned long v; err = kstrtoul(page, 10, &v); if (err || v > UINT_MAX) return -EINVAL; *var = v; return count; } static ssize_t queue_requests_show(struct gendisk *disk, char *page) { return queue_var_show(disk->queue->nr_requests, page); } static ssize_t queue_requests_store(struct gendisk *disk, const char *page, size_t count) { unsigned long nr; int ret, err; if (!queue_is_mq(disk->queue)) return -EINVAL; ret = queue_var_store(&nr, page, count); if (ret < 0) return ret; if (nr < BLKDEV_MIN_RQ) nr = BLKDEV_MIN_RQ; err = blk_mq_update_nr_requests(disk->queue, nr); if (err) return err; return ret; } static ssize_t queue_ra_show(struct gendisk *disk, char *page) { return queue_var_show(disk->bdi->ra_pages << (PAGE_SHIFT - 10), page); } static ssize_t queue_ra_store(struct gendisk *disk, const char *page, size_t count) { unsigned long ra_kb; ssize_t ret; ret = queue_var_store(&ra_kb, page, count); if (ret < 0) return ret; disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10); return ret; } #define QUEUE_SYSFS_LIMIT_SHOW(_field) \ static ssize_t queue_##_field##_show(struct gendisk *disk, char *page) \ { \ return queue_var_show(disk->queue->limits._field, page); \ } QUEUE_SYSFS_LIMIT_SHOW(max_segments) QUEUE_SYSFS_LIMIT_SHOW(max_discard_segments) QUEUE_SYSFS_LIMIT_SHOW(max_integrity_segments) QUEUE_SYSFS_LIMIT_SHOW(max_segment_size) QUEUE_SYSFS_LIMIT_SHOW(logical_block_size) QUEUE_SYSFS_LIMIT_SHOW(physical_block_size) QUEUE_SYSFS_LIMIT_SHOW(chunk_sectors) QUEUE_SYSFS_LIMIT_SHOW(io_min) QUEUE_SYSFS_LIMIT_SHOW(io_opt) QUEUE_SYSFS_LIMIT_SHOW(discard_granularity) QUEUE_SYSFS_LIMIT_SHOW(zone_write_granularity) QUEUE_SYSFS_LIMIT_SHOW(virt_boundary_mask) QUEUE_SYSFS_LIMIT_SHOW(dma_alignment) QUEUE_SYSFS_LIMIT_SHOW(max_open_zones) QUEUE_SYSFS_LIMIT_SHOW(max_active_zones) QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_min) QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_max) #define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(_field) \ static ssize_t queue_##_field##_show(struct gendisk *disk, char *page) \ { \ return sprintf(page, "%llu\n", \ (unsigned long long)disk->queue->limits._field << \ SECTOR_SHIFT); \ } QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_discard_sectors) QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_hw_discard_sectors) QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_write_zeroes_sectors) QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_max_sectors) QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_boundary_sectors) #define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(_field) \ static ssize_t queue_##_field##_show(struct gendisk *disk, char *page) \ { \ return queue_var_show(disk->queue->limits._field >> 1, page); \ } QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_sectors) QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_hw_sectors) #define QUEUE_SYSFS_SHOW_CONST(_name, _val) \ static ssize_t queue_##_name##_show(struct gendisk *disk, char *page) \ { \ return sprintf(page, "%d\n", _val); \ } /* deprecated fields */ QUEUE_SYSFS_SHOW_CONST(discard_zeroes_data, 0) QUEUE_SYSFS_SHOW_CONST(write_same_max, 0) QUEUE_SYSFS_SHOW_CONST(poll_delay, -1) static ssize_t queue_max_discard_sectors_store(struct gendisk *disk, const char *page, size_t count) { unsigned long max_discard_bytes; struct queue_limits lim; ssize_t ret; int err; ret = queue_var_store(&max_discard_bytes, page, count); if (ret < 0) return ret; if (max_discard_bytes & (disk->queue->limits.discard_granularity - 1)) return -EINVAL; if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX) return -EINVAL; lim = queue_limits_start_update(disk->queue); lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT; err = queue_limits_commit_update(disk->queue, &lim); if (err) return err; return ret; } /* * For zone append queue_max_zone_append_sectors does not just return the * underlying queue limits, but actually contains a calculation. Because of * that we can't simply use QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES here. */ static ssize_t queue_zone_append_max_show(struct gendisk *disk, char *page) { return sprintf(page, "%llu\n", (u64)queue_max_zone_append_sectors(disk->queue) << SECTOR_SHIFT); } static ssize_t queue_max_sectors_store(struct gendisk *disk, const char *page, size_t count) { unsigned long max_sectors_kb; struct queue_limits lim; ssize_t ret; int err; ret = queue_var_store(&max_sectors_kb, page, count); if (ret < 0) return ret; lim = queue_limits_start_update(disk->queue); lim.max_user_sectors = max_sectors_kb << 1; err = queue_limits_commit_update(disk->queue, &lim); if (err) return err; return ret; } static ssize_t queue_feature_store(struct gendisk *disk, const char *page, size_t count, blk_features_t feature) { struct queue_limits lim; unsigned long val; ssize_t ret; ret = queue_var_store(&val, page, count); if (ret < 0) return ret; lim = queue_limits_start_update(disk->queue); if (val) lim.features |= feature; else lim.features &= ~feature; ret = queue_limits_commit_update(disk->queue, &lim); if (ret) return ret; return count; } #define QUEUE_SYSFS_FEATURE(_name, _feature) \ static ssize_t queue_##_name##_show(struct gendisk *disk, char *page) \ { \ return sprintf(page, "%u\n", \ !!(disk->queue->limits.features & _feature)); \ } \ static ssize_t queue_##_name##_store(struct gendisk *disk, \ const char *page, size_t count) \ { \ return queue_feature_store(disk, page, count, _feature); \ } QUEUE_SYSFS_FEATURE(rotational, BLK_FEAT_ROTATIONAL) QUEUE_SYSFS_FEATURE(add_random, BLK_FEAT_ADD_RANDOM) QUEUE_SYSFS_FEATURE(iostats, BLK_FEAT_IO_STAT) QUEUE_SYSFS_FEATURE(stable_writes, BLK_FEAT_STABLE_WRITES); #define QUEUE_SYSFS_FEATURE_SHOW(_name, _feature) \ static ssize_t queue_##_name##_show(struct gendisk *disk, char *page) \ { \ return sprintf(page, "%u\n", \ !!(disk->queue->limits.features & _feature)); \ } QUEUE_SYSFS_FEATURE_SHOW(poll, BLK_FEAT_POLL); QUEUE_SYSFS_FEATURE_SHOW(fua, BLK_FEAT_FUA); QUEUE_SYSFS_FEATURE_SHOW(dax, BLK_FEAT_DAX); static ssize_t queue_zoned_show(struct gendisk *disk, char *page) { if (blk_queue_is_zoned(disk->queue)) return sprintf(page, "host-managed\n"); return sprintf(page, "none\n"); } static ssize_t queue_nr_zones_show(struct gendisk *disk, char *page) { return queue_var_show(disk_nr_zones(disk), page); } static ssize_t queue_nomerges_show(struct gendisk *disk, char *page) { return queue_var_show((blk_queue_nomerges(disk->queue) << 1) | blk_queue_noxmerges(disk->queue), page); } static ssize_t queue_nomerges_store(struct gendisk *disk, const char *page, size_t count) { unsigned long nm; ssize_t ret = queue_var_store(&nm, page, count); if (ret < 0) return ret; blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, disk->queue); blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, disk->queue); if (nm == 2) blk_queue_flag_set(QUEUE_FLAG_NOMERGES, disk->queue); else if (nm) blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, disk->queue); return ret; } static ssize_t queue_rq_affinity_show(struct gendisk *disk, char *page) { bool set = test_bit(QUEUE_FLAG_SAME_COMP, &disk->queue->queue_flags); bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &disk->queue->queue_flags); return queue_var_show(set << force, page); } static ssize_t queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count) { ssize_t ret = -EINVAL; #ifdef CONFIG_SMP struct request_queue *q = disk->queue; unsigned long val; ret = queue_var_store(&val, page, count); if (ret < 0) return ret; if (val == 2) { blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q); blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, q); } else if (val == 1) { blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q); blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q); } else if (val == 0) { blk_queue_flag_clear(QUEUE_FLAG_SAME_COMP, q); blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q); } #endif return ret; } static ssize_t queue_poll_delay_store(struct gendisk *disk, const char *page, size_t count) { return count; } static ssize_t queue_poll_store(struct gendisk *disk, const char *page, size_t count) { if (!(disk->queue->limits.features & BLK_FEAT_POLL)) return -EINVAL; pr_info_ratelimited("writes to the poll attribute are ignored.\n"); pr_info_ratelimited("please use driver specific parameters instead.\n"); return count; } static ssize_t queue_io_timeout_show(struct gendisk *disk, char *page) { return sprintf(page, "%u\n", jiffies_to_msecs(disk->queue->rq_timeout)); } static ssize_t queue_io_timeout_store(struct gendisk *disk, const char *page, size_t count) { unsigned int val; int err; err = kstrtou32(page, 10, &val); if (err || val == 0) return -EINVAL; blk_queue_rq_timeout(disk->queue, msecs_to_jiffies(val)); return count; } static ssize_t queue_wc_show(struct gendisk *disk, char *page) { if (blk_queue_write_cache(disk->queue)) return sprintf(page, "write back\n"); return sprintf(page, "write through\n"); } static ssize_t queue_wc_store(struct gendisk *disk, const char *page, size_t count) { struct queue_limits lim; bool disable; int err; if (!strncmp(page, "write back", 10)) { disable = false; } else if (!strncmp(page, "write through", 13) || !strncmp(page, "none", 4)) { disable = true; } else { return -EINVAL; } lim = queue_limits_start_update(disk->queue); if (disable) lim.flags |= BLK_FLAG_WRITE_CACHE_DISABLED; else lim.flags &= ~BLK_FLAG_WRITE_CACHE_DISABLED; err = queue_limits_commit_update(disk->queue, &lim); if (err) return err; return count; } #define QUEUE_RO_ENTRY(_prefix, _name) \ static struct queue_sysfs_entry _prefix##_entry = { \ .attr = { .name = _name, .mode = 0444 }, \ .show = _prefix##_show, \ }; #define QUEUE_RW_ENTRY(_prefix, _name) \ static struct queue_sysfs_entry _prefix##_entry = { \ .attr = { .name = _name, .mode = 0644 }, \ .show = _prefix##_show, \ .store = _prefix##_store, \ }; QUEUE_RW_ENTRY(queue_requests, "nr_requests"); QUEUE_RW_ENTRY(queue_ra, "read_ahead_kb"); QUEUE_RW_ENTRY(queue_max_sectors, "max_sectors_kb"); QUEUE_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb"); QUEUE_RO_ENTRY(queue_max_segments, "max_segments"); QUEUE_RO_ENTRY(queue_max_integrity_segments, "max_integrity_segments"); QUEUE_RO_ENTRY(queue_max_segment_size, "max_segment_size"); QUEUE_RW_ENTRY(elv_iosched, "scheduler"); QUEUE_RO_ENTRY(queue_logical_block_size, "logical_block_size"); QUEUE_RO_ENTRY(queue_physical_block_size, "physical_block_size"); QUEUE_RO_ENTRY(queue_chunk_sectors, "chunk_sectors"); QUEUE_RO_ENTRY(queue_io_min, "minimum_io_size"); QUEUE_RO_ENTRY(queue_io_opt, "optimal_io_size"); QUEUE_RO_ENTRY(queue_max_discard_segments, "max_discard_segments"); QUEUE_RO_ENTRY(queue_discard_granularity, "discard_granularity"); QUEUE_RO_ENTRY(queue_max_hw_discard_sectors, "discard_max_hw_bytes"); QUEUE_RW_ENTRY(queue_max_discard_sectors, "discard_max_bytes"); QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data"); QUEUE_RO_ENTRY(queue_atomic_write_max_sectors, "atomic_write_max_bytes"); QUEUE_RO_ENTRY(queue_atomic_write_boundary_sectors, "atomic_write_boundary_bytes"); QUEUE_RO_ENTRY(queue_atomic_write_unit_max, "atomic_write_unit_max_bytes"); QUEUE_RO_ENTRY(queue_atomic_write_unit_min, "atomic_write_unit_min_bytes"); QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes"); QUEUE_RO_ENTRY(queue_max_write_zeroes_sectors, "write_zeroes_max_bytes"); QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes"); QUEUE_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity"); QUEUE_RO_ENTRY(queue_zoned, "zoned"); QUEUE_RO_ENTRY(queue_nr_zones, "nr_zones"); QUEUE_RO_ENTRY(queue_max_open_zones, "max_open_zones"); QUEUE_RO_ENTRY(queue_max_active_zones, "max_active_zones"); QUEUE_RW_ENTRY(queue_nomerges, "nomerges"); QUEUE_RW_ENTRY(queue_rq_affinity, "rq_affinity"); QUEUE_RW_ENTRY(queue_poll, "io_poll"); QUEUE_RW_ENTRY(queue_poll_delay, "io_poll_delay"); QUEUE_RW_ENTRY(queue_wc, "write_cache"); QUEUE_RO_ENTRY(queue_fua, "fua"); QUEUE_RO_ENTRY(queue_dax, "dax"); QUEUE_RW_ENTRY(queue_io_timeout, "io_timeout"); QUEUE_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask"); QUEUE_RO_ENTRY(queue_dma_alignment, "dma_alignment"); /* legacy alias for logical_block_size: */ static struct queue_sysfs_entry queue_hw_sector_size_entry = { .attr = {.name = "hw_sector_size", .mode = 0444 }, .show = queue_logical_block_size_show, }; QUEUE_RW_ENTRY(queue_rotational, "rotational"); QUEUE_RW_ENTRY(queue_iostats, "iostats"); QUEUE_RW_ENTRY(queue_add_random, "add_random"); QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes"); #ifdef CONFIG_BLK_WBT static ssize_t queue_var_store64(s64 *var, const char *page) { int err; s64 v; err = kstrtos64(page, 10, &v); if (err < 0) return err; *var = v; return 0; } static ssize_t queue_wb_lat_show(struct gendisk *disk, char *page) { if (!wbt_rq_qos(disk->queue)) return -EINVAL; if (wbt_disabled(disk->queue)) return sprintf(page, "0\n"); return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(disk->queue), 1000)); } static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page, size_t count) { struct request_queue *q = disk->queue; struct rq_qos *rqos; ssize_t ret; s64 val; ret = queue_var_store64(&val, page); if (ret < 0) return ret; if (val < -1) return -EINVAL; rqos = wbt_rq_qos(q); if (!rqos) { ret = wbt_init(disk); if (ret) return ret; } if (val == -1) val = wbt_default_latency_nsec(q); else if (val >= 0) val *= 1000ULL; if (wbt_get_min_lat(q) == val) return count; /* * Ensure that the queue is idled, in case the latency update * ends up either enabling or disabling wbt completely. We can't * have IO inflight if that happens. */ blk_mq_quiesce_queue(q); wbt_set_min_lat(q, val); blk_mq_unquiesce_queue(q); return count; } QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec"); #endif /* Common attributes for bio-based and request-based queues. */ static struct attribute *queue_attrs[] = { &queue_ra_entry.attr, &queue_max_hw_sectors_entry.attr, &queue_max_sectors_entry.attr, &queue_max_segments_entry.attr, &queue_max_discard_segments_entry.attr, &queue_max_integrity_segments_entry.attr, &queue_max_segment_size_entry.attr, &queue_hw_sector_size_entry.attr, &queue_logical_block_size_entry.attr, &queue_physical_block_size_entry.attr, &queue_chunk_sectors_entry.attr, &queue_io_min_entry.attr, &queue_io_opt_entry.attr, &queue_discard_granularity_entry.attr, &queue_max_discard_sectors_entry.attr, &queue_max_hw_discard_sectors_entry.attr, &queue_discard_zeroes_data_entry.attr, &queue_atomic_write_max_sectors_entry.attr, &queue_atomic_write_boundary_sectors_entry.attr, &queue_atomic_write_unit_min_entry.attr, &queue_atomic_write_unit_max_entry.attr, &queue_write_same_max_entry.attr, &queue_max_write_zeroes_sectors_entry.attr, &queue_zone_append_max_entry.attr, &queue_zone_write_granularity_entry.attr, &queue_rotational_entry.attr, &queue_zoned_entry.attr, &queue_nr_zones_entry.attr, &queue_max_open_zones_entry.attr, &queue_max_active_zones_entry.attr, &queue_nomerges_entry.attr, &queue_iostats_entry.attr, &queue_stable_writes_entry.attr, &queue_add_random_entry.attr, &queue_poll_entry.attr, &queue_wc_entry.attr, &queue_fua_entry.attr, &queue_dax_entry.attr, &queue_poll_delay_entry.attr, &queue_virt_boundary_mask_entry.attr, &queue_dma_alignment_entry.attr, NULL, }; /* Request-based queue attributes that are not relevant for bio-based queues. */ static struct attribute *blk_mq_queue_attrs[] = { &queue_requests_entry.attr, &elv_iosched_entry.attr, &queue_rq_affinity_entry.attr, &queue_io_timeout_entry.attr, #ifdef CONFIG_BLK_WBT &queue_wb_lat_entry.attr, #endif NULL, }; static umode_t queue_attr_visible(struct kobject *kobj, struct attribute *attr, int n) { struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); struct request_queue *q = disk->queue; if ((attr == &queue_max_open_zones_entry.attr || attr == &queue_max_active_zones_entry.attr) && !blk_queue_is_zoned(q)) return 0; return attr->mode; } static umode_t blk_mq_queue_attr_visible(struct kobject *kobj, struct attribute *attr, int n) { struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); struct request_queue *q = disk->queue; if (!queue_is_mq(q)) return 0; if (attr == &queue_io_timeout_entry.attr && !q->mq_ops->timeout) return 0; return attr->mode; } static struct attribute_group queue_attr_group = { .attrs = queue_attrs, .is_visible = queue_attr_visible, }; static struct attribute_group blk_mq_queue_attr_group = { .attrs = blk_mq_queue_attrs, .is_visible = blk_mq_queue_attr_visible, }; #define to_queue(atr) container_of((atr), struct queue_sysfs_entry, attr) static ssize_t queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { struct queue_sysfs_entry *entry = to_queue(attr); struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); ssize_t res; if (!entry->show) return -EIO; mutex_lock(&disk->queue->sysfs_lock); res = entry->show(disk, page); mutex_unlock(&disk->queue->sysfs_lock); return res; } static ssize_t queue_attr_store(struct kobject *kobj, struct attribute *attr, const char *page, size_t length) { struct queue_sysfs_entry *entry = to_queue(attr); struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj); struct request_queue *q = disk->queue; ssize_t res; if (!entry->store) return -EIO; blk_mq_freeze_queue(q); mutex_lock(&q->sysfs_lock); res = entry->store(disk, page, length); mutex_unlock(&q->sysfs_lock); blk_mq_unfreeze_queue(q); return res; } static const struct sysfs_ops queue_sysfs_ops = { .show = queue_attr_show, .store = queue_attr_store, }; static const struct attribute_group *blk_queue_attr_groups[] = { &queue_attr_group, &blk_mq_queue_attr_group, NULL }; static void blk_queue_release(struct kobject *kobj) { /* nothing to do here, all data is associated with the parent gendisk */ } static const struct kobj_type blk_queue_ktype = { .default_groups = blk_queue_attr_groups, .sysfs_ops = &queue_sysfs_ops, .release = blk_queue_release, }; static void blk_debugfs_remove(struct gendisk *disk) { struct request_queue *q = disk->queue; mutex_lock(&q->debugfs_mutex); blk_trace_shutdown(q); debugfs_remove_recursive(q->debugfs_dir); q->debugfs_dir = NULL; q->sched_debugfs_dir = NULL; q->rqos_debugfs_dir = NULL; mutex_unlock(&q->debugfs_mutex); } /** * blk_register_queue - register a block layer queue with sysfs * @disk: Disk of which the request queue should be registered with sysfs. */ int blk_register_queue(struct gendisk *disk) { struct request_queue *q = disk->queue; int ret; mutex_lock(&q->sysfs_dir_lock); kobject_init(&disk->queue_kobj, &blk_queue_ktype); ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue"); if (ret < 0) goto out_put_queue_kobj; if (queue_is_mq(q)) { ret = blk_mq_sysfs_register(disk); if (ret) goto out_put_queue_kobj; } mutex_lock(&q->sysfs_lock); mutex_lock(&q->debugfs_mutex); q->debugfs_dir = debugfs_create_dir(disk->disk_name, blk_debugfs_root); if (queue_is_mq(q)) blk_mq_debugfs_register(q); mutex_unlock(&q->debugfs_mutex); ret = disk_register_independent_access_ranges(disk); if (ret) goto out_debugfs_remove; if (q->elevator) { ret = elv_register_queue(q, false); if (ret) goto out_unregister_ia_ranges; } ret = blk_crypto_sysfs_register(disk); if (ret) goto out_elv_unregister; blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); wbt_enable_default(disk); /* Now everything is ready and send out KOBJ_ADD uevent */ kobject_uevent(&disk->queue_kobj, KOBJ_ADD); if (q->elevator) kobject_uevent(&q->elevator->kobj, KOBJ_ADD); mutex_unlock(&q->sysfs_lock); mutex_unlock(&q->sysfs_dir_lock); /* * SCSI probing may synchronously create and destroy a lot of * request_queues for non-existent devices. Shutting down a fully * functional queue takes measureable wallclock time as RCU grace * periods are involved. To avoid excessive latency in these * cases, a request_queue starts out in a degraded mode which is * faster to shut down and is made fully functional here as * request_queues for non-existent devices never get registered. */ if (!blk_queue_init_done(q)) { blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q); percpu_ref_switch_to_percpu(&q->q_usage_counter); } return ret; out_elv_unregister: elv_unregister_queue(q); out_unregister_ia_ranges: disk_unregister_independent_access_ranges(disk); out_debugfs_remove: blk_debugfs_remove(disk); mutex_unlock(&q->sysfs_lock); out_put_queue_kobj: kobject_put(&disk->queue_kobj); mutex_unlock(&q->sysfs_dir_lock); return ret; } /** * blk_unregister_queue - counterpart of blk_register_queue() * @disk: Disk of which the request queue should be unregistered from sysfs. * * Note: the caller is responsible for guaranteeing that this function is called * after blk_register_queue() has finished. */ void blk_unregister_queue(struct gendisk *disk) { struct request_queue *q = disk->queue; if (WARN_ON(!q)) return; /* Return early if disk->queue was never registered. */ if (!blk_queue_registered(q)) return; /* * Since sysfs_remove_dir() prevents adding new directory entries * before removal of existing entries starts, protect against * concurrent elv_iosched_store() calls. */ mutex_lock(&q->sysfs_lock); blk_queue_flag_clear(QUEUE_FLAG_REGISTERED, q); mutex_unlock(&q->sysfs_lock); mutex_lock(&q->sysfs_dir_lock); /* * Remove the sysfs attributes before unregistering the queue data * structures that can be modified through sysfs. */ if (queue_is_mq(q)) blk_mq_sysfs_unregister(disk); blk_crypto_sysfs_unregister(disk); mutex_lock(&q->sysfs_lock); elv_unregister_queue(q); disk_unregister_independent_access_ranges(disk); mutex_unlock(&q->sysfs_lock); /* Now that we've deleted all child objects, we can delete the queue. */ kobject_uevent(&disk->queue_kobj, KOBJ_REMOVE); kobject_del(&disk->queue_kobj); mutex_unlock(&q->sysfs_dir_lock); blk_debugfs_remove(disk); } |
| 54 54 57 9 55 4 2 2 7 5 5 3 2 2 7 7 4 7 1 44 44 7 8 7 37 37 1 94 94 1 8 7 5 7 7 3 6 8 8 1 81 46 70 22 62 65 8 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 | // SPDX-License-Identifier: GPL-2.0-only /* * TCP CUBIC: Binary Increase Congestion control for TCP v2.3 * Home page: * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC * This is from the implementation of CUBIC TCP in * Sangtae Ha, Injong Rhee and Lisong Xu, * "CUBIC: A New TCP-Friendly High-Speed TCP Variant" * in ACM SIGOPS Operating System Review, July 2008. * Available from: * http://netsrv.csc.ncsu.edu/export/cubic_a_new_tcp_2008.pdf * * CUBIC integrates a new slow start algorithm, called HyStart. * The details of HyStart are presented in * Sangtae Ha and Injong Rhee, * "Taming the Elephants: New TCP Slow Start", NCSU TechReport 2008. * Available from: * http://netsrv.csc.ncsu.edu/export/hystart_techreport_2008.pdf * * All testing results are available from: * http://netsrv.csc.ncsu.edu/wiki/index.php/TCP_Testing * * Unless CUBIC is enabled and congestion window is large * this behaves the same as the original Reno. */ #include <linux/mm.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/module.h> #include <linux/math64.h> #include <net/tcp.h> #define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation * max_cwnd = snd_cwnd * beta */ #define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */ /* Two methods of hybrid slow start */ #define HYSTART_ACK_TRAIN 0x1 #define HYSTART_DELAY 0x2 /* Number of delay samples for detecting the increase of delay */ #define HYSTART_MIN_SAMPLES 8 #define HYSTART_DELAY_MIN (4000U) /* 4 ms */ #define HYSTART_DELAY_MAX (16000U) /* 16 ms */ #define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) static int fast_convergence __read_mostly = 1; static int beta __read_mostly = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */ static int initial_ssthresh __read_mostly; static int bic_scale __read_mostly = 41; static int tcp_friendliness __read_mostly = 1; static int hystart __read_mostly = 1; static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY; static int hystart_low_window __read_mostly = 16; static int hystart_ack_delta_us __read_mostly = 2000; static u32 cube_rtt_scale __read_mostly; static u32 beta_scale __read_mostly; static u64 cube_factor __read_mostly; /* Note parameters that are used for precomputing scale factors are read-only */ module_param(fast_convergence, int, 0644); MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence"); module_param(beta, int, 0644); MODULE_PARM_DESC(beta, "beta for multiplicative increase"); module_param(initial_ssthresh, int, 0644); MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold"); module_param(bic_scale, int, 0444); MODULE_PARM_DESC(bic_scale, "scale (scaled by 1024) value for bic function (bic_scale/1024)"); module_param(tcp_friendliness, int, 0644); MODULE_PARM_DESC(tcp_friendliness, "turn on/off tcp friendliness"); module_param(hystart, int, 0644); MODULE_PARM_DESC(hystart, "turn on/off hybrid slow start algorithm"); module_param(hystart_detect, int, 0644); MODULE_PARM_DESC(hystart_detect, "hybrid slow start detection mechanisms" " 1: packet-train 2: delay 3: both packet-train and delay"); module_param(hystart_low_window, int, 0644); MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start"); module_param(hystart_ack_delta_us, int, 0644); MODULE_PARM_DESC(hystart_ack_delta_us, "spacing between ack's indicating train (usecs)"); /* BIC TCP Parameters */ struct bictcp { u32 cnt; /* increase cwnd by 1 after ACKs */ u32 last_max_cwnd; /* last maximum snd_cwnd */ u32 last_cwnd; /* the last snd_cwnd */ u32 last_time; /* time when updated last_cwnd */ u32 bic_origin_point;/* origin point of bic function */ u32 bic_K; /* time to origin point from the beginning of the current epoch */ u32 delay_min; /* min delay (usec) */ u32 epoch_start; /* beginning of an epoch */ u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ u16 unused; u8 sample_cnt; /* number of samples to decide curr_rtt */ u8 found; /* the exit point is found? */ u32 round_start; /* beginning of each round */ u32 end_seq; /* end_seq of the round */ u32 last_ack; /* last time when the ACK spacing is close */ u32 curr_rtt; /* the minimum rtt of current round */ }; static inline void bictcp_reset(struct bictcp *ca) { memset(ca, 0, offsetof(struct bictcp, unused)); ca->found = 0; } static inline u32 bictcp_clock_us(const struct sock *sk) { return tcp_sk(sk)->tcp_mstamp; } static inline void bictcp_hystart_reset(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); ca->round_start = ca->last_ack = bictcp_clock_us(sk); ca->end_seq = tp->snd_nxt; ca->curr_rtt = ~0U; ca->sample_cnt = 0; } __bpf_kfunc static void cubictcp_init(struct sock *sk) { struct bictcp *ca = inet_csk_ca(sk); bictcp_reset(ca); if (hystart) bictcp_hystart_reset(sk); if (!hystart && initial_ssthresh) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } __bpf_kfunc static void cubictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event) { if (event == CA_EVENT_TX_START) { struct bictcp *ca = inet_csk_ca(sk); u32 now = tcp_jiffies32; s32 delta; delta = now - tcp_sk(sk)->lsndtime; /* We were application limited (idle) for a while. * Shift epoch_start to keep cwnd growth to cubic curve. */ if (ca->epoch_start && delta > 0) { ca->epoch_start += delta; if (after(ca->epoch_start, now)) ca->epoch_start = now; } return; } } /* calculate the cubic root of x using a table lookup followed by one * Newton-Raphson iteration. * Avg err ~= 0.195% */ static u32 cubic_root(u64 a) { u32 x, b, shift; /* * cbrt(x) MSB values for x MSB values in [0..63]. * Precomputed then refined by hand - Willy Tarreau * * For x in [0..63], * v = cbrt(x << 18) - 1 * cbrt(x) = (v[x] + 10) >> 6 */ static const u8 v[] = { /* 0x00 */ 0, 54, 54, 54, 118, 118, 118, 118, /* 0x08 */ 123, 129, 134, 138, 143, 147, 151, 156, /* 0x10 */ 157, 161, 164, 168, 170, 173, 176, 179, /* 0x18 */ 181, 185, 187, 190, 192, 194, 197, 199, /* 0x20 */ 200, 202, 204, 206, 209, 211, 213, 215, /* 0x28 */ 217, 219, 221, 222, 224, 225, 227, 229, /* 0x30 */ 231, 232, 234, 236, 237, 239, 240, 242, /* 0x38 */ 244, 245, 246, 248, 250, 251, 252, 254, }; b = fls64(a); if (b < 7) { /* a in [0..63] */ return ((u32)v[(u32)a] + 35) >> 6; } b = ((b * 84) >> 8) - 1; shift = (a >> (b * 3)); x = ((u32)(((u32)v[shift] + 10) << b)) >> 6; /* * Newton-Raphson iteration * 2 * x = ( 2 * x + a / x ) / 3 * k+1 k k */ x = (2 * x + (u32)div64_u64(a, (u64)x * (u64)(x - 1))); x = ((x * 341) >> 10); return x; } /* * Compute congestion window to use. */ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) { u32 delta, bic_target, max_cnt; u64 offs, t; ca->ack_cnt += acked; /* count the number of ACKed packets */ if (ca->last_cwnd == cwnd && (s32)(tcp_jiffies32 - ca->last_time) <= HZ / 32) return; /* The CUBIC function can update ca->cnt at most once per jiffy. * On all cwnd reduction events, ca->epoch_start is set to 0, * which will force a recalculation of ca->cnt. */ if (ca->epoch_start && tcp_jiffies32 == ca->last_time) goto tcp_friendliness; ca->last_cwnd = cwnd; ca->last_time = tcp_jiffies32; if (ca->epoch_start == 0) { ca->epoch_start = tcp_jiffies32; /* record beginning */ ca->ack_cnt = acked; /* start counting */ ca->tcp_cwnd = cwnd; /* syn with cubic */ if (ca->last_max_cwnd <= cwnd) { ca->bic_K = 0; ca->bic_origin_point = cwnd; } else { /* Compute new K based on * (wmax-cwnd) * (srtt>>3 / HZ) / c * 2^(3*bictcp_HZ) */ ca->bic_K = cubic_root(cube_factor * (ca->last_max_cwnd - cwnd)); ca->bic_origin_point = ca->last_max_cwnd; } } /* cubic function - calc*/ /* calculate c * time^3 / rtt, * while considering overflow in calculation of time^3 * (so time^3 is done by using 64 bit) * and without the support of division of 64bit numbers * (so all divisions are done by using 32 bit) * also NOTE the unit of those veriables * time = (t - K) / 2^bictcp_HZ * c = bic_scale >> 10 * rtt = (srtt >> 3) / HZ * !!! The following code does not have overflow problems, * if the cwnd < 1 million packets !!! */ t = (s32)(tcp_jiffies32 - ca->epoch_start); t += usecs_to_jiffies(ca->delay_min); /* change the unit from HZ to bictcp_HZ */ t <<= BICTCP_HZ; do_div(t, HZ); if (t < ca->bic_K) /* t - K */ offs = ca->bic_K - t; else offs = t - ca->bic_K; /* c/rtt * (t-K)^3 */ delta = (cube_rtt_scale * offs * offs * offs) >> (10+3*BICTCP_HZ); if (t < ca->bic_K) /* below origin*/ bic_target = ca->bic_origin_point - delta; else /* above origin*/ bic_target = ca->bic_origin_point + delta; /* cubic function - calc bictcp_cnt*/ if (bic_target > cwnd) { ca->cnt = cwnd / (bic_target - cwnd); } else { ca->cnt = 100 * cwnd; /* very small increment*/ } /* * The initial growth of cubic function may be too conservative * when the available bandwidth is still unknown. */ if (ca->last_max_cwnd == 0 && ca->cnt > 20) ca->cnt = 20; /* increase cwnd 5% per RTT */ tcp_friendliness: /* TCP Friendly */ if (tcp_friendliness) { u32 scale = beta_scale; delta = (cwnd * scale) >> 3; while (ca->ack_cnt > delta) { /* update tcp cwnd */ ca->ack_cnt -= delta; ca->tcp_cwnd++; } if (ca->tcp_cwnd > cwnd) { /* if bic is slower than tcp */ delta = ca->tcp_cwnd - cwnd; max_cnt = cwnd / delta; if (ca->cnt > max_cnt) ca->cnt = max_cnt; } } /* The maximum rate of cwnd increase CUBIC allows is 1 packet per * 2 packets ACKed, meaning cwnd grows at 1.5x per RTT. */ ca->cnt = max(ca->cnt, 2U); } __bpf_kfunc static void cubictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); if (!tcp_is_cwnd_limited(sk)) return; if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; } bictcp_update(ca, tcp_snd_cwnd(tp), acked); tcp_cong_avoid_ai(tp, ca->cnt, acked); } __bpf_kfunc static u32 cubictcp_recalc_ssthresh(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); ca->epoch_start = 0; /* end of epoch */ /* Wmax and fast convergence */ if (tcp_snd_cwnd(tp) < ca->last_max_cwnd && fast_convergence) ca->last_max_cwnd = (tcp_snd_cwnd(tp) * (BICTCP_BETA_SCALE + beta)) / (2 * BICTCP_BETA_SCALE); else ca->last_max_cwnd = tcp_snd_cwnd(tp); return max((tcp_snd_cwnd(tp) * beta) / BICTCP_BETA_SCALE, 2U); } __bpf_kfunc static void cubictcp_state(struct sock *sk, u8 new_state) { if (new_state == TCP_CA_Loss) { bictcp_reset(inet_csk_ca(sk)); bictcp_hystart_reset(sk); } } /* Account for TSO/GRO delays. * Otherwise short RTT flows could get too small ssthresh, since during * slow start we begin with small TSO packets and ca->delay_min would * not account for long aggregation delay when TSO packets get bigger. * Ideally even with a very small RTT we would like to have at least one * TSO packet being sent and received by GRO, and another one in qdisc layer. * We apply another 100% factor because @rate is doubled at this point. * We cap the cushion to 1ms. */ static u32 hystart_ack_delay(const struct sock *sk) { unsigned long rate; rate = READ_ONCE(sk->sk_pacing_rate); if (!rate) return 0; return min_t(u64, USEC_PER_MSEC, div64_ul((u64)sk->sk_gso_max_size * 4 * USEC_PER_SEC, rate)); } static void hystart_update(struct sock *sk, u32 delay) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); u32 threshold; if (after(tp->snd_una, ca->end_seq)) bictcp_hystart_reset(sk); if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock_us(sk); /* first detection parameter - ack-train detection */ if ((s32)(now - ca->last_ack) <= hystart_ack_delta_us) { ca->last_ack = now; threshold = ca->delay_min + hystart_ack_delay(sk); /* Hystart ack train triggers if we get ack past * ca->delay_min/2. * Pacing might have delayed packets up to RTT/2 * during slow start. */ if (sk->sk_pacing_status == SK_PACING_NONE) threshold >>= 1; if ((s32)(now - ca->round_start) > threshold) { ca->found = 1; pr_debug("hystart_ack_train (%u > %u) delay_min %u (+ ack_delay %u) cwnd %u\n", now - ca->round_start, threshold, ca->delay_min, hystart_ack_delay(sk), tcp_snd_cwnd(tp)); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINDETECT); NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINCWND, tcp_snd_cwnd(tp)); tp->snd_ssthresh = tcp_snd_cwnd(tp); } } } if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ if (ca->curr_rtt > delay) ca->curr_rtt = delay; if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { ca->found = 1; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYDETECT); NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYCWND, tcp_snd_cwnd(tp)); tp->snd_ssthresh = tcp_snd_cwnd(tp); } } } } __bpf_kfunc static void cubictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); u32 delay; /* Some calls are for duplicates without timetamps */ if (sample->rtt_us < 0) return; /* Discard delay samples right after fast recovery */ if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ) return; delay = sample->rtt_us; if (delay == 0) delay = 1; /* first time call or link delay decreases */ if (ca->delay_min == 0 || ca->delay_min > delay) ca->delay_min = delay; /* hystart triggers when cwnd is larger than some threshold */ if (!ca->found && tcp_in_slow_start(tp) && hystart && tcp_snd_cwnd(tp) >= hystart_low_window) hystart_update(sk, delay); } static struct tcp_congestion_ops cubictcp __read_mostly = { .init = cubictcp_init, .ssthresh = cubictcp_recalc_ssthresh, .cong_avoid = cubictcp_cong_avoid, .set_state = cubictcp_state, .undo_cwnd = tcp_reno_undo_cwnd, .cwnd_event = cubictcp_cwnd_event, .pkts_acked = cubictcp_acked, .owner = THIS_MODULE, .name = "cubic", }; BTF_KFUNCS_START(tcp_cubic_check_kfunc_ids) BTF_ID_FLAGS(func, cubictcp_init) BTF_ID_FLAGS(func, cubictcp_recalc_ssthresh) BTF_ID_FLAGS(func, cubictcp_cong_avoid) BTF_ID_FLAGS(func, cubictcp_state) BTF_ID_FLAGS(func, cubictcp_cwnd_event) BTF_ID_FLAGS(func, cubictcp_acked) BTF_KFUNCS_END(tcp_cubic_check_kfunc_ids) static const struct btf_kfunc_id_set tcp_cubic_kfunc_set = { .owner = THIS_MODULE, .set = &tcp_cubic_check_kfunc_ids, }; static int __init cubictcp_register(void) { int ret; BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE); /* Precompute a bunch of the scaling factors that are used per-packet * based on SRTT of 100ms */ beta_scale = 8*(BICTCP_BETA_SCALE+beta) / 3 / (BICTCP_BETA_SCALE - beta); cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */ /* calculate the "K" for (wmax-cwnd) = c/rtt * K^3 * so K = cubic_root( (wmax-cwnd)*rtt/c ) * the unit of K is bictcp_HZ=2^10, not HZ * * c = bic_scale >> 10 * rtt = 100ms * * the following code has been designed and tested for * cwnd < 1 million packets * RTT < 100 seconds * HZ < 1,000,00 (corresponding to 10 nano-second) */ /* 1/c * 2^2*bictcp_HZ * srtt */ cube_factor = 1ull << (10+3*BICTCP_HZ); /* 2^40 */ /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS, &tcp_cubic_kfunc_set); if (ret < 0) return ret; return tcp_register_congestion_control(&cubictcp); } static void __exit cubictcp_unregister(void) { tcp_unregister_congestion_control(&cubictcp); } module_init(cubictcp_register); module_exit(cubictcp_unregister); MODULE_AUTHOR("Sangtae Ha, Stephen Hemminger"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CUBIC TCP"); MODULE_VERSION("2.3"); |
| 150 140 76 152 46 46 150 150 152 79 93 139 83 152 150 95 30 76 83 152 1 29 139 139 138 140 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> * * Development of this code funded by Astaro AG (http://www.astaro.com/) */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> #include <linux/list.h> #include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/static_key.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_log.h> #include <net/netfilter/nft_meta.h> #if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_X86) static struct static_key_false nf_tables_skip_direct_calls; static bool nf_skip_indirect_calls(void) { return static_branch_likely(&nf_tables_skip_direct_calls); } static void __init nf_skip_indirect_calls_enable(void) { if (!cpu_feature_enabled(X86_FEATURE_RETPOLINE)) static_branch_enable(&nf_tables_skip_direct_calls); } #else static inline bool nf_skip_indirect_calls(void) { return false; } static inline void nf_skip_indirect_calls_enable(void) { } #endif static noinline void __nft_trace_packet(const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, const struct nft_rule_dp *rule, struct nft_traceinfo *info, enum nft_trace_types type) { if (!info->trace || !info->nf_trace) return; info->type = type; nft_trace_notify(pkt, verdict, rule, info); } static inline void nft_trace_packet(const struct nft_pktinfo *pkt, struct nft_verdict *verdict, struct nft_traceinfo *info, const struct nft_rule_dp *rule, enum nft_trace_types type) { if (static_branch_unlikely(&nft_trace_enabled)) { info->nf_trace = pkt->skb->nf_trace; __nft_trace_packet(pkt, verdict, rule, info, type); } } static inline void nft_trace_copy_nftrace(const struct nft_pktinfo *pkt, struct nft_traceinfo *info) { if (static_branch_unlikely(&nft_trace_enabled)) info->nf_trace = pkt->skb->nf_trace; } static void nft_bitwise_fast_eval(const struct nft_expr *expr, struct nft_regs *regs) { const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr); u32 *src = ®s->data[priv->sreg]; u32 *dst = ®s->data[priv->dreg]; *dst = (*src & priv->mask) ^ priv->xor; } static void nft_cmp_fast_eval(const struct nft_expr *expr, struct nft_regs *regs) { const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr); if (((regs->data[priv->sreg] & priv->mask) == priv->data) ^ priv->inv) return; regs->verdict.code = NFT_BREAK; } static void nft_cmp16_fast_eval(const struct nft_expr *expr, struct nft_regs *regs) { const struct nft_cmp16_fast_expr *priv = nft_expr_priv(expr); const u64 *reg_data = (const u64 *)®s->data[priv->sreg]; const u64 *mask = (const u64 *)&priv->mask; const u64 *data = (const u64 *)&priv->data; if (((reg_data[0] & mask[0]) == data[0] && ((reg_data[1] & mask[1]) == data[1])) ^ priv->inv) return; regs->verdict.code = NFT_BREAK; } static noinline void __nft_trace_verdict(const struct nft_pktinfo *pkt, struct nft_traceinfo *info, const struct nft_rule_dp *rule, const struct nft_regs *regs) { enum nft_trace_types type; switch (regs->verdict.code & NF_VERDICT_MASK) { case NFT_CONTINUE: case NFT_RETURN: type = NFT_TRACETYPE_RETURN; break; case NF_STOLEN: type = NFT_TRACETYPE_RULE; /* can't access skb->nf_trace; use copy */ break; default: type = NFT_TRACETYPE_RULE; if (info->trace) info->nf_trace = pkt->skb->nf_trace; break; } __nft_trace_packet(pkt, ®s->verdict, rule, info, type); } static inline void nft_trace_verdict(const struct nft_pktinfo *pkt, struct nft_traceinfo *info, const struct nft_rule_dp *rule, const struct nft_regs *regs) { if (static_branch_unlikely(&nft_trace_enabled)) __nft_trace_verdict(pkt, info, rule, regs); } static bool nft_payload_fast_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_payload *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; u32 *dest = ®s->data[priv->dreg]; unsigned char *ptr; if (priv->base == NFT_PAYLOAD_NETWORK_HEADER) ptr = skb_network_header(skb); else { if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) return false; ptr = skb->data + nft_thoff(pkt); } ptr += priv->offset; if (unlikely(ptr + priv->len > skb_tail_pointer(skb))) return false; *dest = 0; if (priv->len == 2) *(u16 *)dest = *(u16 *)ptr; else if (priv->len == 4) *(u32 *)dest = *(u32 *)ptr; else *(u8 *)dest = *(u8 *)ptr; return true; } DEFINE_STATIC_KEY_FALSE(nft_counters_enabled); static noinline void nft_update_chain_stats(const struct nft_chain *chain, const struct nft_pktinfo *pkt) { struct nft_base_chain *base_chain; struct nft_stats __percpu *pstats; struct nft_stats *stats; base_chain = nft_base_chain(chain); pstats = READ_ONCE(base_chain->stats); if (pstats) { local_bh_disable(); stats = this_cpu_ptr(pstats); u64_stats_update_begin(&stats->syncp); stats->pkts++; stats->bytes += pkt->skb->len; u64_stats_update_end(&stats->syncp); local_bh_enable(); } } struct nft_jumpstack { const struct nft_rule_dp *rule; }; static void expr_call_ops_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nft_pktinfo *pkt) { #ifdef CONFIG_MITIGATION_RETPOLINE unsigned long e; if (nf_skip_indirect_calls()) goto indirect_call; e = (unsigned long)expr->ops->eval; #define X(e, fun) \ do { if ((e) == (unsigned long)(fun)) \ return fun(expr, regs, pkt); } while (0) X(e, nft_payload_eval); X(e, nft_cmp_eval); X(e, nft_counter_eval); X(e, nft_meta_get_eval); X(e, nft_lookup_eval); #if IS_ENABLED(CONFIG_NFT_CT) X(e, nft_ct_get_fast_eval); #endif X(e, nft_range_eval); X(e, nft_immediate_eval); X(e, nft_byteorder_eval); X(e, nft_dynset_eval); X(e, nft_rt_get_eval); X(e, nft_bitwise_eval); X(e, nft_objref_eval); X(e, nft_objref_map_eval); #undef X indirect_call: #endif /* CONFIG_MITIGATION_RETPOLINE */ expr->ops->eval(expr, regs, pkt); } #define nft_rule_expr_first(rule) (struct nft_expr *)&rule->data[0] #define nft_rule_expr_next(expr) ((void *)expr) + expr->ops->size #define nft_rule_expr_last(rule) (struct nft_expr *)&rule->data[rule->dlen] #define nft_rule_dp_for_each_expr(expr, last, rule) \ for ((expr) = nft_rule_expr_first(rule), (last) = nft_rule_expr_last(rule); \ (expr) != (last); \ (expr) = nft_rule_expr_next(expr)) unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv) { const struct nft_chain *chain = priv, *basechain = chain; const struct net *net = nft_net(pkt); const struct nft_expr *expr, *last; const struct nft_rule_dp *rule; struct nft_regs regs = {}; unsigned int stackptr = 0; struct nft_jumpstack jumpstack[NFT_JUMP_STACK_SIZE]; bool genbit = READ_ONCE(net->nft.gencursor); struct nft_rule_blob *blob; struct nft_traceinfo info; info.trace = false; if (static_branch_unlikely(&nft_trace_enabled)) nft_trace_init(&info, pkt, basechain); do_chain: if (genbit) blob = rcu_dereference(chain->blob_gen_1); else blob = rcu_dereference(chain->blob_gen_0); rule = (struct nft_rule_dp *)blob->data; next_rule: regs.verdict.code = NFT_CONTINUE; for (; !rule->is_last ; rule = nft_rule_next(rule)) { nft_rule_dp_for_each_expr(expr, last, rule) { if (expr->ops == &nft_cmp_fast_ops) nft_cmp_fast_eval(expr, ®s); else if (expr->ops == &nft_cmp16_fast_ops) nft_cmp16_fast_eval(expr, ®s); else if (expr->ops == &nft_bitwise_fast_ops) nft_bitwise_fast_eval(expr, ®s); else if (expr->ops != &nft_payload_fast_ops || !nft_payload_fast_eval(expr, ®s, pkt)) expr_call_ops_eval(expr, ®s, pkt); if (regs.verdict.code != NFT_CONTINUE) break; } switch (regs.verdict.code) { case NFT_BREAK: regs.verdict.code = NFT_CONTINUE; nft_trace_copy_nftrace(pkt, &info); continue; case NFT_CONTINUE: nft_trace_packet(pkt, ®s.verdict, &info, rule, NFT_TRACETYPE_RULE); continue; } break; } nft_trace_verdict(pkt, &info, rule, ®s); switch (regs.verdict.code & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_QUEUE: case NF_STOLEN: return regs.verdict.code; case NF_DROP: return NF_DROP_REASON(pkt->skb, SKB_DROP_REASON_NETFILTER_DROP, EPERM); } switch (regs.verdict.code) { case NFT_JUMP: if (WARN_ON_ONCE(stackptr >= NFT_JUMP_STACK_SIZE)) return NF_DROP; jumpstack[stackptr].rule = nft_rule_next(rule); stackptr++; fallthrough; case NFT_GOTO: chain = regs.verdict.chain; goto do_chain; case NFT_CONTINUE: case NFT_RETURN: break; default: WARN_ON_ONCE(1); } if (stackptr > 0) { stackptr--; rule = jumpstack[stackptr].rule; goto next_rule; } nft_trace_packet(pkt, ®s.verdict, &info, NULL, NFT_TRACETYPE_POLICY); if (static_branch_unlikely(&nft_counters_enabled)) nft_update_chain_stats(basechain, pkt); if (nft_base_chain(basechain)->policy == NF_DROP) return NF_DROP_REASON(pkt->skb, SKB_DROP_REASON_NETFILTER_DROP, EPERM); return nft_base_chain(basechain)->policy; } EXPORT_SYMBOL_GPL(nft_do_chain); static struct nft_expr_type *nft_basic_types[] = { &nft_imm_type, &nft_cmp_type, &nft_lookup_type, &nft_bitwise_type, &nft_byteorder_type, &nft_payload_type, &nft_dynset_type, &nft_range_type, &nft_meta_type, &nft_rt_type, &nft_exthdr_type, &nft_last_type, &nft_counter_type, &nft_objref_type, &nft_inner_type, }; static struct nft_object_type *nft_basic_objects[] = { #ifdef CONFIG_NETWORK_SECMARK &nft_secmark_obj_type, #endif &nft_counter_obj_type, }; int __init nf_tables_core_module_init(void) { int err, i, j = 0; nft_counter_init_seqcount(); for (i = 0; i < ARRAY_SIZE(nft_basic_objects); i++) { err = nft_register_obj(nft_basic_objects[i]); if (err) goto err; } for (j = 0; j < ARRAY_SIZE(nft_basic_types); j++) { err = nft_register_expr(nft_basic_types[j]); if (err) goto err; } nf_skip_indirect_calls_enable(); return 0; err: while (j-- > 0) nft_unregister_expr(nft_basic_types[j]); while (i-- > 0) nft_unregister_obj(nft_basic_objects[i]); return err; } void nf_tables_core_module_exit(void) { int i; i = ARRAY_SIZE(nft_basic_types); while (i-- > 0) nft_unregister_expr(nft_basic_types[i]); i = ARRAY_SIZE(nft_basic_objects); while (i-- > 0) nft_unregister_obj(nft_basic_objects[i]); } |
| 316 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Scatterlist Cryptographic API. * * Copyright (c) 2002 James Morris <jmorris@intercode.com.au> * Copyright (c) 2002 David S. Miller (davem@redhat.com) * Copyright (c) 2005 Herbert Xu <herbert@gondor.apana.org.au> * * Portions derived from Cryptoapi, by Alexander Kjeldaas <astor@fast.no> * and Nettle, by Niels Möller. */ #ifndef _LINUX_CRYPTO_H #define _LINUX_CRYPTO_H #include <linux/completion.h> #include <linux/refcount.h> #include <linux/slab.h> #include <linux/types.h> /* * Algorithm masks and types. */ #define CRYPTO_ALG_TYPE_MASK 0x0000000f #define CRYPTO_ALG_TYPE_CIPHER 0x00000001 #define CRYPTO_ALG_TYPE_COMPRESS 0x00000002 #define CRYPTO_ALG_TYPE_AEAD 0x00000003 #define CRYPTO_ALG_TYPE_LSKCIPHER 0x00000004 #define CRYPTO_ALG_TYPE_SKCIPHER 0x00000005 #define CRYPTO_ALG_TYPE_AKCIPHER 0x00000006 #define CRYPTO_ALG_TYPE_SIG 0x00000007 #define CRYPTO_ALG_TYPE_KPP 0x00000008 #define CRYPTO_ALG_TYPE_ACOMPRESS 0x0000000a #define CRYPTO_ALG_TYPE_SCOMPRESS 0x0000000b #define CRYPTO_ALG_TYPE_RNG 0x0000000c #define CRYPTO_ALG_TYPE_HASH 0x0000000e #define CRYPTO_ALG_TYPE_SHASH 0x0000000e #define CRYPTO_ALG_TYPE_AHASH 0x0000000f #define CRYPTO_ALG_TYPE_ACOMPRESS_MASK 0x0000000e #define CRYPTO_ALG_LARVAL 0x00000010 #define CRYPTO_ALG_DEAD 0x00000020 #define CRYPTO_ALG_DYING 0x00000040 #define CRYPTO_ALG_ASYNC 0x00000080 /* * Set if the algorithm (or an algorithm which it uses) requires another * algorithm of the same type to handle corner cases. */ #define CRYPTO_ALG_NEED_FALLBACK 0x00000100 /* * Set if the algorithm has passed automated run-time testing. Note that * if there is no run-time testing for a given algorithm it is considered * to have passed. */ #define CRYPTO_ALG_TESTED 0x00000400 /* * Set if the algorithm is an instance that is built from templates. */ #define CRYPTO_ALG_INSTANCE 0x00000800 /* Set this bit if the algorithm provided is hardware accelerated but * not available to userspace via instruction set or so. */ #define CRYPTO_ALG_KERN_DRIVER_ONLY 0x00001000 /* * Mark a cipher as a service implementation only usable by another * cipher and never by a normal user of the kernel crypto API */ #define CRYPTO_ALG_INTERNAL 0x00002000 /* * Set if the algorithm has a ->setkey() method but can be used without * calling it first, i.e. there is a default key. */ #define CRYPTO_ALG_OPTIONAL_KEY 0x00004000 /* * Don't trigger module loading */ #define CRYPTO_NOLOAD 0x00008000 /* * The algorithm may allocate memory during request processing, i.e. during * encryption, decryption, or hashing. Users can request an algorithm with this * flag unset if they can't handle memory allocation failures. * * This flag is currently only implemented for algorithms of type "skcipher", * "aead", "ahash", "shash", and "cipher". Algorithms of other types might not * have this flag set even if they allocate memory. * * In some edge cases, algorithms can allocate memory regardless of this flag. * To avoid these cases, users must obey the following usage constraints: * skcipher: * - The IV buffer and all scatterlist elements must be aligned to the * algorithm's alignmask. * - If the data were to be divided into chunks of size * crypto_skcipher_walksize() (with any remainder going at the end), no * chunk can cross a page boundary or a scatterlist element boundary. * aead: * - The IV buffer and all scatterlist elements must be aligned to the * algorithm's alignmask. * - The first scatterlist element must contain all the associated data, * and its pages must be !PageHighMem. * - If the plaintext/ciphertext were to be divided into chunks of size * crypto_aead_walksize() (with the remainder going at the end), no chunk * can cross a page boundary or a scatterlist element boundary. * ahash: * - crypto_ahash_finup() must not be used unless the algorithm implements * ->finup() natively. */ #define CRYPTO_ALG_ALLOCATES_MEMORY 0x00010000 /* * Mark an algorithm as a service implementation only usable by a * template and never by a normal user of the kernel crypto API. * This is intended to be used by algorithms that are themselves * not FIPS-approved but may instead be used to implement parts of * a FIPS-approved algorithm (e.g., dh vs. ffdhe2048(dh)). */ #define CRYPTO_ALG_FIPS_INTERNAL 0x00020000 /* * Transform masks and values (for crt_flags). */ #define CRYPTO_TFM_NEED_KEY 0x00000001 #define CRYPTO_TFM_REQ_MASK 0x000fff00 #define CRYPTO_TFM_REQ_FORBID_WEAK_KEYS 0x00000100 #define CRYPTO_TFM_REQ_MAY_SLEEP 0x00000200 #define CRYPTO_TFM_REQ_MAY_BACKLOG 0x00000400 /* * Miscellaneous stuff. */ #define CRYPTO_MAX_ALG_NAME 128 /* * The macro CRYPTO_MINALIGN_ATTR (along with the void * type in the actual * declaration) is used to ensure that the crypto_tfm context structure is * aligned correctly for the given architecture so that there are no alignment * faults for C data types. On architectures that support non-cache coherent * DMA, such as ARM or arm64, it also takes into account the minimal alignment * that is required to ensure that the context struct member does not share any * cachelines with the rest of the struct. This is needed to ensure that cache * maintenance for non-coherent DMA (cache invalidation in particular) does not * affect data that may be accessed by the CPU concurrently. */ #define CRYPTO_MINALIGN ARCH_KMALLOC_MINALIGN #define CRYPTO_MINALIGN_ATTR __attribute__ ((__aligned__(CRYPTO_MINALIGN))) struct crypto_tfm; struct crypto_type; struct module; typedef void (*crypto_completion_t)(void *req, int err); /** * DOC: Block Cipher Context Data Structures * * These data structures define the operating context for each block cipher * type. */ struct crypto_async_request { struct list_head list; crypto_completion_t complete; void *data; struct crypto_tfm *tfm; u32 flags; }; /** * DOC: Block Cipher Algorithm Definitions * * These data structures define modular crypto algorithm implementations, * managed via crypto_register_alg() and crypto_unregister_alg(). */ /** * struct cipher_alg - single-block symmetric ciphers definition * @cia_min_keysize: Minimum key size supported by the transformation. This is * the smallest key length supported by this transformation * algorithm. This must be set to one of the pre-defined * values as this is not hardware specific. Possible values * for this field can be found via git grep "_MIN_KEY_SIZE" * include/crypto/ * @cia_max_keysize: Maximum key size supported by the transformation. This is * the largest key length supported by this transformation * algorithm. This must be set to one of the pre-defined values * as this is not hardware specific. Possible values for this * field can be found via git grep "_MAX_KEY_SIZE" * include/crypto/ * @cia_setkey: Set key for the transformation. This function is used to either * program a supplied key into the hardware or store the key in the * transformation context for programming it later. Note that this * function does modify the transformation context. This function * can be called multiple times during the existence of the * transformation object, so one must make sure the key is properly * reprogrammed into the hardware. This function is also * responsible for checking the key length for validity. * @cia_encrypt: Encrypt a single block. This function is used to encrypt a * single block of data, which must be @cra_blocksize big. This * always operates on a full @cra_blocksize and it is not possible * to encrypt a block of smaller size. The supplied buffers must * therefore also be at least of @cra_blocksize size. Both the * input and output buffers are always aligned to @cra_alignmask. * In case either of the input or output buffer supplied by user * of the crypto API is not aligned to @cra_alignmask, the crypto * API will re-align the buffers. The re-alignment means that a * new buffer will be allocated, the data will be copied into the * new buffer, then the processing will happen on the new buffer, * then the data will be copied back into the original buffer and * finally the new buffer will be freed. In case a software * fallback was put in place in the @cra_init call, this function * might need to use the fallback if the algorithm doesn't support * all of the key sizes. In case the key was stored in * transformation context, the key might need to be re-programmed * into the hardware in this function. This function shall not * modify the transformation context, as this function may be * called in parallel with the same transformation object. * @cia_decrypt: Decrypt a single block. This is a reverse counterpart to * @cia_encrypt, and the conditions are exactly the same. * * All fields are mandatory and must be filled. */ struct cipher_alg { unsigned int cia_min_keysize; unsigned int cia_max_keysize; int (*cia_setkey)(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen); void (*cia_encrypt)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); void (*cia_decrypt)(struct crypto_tfm *tfm, u8 *dst, const u8 *src); }; /** * struct compress_alg - compression/decompression algorithm * @coa_compress: Compress a buffer of specified length, storing the resulting * data in the specified buffer. Return the length of the * compressed data in dlen. * @coa_decompress: Decompress the source buffer, storing the uncompressed * data in the specified buffer. The length of the data is * returned in dlen. * * All fields are mandatory. */ struct compress_alg { int (*coa_compress)(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); int (*coa_decompress)(struct crypto_tfm *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); }; #define cra_cipher cra_u.cipher #define cra_compress cra_u.compress /** * struct crypto_alg - definition of a cryptograpic cipher algorithm * @cra_flags: Flags describing this transformation. See include/linux/crypto.h * CRYPTO_ALG_* flags for the flags which go in here. Those are * used for fine-tuning the description of the transformation * algorithm. * @cra_blocksize: Minimum block size of this transformation. The size in bytes * of the smallest possible unit which can be transformed with * this algorithm. The users must respect this value. * In case of HASH transformation, it is possible for a smaller * block than @cra_blocksize to be passed to the crypto API for * transformation, in case of any other transformation type, an * error will be returned upon any attempt to transform smaller * than @cra_blocksize chunks. * @cra_ctxsize: Size of the operational context of the transformation. This * value informs the kernel crypto API about the memory size * needed to be allocated for the transformation context. * @cra_alignmask: For cipher, skcipher, lskcipher, and aead algorithms this is * 1 less than the alignment, in bytes, that the algorithm * implementation requires for input and output buffers. When * the crypto API is invoked with buffers that are not aligned * to this alignment, the crypto API automatically utilizes * appropriately aligned temporary buffers to comply with what * the algorithm needs. (For scatterlists this happens only if * the algorithm uses the skcipher_walk helper functions.) This * misalignment handling carries a performance penalty, so it is * preferred that algorithms do not set a nonzero alignmask. * Also, crypto API users may wish to allocate buffers aligned * to the alignmask of the algorithm being used, in order to * avoid the API having to realign them. Note: the alignmask is * not supported for hash algorithms and is always 0 for them. * @cra_priority: Priority of this transformation implementation. In case * multiple transformations with same @cra_name are available to * the Crypto API, the kernel will use the one with highest * @cra_priority. * @cra_name: Generic name (usable by multiple implementations) of the * transformation algorithm. This is the name of the transformation * itself. This field is used by the kernel when looking up the * providers of particular transformation. * @cra_driver_name: Unique name of the transformation provider. This is the * name of the provider of the transformation. This can be any * arbitrary value, but in the usual case, this contains the * name of the chip or provider and the name of the * transformation algorithm. * @cra_type: Type of the cryptographic transformation. This is a pointer to * struct crypto_type, which implements callbacks common for all * transformation types. There are multiple options, such as * &crypto_skcipher_type, &crypto_ahash_type, &crypto_rng_type. * This field might be empty. In that case, there are no common * callbacks. This is the case for: cipher, compress, shash. * @cra_u: Callbacks implementing the transformation. This is a union of * multiple structures. Depending on the type of transformation selected * by @cra_type and @cra_flags above, the associated structure must be * filled with callbacks. This field might be empty. This is the case * for ahash, shash. * @cra_init: Initialize the cryptographic transformation object. This function * is used to initialize the cryptographic transformation object. * This function is called only once at the instantiation time, right * after the transformation context was allocated. In case the * cryptographic hardware has some special requirements which need to * be handled by software, this function shall check for the precise * requirement of the transformation and put any software fallbacks * in place. * @cra_exit: Deinitialize the cryptographic transformation object. This is a * counterpart to @cra_init, used to remove various changes set in * @cra_init. * @cra_u.cipher: Union member which contains a single-block symmetric cipher * definition. See @struct @cipher_alg. * @cra_u.compress: Union member which contains a (de)compression algorithm. * See @struct @compress_alg. * @cra_module: Owner of this transformation implementation. Set to THIS_MODULE * @cra_list: internally used * @cra_users: internally used * @cra_refcnt: internally used * @cra_destroy: internally used * * The struct crypto_alg describes a generic Crypto API algorithm and is common * for all of the transformations. Any variable not documented here shall not * be used by a cipher implementation as it is internal to the Crypto API. */ struct crypto_alg { struct list_head cra_list; struct list_head cra_users; u32 cra_flags; unsigned int cra_blocksize; unsigned int cra_ctxsize; unsigned int cra_alignmask; int cra_priority; refcount_t cra_refcnt; char cra_name[CRYPTO_MAX_ALG_NAME]; char cra_driver_name[CRYPTO_MAX_ALG_NAME]; const struct crypto_type *cra_type; union { struct cipher_alg cipher; struct compress_alg compress; } cra_u; int (*cra_init)(struct crypto_tfm *tfm); void (*cra_exit)(struct crypto_tfm *tfm); void (*cra_destroy)(struct crypto_alg *alg); struct module *cra_module; } CRYPTO_MINALIGN_ATTR; /* * A helper struct for waiting for completion of async crypto ops */ struct crypto_wait { struct completion completion; int err; }; /* * Macro for declaring a crypto op async wait object on stack */ #define DECLARE_CRYPTO_WAIT(_wait) \ struct crypto_wait _wait = { \ COMPLETION_INITIALIZER_ONSTACK((_wait).completion), 0 } /* * Async ops completion helper functioons */ void crypto_req_done(void *req, int err); static inline int crypto_wait_req(int err, struct crypto_wait *wait) { switch (err) { case -EINPROGRESS: case -EBUSY: wait_for_completion(&wait->completion); reinit_completion(&wait->completion); err = wait->err; break; } return err; } static inline void crypto_init_wait(struct crypto_wait *wait) { init_completion(&wait->completion); } /* * Algorithm query interface. */ int crypto_has_alg(const char *name, u32 type, u32 mask); /* * Transforms: user-instantiated objects which encapsulate algorithms * and core processing logic. Managed via crypto_alloc_*() and * crypto_free_*(), as well as the various helpers below. */ struct crypto_tfm { refcount_t refcnt; u32 crt_flags; int node; void (*exit)(struct crypto_tfm *tfm); struct crypto_alg *__crt_alg; void *__crt_ctx[] CRYPTO_MINALIGN_ATTR; }; struct crypto_comp { struct crypto_tfm base; }; /* * Transform user interface. */ struct crypto_tfm *crypto_alloc_base(const char *alg_name, u32 type, u32 mask); void crypto_destroy_tfm(void *mem, struct crypto_tfm *tfm); static inline void crypto_free_tfm(struct crypto_tfm *tfm) { return crypto_destroy_tfm(tfm, tfm); } /* * Transform helpers which query the underlying algorithm. */ static inline const char *crypto_tfm_alg_name(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_name; } static inline const char *crypto_tfm_alg_driver_name(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_driver_name; } static inline unsigned int crypto_tfm_alg_blocksize(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_blocksize; } static inline unsigned int crypto_tfm_alg_alignmask(struct crypto_tfm *tfm) { return tfm->__crt_alg->cra_alignmask; } static inline u32 crypto_tfm_get_flags(struct crypto_tfm *tfm) { return tfm->crt_flags; } static inline void crypto_tfm_set_flags(struct crypto_tfm *tfm, u32 flags) { tfm->crt_flags |= flags; } static inline void crypto_tfm_clear_flags(struct crypto_tfm *tfm, u32 flags) { tfm->crt_flags &= ~flags; } static inline unsigned int crypto_tfm_ctx_alignment(void) { struct crypto_tfm *tfm; return __alignof__(tfm->__crt_ctx); } static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm) { return (struct crypto_comp *)tfm; } static inline struct crypto_comp *crypto_alloc_comp(const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_COMPRESS; mask |= CRYPTO_ALG_TYPE_MASK; return __crypto_comp_cast(crypto_alloc_base(alg_name, type, mask)); } static inline struct crypto_tfm *crypto_comp_tfm(struct crypto_comp *tfm) { return &tfm->base; } static inline void crypto_free_comp(struct crypto_comp *tfm) { crypto_free_tfm(crypto_comp_tfm(tfm)); } static inline int crypto_has_comp(const char *alg_name, u32 type, u32 mask) { type &= ~CRYPTO_ALG_TYPE_MASK; type |= CRYPTO_ALG_TYPE_COMPRESS; mask |= CRYPTO_ALG_TYPE_MASK; return crypto_has_alg(alg_name, type, mask); } static inline const char *crypto_comp_name(struct crypto_comp *tfm) { return crypto_tfm_alg_name(crypto_comp_tfm(tfm)); } int crypto_comp_compress(struct crypto_comp *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); int crypto_comp_decompress(struct crypto_comp *tfm, const u8 *src, unsigned int slen, u8 *dst, unsigned int *dlen); #endif /* _LINUX_CRYPTO_H */ |
| 204 201 3 4 24 24 24 24 24 4 19 2 17 20 18 25 25 6 18 24 22 4 4 8 4 19 14 5 20 8 2 27 26 1 27 30 7 5 2 3 2 2 1 1 1 1 20 20 7 5 2 2 1 1 3 3 2 3 1 3 3 3 3 4 1 7 8 4 4 8 8 8 6 1 3 21 21 8 1 1 1 2 1 19 18 2 2 14 12 21 21 37 8 8 1 21 2 7 4 33 1 11 11 11 11 3 2 3 9 9 2 7 7 3 4 4 2 2 3 1 3 1 3 15 15 6 9 15 176 135 23 18 15 13 1 1 1 1 2 15 27 7 34 12 2 12 1 6 6 2 4 31 23 7 12 11 1 19 19 18 1 1 1 3 16 1 1 3 1 1 26 1 21 5 1 2 3 2 3 2 24 19 5 1 13 7 17 1 3 13 3 1 6 1 1 11 12 2 1 1 1 12 4 1 7 1 3 1 2 28 20 5 4 8 8 8 8 216 216 158 65 152 23 217 4 1 1 1 1 2 2 2 384 385 385 363 24 383 1 5 4 3 1344 1086 286 54 21 27 19 22 312 119 14 342 343 343 342 342 341 341 41 1 119 88 16 7 2 5 1 2 3 19 8 29 11 15 4 1 2 3 6 2 1 29 26 8 1 19 26 1 8 19 24 3 27 14 1 4 8 26 27 19 8 25 5 73 27 1 1 100 1 97 2 1 1 1 1 5 1 3 2 3 1 4 4 2 6 1 22 1 1 178 34 22 16 225 8 33 198 129 103 227 225 1 8 25 43 142 8 1 30 183 221 215 3 219 218 119 14 84 182 16 17 182 64 244 9 240 11 1 11 11 11 10 1 11 11 11 11 8 3 11 9 3 6 9 1 1 3 5 3 4 7 3 4 4 2 2 7 5 2 7 2 5 5 1 9 2 1 1 10 1 1 8 8 8 2 5 7 7 28 1 1 24 19 6 5 19 1 1 20 21 7 1 13 15 4 6 6 1 6 1 1 20 2 1 1 1 1 2 1 2 1 1 2 1 1 1 5 1 1 2 1 2 1 1 13 1 1 10 3 1 1 1 9 10 7 10 5 2 1 1 1 4 9 2 2 156 1 63 1 21 1 13 10 1 1 1 1 1 1 1 1 2 1 1 1 1 2 1 1 1 2 2 1 1 2 1 1 2 1 6 4 2 2 3 1 1 1 26 1 24 1 26 1 1 1 1 1 1 2 2 1 1 2 27 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 906 900 900 117 27 2 56 1 2 2 1 24 1 900 47 45 1 10 9 3 10 9 3 2 2 5 5 4 4 1 1 15 16 28 1 25 1 12 12 1 1 22 1 1 1 1 17 4 3 1 2 5 3 2 12 13 5 13 2 12 13 1 4 7 1 6 6 5 1 1 4 4 4 4 4 4 6 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * PACKET - implements raw packet sockets. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * * Fixes: * Alan Cox : verify_area() now used correctly * Alan Cox : new skbuff lists, look ma no backlogs! * Alan Cox : tidied skbuff lists. * Alan Cox : Now uses generic datagram routines I * added. Also fixed the peek/read crash * from all old Linux datagram code. * Alan Cox : Uses the improved datagram code. * Alan Cox : Added NULL's for socket options. * Alan Cox : Re-commented the code. * Alan Cox : Use new kernel side addressing * Rob Janssen : Correct MTU usage. * Dave Platt : Counter leaks caused by incorrect * interrupt locking and some slightly * dubious gcc output. Can you read * compiler: it said _VOLATILE_ * Richard Kooijman : Timestamp fixes. * Alan Cox : New buffers. Use sk->mac.raw. * Alan Cox : sendmsg/recvmsg support. * Alan Cox : Protocol setting support * Alexey Kuznetsov : Untied from IPv4 stack. * Cyrus Durgin : Fixed kerneld for kmod. * Michal Ostrowski : Module initialization cleanup. * Ulises Alonso : Frame number limit removal and * packet_set_ring memory leak. * Eric Biederman : Allow for > 8 byte hardware addresses. * The convention is that longer addresses * will simply extend the hardware address * byte arrays at the end of sockaddr_ll * and packet_mreq. * Johann Baudy : Added TX RING. * Chetan Loke : Implemented TPACKET_V3 block abstraction * layer. * Copyright (C) 2011, <lokec@ccs.neu.edu> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/ethtool.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/fcntl.h> #include <linux/socket.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/if_packet.h> #include <linux/wireless.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/protocol.h> #include <linux/skbuff.h> #include <net/sock.h> #include <linux/errno.h> #include <linux/timer.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <asm/page.h> #include <asm/cacheflush.h> #include <asm/io.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/poll.h> #include <linux/module.h> #include <linux/init.h> #include <linux/mutex.h> #include <linux/if_vlan.h> #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> #include <linux/percpu.h> #ifdef CONFIG_INET #include <net/inet_common.h> #endif #include <linux/bpf.h> #include <net/compat.h> #include <linux/netfilter_netdev.h> #include "internal.h" /* Assumptions: - If the device has no dev->header_ops->create, there is no LL header visible above the device. In this case, its hard_header_len should be 0. The device may prepend its own header internally. In this case, its needed_headroom should be set to the space needed for it to add its internal header. For example, a WiFi driver pretending to be an Ethernet driver should set its hard_header_len to be the Ethernet header length, and set its needed_headroom to be (the real WiFi header length - the fake Ethernet header length). - packet socket receives packets with pulled ll header, so that SOCK_RAW should push it back. On receive: ----------- Incoming, dev_has_header(dev) == true mac_header -> ll header data -> data Outgoing, dev_has_header(dev) == true mac_header -> ll header data -> ll header Incoming, dev_has_header(dev) == false mac_header -> data However drivers often make it point to the ll header. This is incorrect because the ll header should be invisible to us. data -> data Outgoing, dev_has_header(dev) == false mac_header -> data. ll header is invisible to us. data -> data Resume If dev_has_header(dev) == false we are unable to restore the ll header, because it is invisible to us. On transmit: ------------ dev_has_header(dev) == true mac_header -> ll header data -> ll header dev_has_header(dev) == false (ll header is invisible to us) mac_header -> data data -> data We should set network_header on output to the correct position, packet classifier depends on it. */ /* Private packet socket structures. */ /* identical to struct packet_mreq except it has * a longer address field. */ struct packet_mreq_max { int mr_ifindex; unsigned short mr_type; unsigned short mr_alen; unsigned char mr_address[MAX_ADDR_LEN]; }; union tpacket_uhdr { struct tpacket_hdr *h1; struct tpacket2_hdr *h2; struct tpacket3_hdr *h3; void *raw; }; static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring); #define V3_ALIGNMENT (8) #define BLK_HDR_LEN (ALIGN(sizeof(struct tpacket_block_desc), V3_ALIGNMENT)) #define BLK_PLUS_PRIV(sz_of_priv) \ (BLK_HDR_LEN + ALIGN((sz_of_priv), V3_ALIGNMENT)) #define BLOCK_STATUS(x) ((x)->hdr.bh1.block_status) #define BLOCK_NUM_PKTS(x) ((x)->hdr.bh1.num_pkts) #define BLOCK_O2FP(x) ((x)->hdr.bh1.offset_to_first_pkt) #define BLOCK_LEN(x) ((x)->hdr.bh1.blk_len) #define BLOCK_SNUM(x) ((x)->hdr.bh1.seq_num) #define BLOCK_O2PRIV(x) ((x)->offset_to_priv) struct packet_sock; static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status); static void packet_increment_head(struct packet_ring_buffer *buff); static int prb_curr_blk_in_use(struct tpacket_block_desc *); static void *prb_dispatch_next_block(struct tpacket_kbdq_core *, struct packet_sock *); static void prb_retire_current_block(struct tpacket_kbdq_core *, struct packet_sock *, unsigned int status); static int prb_queue_frozen(struct tpacket_kbdq_core *); static void prb_open_block(struct tpacket_kbdq_core *, struct tpacket_block_desc *); static void prb_retire_rx_blk_timer_expired(struct timer_list *); static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *); static void prb_fill_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_clear_rxhash(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); static u16 packet_pick_tx_queue(struct sk_buff *skb); struct packet_skb_cb { union { struct sockaddr_pkt pkt; union { /* Trick: alias skb original length with * ll.sll_family and ll.protocol in order * to save room. */ unsigned int origlen; struct sockaddr_ll ll; }; } sa; }; #define vio_le() virtio_legacy_is_little_endian() #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) #define GET_PBDQC_FROM_RB(x) ((struct tpacket_kbdq_core *)(&(x)->prb_bdqc)) #define GET_PBLOCK_DESC(x, bid) \ ((struct tpacket_block_desc *)((x)->pkbdq[(bid)].buffer)) #define GET_CURR_PBLOCK_DESC_FROM_CORE(x) \ ((struct tpacket_block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer)) #define GET_NEXT_PRB_BLK_NUM(x) \ (((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \ ((x)->kactive_blk_num+1) : 0) static void __fanout_unlink(struct sock *sk, struct packet_sock *po); static void __fanout_link(struct sock *sk, struct packet_sock *po); #ifdef CONFIG_NETFILTER_EGRESS static noinline struct sk_buff *nf_hook_direct_egress(struct sk_buff *skb) { struct sk_buff *next, *head = NULL, *tail; int rc; rcu_read_lock(); for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); if (!nf_hook_egress(skb, &rc, skb->dev)) continue; if (!head) head = skb; else tail->next = skb; tail = skb; } rcu_read_unlock(); return head; } #endif static int packet_xmit(const struct packet_sock *po, struct sk_buff *skb) { if (!packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS)) return dev_queue_xmit(skb); #ifdef CONFIG_NETFILTER_EGRESS if (nf_hook_egress_active()) { skb = nf_hook_direct_egress(skb); if (!skb) return NET_XMIT_DROP; } #endif return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } static struct net_device *packet_cached_dev_get(struct packet_sock *po) { struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(po->cached_dev); dev_hold(dev); rcu_read_unlock(); return dev; } static void packet_cached_dev_assign(struct packet_sock *po, struct net_device *dev) { rcu_assign_pointer(po->cached_dev, dev); } static void packet_cached_dev_reset(struct packet_sock *po) { RCU_INIT_POINTER(po->cached_dev, NULL); } static u16 packet_pick_tx_queue(struct sk_buff *skb) { struct net_device *dev = skb->dev; const struct net_device_ops *ops = dev->netdev_ops; int cpu = raw_smp_processor_id(); u16 queue_index; #ifdef CONFIG_XPS skb->sender_cpu = cpu + 1; #endif skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues); if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb, NULL); queue_index = netdev_cap_txqueue(dev, queue_index); } else { queue_index = netdev_pick_tx(dev, skb, NULL); } return queue_index; } /* __register_prot_hook must be invoked through register_prot_hook * or from a context in which asynchronous accesses to the packet * socket is not possible (packet_create()). */ static void __register_prot_hook(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); if (!packet_sock_flag(po, PACKET_SOCK_RUNNING)) { if (po->fanout) __fanout_link(sk, po); else dev_add_pack(&po->prot_hook); sock_hold(sk); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 1); } } static void register_prot_hook(struct sock *sk) { lockdep_assert_held_once(&pkt_sk(sk)->bind_lock); __register_prot_hook(sk); } /* If the sync parameter is true, we will temporarily drop * the po->bind_lock and do a synchronize_net to make sure no * asynchronous packet processing paths still refer to the elements * of po->prot_hook. If the sync parameter is false, it is the * callers responsibility to take care of this. */ static void __unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); lockdep_assert_held_once(&po->bind_lock); packet_sock_flag_set(po, PACKET_SOCK_RUNNING, 0); if (po->fanout) __fanout_unlink(sk, po); else __dev_remove_pack(&po->prot_hook); __sock_put(sk); if (sync) { spin_unlock(&po->bind_lock); synchronize_net(); spin_lock(&po->bind_lock); } } static void unregister_prot_hook(struct sock *sk, bool sync) { struct packet_sock *po = pkt_sk(sk); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) __unregister_prot_hook(sk, sync); } static inline struct page * __pure pgv_to_page(void *addr) { if (is_vmalloc_addr(addr)) return vmalloc_to_page(addr); return virt_to_page(addr); } static void __packet_set_status(struct packet_sock *po, void *frame, int status) { union tpacket_uhdr h; /* WRITE_ONCE() are paired with READ_ONCE() in __packet_get_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: WRITE_ONCE(h.h1->tp_status, status); flush_dcache_page(pgv_to_page(&h.h1->tp_status)); break; case TPACKET_V2: WRITE_ONCE(h.h2->tp_status, status); flush_dcache_page(pgv_to_page(&h.h2->tp_status)); break; case TPACKET_V3: WRITE_ONCE(h.h3->tp_status, status); flush_dcache_page(pgv_to_page(&h.h3->tp_status)); break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } smp_wmb(); } static int __packet_get_status(const struct packet_sock *po, void *frame) { union tpacket_uhdr h; smp_rmb(); /* READ_ONCE() are paired with WRITE_ONCE() in __packet_set_status */ h.raw = frame; switch (po->tp_version) { case TPACKET_V1: flush_dcache_page(pgv_to_page(&h.h1->tp_status)); return READ_ONCE(h.h1->tp_status); case TPACKET_V2: flush_dcache_page(pgv_to_page(&h.h2->tp_status)); return READ_ONCE(h.h2->tp_status); case TPACKET_V3: flush_dcache_page(pgv_to_page(&h.h3->tp_status)); return READ_ONCE(h.h3->tp_status); default: WARN(1, "TPACKET version not supported.\n"); BUG(); return 0; } } static __u32 tpacket_get_timestamp(struct sk_buff *skb, struct timespec64 *ts, unsigned int flags) { struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); if (shhwtstamps && (flags & SOF_TIMESTAMPING_RAW_HARDWARE) && ktime_to_timespec64_cond(shhwtstamps->hwtstamp, ts)) return TP_STATUS_TS_RAW_HARDWARE; if ((flags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb_tstamp(skb), ts)) return TP_STATUS_TS_SOFTWARE; return 0; } static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame, struct sk_buff *skb) { union tpacket_uhdr h; struct timespec64 ts; __u32 ts_status; if (!(ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp)))) return 0; h.raw = frame; /* * versions 1 through 3 overflow the timestamps in y2106, since they * all store the seconds in a 32-bit unsigned integer. * If we create a version 4, that should have a 64-bit timestamp, * either 64-bit seconds + 32-bit nanoseconds, or just 64-bit * nanoseconds. */ switch (po->tp_version) { case TPACKET_V1: h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; break; case TPACKET_V2: h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; break; case TPACKET_V3: h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; break; default: WARN(1, "TPACKET version not supported.\n"); BUG(); } /* one flush is safe, as both fields always lie on the same cacheline */ flush_dcache_page(pgv_to_page(&h.h1->tp_sec)); smp_wmb(); return ts_status; } static void *packet_lookup_frame(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int position, int status) { unsigned int pg_vec_pos, frame_offset; union tpacket_uhdr h; pg_vec_pos = position / rb->frames_per_block; frame_offset = position % rb->frames_per_block; h.raw = rb->pg_vec[pg_vec_pos].buffer + (frame_offset * rb->frame_size); if (status != __packet_get_status(po, h.raw)) return NULL; return h.raw; } static void *packet_current_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { return packet_lookup_frame(po, rb, rb->head, status); } static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) { u8 *skb_orig_data = skb->data; int skb_orig_len = skb->len; struct vlan_hdr vhdr, *vh; unsigned int header_len; if (!dev) return 0; /* In the SOCK_DGRAM scenario, skb data starts at the network * protocol, which is after the VLAN headers. The outer VLAN * header is at the hard_header_len offset in non-variable * length link layer headers. If it's a VLAN device, the * min_header_len should be used to exclude the VLAN header * size. */ if (dev->min_header_len == dev->hard_header_len) header_len = dev->hard_header_len; else if (is_vlan_dev(dev)) header_len = dev->min_header_len; else return 0; skb_push(skb, skb->data - skb_mac_header(skb)); vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); if (skb_orig_data != skb->data) { skb->data = skb_orig_data; skb->len = skb_orig_len; } if (unlikely(!vh)) return 0; return ntohs(vh->h_vlan_TCI); } static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) { __be16 proto = skb->protocol; if (unlikely(eth_type_vlan(proto))) { u8 *skb_orig_data = skb->data; int skb_orig_len = skb->len; skb_push(skb, skb->data - skb_mac_header(skb)); proto = __vlan_get_protocol(skb, proto, NULL); if (skb_orig_data != skb->data) { skb->data = skb_orig_data; skb->len = skb_orig_len; } } return proto; } static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { del_timer_sync(&pkc->retire_blk_timer); } static void prb_shutdown_retire_blk_timer(struct packet_sock *po, struct sk_buff_head *rb_queue) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); spin_lock_bh(&rb_queue->lock); pkc->delete_blk_timer = 1; spin_unlock_bh(&rb_queue->lock); prb_del_retire_blk_timer(pkc); } static void prb_setup_retire_blk_timer(struct packet_sock *po) { struct tpacket_kbdq_core *pkc; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); timer_setup(&pkc->retire_blk_timer, prb_retire_rx_blk_timer_expired, 0); pkc->retire_blk_timer.expires = jiffies; } static int prb_calc_retire_blk_tmo(struct packet_sock *po, int blk_size_in_bytes) { struct net_device *dev; unsigned int mbits, div; struct ethtool_link_ksettings ecmd; int err; rtnl_lock(); dev = __dev_get_by_index(sock_net(&po->sk), po->ifindex); if (unlikely(!dev)) { rtnl_unlock(); return DEFAULT_PRB_RETIRE_TOV; } err = __ethtool_get_link_ksettings(dev, &ecmd); rtnl_unlock(); if (err) return DEFAULT_PRB_RETIRE_TOV; /* If the link speed is so slow you don't really * need to worry about perf anyways */ if (ecmd.base.speed < SPEED_1000 || ecmd.base.speed == SPEED_UNKNOWN) return DEFAULT_PRB_RETIRE_TOV; div = ecmd.base.speed / 1000; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); if (div) mbits /= div; if (div) return mbits + 1; return mbits; } static void prb_init_ft_ops(struct tpacket_kbdq_core *p1, union tpacket_req_u *req_u) { p1->feature_req_word = req_u->req3.tp_feature_req_word; } static void init_prb_bdqc(struct packet_sock *po, struct packet_ring_buffer *rb, struct pgv *pg_vec, union tpacket_req_u *req_u) { struct tpacket_kbdq_core *p1 = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd; memset(p1, 0x0, sizeof(*p1)); p1->knxt_seq_num = 1; p1->pkbdq = pg_vec; pbd = (struct tpacket_block_desc *)pg_vec[0].buffer; p1->pkblk_start = pg_vec[0].buffer; p1->kblk_size = req_u->req3.tp_block_size; p1->knum_blocks = req_u->req3.tp_block_nr; p1->hdrlen = po->tp_hdrlen; p1->version = po->tp_version; p1->last_kactive_blk_num = 0; po->stats.stats3.tp_freeze_q_cnt = 0; if (req_u->req3.tp_retire_blk_tov) p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov; else p1->retire_blk_tov = prb_calc_retire_blk_tmo(po, req_u->req3.tp_block_size); p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov); p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv; rwlock_init(&p1->blk_fill_in_prog_lock); p1->max_frame_len = p1->kblk_size - BLK_PLUS_PRIV(p1->blk_sizeof_priv); prb_init_ft_ops(p1, req_u); prb_setup_retire_blk_timer(po); prb_open_block(p1, pbd); } /* Do NOT update the last_blk_num first. * Assumes sk_buff_head lock is held. */ static void _prb_refresh_rx_retire_blk_timer(struct tpacket_kbdq_core *pkc) { mod_timer(&pkc->retire_blk_timer, jiffies + pkc->tov_in_jiffies); pkc->last_kactive_blk_num = pkc->kactive_blk_num; } /* * Timer logic: * 1) We refresh the timer only when we open a block. * By doing this we don't waste cycles refreshing the timer * on packet-by-packet basis. * * With a 1MB block-size, on a 1Gbps line, it will take * i) ~8 ms to fill a block + ii) memcpy etc. * In this cut we are not accounting for the memcpy time. * * So, if the user sets the 'tmo' to 10ms then the timer * will never fire while the block is still getting filled * (which is what we want). However, the user could choose * to close a block early and that's fine. * * But when the timer does fire, we check whether or not to refresh it. * Since the tmo granularity is in msecs, it is not too expensive * to refresh the timer, lets say every '8' msecs. * Either the user can set the 'tmo' or we can derive it based on * a) line-speed and b) block-size. * prb_calc_retire_blk_tmo() calculates the tmo. * */ static void prb_retire_rx_blk_timer_expired(struct timer_list *t) { struct packet_sock *po = from_timer(po, t, rx_ring.prb_bdqc.retire_blk_timer); struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(&po->rx_ring); unsigned int frozen; struct tpacket_block_desc *pbd; spin_lock(&po->sk.sk_receive_queue.lock); frozen = prb_queue_frozen(pkc); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); if (unlikely(pkc->delete_blk_timer)) goto out; /* We only need to plug the race when the block is partially filled. * tpacket_rcv: * lock(); increment BLOCK_NUM_PKTS; unlock() * copy_bits() is in progress ... * timer fires on other cpu: * we can't retire the current block because copy_bits * is in progress. * */ if (BLOCK_NUM_PKTS(pbd)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) { if (!frozen) { if (!BLOCK_NUM_PKTS(pbd)) { /* An empty block. Just refresh the timer. */ goto refresh_timer; } prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO); if (!prb_dispatch_next_block(pkc, po)) goto refresh_timer; else goto out; } else { /* Case 1. Queue was frozen because user-space was * lagging behind. */ if (prb_curr_blk_in_use(pbd)) { /* * Ok, user-space is still behind. * So just refresh the timer. */ goto refresh_timer; } else { /* Case 2. queue was frozen,user-space caught up, * now the link went idle && the timer fired. * We don't have a block to close.So we open this * block and restart the timer. * opening a block thaws the queue,restarts timer * Thawing/timer-refresh is a side effect. */ prb_open_block(pkc, pbd); goto out; } } } refresh_timer: _prb_refresh_rx_retire_blk_timer(pkc); out: spin_unlock(&po->sk.sk_receive_queue.lock); } static void prb_flush_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, __u32 status) { /* Flush everything minus the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 u8 *start, *end; start = (u8 *)pbd1; /* Skip the block header(we know header WILL fit in 4K) */ start += PAGE_SIZE; end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end); for (; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif /* Now update the block status. */ BLOCK_STATUS(pbd1) = status; /* Flush the block header */ #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 start = (u8 *)pbd1; flush_dcache_page(pgv_to_page(start)); smp_wmb(); #endif } /* * Side effect: * * 1) flush the block * 2) Increment active_blk_num * * Note:We DONT refresh the timer on purpose. * Because almost always the next block will be opened. */ static void prb_close_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1, struct packet_sock *po, unsigned int stat) { __u32 status = TP_STATUS_USER | stat; struct tpacket3_hdr *last_pkt; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; struct sock *sk = &po->sk; if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; last_pkt = (struct tpacket3_hdr *)pkc1->prev; last_pkt->tp_next_offset = 0; /* Get the ts of the last pkt */ if (BLOCK_NUM_PKTS(pbd1)) { h1->ts_last_pkt.ts_sec = last_pkt->tp_sec; h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec; } else { /* Ok, we tmo'd - so get the current time. * * It shouldn't really happen as we don't close empty * blocks. See prb_retire_rx_blk_timer_expired(). */ struct timespec64 ts; ktime_get_real_ts64(&ts); h1->ts_last_pkt.ts_sec = ts.tv_sec; h1->ts_last_pkt.ts_nsec = ts.tv_nsec; } smp_wmb(); /* Flush the block */ prb_flush_block(pkc1, pbd1, status); sk->sk_data_ready(sk); pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1); } static void prb_thaw_queue(struct tpacket_kbdq_core *pkc) { pkc->reset_pending_on_curr_blk = 0; } /* * Side effect of opening a block: * * 1) prb_queue is thawed. * 2) retire_blk_timer is refreshed. * */ static void prb_open_block(struct tpacket_kbdq_core *pkc1, struct tpacket_block_desc *pbd1) { struct timespec64 ts; struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; smp_rmb(); /* We could have just memset this but we will lose the * flexibility of making the priv area sticky */ BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++; BLOCK_NUM_PKTS(pbd1) = 0; BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); ktime_get_real_ts64(&ts); h1->ts_first_pkt.ts_sec = ts.tv_sec; h1->ts_first_pkt.ts_nsec = ts.tv_nsec; pkc1->pkblk_start = (char *)pbd1; pkc1->nxt_offset = pkc1->pkblk_start + BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv); BLOCK_O2PRIV(pbd1) = BLK_HDR_LEN; pbd1->version = pkc1->version; pkc1->prev = pkc1->nxt_offset; pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size; prb_thaw_queue(pkc1); _prb_refresh_rx_retire_blk_timer(pkc1); smp_wmb(); } /* * Queue freeze logic: * 1) Assume tp_block_nr = 8 blocks. * 2) At time 't0', user opens Rx ring. * 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7 * 4) user-space is either sleeping or processing block '0'. * 5) tpacket_rcv is currently filling block '7', since there is no space left, * it will close block-7,loop around and try to fill block '0'. * call-flow: * __packet_lookup_frame_in_block * prb_retire_current_block() * prb_dispatch_next_block() * |->(BLOCK_STATUS == USER) evaluates to true * 5.1) Since block-0 is currently in-use, we just freeze the queue. * 6) Now there are two cases: * 6.1) Link goes idle right after the queue is frozen. * But remember, the last open_block() refreshed the timer. * When this timer expires,it will refresh itself so that we can * re-open block-0 in near future. * 6.2) Link is busy and keeps on receiving packets. This is a simple * case and __packet_lookup_frame_in_block will check if block-0 * is free and can now be re-used. */ static void prb_freeze_queue(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { pkc->reset_pending_on_curr_blk = 1; po->stats.stats3.tp_freeze_q_cnt++; } #define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN((length), V3_ALIGNMENT)) /* * If the next block is free then we will dispatch it * and return a good offset. * Else, we will freeze the queue. * So, caller must check the return value. */ static void *prb_dispatch_next_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po) { struct tpacket_block_desc *pbd; smp_rmb(); /* 1. Get current block num */ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* 2. If this block is currently in_use then freeze the queue */ if (TP_STATUS_USER & BLOCK_STATUS(pbd)) { prb_freeze_queue(pkc, po); return NULL; } /* * 3. * open this block and return the offset where the first packet * needs to get stored. */ prb_open_block(pkc, pbd); return (void *)pkc->nxt_offset; } static void prb_retire_current_block(struct tpacket_kbdq_core *pkc, struct packet_sock *po, unsigned int status) { struct tpacket_block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* retire/close the current block */ if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) { /* * Plug the case where copy_bits() is in progress on * cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't * have space to copy the pkt in the current block and * called prb_retire_current_block() * * We don't need to worry about the TMO case because * the timer-handler already handled this case. */ if (!(status & TP_STATUS_BLK_TMO)) { /* Waiting for skb_copy_bits to finish... */ write_lock(&pkc->blk_fill_in_prog_lock); write_unlock(&pkc->blk_fill_in_prog_lock); } prb_close_block(pkc, pbd, po, status); return; } } static int prb_curr_blk_in_use(struct tpacket_block_desc *pbd) { return TP_STATUS_USER & BLOCK_STATUS(pbd); } static int prb_queue_frozen(struct tpacket_kbdq_core *pkc) { return pkc->reset_pending_on_curr_blk; } static void prb_clear_blk_fill_status(struct packet_ring_buffer *rb) __releases(&pkc->blk_fill_in_prog_lock) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); read_unlock(&pkc->blk_fill_in_prog_lock); } static void prb_fill_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = skb_get_hash(pkc->skb); } static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_rxhash = 0; } static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; ppd->tp_status = TP_STATUS_AVAILABLE; } } static void prb_run_all_ft_ops(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { ppd->hv1.tp_padding = 0; prb_fill_vlan_info(pkc, ppd); if (pkc->feature_req_word & TP_FT_REQ_FILL_RXHASH) prb_fill_rxhash(pkc, ppd); else prb_clear_rxhash(pkc, ppd); } static void prb_fill_curr_block(char *curr, struct tpacket_kbdq_core *pkc, struct tpacket_block_desc *pbd, unsigned int len) __acquires(&pkc->blk_fill_in_prog_lock) { struct tpacket3_hdr *ppd; ppd = (struct tpacket3_hdr *)curr; ppd->tp_next_offset = TOTAL_PKT_LEN_INCL_ALIGN(len); pkc->prev = curr; pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len); BLOCK_NUM_PKTS(pbd) += 1; read_lock(&pkc->blk_fill_in_prog_lock); prb_run_all_ft_ops(pkc, ppd); } /* Assumes caller has the sk->rx_queue.lock */ static void *__packet_lookup_frame_in_block(struct packet_sock *po, struct sk_buff *skb, unsigned int len ) { struct tpacket_kbdq_core *pkc; struct tpacket_block_desc *pbd; char *curr, *end; pkc = GET_PBDQC_FROM_RB(&po->rx_ring); pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); /* Queue is frozen when user space is lagging behind */ if (prb_queue_frozen(pkc)) { /* * Check if that last block which caused the queue to freeze, * is still in_use by user-space. */ if (prb_curr_blk_in_use(pbd)) { /* Can't record this packet */ return NULL; } else { /* * Ok, the block was released by user-space. * Now let's open that block. * opening a block also thaws the queue. * Thawing is a side effect. */ prb_open_block(pkc, pbd); } } smp_mb(); curr = pkc->nxt_offset; pkc->skb = skb; end = (char *)pbd + pkc->kblk_size; /* first try the current block */ if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) { prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* Ok, close the current block */ prb_retire_current_block(pkc, po, 0); /* Now, try to dispatch the next block */ curr = (char *)prb_dispatch_next_block(pkc, po); if (curr) { pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc); prb_fill_curr_block(curr, pkc, pbd, len); return (void *)curr; } /* * No free blocks are available.user_space hasn't caught up yet. * Queue was just frozen and now this packet will get dropped. */ return NULL; } static void *packet_current_rx_frame(struct packet_sock *po, struct sk_buff *skb, int status, unsigned int len) { char *curr = NULL; switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: curr = packet_lookup_frame(po, &po->rx_ring, po->rx_ring.head, status); return curr; case TPACKET_V3: return __packet_lookup_frame_in_block(po, skb, len); default: WARN(1, "TPACKET version not supported\n"); BUG(); return NULL; } } static void *prb_lookup_block(const struct packet_sock *po, const struct packet_ring_buffer *rb, unsigned int idx, int status) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx); if (status != BLOCK_STATUS(pbd)) return NULL; return pbd; } static int prb_previous_blk_num(struct packet_ring_buffer *rb) { unsigned int prev; if (rb->prb_bdqc.kactive_blk_num) prev = rb->prb_bdqc.kactive_blk_num-1; else prev = rb->prb_bdqc.knum_blocks-1; return prev; } /* Assumes caller has held the rx_queue.lock */ static void *__prb_previous_block(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = prb_previous_blk_num(rb); return prb_lookup_block(po, rb, previous, status); } static void *packet_previous_rx_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { if (po->tp_version <= TPACKET_V2) return packet_previous_frame(po, rb, status); return __prb_previous_block(po, rb, status); } static void packet_increment_rx_head(struct packet_sock *po, struct packet_ring_buffer *rb) { switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: return packet_increment_head(rb); case TPACKET_V3: default: WARN(1, "TPACKET version not supported.\n"); BUG(); return; } } static void *packet_previous_frame(struct packet_sock *po, struct packet_ring_buffer *rb, int status) { unsigned int previous = rb->head ? rb->head - 1 : rb->frame_max; return packet_lookup_frame(po, rb, previous, status); } static void packet_increment_head(struct packet_ring_buffer *buff) { buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } static void packet_inc_pending(struct packet_ring_buffer *rb) { this_cpu_inc(*rb->pending_refcnt); } static void packet_dec_pending(struct packet_ring_buffer *rb) { this_cpu_dec(*rb->pending_refcnt); } static unsigned int packet_read_pending(const struct packet_ring_buffer *rb) { unsigned int refcnt = 0; int cpu; /* We don't use pending refcount in rx_ring. */ if (rb->pending_refcnt == NULL) return 0; for_each_possible_cpu(cpu) refcnt += *per_cpu_ptr(rb->pending_refcnt, cpu); return refcnt; } static int packet_alloc_pending(struct packet_sock *po) { po->rx_ring.pending_refcnt = NULL; po->tx_ring.pending_refcnt = alloc_percpu(unsigned int); if (unlikely(po->tx_ring.pending_refcnt == NULL)) return -ENOBUFS; return 0; } static void packet_free_pending(struct packet_sock *po) { free_percpu(po->tx_ring.pending_refcnt); } #define ROOM_POW_OFF 2 #define ROOM_NONE 0x0 #define ROOM_LOW 0x1 #define ROOM_NORMAL 0x2 static bool __tpacket_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.frame_max) + 1; idx = READ_ONCE(po->rx_ring.head); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off) { int idx, len; len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks); idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num); if (pow_off) idx += len >> pow_off; if (idx >= len) idx -= len; return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } static int __packet_rcv_has_room(const struct packet_sock *po, const struct sk_buff *skb) { const struct sock *sk = &po->sk; int ret = ROOM_NONE; if (po->prot_hook.func != tpacket_rcv) { int rcvbuf = READ_ONCE(sk->sk_rcvbuf); int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc) - (skb ? skb->truesize : 0); if (avail > (rcvbuf >> ROOM_POW_OFF)) return ROOM_NORMAL; else if (avail > 0) return ROOM_LOW; else return ROOM_NONE; } if (po->tp_version == TPACKET_V3) { if (__tpacket_v3_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_v3_has_room(po, 0)) ret = ROOM_LOW; } else { if (__tpacket_has_room(po, ROOM_POW_OFF)) ret = ROOM_NORMAL; else if (__tpacket_has_room(po, 0)) ret = ROOM_LOW; } return ret; } static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { bool pressure; int ret; ret = __packet_rcv_has_room(po, skb); pressure = ret != ROOM_NORMAL; if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) != pressure) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, pressure); return ret; } static void packet_rcv_try_clear_pressure(struct packet_sock *po) { if (packet_sock_flag(po, PACKET_SOCK_PRESSURE) && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) packet_sock_flag_set(po, PACKET_SOCK_PRESSURE, false); } static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); WARN_ON(atomic_read(&sk->sk_rmem_alloc)); WARN_ON(refcount_read(&sk->sk_wmem_alloc)); if (!sock_flag(sk, SOCK_DEAD)) { pr_err("Attempt to release alive packet socket: %p\n", sk); return; } } static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) { u32 *history = po->rollover->history; u32 victim, rxhash; int i, count = 0; rxhash = skb_get_hash(skb); for (i = 0; i < ROLLOVER_HLEN; i++) if (READ_ONCE(history[i]) == rxhash) count++; victim = get_random_u32_below(ROLLOVER_HLEN); /* Avoid dirtying the cache line if possible */ if (READ_ONCE(history[victim]) != rxhash) WRITE_ONCE(history[victim], rxhash); return count > (ROLLOVER_HLEN >> 1); } static unsigned int fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return reciprocal_scale(__skb_get_hash_symmetric(skb), num); } static unsigned int fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { unsigned int val = atomic_inc_return(&f->rr_cur); return val % num; } static unsigned int fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return smp_processor_id() % num; } static unsigned int fanout_demux_rnd(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return get_random_u32_below(num); } static unsigned int fanout_demux_rollover(struct packet_fanout *f, struct sk_buff *skb, unsigned int idx, bool try_self, unsigned int num) { struct packet_sock *po, *po_next, *po_skip = NULL; unsigned int i, j, room = ROOM_NONE; po = pkt_sk(rcu_dereference(f->arr[idx])); if (try_self) { room = packet_rcv_has_room(po, skb); if (room == ROOM_NORMAL || (room == ROOM_LOW && !fanout_flow_is_huge(po, skb))) return idx; po_skip = po; } i = j = min_t(int, po->rollover->sock, num - 1); do { po_next = pkt_sk(rcu_dereference(f->arr[i])); if (po_next != po_skip && !packet_sock_flag(po_next, PACKET_SOCK_PRESSURE) && packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) po->rollover->sock = i; atomic_long_inc(&po->rollover->num); if (room == ROOM_LOW) atomic_long_inc(&po->rollover->num_huge); return i; } if (++i == num) i = 0; } while (i != j); atomic_long_inc(&po->rollover->num_failed); return idx; } static unsigned int fanout_demux_qm(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { return skb_get_queue_mapping(skb) % num; } static unsigned int fanout_demux_bpf(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) { struct bpf_prog *prog; unsigned int ret = 0; rcu_read_lock(); prog = rcu_dereference(f->bpf_prog); if (prog) ret = bpf_prog_run_clear_cb(prog, skb) % num; rcu_read_unlock(); return ret; } static bool fanout_has_flag(struct packet_fanout *f, u16 flag) { return f->flags & (flag >> 8); } static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct packet_fanout *f = pt->af_packet_priv; unsigned int num = READ_ONCE(f->num_members); struct net *net = read_pnet(&f->net); struct packet_sock *po; unsigned int idx; if (!net_eq(dev_net(dev), net) || !num) { kfree_skb(skb); return 0; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_DEFRAG)) { skb = ip_check_defrag(net, skb, IP_DEFRAG_AF_PACKET); if (!skb) return 0; } switch (f->type) { case PACKET_FANOUT_HASH: default: idx = fanout_demux_hash(f, skb, num); break; case PACKET_FANOUT_LB: idx = fanout_demux_lb(f, skb, num); break; case PACKET_FANOUT_CPU: idx = fanout_demux_cpu(f, skb, num); break; case PACKET_FANOUT_RND: idx = fanout_demux_rnd(f, skb, num); break; case PACKET_FANOUT_QM: idx = fanout_demux_qm(f, skb, num); break; case PACKET_FANOUT_ROLLOVER: idx = fanout_demux_rollover(f, skb, 0, false, num); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: idx = fanout_demux_bpf(f, skb, num); break; } if (fanout_has_flag(f, PACKET_FANOUT_FLAG_ROLLOVER)) idx = fanout_demux_rollover(f, skb, idx, true, num); po = pkt_sk(rcu_dereference(f->arr[idx])); return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); } DEFINE_MUTEX(fanout_mutex); EXPORT_SYMBOL_GPL(fanout_mutex); static LIST_HEAD(fanout_list); static u16 fanout_next_id; static void __fanout_link(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; spin_lock(&f->lock); rcu_assign_pointer(f->arr[f->num_members], sk); smp_wmb(); f->num_members++; if (f->num_members == 1) dev_add_pack(&f->prot_hook); spin_unlock(&f->lock); } static void __fanout_unlink(struct sock *sk, struct packet_sock *po) { struct packet_fanout *f = po->fanout; int i; spin_lock(&f->lock); for (i = 0; i < f->num_members; i++) { if (rcu_dereference_protected(f->arr[i], lockdep_is_held(&f->lock)) == sk) break; } BUG_ON(i >= f->num_members); rcu_assign_pointer(f->arr[i], rcu_dereference_protected(f->arr[f->num_members - 1], lockdep_is_held(&f->lock))); f->num_members--; if (f->num_members == 0) __dev_remove_pack(&f->prot_hook); spin_unlock(&f->lock); } static bool match_fanout_group(struct packet_type *ptype, struct sock *sk) { if (sk->sk_family != PF_PACKET) return false; return ptype->af_packet_priv == pkt_sk(sk)->fanout; } static void fanout_init_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_LB: atomic_set(&f->rr_cur, 0); break; case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: RCU_INIT_POINTER(f->bpf_prog, NULL); break; } } static void __fanout_set_data_bpf(struct packet_fanout *f, struct bpf_prog *new) { struct bpf_prog *old; spin_lock(&f->lock); old = rcu_dereference_protected(f->bpf_prog, lockdep_is_held(&f->lock)); rcu_assign_pointer(f->bpf_prog, new); spin_unlock(&f->lock); if (old) { synchronize_net(); bpf_prog_destroy(old); } } static int fanout_set_data_cbpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; struct sock_fprog fprog; int ret; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; ret = copy_bpf_fprog_from_user(&fprog, data, len); if (ret) return ret; ret = bpf_prog_create_from_user(&new, &fprog, NULL, false); if (ret) return ret; __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data_ebpf(struct packet_sock *po, sockptr_t data, unsigned int len) { struct bpf_prog *new; u32 fd; if (sock_flag(&po->sk, SOCK_FILTER_LOCKED)) return -EPERM; if (len != sizeof(fd)) return -EINVAL; if (copy_from_sockptr(&fd, data, len)) return -EFAULT; new = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); if (IS_ERR(new)) return PTR_ERR(new); __fanout_set_data_bpf(po->fanout, new); return 0; } static int fanout_set_data(struct packet_sock *po, sockptr_t data, unsigned int len) { switch (po->fanout->type) { case PACKET_FANOUT_CBPF: return fanout_set_data_cbpf(po, data, len); case PACKET_FANOUT_EBPF: return fanout_set_data_ebpf(po, data, len); default: return -EINVAL; } } static void fanout_release_data(struct packet_fanout *f) { switch (f->type) { case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: __fanout_set_data_bpf(f, NULL); } } static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id) { struct packet_fanout *f; list_for_each_entry(f, &fanout_list, list) { if (f->id == candidate_id && read_pnet(&f->net) == sock_net(sk)) { return false; } } return true; } static bool fanout_find_new_id(struct sock *sk, u16 *new_id) { u16 id = fanout_next_id; do { if (__fanout_id_is_free(sk, id)) { *new_id = id; fanout_next_id = id + 1; return true; } id++; } while (id != fanout_next_id); return false; } static int fanout_add(struct sock *sk, struct fanout_args *args) { struct packet_rollover *rollover = NULL; struct packet_sock *po = pkt_sk(sk); u16 type_flags = args->type_flags; struct packet_fanout *f, *match; u8 type = type_flags & 0xff; u8 flags = type_flags >> 8; u16 id = args->id; int err; switch (type) { case PACKET_FANOUT_ROLLOVER: if (type_flags & PACKET_FANOUT_FLAG_ROLLOVER) return -EINVAL; break; case PACKET_FANOUT_HASH: case PACKET_FANOUT_LB: case PACKET_FANOUT_CPU: case PACKET_FANOUT_RND: case PACKET_FANOUT_QM: case PACKET_FANOUT_CBPF: case PACKET_FANOUT_EBPF: break; default: return -EINVAL; } mutex_lock(&fanout_mutex); err = -EALREADY; if (po->fanout) goto out; if (type == PACKET_FANOUT_ROLLOVER || (type_flags & PACKET_FANOUT_FLAG_ROLLOVER)) { err = -ENOMEM; rollover = kzalloc(sizeof(*rollover), GFP_KERNEL); if (!rollover) goto out; atomic_long_set(&rollover->num, 0); atomic_long_set(&rollover->num_huge, 0); atomic_long_set(&rollover->num_failed, 0); } if (type_flags & PACKET_FANOUT_FLAG_UNIQUEID) { if (id != 0) { err = -EINVAL; goto out; } if (!fanout_find_new_id(sk, &id)) { err = -ENOMEM; goto out; } /* ephemeral flag for the first socket in the group: drop it */ flags &= ~(PACKET_FANOUT_FLAG_UNIQUEID >> 8); } match = NULL; list_for_each_entry(f, &fanout_list, list) { if (f->id == id && read_pnet(&f->net) == sock_net(sk)) { match = f; break; } } err = -EINVAL; if (match) { if (match->flags != flags) goto out; if (args->max_num_members && args->max_num_members != match->max_num_members) goto out; } else { if (args->max_num_members > PACKET_FANOUT_MAX) goto out; if (!args->max_num_members) /* legacy PACKET_FANOUT_MAX */ args->max_num_members = 256; err = -ENOMEM; match = kvzalloc(struct_size(match, arr, args->max_num_members), GFP_KERNEL); if (!match) goto out; write_pnet(&match->net, sock_net(sk)); match->id = id; match->type = type; match->flags = flags; INIT_LIST_HEAD(&match->list); spin_lock_init(&match->lock); refcount_set(&match->sk_ref, 0); fanout_init_data(match); match->prot_hook.type = po->prot_hook.type; match->prot_hook.dev = po->prot_hook.dev; match->prot_hook.func = packet_rcv_fanout; match->prot_hook.af_packet_priv = match; match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; match->prot_hook.ignore_outgoing = type_flags & PACKET_FANOUT_FLAG_IGNORE_OUTGOING; list_add(&match->list, &fanout_list); } err = -EINVAL; spin_lock(&po->bind_lock); if (packet_sock_flag(po, PACKET_SOCK_RUNNING) && match->type == type && match->prot_hook.type == po->prot_hook.type && match->prot_hook.dev == po->prot_hook.dev) { err = -ENOSPC; if (refcount_read(&match->sk_ref) < match->max_num_members) { __dev_remove_pack(&po->prot_hook); /* Paired with packet_setsockopt(PACKET_FANOUT_DATA) */ WRITE_ONCE(po->fanout, match); po->rollover = rollover; rollover = NULL; refcount_set(&match->sk_ref, refcount_read(&match->sk_ref) + 1); __fanout_link(sk, po); err = 0; } } spin_unlock(&po->bind_lock); if (err && !refcount_read(&match->sk_ref)) { list_del(&match->list); kvfree(match); } out: kfree(rollover); mutex_unlock(&fanout_mutex); return err; } /* If pkt_sk(sk)->fanout->sk_ref is zero, this function removes * pkt_sk(sk)->fanout from fanout_list and returns pkt_sk(sk)->fanout. * It is the responsibility of the caller to call fanout_release_data() and * free the returned packet_fanout (after synchronize_net()) */ static struct packet_fanout *fanout_release(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_fanout *f; mutex_lock(&fanout_mutex); f = po->fanout; if (f) { po->fanout = NULL; if (refcount_dec_and_test(&f->sk_ref)) list_del(&f->list); else f = NULL; } mutex_unlock(&fanout_mutex); return f; } static bool packet_extra_vlan_len_allowed(const struct net_device *dev, struct sk_buff *skb) { /* Earlier code assumed this would be a VLAN pkt, double-check * this now that we have the actual packet in hand. We can only * do this check on Ethernet devices. */ if (unlikely(dev->type != ARPHRD_ETHER)) return false; skb_reset_mac_header(skb); return likely(eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)); } static const struct proto_ops packet_ops; static const struct proto_ops packet_ops_spkt; static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct sock *sk; struct sockaddr_pkt *spkt; /* * When we registered the protocol we saved the socket in the data * field for just this event. */ sk = pt->af_packet_priv; /* * Yank back the headers [hope the device set this * right or kerboom...] * * Incoming packets have ll header pulled, * push it back. * * For outgoing ones skb->data == skb_mac_header(skb) * so that this procedure is noop. */ if (skb->pkt_type == PACKET_LOOPBACK) goto out; if (!net_eq(dev_net(dev), sock_net(sk))) goto out; skb = skb_share_check(skb, GFP_ATOMIC); if (skb == NULL) goto oom; /* drop any routing info */ skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spkt = &PACKET_SKB_CB(skb)->sa.pkt; skb_push(skb, skb->data - skb_mac_header(skb)); /* * The SOCK_PACKET socket receives _all_ frames. */ spkt->spkt_family = dev->type; strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); spkt->spkt_protocol = skb->protocol; /* * Charge the memory to the socket. This is done specifically * to prevent sockets using all the memory up. */ if (sock_queue_rcv_skb(sk, skb) == 0) return 0; out: kfree_skb(skb); oom: return 0; } static void packet_parse_headers(struct sk_buff *skb, struct socket *sock) { int depth; if ((!skb->protocol || skb->protocol == htons(ETH_P_ALL)) && sock->type == SOCK_RAW) { skb_reset_mac_header(skb); skb->protocol = dev_parse_header_protocol(skb); } /* Move network header to the right position for VLAN tagged packets */ if (likely(skb->dev->type == ARPHRD_ETHER) && eth_type_vlan(skb->protocol) && vlan_get_protocol_and_depth(skb, skb->protocol, &depth) != 0) skb_set_network_header(skb, depth); skb_probe_transport_header(skb); } /* * Output a raw packet to a device layer. This bypasses all the other * protocol layers and you must therefore supply it with a complete frame */ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_pkt *, saddr, msg->msg_name); struct sk_buff *skb = NULL; struct net_device *dev; struct sockcm_cookie sockc; __be16 proto = 0; int err; int extra_len = 0; /* * Get and verify the address. */ if (saddr) { if (msg->msg_namelen < sizeof(struct sockaddr)) return -EINVAL; if (msg->msg_namelen == sizeof(struct sockaddr_pkt)) proto = saddr->spkt_protocol; } else return -ENOTCONN; /* SOCK_PACKET must be sent giving an address */ /* * Find the device first to size check it */ saddr->spkt_device[sizeof(saddr->spkt_device) - 1] = 0; retry: rcu_read_lock(); dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device); err = -ENODEV; if (dev == NULL) goto out_unlock; err = -ENETDOWN; if (!(dev->flags & IFF_UP)) goto out_unlock; /* * You may not queue a frame bigger than the mtu. This is the lowest level * raw protocol and you must do your own fragmentation at this level. */ if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (len > dev->mtu + dev->hard_header_len + VLAN_HLEN + extra_len) goto out_unlock; if (!skb) { size_t reserved = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0; rcu_read_unlock(); skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL); if (skb == NULL) return -ENOBUFS; /* FIXME: Save some space for broken drivers that write a hard * header at transmission time by themselves. PPP is the notable * one here. This should really be fixed at the driver level. */ skb_reserve(skb, reserved); skb_reset_network_header(skb); /* Try to align data part correctly */ if (hhlen) { skb->data -= hhlen; skb->tail -= hhlen; if (len < hhlen) skb_reset_network_header(skb); } err = memcpy_from_msg(skb_put(skb, len), msg, len); if (err) goto out_free; goto retry; } if (!dev_validate_header(dev, skb->data, len) || !skb->len) { err = -EINVAL; goto out_unlock; } if (len > (dev->mtu + dev->hard_header_len + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_unlock; } sockcm_init(&sockc, sk); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = READ_ONCE(sk->sk_mark); skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); dev_queue_xmit(skb); rcu_read_unlock(); return len; out_unlock: rcu_read_unlock(); out_free: kfree_skb(skb); return err; } static unsigned int run_filter(struct sk_buff *skb, const struct sock *sk, unsigned int res) { struct sk_filter *filter; rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (filter != NULL) res = bpf_prog_run_clear_cb(filter->prog, skb); rcu_read_unlock(); return res; } static int packet_rcv_vnet(struct msghdr *msg, const struct sk_buff *skb, size_t *len, int vnet_hdr_sz) { struct virtio_net_hdr_mrg_rxbuf vnet_hdr = { .num_buffers = 0 }; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)&vnet_hdr, vio_le(), true, 0)) return -EINVAL; return memcpy_to_msg(msg, (void *)&vnet_hdr, vnet_hdr_sz); } /* * This function makes lazy skb cloning in hope that most of packets * are discarded by BPF. * * Note tricky part: we DO mangle shared skb! skb->data, skb->len * and skb->cb are mangled. It works because (and until) packets * falling here are owned by current CPU. Output packets are cloned * by dev_queue_xmit_nit(), input packets are processed by net_bh * sequentially, so that if we return skb to original state on exit, * we will not harm anyone. */ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct sockaddr_ll *sll; struct packet_sock *po; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; skb->dev = dev; if (dev_has_header(dev)) { /* The device has an explicit notion of ll header, * exported to higher levels. * * Otherwise, the device hides details of its frame * structure, so that corresponding packet head is * never delivered to user. */ if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb->len; res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; if (snaplen > res) snaplen = res; if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto drop_n_acct; if (skb_shared(skb)) { struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC); if (nskb == NULL) goto drop_n_acct; if (skb_head != skb->data) { skb->data = skb_head; skb->len = skb_len; } consume_skb(skb); skb = nskb; } sock_skb_cb_check_size(sizeof(*PACKET_SKB_CB(skb)) + MAX_ADDR_LEN - 8); sll = &PACKET_SKB_CB(skb)->sa.ll; sll->sll_hatype = dev->type; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; sll->sll_halen = dev_parse_header(skb, sll->sll_addr); /* sll->sll_family and sll->sll_protocol are set in packet_recvmsg(). * Use their space for storing the original skb length. */ PACKET_SKB_CB(skb)->sa.origlen = skb->len; if (pskb_trim(skb, snaplen)) goto drop_n_acct; skb_set_owner_r(skb, sk); skb->dev = NULL; skb_dst_drop(skb); /* drop conntrack reference */ nf_reset_ct(skb); spin_lock(&sk->sk_receive_queue.lock); po->stats.stats1.tp_packets++; sock_skb_set_dropcount(sk, skb); skb_clear_delivery_time(skb); __skb_queue_tail(&sk->sk_receive_queue, skb); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); return 0; drop_n_acct: atomic_inc(&po->tp_drops); atomic_inc(&sk->sk_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; } static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { enum skb_drop_reason drop_reason = SKB_CONSUMED; struct sock *sk = NULL; struct packet_sock *po; struct sockaddr_ll *sll; union tpacket_uhdr h; u8 *skb_head = skb->data; int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; unsigned short macoff, hdrlen; unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec64 ts; __u32 ts_status; unsigned int slot_id = 0; int vnet_hdr_sz = 0; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. * We may add members to them until current aligned size without forcing * userspace to call getsockopt(..., PACKET_HDRLEN, ...). */ BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h2)) != 32); BUILD_BUG_ON(TPACKET_ALIGN(sizeof(*h.h3)) != 48); if (skb->pkt_type == PACKET_LOOPBACK) goto drop; sk = pt->af_packet_priv; po = pkt_sk(sk); if (!net_eq(dev_net(dev), sock_net(sk))) goto drop; if (dev_has_header(dev)) { if (sk->sk_type != SOCK_DGRAM) skb_push(skb, skb->data - skb_mac_header(skb)); else if (skb->pkt_type == PACKET_OUTGOING) { /* Special case: outgoing packets have ll header at head */ skb_pull(skb, skb_network_offset(skb)); } } snaplen = skb->len; res = run_filter(skb, sk, snaplen); if (!res) goto drop_n_restore; /* If we are flooded, just give up */ if (__packet_rcv_has_room(po, skb) == ROOM_NONE) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) status |= TP_STATUS_GSO_TCP; if (snaplen > res) snaplen = res; if (sk->sk_type == SOCK_DGRAM) { macoff = netoff = TPACKET_ALIGN(po->tp_hdrlen) + 16 + po->tp_reserve; } else { unsigned int maclen = skb_network_offset(skb); netoff = TPACKET_ALIGN(po->tp_hdrlen + (maclen < 16 ? 16 : maclen)) + po->tp_reserve; vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); if (vnet_hdr_sz) netoff += vnet_hdr_sz; macoff = netoff - maclen; } if (netoff > USHRT_MAX) { atomic_inc(&po->tp_drops); goto drop_n_restore; } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (READ_ONCE(po->copy_thresh) && atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); } else { copy_skb = skb_get(skb); skb_head = skb->data; } if (copy_skb) { memset(&PACKET_SKB_CB(copy_skb)->sa.ll, 0, sizeof(PACKET_SKB_CB(copy_skb)->sa.ll)); skb_set_owner_r(copy_skb, sk); } } snaplen = po->rx_ring.frame_size - macoff; if ((int)snaplen < 0) { snaplen = 0; vnet_hdr_sz = 0; } } } else if (unlikely(macoff + snaplen > GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len)) { u32 nval; nval = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len - macoff; pr_err_once("tpacket_rcv: packet too big, clamped from %u to %u. macoff=%u\n", snaplen, nval, macoff); snaplen = nval; if (unlikely((int)snaplen < 0)) { snaplen = 0; macoff = GET_PBDQC_FROM_RB(&po->rx_ring)->max_frame_len; vnet_hdr_sz = 0; } } spin_lock(&sk->sk_receive_queue.lock); h.raw = packet_current_rx_frame(po, skb, TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; if (po->tp_version <= TPACKET_V2) { slot_id = po->rx_ring.head; if (test_bit(slot_id, po->rx_ring.rx_owner_map)) goto drop_n_account; __set_bit(slot_id, po->rx_ring.rx_owner_map); } if (vnet_hdr_sz && virtio_net_hdr_from_skb(skb, h.raw + macoff - sizeof(struct virtio_net_hdr), vio_le(), true, 0)) { if (po->tp_version == TPACKET_V3) prb_clear_blk_fill_status(&po->rx_ring); goto drop_n_account; } if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* * LOSING will be reported till you read the stats, * because it's COR - Clear On Read. * Anyways, moving it for V1/V2 only as V3 doesn't need this * at packet level. */ if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; } po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; skb_clear_delivery_time(copy_skb); __skb_queue_tail(&sk->sk_receive_queue, copy_skb); } spin_unlock(&sk->sk_receive_queue.lock); skb_copy_bits(skb, 0, h.raw + macoff, snaplen); /* Always timestamp; prefer an existing software timestamp taken * closer to the time of capture. */ ts_status = tpacket_get_timestamp(skb, &ts, READ_ONCE(po->tp_tstamp) | SOF_TIMESTAMPING_SOFTWARE); if (!ts_status) ktime_get_real_ts64(&ts); status |= ts_status; switch (po->tp_version) { case TPACKET_V1: h.h1->tp_len = skb->len; h.h1->tp_snaplen = snaplen; h.h1->tp_mac = macoff; h.h1->tp_net = netoff; h.h1->tp_sec = ts.tv_sec; h.h1->tp_usec = ts.tv_nsec / NSEC_PER_USEC; hdrlen = sizeof(*h.h1); break; case TPACKET_V2: h.h2->tp_len = skb->len; h.h2->tp_snaplen = snaplen; h.h2->tp_mac = macoff; h.h2->tp_net = netoff; h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; if (skb_vlan_tag_present(skb)) { h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); h.h2->tp_vlan_tpid = ntohs(skb->protocol); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; } memset(h.h2->tp_padding, 0, sizeof(h.h2->tp_padding)); hdrlen = sizeof(*h.h2); break; case TPACKET_V3: /* tp_nxt_offset,vlan are already populated above. * So DONT clear those fields here */ h.h3->tp_status |= status; h.h3->tp_len = skb->len; h.h3->tp_snaplen = snaplen; h.h3->tp_mac = macoff; h.h3->tp_net = netoff; h.h3->tp_sec = ts.tv_sec; h.h3->tp_nsec = ts.tv_nsec; memset(h.h3->tp_padding, 0, sizeof(h.h3->tp_padding)); hdrlen = sizeof(*h.h3); break; default: BUG(); } sll = h.raw + TPACKET_ALIGN(hdrlen); sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; else sll->sll_ifindex = dev->ifindex; smp_mb(); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 if (po->tp_version <= TPACKET_V2) { u8 *start, *end; end = (u8 *) PAGE_ALIGN((unsigned long) h.raw + macoff + snaplen); for (start = h.raw; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); } smp_wmb(); #endif if (po->tp_version <= TPACKET_V2) { spin_lock(&sk->sk_receive_queue.lock); __packet_set_status(po, h.raw, status); __clear_bit(slot_id, po->rx_ring.rx_owner_map); spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); } else if (po->tp_version == TPACKET_V3) { prb_clear_blk_fill_status(&po->rx_ring); } drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { skb->data = skb_head; skb->len = skb_len; } drop: sk_skb_reason_drop(sk, skb, drop_reason); return 0; drop_n_account: spin_unlock(&sk->sk_receive_queue.lock); atomic_inc(&po->tp_drops); drop_reason = SKB_DROP_REASON_PACKET_SOCK_ERROR; sk->sk_data_ready(sk); sk_skb_reason_drop(sk, copy_skb, drop_reason); goto drop_n_restore; } static void tpacket_destruct_skb(struct sk_buff *skb) { struct packet_sock *po = pkt_sk(skb->sk); if (likely(po->tx_ring.pg_vec)) { void *ph; __u32 ts; ph = skb_zcopy_get_nouarg(skb); packet_dec_pending(&po->tx_ring); ts = __packet_set_timestamp(po, ph, skb); __packet_set_status(po, ph, TP_STATUS_AVAILABLE | ts); complete(&po->skb_completion); } sock_wfree(skb); } static int __packet_snd_vnet_parse(struct virtio_net_hdr *vnet_hdr, size_t len) { if ((vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && (__virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2 > __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len))) vnet_hdr->hdr_len = __cpu_to_virtio16(vio_le(), __virtio16_to_cpu(vio_le(), vnet_hdr->csum_start) + __virtio16_to_cpu(vio_le(), vnet_hdr->csum_offset) + 2); if (__virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len) > len) return -EINVAL; return 0; } static int packet_snd_vnet_parse(struct msghdr *msg, size_t *len, struct virtio_net_hdr *vnet_hdr, int vnet_hdr_sz) { int ret; if (*len < vnet_hdr_sz) return -EINVAL; *len -= vnet_hdr_sz; if (!copy_from_iter_full(vnet_hdr, sizeof(*vnet_hdr), &msg->msg_iter)) return -EFAULT; ret = __packet_snd_vnet_parse(vnet_hdr, *len); if (ret) return ret; /* move iter to point to the start of mac header */ if (vnet_hdr_sz != sizeof(struct virtio_net_hdr)) iov_iter_advance(&msg->msg_iter, vnet_hdr_sz - sizeof(struct virtio_net_hdr)); return 0; } static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, void *frame, struct net_device *dev, void *data, int tp_len, __be16 proto, unsigned char *addr, int hlen, int copylen, const struct sockcm_cookie *sockc) { union tpacket_uhdr ph; int to_write, offset, len, nr_frags, len_max; struct socket *sock = po->sk.sk_socket; struct page *page; int err; ph.raw = frame; skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(po->sk.sk_priority); skb->mark = READ_ONCE(po->sk.sk_mark); skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid); skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); skb_reset_network_header(skb); to_write = tp_len; if (sock->type == SOCK_DGRAM) { err = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, tp_len); if (unlikely(err < 0)) return -EINVAL; } else if (copylen) { int hdrlen = min_t(int, copylen, tp_len); skb_push(skb, dev->hard_header_len); skb_put(skb, copylen - dev->hard_header_len); err = skb_store_bits(skb, 0, data, hdrlen); if (unlikely(err)) return err; if (!dev_validate_header(dev, skb->data, hdrlen)) return -EINVAL; data += hdrlen; to_write -= hdrlen; } offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); skb->data_len = to_write; skb->len += to_write; skb->truesize += to_write; refcount_add(to_write, &po->sk.sk_wmem_alloc); while (likely(to_write)) { nr_frags = skb_shinfo(skb)->nr_frags; if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { pr_err("Packet exceed the number of skb frags(%u)\n", (unsigned int)MAX_SKB_FRAGS); return -EFAULT; } page = pgv_to_page(data); data += len; flush_dcache_page(page); get_page(page); skb_fill_page_desc(skb, nr_frags, page, offset, len); to_write -= len; offset = 0; len_max = PAGE_SIZE; len = ((to_write > len_max) ? len_max : to_write); } packet_parse_headers(skb, sock); return tp_len; } static int tpacket_parse_header(struct packet_sock *po, void *frame, int size_max, void **data) { union tpacket_uhdr ph; int tp_len, off; ph.raw = frame; switch (po->tp_version) { case TPACKET_V3: if (ph.h3->tp_next_offset != 0) { pr_warn_once("variable sized slot not supported"); return -EINVAL; } tp_len = ph.h3->tp_len; break; case TPACKET_V2: tp_len = ph.h2->tp_len; break; default: tp_len = ph.h1->tp_len; break; } if (unlikely(tp_len > size_max)) { pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); return -EMSGSIZE; } if (unlikely(packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF))) { int off_min, off_max; off_min = po->tp_hdrlen - sizeof(struct sockaddr_ll); off_max = po->tx_ring.frame_size - tp_len; if (po->sk.sk_type == SOCK_DGRAM) { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_net; break; case TPACKET_V2: off = ph.h2->tp_net; break; default: off = ph.h1->tp_net; break; } } else { switch (po->tp_version) { case TPACKET_V3: off = ph.h3->tp_mac; break; case TPACKET_V2: off = ph.h2->tp_mac; break; default: off = ph.h1->tp_mac; break; } } if (unlikely((off < off_min) || (off_max < off))) return -EINVAL; } else { off = po->tp_hdrlen - sizeof(struct sockaddr_ll); } *data = frame + off; return tp_len; } static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) { struct sk_buff *skb = NULL; struct net_device *dev; struct virtio_net_hdr *vnet_hdr = NULL; struct sockcm_cookie sockc; __be16 proto; int err, reserve = 0; void *ph; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); bool need_wait = !(msg->msg_flags & MSG_DONTWAIT); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); unsigned char *addr = NULL; int tp_len, size_max; void *data; int len_sum = 0; int status = TP_STATUS_AVAILABLE; int hlen, tlen, copylen = 0; long timeo = 0; mutex_lock(&po->pg_vec_lock); /* packet_sendmsg() check on tx_ring.pg_vec was lockless, * we need to confirm it under protection of pg_vec_lock. */ if (unlikely(!po->tx_ring.pg_vec)) { err = -EBUSY; goto out; } if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); if (po->sk.sk_socket->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_put; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; sockcm_init(&sockc, &po->sk); if (msg->msg_controllen) { err = sock_cmsg_send(&po->sk, msg, &sockc); if (unlikely(err)) goto out_put; } if (po->sk.sk_socket->type == SOCK_RAW) reserve = dev->hard_header_len; size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); if ((size_max > dev->mtu + reserve + VLAN_HLEN) && !vnet_hdr_sz) size_max = dev->mtu + reserve + VLAN_HLEN; reinit_completion(&po->skb_completion); do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); if (unlikely(ph == NULL)) { if (need_wait && skb) { timeo = sock_sndtimeo(&po->sk, msg->msg_flags & MSG_DONTWAIT); timeo = wait_for_completion_interruptible_timeout(&po->skb_completion, timeo); if (timeo <= 0) { err = !timeo ? -ETIMEDOUT : -ERESTARTSYS; goto out_put; } } /* check for additional frames */ continue; } skb = NULL; tp_len = tpacket_parse_header(po, ph, size_max, &data); if (tp_len < 0) goto tpacket_error; status = TP_STATUS_SEND_REQUEST; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; if (vnet_hdr_sz) { vnet_hdr = data; data += vnet_hdr_sz; tp_len -= vnet_hdr_sz; if (tp_len < 0 || __packet_snd_vnet_parse(vnet_hdr, tp_len)) { tp_len = -EINVAL; goto tpacket_error; } copylen = __virtio16_to_cpu(vio_le(), vnet_hdr->hdr_len); } copylen = max_t(int, copylen, dev->hard_header_len); skb = sock_alloc_send_skb(&po->sk, hlen + tlen + sizeof(struct sockaddr_ll) + (copylen - dev->hard_header_len), !need_wait, &err); if (unlikely(skb == NULL)) { /* we assume the socket was initially writeable ... */ if (likely(len_sum > 0)) err = len_sum; goto out_status; } tp_len = tpacket_fill_skb(po, skb, ph, dev, data, tp_len, proto, addr, hlen, copylen, &sockc); if (likely(tp_len >= 0) && tp_len > dev->mtu + reserve && !vnet_hdr_sz && !packet_extra_vlan_len_allowed(dev, skb)) tp_len = -EMSGSIZE; if (unlikely(tp_len < 0)) { tpacket_error: if (packet_sock_flag(po, PACKET_SOCK_TP_LOSS)) { __packet_set_status(po, ph, TP_STATUS_AVAILABLE); packet_increment_head(&po->tx_ring); kfree_skb(skb); continue; } else { status = TP_STATUS_WRONG_FORMAT; err = tp_len; goto out_status; } } if (vnet_hdr_sz) { if (virtio_net_hdr_to_skb(skb, vnet_hdr, vio_le())) { tp_len = -EINVAL; goto tpacket_error; } virtio_net_hdr_set_proto(skb, vnet_hdr); } skb->destructor = tpacket_destruct_skb; __packet_set_status(po, ph, TP_STATUS_SENDING); packet_inc_pending(&po->tx_ring); status = TP_STATUS_SEND_REQUEST; err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err && __packet_get_status(po, ph) == TP_STATUS_AVAILABLE) { /* skb was destructed already */ skb = NULL; goto out_status; } /* * skb was dropped but not destructed yet; * let's treat it like congestion or err < 0 */ err = 0; } packet_increment_head(&po->tx_ring); len_sum += tp_len; } while (likely((ph != NULL) || /* Note: packet_read_pending() might be slow if we have * to call it as it's per_cpu variable, but in fast-path * we already short-circuit the loop with the first * condition, and luckily don't have to go that path * anyway. */ (need_wait && packet_read_pending(&po->tx_ring)))); err = len_sum; goto out_put; out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; } static struct sk_buff *packet_alloc_skb(struct sock *sk, size_t prepad, size_t reserve, size_t len, size_t linear, int noblock, int *err) { struct sk_buff *skb; /* Under a page? Don't bother with paged skb. */ if (prepad + len < PAGE_SIZE || !linear) linear = len; if (len - linear > MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) linear = len - MAX_SKB_FRAGS * (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER); skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock, err, PAGE_ALLOC_COSTLY_ORDER); if (!skb) return NULL; skb_reserve(skb, reserve); skb_put(skb, linear); skb->data_len = len - linear; skb->len += len - linear; return skb; } static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; DECLARE_SOCKADDR(struct sockaddr_ll *, saddr, msg->msg_name); struct sk_buff *skb; struct net_device *dev; __be16 proto; unsigned char *addr = NULL; int err, reserve = 0; struct sockcm_cookie sockc; struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; struct packet_sock *po = pkt_sk(sk); int vnet_hdr_sz = READ_ONCE(po->vnet_hdr_sz); int hlen, tlen, linear; int extra_len = 0; /* * Get and verify the address. */ if (likely(saddr == NULL)) { dev = packet_cached_dev_get(po); proto = READ_ONCE(po->num); } else { err = -EINVAL; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; proto = saddr->sll_protocol; dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); if (sock->type == SOCK_DGRAM) { if (dev && msg->msg_namelen < dev->addr_len + offsetof(struct sockaddr_ll, sll_addr)) goto out_unlock; addr = saddr->sll_addr; } } err = -ENXIO; if (unlikely(dev == NULL)) goto out_unlock; err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_unlock; sockcm_init(&sockc, sk); sockc.mark = READ_ONCE(sk->sk_mark); if (msg->msg_controllen) { err = sock_cmsg_send(sk, msg, &sockc); if (unlikely(err)) goto out_unlock; } if (sock->type == SOCK_RAW) reserve = dev->hard_header_len; if (vnet_hdr_sz) { err = packet_snd_vnet_parse(msg, &len, &vnet_hdr, vnet_hdr_sz); if (err) goto out_unlock; } if (unlikely(sock_flag(sk, SOCK_NOFCS))) { if (!netif_supports_nofcs(dev)) { err = -EPROTONOSUPPORT; goto out_unlock; } extra_len = 4; /* We're doing our own CRC */ } err = -EMSGSIZE; if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + VLAN_HLEN + extra_len)) goto out_unlock; err = -ENOBUFS; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; linear = __virtio16_to_cpu(vio_le(), vnet_hdr.hdr_len); linear = max(linear, min_t(int, len, dev->hard_header_len)); skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, linear, msg->msg_flags & MSG_DONTWAIT, &err); if (skb == NULL) goto out_unlock; skb_reset_network_header(skb); err = -EINVAL; if (sock->type == SOCK_DGRAM) { offset = dev_hard_header(skb, dev, ntohs(proto), addr, NULL, len); if (unlikely(offset < 0)) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); if (len < reserve + sizeof(struct ipv6hdr) && dev->min_header_len != dev->hard_header_len) skb_reset_network_header(skb); } /* Returns -EFAULT on error */ err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len); if (err) goto out_free; if ((sock->type == SOCK_RAW && !dev_validate_header(dev, skb->data, len)) || !skb->len) { err = -EINVAL; goto out_free; } skb_setup_tx_timestamp(skb, sockc.tsflags); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { err = -EMSGSIZE; goto out_free; } skb->protocol = proto; skb->dev = dev; skb->priority = READ_ONCE(sk->sk_priority); skb->mark = sockc.mark; skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid); if (unlikely(extra_len == 4)) skb->no_fcs = 1; packet_parse_headers(skb, sock); if (vnet_hdr_sz) { err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le()); if (err) goto out_free; len += vnet_hdr_sz; virtio_net_hdr_set_proto(skb, &vnet_hdr); } err = packet_xmit(po, skb); if (unlikely(err != 0)) { if (err > 0) err = net_xmit_errno(err); if (err) goto out_unlock; } dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: dev_put(dev); out: return err; } static int packet_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); /* Reading tx_ring.pg_vec without holding pg_vec_lock is racy. * tpacket_snd() will redo the check safely. */ if (data_race(po->tx_ring.pg_vec)) return tpacket_snd(po, msg); return packet_snd(sock, msg, len); } /* * Close a PACKET socket. This is fairly simple. We immediately go * to 'closed' state and remove our protocol entry in the device list. */ static int packet_release(struct socket *sock) { struct sock *sk = sock->sk; struct packet_sock *po; struct packet_fanout *f; struct net *net; union tpacket_req_u req_u; if (!sk) return 0; net = sock_net(sk); po = pkt_sk(sk); mutex_lock(&net->packet.sklist_lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, sk->sk_prot, -1); spin_lock(&po->bind_lock); unregister_prot_hook(sk, false); packet_cached_dev_reset(po); if (po->prot_hook.dev) { netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); packet_flush_mclist(sk); lock_sock(sk); if (po->rx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 0); } if (po->tx_ring.pg_vec) { memset(&req_u, 0, sizeof(req_u)); packet_set_ring(sk, &req_u, 1, 1); } release_sock(sk); f = fanout_release(sk); synchronize_net(); kfree(po->rollover); if (f) { fanout_release_data(f); kvfree(f); } /* * Now the socket is dead. No more input will appear. */ sock_orphan(sk); sock->sk = NULL; /* Purge queues */ skb_queue_purge(&sk->sk_receive_queue); packet_free_pending(po); sock_put(sk); return 0; } /* * Attach a packet hook. */ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, __be16 proto) { struct packet_sock *po = pkt_sk(sk); struct net_device *dev = NULL; bool unlisted = false; bool need_rehook; int ret = 0; lock_sock(sk); spin_lock(&po->bind_lock); if (!proto) proto = po->num; rcu_read_lock(); if (po->fanout) { ret = -EINVAL; goto out_unlock; } if (name) { dev = dev_get_by_name_rcu(sock_net(sk), name); if (!dev) { ret = -ENODEV; goto out_unlock; } } else if (ifindex) { dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (!dev) { ret = -ENODEV; goto out_unlock; } } need_rehook = po->prot_hook.type != proto || po->prot_hook.dev != dev; if (need_rehook) { dev_hold(dev); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { rcu_read_unlock(); /* prevents packet_notifier() from calling * register_prot_hook() */ WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, true); rcu_read_lock(); if (dev) unlisted = !dev_get_by_index_rcu(sock_net(sk), dev->ifindex); } BUG_ON(packet_sock_flag(po, PACKET_SOCK_RUNNING)); WRITE_ONCE(po->num, proto); po->prot_hook.type = proto; netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); if (unlikely(unlisted)) { po->prot_hook.dev = NULL; WRITE_ONCE(po->ifindex, -1); packet_cached_dev_reset(po); } else { netdev_hold(dev, &po->prot_hook.dev_tracker, GFP_ATOMIC); po->prot_hook.dev = dev; WRITE_ONCE(po->ifindex, dev ? dev->ifindex : 0); packet_cached_dev_assign(po, dev); } dev_put(dev); } if (proto == 0 || !need_rehook) goto out_unlock; if (!unlisted && (!dev || (dev->flags & IFF_UP))) { register_prot_hook(sk); } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } out_unlock: rcu_read_unlock(); spin_unlock(&po->bind_lock); release_sock(sk); return ret; } /* * Bind a packet socket to a device */ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality */ if (addr_len != sizeof(struct sockaddr)) return -EINVAL; /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr; struct sock *sk = sock->sk; /* * Check legality */ if (addr_len < sizeof(struct sockaddr_ll)) return -EINVAL; if (sll->sll_family != AF_PACKET) return -EINVAL; return packet_do_bind(sk, NULL, sll->sll_ifindex, sll->sll_protocol); } static struct proto packet_proto = { .name = "PACKET", .owner = THIS_MODULE, .obj_size = sizeof(struct packet_sock), }; /* * Create a packet of type SOCK_PACKET. */ static int packet_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; struct packet_sock *po; __be16 proto = (__force __be16)protocol; /* weird, but documented */ int err; if (!ns_capable(net->user_ns, CAP_NET_RAW)) return -EPERM; if (sock->type != SOCK_DGRAM && sock->type != SOCK_RAW && sock->type != SOCK_PACKET) return -ESOCKTNOSUPPORT; sock->state = SS_UNCONNECTED; err = -ENOBUFS; sk = sk_alloc(net, PF_PACKET, GFP_KERNEL, &packet_proto, kern); if (sk == NULL) goto out; sock->ops = &packet_ops; if (sock->type == SOCK_PACKET) sock->ops = &packet_ops_spkt; sock_init_data(sock, sk); po = pkt_sk(sk); init_completion(&po->skb_completion); sk->sk_family = PF_PACKET; po->num = proto; err = packet_alloc_pending(po); if (err) goto out2; packet_cached_dev_reset(po); sk->sk_destruct = packet_sock_destruct; /* * Attach a protocol block */ spin_lock_init(&po->bind_lock); mutex_init(&po->pg_vec_lock); po->rollover = NULL; po->prot_hook.func = packet_rcv; if (sock->type == SOCK_PACKET) po->prot_hook.func = packet_rcv_spkt; po->prot_hook.af_packet_priv = sk; po->prot_hook.af_packet_net = sock_net(sk); if (proto) { po->prot_hook.type = proto; __register_prot_hook(sk); } mutex_lock(&net->packet.sklist_lock); sk_add_node_tail_rcu(sk, &net->packet.sklist); mutex_unlock(&net->packet.sklist_lock); sock_prot_inuse_add(net, &packet_proto, 1); return 0; out2: sk_free(sk); out: return err; } /* * Pull a packet from our receive queue and hand it to the user. * If necessary we block. */ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; struct sk_buff *skb; int copied, err; int vnet_hdr_len = READ_ONCE(pkt_sk(sk)->vnet_hdr_sz); unsigned int origlen = 0; err = -EINVAL; if (flags & ~(MSG_PEEK|MSG_DONTWAIT|MSG_TRUNC|MSG_CMSG_COMPAT|MSG_ERRQUEUE)) goto out; #if 0 /* What error should we return now? EUNATTACH? */ if (pkt_sk(sk)->ifindex < 0) return -ENODEV; #endif if (flags & MSG_ERRQUEUE) { err = sock_recv_errqueue(sk, msg, len, SOL_PACKET, PACKET_TX_TIMESTAMP); goto out; } /* * Call the generic datagram receiver. This handles all sorts * of horrible races and re-entrancy so we can forget about it * in the protocol layers. * * Now it will return ENETDOWN, if device have just gone down, * but then it will block. */ skb = skb_recv_datagram(sk, flags, &err); /* * An error occurred so return it. Because skb_recv_datagram() * handles the blocking we don't see and worry about blocking * retries. */ if (skb == NULL) goto out; packet_rcv_try_clear_pressure(pkt_sk(sk)); if (vnet_hdr_len) { err = packet_rcv_vnet(msg, skb, &len, vnet_hdr_len); if (err) goto out_free; } /* You lose any data beyond the buffer you gave. If it worries * a user program they can ask the device for its MTU * anyway. */ copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err) goto out_free; if (sock->type != SOCK_PACKET) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; sll->sll_protocol = (sock->type == SOCK_DGRAM) ? vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_cmsgs(msg, sk, skb); if (msg->msg_name) { const size_t max_len = min(sizeof(skb->cb), sizeof(struct sockaddr_storage)); int copy_len; /* If the address length field is there to be filled * in, we fill it in now. */ if (sock->type == SOCK_PACKET) { __sockaddr_check_size(sizeof(struct sockaddr_pkt)); msg->msg_namelen = sizeof(struct sockaddr_pkt); copy_len = msg->msg_namelen; } else { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; msg->msg_namelen = sll->sll_halen + offsetof(struct sockaddr_ll, sll_addr); copy_len = msg->msg_namelen; if (msg->msg_namelen < sizeof(struct sockaddr_ll)) { memset(msg->msg_name + offsetof(struct sockaddr_ll, sll_addr), 0, sizeof(sll->sll_addr)); msg->msg_namelen = sizeof(struct sockaddr_ll); } } if (WARN_ON_ONCE(copy_len > max_len)) { copy_len = max_len; msg->msg_namelen = copy_len; } memcpy(msg->msg_name, &PACKET_SKB_CB(skb)->sa, copy_len); } if (packet_sock_flag(pkt_sk(sk), PACKET_SOCK_AUXDATA)) { struct tpacket_auxdata aux; aux.tp_status = TP_STATUS_USER; if (skb->ip_summed == CHECKSUM_PARTIAL) aux.tp_status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && skb_csum_unnecessary(skb)) aux.tp_status |= TP_STATUS_CSUM_VALID; if (skb_is_gso(skb) && skb_is_gso_tcp(skb)) aux.tp_status |= TP_STATUS_GSO_TCP; aux.tp_len = origlen; aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); if (skb_vlan_tag_present(skb)) { aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); if (dev) { aux.tp_vlan_tci = vlan_get_tci(skb, dev); aux.tp_vlan_tpid = ntohs(skb->protocol); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; } put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } /* * Free or return the buffer as appropriate. Again this * hides all the races and re-entrancy issues from us. */ err = vnet_hdr_len + ((flags&MSG_TRUNC) ? skb->len : copied); out_free: skb_free_datagram(sk, skb); out: return err; } static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; if (peer) return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); } static int packet_getname(struct socket *sock, struct sockaddr *uaddr, int peer) { struct net_device *dev; struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); DECLARE_SOCKADDR(struct sockaddr_ll *, sll, uaddr); int ifindex; if (peer) return -EOPNOTSUPP; ifindex = READ_ONCE(po->ifindex); sll->sll_family = AF_PACKET; sll->sll_ifindex = ifindex; sll->sll_protocol = READ_ONCE(po->num); sll->sll_pkttype = 0; rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; /* Let __fortify_memcpy_chk() know the actual buffer size. */ memcpy(((struct sockaddr_storage *)sll)->__data + offsetof(struct sockaddr_ll, sll_addr) - offsetofend(struct sockaddr_ll, sll_family), dev->dev_addr, dev->addr_len); } else { sll->sll_hatype = 0; /* Bad: we have no ARPHRD_UNSPEC */ sll->sll_halen = 0; } rcu_read_unlock(); return offsetof(struct sockaddr_ll, sll_addr) + sll->sll_halen; } static int packet_dev_mc(struct net_device *dev, struct packet_mclist *i, int what) { switch (i->type) { case PACKET_MR_MULTICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_mc_add(dev, i->addr); else return dev_mc_del(dev, i->addr); break; case PACKET_MR_PROMISC: return dev_set_promiscuity(dev, what); case PACKET_MR_ALLMULTI: return dev_set_allmulti(dev, what); case PACKET_MR_UNICAST: if (i->alen != dev->addr_len) return -EINVAL; if (what > 0) return dev_uc_add(dev, i->addr); else return dev_uc_del(dev, i->addr); break; default: break; } return 0; } static void packet_dev_mclist_delete(struct net_device *dev, struct packet_mclist **mlp) { struct packet_mclist *ml; while ((ml = *mlp) != NULL) { if (ml->ifindex == dev->ifindex) { packet_dev_mc(dev, ml, -1); *mlp = ml->next; kfree(ml); } else mlp = &ml->next; } } static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml, *i; struct net_device *dev; int err; rtnl_lock(); err = -ENODEV; dev = __dev_get_by_index(sock_net(sk), mreq->mr_ifindex); if (!dev) goto done; err = -EINVAL; if (mreq->mr_alen > dev->addr_len) goto done; err = -ENOBUFS; i = kmalloc(sizeof(*i), GFP_KERNEL); if (i == NULL) goto done; err = 0; for (ml = po->mclist; ml; ml = ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { ml->count++; /* Free the new element ... */ kfree(i); goto done; } } i->type = mreq->mr_type; i->ifindex = mreq->mr_ifindex; i->alen = mreq->mr_alen; memcpy(i->addr, mreq->mr_address, i->alen); memset(i->addr + i->alen, 0, sizeof(i->addr) - i->alen); i->count = 1; i->next = po->mclist; po->mclist = i; err = packet_dev_mc(dev, i, 1); if (err) { po->mclist = i->next; kfree(i); } done: rtnl_unlock(); return err; } static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq) { struct packet_mclist *ml, **mlp; rtnl_lock(); for (mlp = &pkt_sk(sk)->mclist; (ml = *mlp) != NULL; mlp = &ml->next) { if (ml->ifindex == mreq->mr_ifindex && ml->type == mreq->mr_type && ml->alen == mreq->mr_alen && memcmp(ml->addr, mreq->mr_address, ml->alen) == 0) { if (--ml->count == 0) { struct net_device *dev; *mlp = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev) packet_dev_mc(dev, ml, -1); kfree(ml); } break; } } rtnl_unlock(); return 0; } static void packet_flush_mclist(struct sock *sk) { struct packet_sock *po = pkt_sk(sk); struct packet_mclist *ml; if (!po->mclist) return; rtnl_lock(); while ((ml = po->mclist) != NULL) { struct net_device *dev; po->mclist = ml->next; dev = __dev_get_by_index(sock_net(sk), ml->ifindex); if (dev != NULL) packet_dev_mc(dev, ml, -1); kfree(ml); } rtnl_unlock(); } static int packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); int ret; if (level != SOL_PACKET) return -ENOPROTOOPT; switch (optname) { case PACKET_ADD_MEMBERSHIP: case PACKET_DROP_MEMBERSHIP: { struct packet_mreq_max mreq; int len = optlen; memset(&mreq, 0, sizeof(mreq)); if (len < sizeof(struct packet_mreq)) return -EINVAL; if (len > sizeof(mreq)) len = sizeof(mreq); if (copy_from_sockptr(&mreq, optval, len)) return -EFAULT; if (len < (mreq.mr_alen + offsetof(struct packet_mreq, mr_address))) return -EINVAL; if (optname == PACKET_ADD_MEMBERSHIP) ret = packet_mc_add(sk, &mreq); else ret = packet_mc_drop(sk, &mreq); return ret; } case PACKET_RX_RING: case PACKET_TX_RING: { union tpacket_req_u req_u; ret = -EINVAL; lock_sock(sk); switch (po->tp_version) { case TPACKET_V1: case TPACKET_V2: if (optlen < sizeof(req_u.req)) break; ret = copy_from_sockptr(&req_u.req, optval, sizeof(req_u.req)) ? -EINVAL : 0; break; case TPACKET_V3: default: if (optlen < sizeof(req_u.req3)) break; ret = copy_from_sockptr(&req_u.req3, optval, sizeof(req_u.req3)) ? -EINVAL : 0; break; } if (!ret) ret = packet_set_ring(sk, &req_u, 0, optname == PACKET_TX_RING); release_sock(sk); return ret; } case PACKET_COPY_THRESH: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(pkt_sk(sk)->copy_thresh, val); return 0; } case PACKET_VERSION: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; switch (val) { case TPACKET_V1: case TPACKET_V2: case TPACKET_V3: break; default: return -EINVAL; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_version = val; ret = 0; } release_sock(sk); return ret; } case PACKET_RESERVE: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val > INT_MAX) return -EINVAL; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { po->tp_reserve = val; ret = 0; } release_sock(sk); return ret; } case PACKET_LOSS: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { packet_sock_flag_set(po, PACKET_SOCK_TP_LOSS, val); ret = 0; } release_sock(sk); return ret; } case PACKET_AUXDATA: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_AUXDATA, val); return 0; } case PACKET_ORIGDEV: { int val; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_ORIGDEV, val); return 0; } case PACKET_VNET_HDR: case PACKET_VNET_HDR_SZ: { int val, hdr_len; if (sock->type != SOCK_RAW) return -EINVAL; if (optlen < sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (optname == PACKET_VNET_HDR_SZ) { if (val && val != sizeof(struct virtio_net_hdr) && val != sizeof(struct virtio_net_hdr_mrg_rxbuf)) return -EINVAL; hdr_len = val; } else { hdr_len = val ? sizeof(struct virtio_net_hdr) : 0; } lock_sock(sk); if (po->rx_ring.pg_vec || po->tx_ring.pg_vec) { ret = -EBUSY; } else { WRITE_ONCE(po->vnet_hdr_sz, hdr_len); ret = 0; } release_sock(sk); return ret; } case PACKET_TIMESTAMP: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; WRITE_ONCE(po->tp_tstamp, val); return 0; } case PACKET_FANOUT: { struct fanout_args args = { 0 }; if (optlen != sizeof(int) && optlen != sizeof(args)) return -EINVAL; if (copy_from_sockptr(&args, optval, optlen)) return -EFAULT; return fanout_add(sk, &args); } case PACKET_FANOUT_DATA: { /* Paired with the WRITE_ONCE() in fanout_add() */ if (!READ_ONCE(po->fanout)) return -EINVAL; return fanout_set_data(po, optval, optlen); } case PACKET_IGNORE_OUTGOING: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; if (val < 0 || val > 1) return -EINVAL; WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: { unsigned int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; lock_sock(sk); if (!po->rx_ring.pg_vec && !po->tx_ring.pg_vec) packet_sock_flag_set(po, PACKET_SOCK_TX_HAS_OFF, val); release_sock(sk); return 0; } case PACKET_QDISC_BYPASS: { int val; if (optlen != sizeof(val)) return -EINVAL; if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; packet_sock_flag_set(po, PACKET_SOCK_QDISC_BYPASS, val); return 0; } default: return -ENOPROTOOPT; } } static int packet_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { int len; int val, lv = sizeof(val); struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; int drops; if (level != SOL_PACKET) return -ENOPROTOOPT; if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; switch (optname) { case PACKET_STATISTICS: spin_lock_bh(&sk->sk_receive_queue.lock); memcpy(&st, &po->stats, sizeof(st)); memset(&po->stats, 0, sizeof(po->stats)); spin_unlock_bh(&sk->sk_receive_queue.lock); drops = atomic_xchg(&po->tp_drops, 0); if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); st.stats3.tp_drops = drops; st.stats3.tp_packets += drops; data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); st.stats1.tp_drops = drops; st.stats1.tp_packets += drops; data = &st.stats1; } break; case PACKET_AUXDATA: val = packet_sock_flag(po, PACKET_SOCK_AUXDATA); break; case PACKET_ORIGDEV: val = packet_sock_flag(po, PACKET_SOCK_ORIGDEV); break; case PACKET_VNET_HDR: val = !!READ_ONCE(po->vnet_hdr_sz); break; case PACKET_VNET_HDR_SZ: val = READ_ONCE(po->vnet_hdr_sz); break; case PACKET_COPY_THRESH: val = READ_ONCE(pkt_sk(sk)->copy_thresh); break; case PACKET_VERSION: val = po->tp_version; break; case PACKET_HDRLEN: if (len > sizeof(int)) len = sizeof(int); if (len < sizeof(int)) return -EINVAL; if (copy_from_user(&val, optval, len)) return -EFAULT; switch (val) { case TPACKET_V1: val = sizeof(struct tpacket_hdr); break; case TPACKET_V2: val = sizeof(struct tpacket2_hdr); break; case TPACKET_V3: val = sizeof(struct tpacket3_hdr); break; default: return -EINVAL; } break; case PACKET_RESERVE: val = po->tp_reserve; break; case PACKET_LOSS: val = packet_sock_flag(po, PACKET_SOCK_TP_LOSS); break; case PACKET_TIMESTAMP: val = READ_ONCE(po->tp_tstamp); break; case PACKET_FANOUT: val = (po->fanout ? ((u32)po->fanout->id | ((u32)po->fanout->type << 16) | ((u32)po->fanout->flags << 24)) : 0); break; case PACKET_IGNORE_OUTGOING: val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) return -EINVAL; rstats.tp_all = atomic_long_read(&po->rollover->num); rstats.tp_huge = atomic_long_read(&po->rollover->num_huge); rstats.tp_failed = atomic_long_read(&po->rollover->num_failed); data = &rstats; lv = sizeof(rstats); break; case PACKET_TX_HAS_OFF: val = packet_sock_flag(po, PACKET_SOCK_TX_HAS_OFF); break; case PACKET_QDISC_BYPASS: val = packet_sock_flag(po, PACKET_SOCK_QDISC_BYPASS); break; default: return -ENOPROTOOPT; } if (len > lv) len = lv; if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, data, len)) return -EFAULT; return 0; } static int packet_notifier(struct notifier_block *this, unsigned long msg, void *ptr) { struct sock *sk; struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); rcu_read_lock(); sk_for_each_rcu(sk, &net->packet.sklist) { struct packet_sock *po = pkt_sk(sk); switch (msg) { case NETDEV_UNREGISTER: if (po->mclist) packet_dev_mclist_delete(dev, &po->mclist); fallthrough; case NETDEV_DOWN: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (packet_sock_flag(po, PACKET_SOCK_RUNNING)) { __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { packet_cached_dev_reset(po); WRITE_ONCE(po->ifindex, -1); netdev_put(po->prot_hook.dev, &po->prot_hook.dev_tracker); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); } break; case NETDEV_UP: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (po->num) register_prot_hook(sk); spin_unlock(&po->bind_lock); } break; } } rcu_read_unlock(); return NOTIFY_DONE; } static int packet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } #ifdef CONFIG_INET case SIOCADDRT: case SIOCDELRT: case SIOCDARP: case SIOCGARP: case SIOCSARP: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCSIFFLAGS: return inet_dgram_ops.ioctl(sock, cmd, arg); #endif default: return -ENOIOCTLCMD; } return 0; } static __poll_t packet_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); __poll_t mask = datagram_poll(file, sock, wait); spin_lock_bh(&sk->sk_receive_queue.lock); if (po->rx_ring.pg_vec) { if (!packet_previous_rx_frame(po, &po->rx_ring, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { if (packet_current_frame(po, &po->tx_ring, TP_STATUS_AVAILABLE)) mask |= EPOLLOUT | EPOLLWRNORM; } spin_unlock_bh(&sk->sk_write_queue.lock); return mask; } /* Dirty? Well, I still did not learn better way to account * for user mmaps. */ static void packet_mm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_inc(&pkt_sk(sk)->mapped); } static void packet_mm_close(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct socket *sock = file->private_data; struct sock *sk = sock->sk; if (sk) atomic_long_dec(&pkt_sk(sk)->mapped); } static const struct vm_operations_struct packet_mmap_ops = { .open = packet_mm_open, .close = packet_mm_close, }; static void free_pg_vec(struct pgv *pg_vec, unsigned int order, unsigned int len) { int i; for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { if (is_vmalloc_addr(pg_vec[i].buffer)) vfree(pg_vec[i].buffer); else free_pages((unsigned long)pg_vec[i].buffer, order); pg_vec[i].buffer = NULL; } } kfree(pg_vec); } static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer; gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* __get_free_pages failed, fall back to vmalloc */ buffer = vzalloc(array_size((1 << order), PAGE_SIZE)); if (buffer) return buffer; /* vmalloc failed, lets dig into swap here */ gfp_flags &= ~__GFP_NORETRY; buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; /* complete and utter failure */ return NULL; } static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) { unsigned int block_nr = req->tp_block_nr; struct pgv *pg_vec; int i; pg_vec = kcalloc(block_nr, sizeof(struct pgv), GFP_KERNEL | __GFP_NOWARN); if (unlikely(!pg_vec)) goto out; for (i = 0; i < block_nr; i++) { pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } out: return pg_vec; out_free_pgvec: free_pg_vec(pg_vec, order, block_nr); pg_vec = NULL; goto out; } static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, int closing, int tx_ring) { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); unsigned long *rx_owner_map = NULL; int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; __be16 num; int err; /* Added to avoid minimal code churn */ struct tpacket_req *req = &req_u->req; rb = tx_ring ? &po->tx_ring : &po->rx_ring; rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue; err = -EBUSY; if (!closing) { if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; } if (req->tp_block_nr) { unsigned int min_frame_size; /* Sanity tests and some calculations */ err = -EBUSY; if (unlikely(rb->pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V1: po->tp_hdrlen = TPACKET_HDRLEN; break; case TPACKET_V2: po->tp_hdrlen = TPACKET2_HDRLEN; break; case TPACKET_V3: po->tp_hdrlen = TPACKET3_HDRLEN; break; } err = -EINVAL; if (unlikely((int)req->tp_block_size <= 0)) goto out; if (unlikely(!PAGE_ALIGNED(req->tp_block_size))) goto out; min_frame_size = po->tp_hdrlen + po->tp_reserve; if (po->tp_version >= TPACKET_V3 && req->tp_block_size < BLK_PLUS_PRIV((u64)req_u->req3.tp_sizeof_priv) + min_frame_size) goto out; if (unlikely(req->tp_frame_size < min_frame_size)) goto out; if (unlikely(req->tp_frame_size & (TPACKET_ALIGNMENT - 1))) goto out; rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) goto out; err = -ENOMEM; order = get_order(req->tp_block_size); pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; switch (po->tp_version) { case TPACKET_V3: /* Block transmit is not supported yet */ if (!tx_ring) { init_prb_bdqc(po, rb, pg_vec, req_u); } else { struct tpacket_req3 *req3 = &req_u->req3; if (req3->tp_retire_blk_tov || req3->tp_sizeof_priv || req3->tp_feature_req_word) { err = -EINVAL; goto out_free_pg_vec; } } break; default: if (!tx_ring) { rx_owner_map = bitmap_alloc(req->tp_frame_nr, GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); if (!rx_owner_map) goto out_free_pg_vec; } break; } } /* Done */ else { err = -EINVAL; if (unlikely(req->tp_frame_nr)) goto out; } /* Detach socket from network */ spin_lock(&po->bind_lock); was_running = packet_sock_flag(po, PACKET_SOCK_RUNNING); num = po->num; if (was_running) { WRITE_ONCE(po->num, 0); __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); synchronize_net(); err = -EBUSY; mutex_lock(&po->pg_vec_lock); if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); if (po->tp_version <= TPACKET_V2) swap(rb->rx_owner_map, rx_owner_map); rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; spin_unlock_bh(&rb_queue->lock); swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); if (atomic_long_read(&po->mapped)) pr_err("packet_mmap: vma is busy: %ld\n", atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); if (was_running) { WRITE_ONCE(po->num, num); register_prot_hook(sk); } spin_unlock(&po->bind_lock); if (pg_vec && (po->tp_version > TPACKET_V2)) { /* Because we don't support block-based V3 on tx-ring */ if (!tx_ring) prb_shutdown_retire_blk_timer(po, rb_queue); } out_free_pg_vec: if (pg_vec) { bitmap_free(rx_owner_map); free_pg_vec(pg_vec, order, req->tp_block_nr); } out: return err; } static int packet_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); unsigned long size, expected_size; struct packet_ring_buffer *rb; unsigned long start; int err = -EINVAL; int i; if (vma->vm_pgoff) return -EINVAL; mutex_lock(&po->pg_vec_lock); expected_size = 0; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec) { expected_size += rb->pg_vec_len * rb->pg_vec_pages * PAGE_SIZE; } } if (expected_size == 0) goto out; size = vma->vm_end - vma->vm_start; if (size != expected_size) goto out; start = vma->vm_start; for (rb = &po->rx_ring; rb <= &po->tx_ring; rb++) { if (rb->pg_vec == NULL) continue; for (i = 0; i < rb->pg_vec_len; i++) { struct page *page; void *kaddr = rb->pg_vec[i].buffer; int pg_num; for (pg_num = 0; pg_num < rb->pg_vec_pages; pg_num++) { page = pgv_to_page(kaddr); err = vm_insert_page(vma, start, page); if (unlikely(err)) goto out; start += PAGE_SIZE; kaddr += PAGE_SIZE; } } } atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0; out: mutex_unlock(&po->pg_vec_lock); return err; } static const struct proto_ops packet_ops_spkt = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind_spkt, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname_spkt, .poll = datagram_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .sendmsg = packet_sendmsg_spkt, .recvmsg = packet_recvmsg, .mmap = sock_no_mmap, }; static const struct proto_ops packet_ops = { .family = PF_PACKET, .owner = THIS_MODULE, .release = packet_release, .bind = packet_bind, .connect = sock_no_connect, .socketpair = sock_no_socketpair, .accept = sock_no_accept, .getname = packet_getname, .poll = packet_poll, .ioctl = packet_ioctl, .gettstamp = sock_gettstamp, .listen = sock_no_listen, .shutdown = sock_no_shutdown, .setsockopt = packet_setsockopt, .getsockopt = packet_getsockopt, .sendmsg = packet_sendmsg, .recvmsg = packet_recvmsg, .mmap = packet_mmap, }; static const struct net_proto_family packet_family_ops = { .family = PF_PACKET, .create = packet_create, .owner = THIS_MODULE, }; static struct notifier_block packet_netdev_notifier = { .notifier_call = packet_notifier, }; #ifdef CONFIG_PROC_FS static void *packet_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct net *net = seq_file_net(seq); rcu_read_lock(); return seq_hlist_start_head_rcu(&net->packet.sklist, *pos); } static void *packet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net *net = seq_file_net(seq); return seq_hlist_next_rcu(v, &net->packet.sklist, pos); } static void packet_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int packet_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%*sRefCnt Type Proto Iface R Rmem User Inode\n", IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk"); else { struct sock *s = sk_entry(v); const struct packet_sock *po = pkt_sk(s); seq_printf(seq, "%pK %-6d %-4d %04x %-5d %1d %-6u %-6u %-6lu\n", s, refcount_read(&s->sk_refcnt), s->sk_type, ntohs(READ_ONCE(po->num)), READ_ONCE(po->ifindex), packet_sock_flag(po, PACKET_SOCK_RUNNING), atomic_read(&s->sk_rmem_alloc), from_kuid_munged(seq_user_ns(seq), sock_i_uid(s)), sock_i_ino(s)); } return 0; } static const struct seq_operations packet_seq_ops = { .start = packet_seq_start, .next = packet_seq_next, .stop = packet_seq_stop, .show = packet_seq_show, }; #endif static int __net_init packet_net_init(struct net *net) { mutex_init(&net->packet.sklist_lock); INIT_HLIST_HEAD(&net->packet.sklist); #ifdef CONFIG_PROC_FS if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; #endif /* CONFIG_PROC_FS */ return 0; } static void __net_exit packet_net_exit(struct net *net) { remove_proc_entry("packet", net->proc_net); WARN_ON_ONCE(!hlist_empty(&net->packet.sklist)); } static struct pernet_operations packet_net_ops = { .init = packet_net_init, .exit = packet_net_exit, }; static void __exit packet_exit(void) { sock_unregister(PF_PACKET); proto_unregister(&packet_proto); unregister_netdevice_notifier(&packet_netdev_notifier); unregister_pernet_subsys(&packet_net_ops); } static int __init packet_init(void) { int rc; rc = register_pernet_subsys(&packet_net_ops); if (rc) goto out; rc = register_netdevice_notifier(&packet_netdev_notifier); if (rc) goto out_pernet; rc = proto_register(&packet_proto, 0); if (rc) goto out_notifier; rc = sock_register(&packet_family_ops); if (rc) goto out_proto; return 0; out_proto: proto_unregister(&packet_proto); out_notifier: unregister_netdevice_notifier(&packet_netdev_notifier); out_pernet: unregister_pernet_subsys(&packet_net_ops); out: return rc; } module_init(packet_init); module_exit(packet_exit); MODULE_DESCRIPTION("Packet socket support (AF_PACKET)"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_PACKET); |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_NOSPEC_BRANCH_H_ #define _ASM_X86_NOSPEC_BRANCH_H_ #include <linux/static_key.h> #include <linux/objtool.h> #include <linux/linkage.h> #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/msr-index.h> #include <asm/unwind_hints.h> #include <asm/percpu.h> #include <asm/current.h> /* * Call depth tracking for Intel SKL CPUs to address the RSB underflow * issue in software. * * The tracking does not use a counter. It uses uses arithmetic shift * right on call entry and logical shift left on return. * * The depth tracking variable is initialized to 0x8000.... when the call * depth is zero. The arithmetic shift right sign extends the MSB and * saturates after the 12th call. The shift count is 5 for both directions * so the tracking covers 12 nested calls. * * Call * 0: 0x8000000000000000 0x0000000000000000 * 1: 0xfc00000000000000 0xf000000000000000 * ... * 11: 0xfffffffffffffff8 0xfffffffffffffc00 * 12: 0xffffffffffffffff 0xffffffffffffffe0 * * After a return buffer fill the depth is credited 12 calls before the * next stuffing has to take place. * * There is a inaccuracy for situations like this: * * 10 calls * 5 returns * 3 calls * 4 returns * 3 calls * .... * * The shift count might cause this to be off by one in either direction, * but there is still a cushion vs. the RSB depth. The algorithm does not * claim to be perfect and it can be speculated around by the CPU, but it * is considered that it obfuscates the problem enough to make exploitation * extremely difficult. */ #define RET_DEPTH_SHIFT 5 #define RSB_RET_STUFF_LOOPS 16 #define RET_DEPTH_INIT 0x8000000000000000ULL #define RET_DEPTH_INIT_FROM_CALL 0xfc00000000000000ULL #define RET_DEPTH_CREDIT 0xffffffffffffffffULL #ifdef CONFIG_CALL_THUNKS_DEBUG # define CALL_THUNKS_DEBUG_INC_CALLS \ incq PER_CPU_VAR(__x86_call_count); # define CALL_THUNKS_DEBUG_INC_RETS \ incq PER_CPU_VAR(__x86_ret_count); # define CALL_THUNKS_DEBUG_INC_STUFFS \ incq PER_CPU_VAR(__x86_stuffs_count); # define CALL_THUNKS_DEBUG_INC_CTXSW \ incq PER_CPU_VAR(__x86_ctxsw_count); #else # define CALL_THUNKS_DEBUG_INC_CALLS # define CALL_THUNKS_DEBUG_INC_RETS # define CALL_THUNKS_DEBUG_INC_STUFFS # define CALL_THUNKS_DEBUG_INC_CTXSW #endif #if defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS) #include <asm/asm-offsets.h> #define CREDIT_CALL_DEPTH \ movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth); #define RESET_CALL_DEPTH \ xor %eax, %eax; \ bts $63, %rax; \ movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); #define RESET_CALL_DEPTH_FROM_CALL \ movb $0xfc, %al; \ shl $56, %rax; \ movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #define INCREMENT_CALL_DEPTH \ sarq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ CALL_THUNKS_DEBUG_INC_CALLS #else #define CREDIT_CALL_DEPTH #define RESET_CALL_DEPTH #define RESET_CALL_DEPTH_FROM_CALL #define INCREMENT_CALL_DEPTH #endif /* * Fill the CPU return stack buffer. * * Each entry in the RSB, if used for a speculative 'ret', contains an * infinite 'pause; lfence; jmp' loop to capture speculative execution. * * This is required in various cases for retpoline and IBRS-based * mitigations for the Spectre variant 2 vulnerability. Sometimes to * eliminate potentially bogus entries from the RSB, and sometimes * purely to ensure that it doesn't get empty, which on some CPUs would * allow predictions from other (unwanted!) sources to be used. * * We define a CPP macro such that it can be used from both .S files and * inline assembly. It's possible to do a .macro and then include that * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. */ #define RETPOLINE_THUNK_SIZE 32 #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ /* * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN. */ #define __FILL_RETURN_SLOT \ ANNOTATE_INTRA_FUNCTION_CALL; \ call 772f; \ int3; \ 772: /* * Stuff the entire RSB. * * Google experimented with loop-unrolling and this turned out to be * the optimal version - two calls, each with their own speculation * trap should their return address end up getting used, in a loop. */ #ifdef CONFIG_X86_64 #define __FILL_RETURN_BUFFER(reg, nr) \ mov $(nr/2), reg; \ 771: \ __FILL_RETURN_SLOT \ __FILL_RETURN_SLOT \ add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \ dec reg; \ jnz 771b; \ /* barrier for jnz misprediction */ \ lfence; \ CREDIT_CALL_DEPTH \ CALL_THUNKS_DEBUG_INC_CTXSW #else /* * i386 doesn't unconditionally have LFENCE, as such it can't * do a loop. */ #define __FILL_RETURN_BUFFER(reg, nr) \ .rept nr; \ __FILL_RETURN_SLOT; \ .endr; \ add $(BITS_PER_LONG/8) * nr, %_ASM_SP; #endif /* * Stuff a single RSB slot. * * To mitigate Post-Barrier RSB speculation, one CALL instruction must be * forced to retire before letting a RET instruction execute. * * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed * before this point. */ #define __FILL_ONE_RETURN \ __FILL_RETURN_SLOT \ add $(BITS_PER_LONG/8), %_ASM_SP; \ lfence; #ifdef __ASSEMBLY__ /* * This should be used immediately before an indirect jump/call. It tells * objtool the subsequent indirect jump/call is vouched safe for retpoline * builds. */ .macro ANNOTATE_RETPOLINE_SAFE .Lhere_\@: .pushsection .discard.retpoline_safe .long .Lhere_\@ .popsection .endm /* * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions * vs RETBleed validation. */ #define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE /* * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should * eventually turn into its own annotation. */ .macro VALIDATE_UNRET_END #if defined(CONFIG_NOINSTR_VALIDATION) && \ (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif .endm /* * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call * to the retpoline thunk with a CS prefix when the register requires * a RAX prefix byte to encode. Also see apply_retpolines(). */ .macro __CS_PREFIX reg:req .irp rs,r8,r9,r10,r11,r12,r13,r14,r15 .ifc \reg,\rs .byte 0x2e .endif .endr .endm /* * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 * attack. * * NOTE: these do not take kCFI into account and are thus not comparable to C * indirect calls, take care when using. The target of these should be an ENDBR * instruction irrespective of kCFI. */ .macro JMP_NOSPEC reg:req #ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg jmp __x86_indirect_thunk_\reg #else jmp *%\reg int3 #endif .endm .macro CALL_NOSPEC reg:req #ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg call __x86_indirect_thunk_\reg #else call *%\reg #endif .endm /* * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP * monstrosity above, manually. */ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS) ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \ __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \ __stringify(nop;nop;__FILL_ONE_RETURN), \ftr2 .Lskip_rsb_\@: .endm /* * The CALL to srso_alias_untrain_ret() must be patched in directly at * the spot where untraining must be done, ie., srso_alias_untrain_ret() * must be the target of a CALL instruction instead of indirectly * jumping to a wrapper which then calls it. Therefore, this macro is * called outside of __UNTRAIN_RET below, for the time being, before the * kernel can support nested alternatives with arbitrary nesting. */ .macro CALL_UNTRAIN_RET #if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif .endm /* * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the * return thunk isn't mapped into the userspace tables (then again, AMD * typically has NO_MELTDOWN). * * While retbleed_untrain_ret() doesn't clobber anything but requires stack, * entry_ibpb() will clobber AX, CX, DX. * * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. */ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns #if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY) VALIDATE_UNRET_END CALL_UNTRAIN_RET ALTERNATIVE_2 "", \ "call entry_ibpb", \ibpb_feature, \ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH #endif .endm #define UNTRAIN_RET \ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH) #define UNTRAIN_RET_VM \ __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH) #define UNTRAIN_RET_FROM_CALL \ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL) .macro CALL_DEPTH_ACCOUNT #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING ALTERNATIVE "", \ __stringify(INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH #endif .endm /* * Macro to execute VERW instruction that mitigate transient data sampling * attacks such as MDS. On affected systems a microcode update overloaded VERW * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF. * * Note: Only the memory operand variant of VERW clears the CPU buffers. */ .macro CLEAR_CPU_BUFFERS ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF .endm #ifdef CONFIG_X86_64 .macro CLEAR_BRANCH_HISTORY ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP .endm .macro CLEAR_BRANCH_HISTORY_VMEXIT ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT .endm #else #define CLEAR_BRANCH_HISTORY #define CLEAR_BRANCH_HISTORY_VMEXIT #endif #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ "999:\n\t" \ ".pushsection .discard.retpoline_safe\n\t" \ ".long 999b\n\t" \ ".popsection\n\t" typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; #ifdef CONFIG_MITIGATION_RETHUNK extern void __x86_return_thunk(void); #else static inline void __x86_return_thunk(void) {} #endif #ifdef CONFIG_MITIGATION_UNRET_ENTRY extern void retbleed_return_thunk(void); #else static inline void retbleed_return_thunk(void) {} #endif extern void srso_alias_untrain_ret(void); #ifdef CONFIG_MITIGATION_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); #else static inline void srso_return_thunk(void) {} static inline void srso_alias_return_thunk(void) {} #endif extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); #ifdef CONFIG_X86_64 extern void clear_bhb_loop(void); #endif extern void (*x86_return_thunk)(void); extern void __warn_thunk(void); #ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING extern void call_depth_return_thunk(void); #define CALL_DEPTH_ACCOUNT \ ALTERNATIVE("", \ __stringify(INCREMENT_CALL_DEPTH), \ X86_FEATURE_CALL_DEPTH) #ifdef CONFIG_CALL_THUNKS_DEBUG DECLARE_PER_CPU(u64, __x86_call_count); DECLARE_PER_CPU(u64, __x86_ret_count); DECLARE_PER_CPU(u64, __x86_stuffs_count); DECLARE_PER_CPU(u64, __x86_ctxsw_count); #endif #else /* !CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ static inline void call_depth_return_thunk(void) {} #define CALL_DEPTH_ACCOUNT "" #endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ #ifdef CONFIG_MITIGATION_RETPOLINE #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_call_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_jump_thunk_ ## reg; #include <asm/GEN-for-each-reg.h> #undef GEN #ifdef CONFIG_X86_64 /* * Inline asm uses the %V modifier which is only in newer GCC * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ "call __x86_indirect_thunk_%V[thunk_target]\n", \ X86_FEATURE_RETPOLINE, \ "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "r" (addr) #else /* CONFIG_X86_32 */ /* * For i386 we use the original ret-equivalent retpoline, because * otherwise we'll run out of registers. We don't care about CET * here, anyway. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ " jmp 904f;\n" \ " .align 16\n" \ "901: call 903f;\n" \ "902: pause;\n" \ " lfence;\n" \ " jmp 902b;\n" \ " .align 16\n" \ "903: lea 4(%%esp), %%esp;\n" \ " pushl %[thunk_target];\n" \ " ret;\n" \ " .align 16\n" \ "904: call 901b;\n", \ X86_FEATURE_RETPOLINE, \ "lfence;\n" \ ANNOTATE_RETPOLINE_SAFE \ "call *%[thunk_target]\n", \ X86_FEATURE_RETPOLINE_LFENCE) # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif #else /* No retpoline for C / inline asm */ # define CALL_NOSPEC "call *%[thunk_target]\n" # define THUNK_TARGET(addr) [thunk_target] "rm" (addr) #endif /* The Spectre V2 mitigation variants */ enum spectre_v2_mitigation { SPECTRE_V2_NONE, SPECTRE_V2_RETPOLINE, SPECTRE_V2_LFENCE, SPECTRE_V2_EIBRS, SPECTRE_V2_EIBRS_RETPOLINE, SPECTRE_V2_EIBRS_LFENCE, SPECTRE_V2_IBRS, }; /* The indirect branch speculation control variants */ enum spectre_v2_user_mitigation { SPECTRE_V2_USER_NONE, SPECTRE_V2_USER_STRICT, SPECTRE_V2_USER_STRICT_PREFERRED, SPECTRE_V2_USER_PRCTL, SPECTRE_V2_USER_SECCOMP, }; /* The Speculative Store Bypass disable variants */ enum ssb_mitigation { SPEC_STORE_BYPASS_NONE, SPEC_STORE_BYPASS_DISABLE, SPEC_STORE_BYPASS_PRCTL, SPEC_STORE_BYPASS_SECCOMP, }; static __always_inline void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) { asm volatile(ALTERNATIVE("", "wrmsr", %c[feature]) : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)), [feature] "i" (feature) : "memory"); } extern u64 x86_pred_cmd; static inline void indirect_branch_prediction_barrier(void) { alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB); } /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; DECLARE_PER_CPU(u64, x86_spec_ctrl_current); extern void update_spec_ctrl_cond(u64 val); extern u64 spec_ctrl_current(void); /* * With retpoline, we must use IBRS to restrict branch prediction * before calling into firmware. * * (Implemented as CPP macros due to header hell.) */ #define firmware_restrict_branch_speculation_start() \ do { \ preempt_disable(); \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current() | SPEC_CTRL_IBRS, \ X86_FEATURE_USE_IBRS_FW); \ alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \ X86_FEATURE_USE_IBPB_FW); \ } while (0) #define firmware_restrict_branch_speculation_end() \ do { \ alternative_msr_write(MSR_IA32_SPEC_CTRL, \ spec_ctrl_current(), \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0) DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); DECLARE_STATIC_KEY_FALSE(mds_idle_clear); DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear); extern u16 mds_verw_sel; #include <asm/segment.h> /** * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability * * This uses the otherwise unused and obsolete VERW instruction in * combination with microcode which triggers a CPU buffer flush when the * instruction is executed. */ static __always_inline void mds_clear_cpu_buffers(void) { static const u16 ds = __KERNEL_DS; /* * Has to be the memory-operand variant because only that * guarantees the CPU buffer flush functionality according to * documentation. The register-operand variant does not. * Works with any segment selector, but a valid writable * data segment is the fastest variant. * * "cc" clobber is required because VERW modifies ZF. */ asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); } /** * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability * * Clear CPU buffers if the corresponding static key is enabled */ static __always_inline void mds_idle_clear_cpu_buffers(void) { if (static_branch_likely(&mds_idle_clear)) mds_clear_cpu_buffers(); } #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ |
| 170 167 1 172 171 13 13 131 131 129 132 128 4 4 132 1 131 124 1 131 130 128 4 4 21 21 21 21 21 19 2 2 21 21 1 20 18 20 20 19 2 2 21 21 21 20 20 20 1 1 99 99 22 22 22 21 6 22 22 1 1 1 1 1 1 2 2 2 3 1 10 18 11 7 7 4 2 5 4 1 1 8 8 8 14 14 4 4 4 1 1 11 181 11 11 40 180 1 179 181 177 1 1 172 181 181 172 65 107 106 179 74 181 98 99 97 25 12 22 1 13 21 24 6 25 26 26 21 21 20 1 1 20 21 21 3 1 2 2 29 3 29 2 2 2 28 29 29 29 26 26 26 26 22 22 22 22 1 20 2 2 20 22 22 7 7 7 20 1 21 21 20 21 21 1 2 22 2 2 2 147 148 148 1 1 1 7 5 5 3 1 1 3 2 2 2 1 7 7 7 7 3 2 1 6 1 1 1 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 | // SPDX-License-Identifier: GPL-2.0-or-later /* SCTP kernel implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (c) 1999-2000 Cisco, Inc. * Copyright (c) 1999-2001 Motorola, Inc. * Copyright (c) 2001-2002 Intel Corp. * * This file is part of the SCTP kernel implementation * * These functions work with the state functions in sctp_sm_statefuns.c * to implement the state operations. These functions implement the * steps which require modifying existing data structures. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * C. Robin <chris@hundredacre.ac.uk> * Jon Grimm <jgrimm@us.ibm.com> * Xingang Guo <xingang.guo@intel.com> * Dajiang Zhang <dajiang.zhang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Daisy Chang <daisyc@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> * Kevin Gao <kevin.gao@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <crypto/hash.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/net.h> #include <linux/inet.h> #include <linux/scatterlist.h> #include <linux/slab.h> #include <net/sock.h> #include <linux/skbuff.h> #include <linux/random.h> /* for get_random_bytes */ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> static struct sctp_chunk *sctp_make_control(const struct sctp_association *asoc, __u8 type, __u8 flags, int paylen, gfp_t gfp); static struct sctp_chunk *sctp_make_data(const struct sctp_association *asoc, __u8 flags, int paylen, gfp_t gfp); static struct sctp_chunk *_sctp_make_chunk(const struct sctp_association *asoc, __u8 type, __u8 flags, int paylen, gfp_t gfp); static struct sctp_cookie_param *sctp_pack_cookie( const struct sctp_endpoint *ep, const struct sctp_association *asoc, const struct sctp_chunk *init_chunk, int *cookie_len, const __u8 *raw_addrs, int addrs_len); static int sctp_process_param(struct sctp_association *asoc, union sctp_params param, const union sctp_addr *peer_addr, gfp_t gfp); static void *sctp_addto_param(struct sctp_chunk *chunk, int len, const void *data); /* Control chunk destructor */ static void sctp_control_release_owner(struct sk_buff *skb) { struct sctp_chunk *chunk = skb_shinfo(skb)->destructor_arg; if (chunk->shkey) { struct sctp_shared_key *shkey = chunk->shkey; struct sctp_association *asoc = chunk->asoc; /* refcnt == 2 and !list_empty mean after this release, it's * not being used anywhere, and it's time to notify userland * that this shkey can be freed if it's been deactivated. */ if (shkey->deactivated && !list_empty(&shkey->key_list) && refcount_read(&shkey->refcnt) == 2) { struct sctp_ulpevent *ev; ev = sctp_ulpevent_make_authkey(asoc, shkey->key_id, SCTP_AUTH_FREE_KEY, GFP_KERNEL); if (ev) asoc->stream.si->enqueue_event(&asoc->ulpq, ev); } sctp_auth_shkey_release(chunk->shkey); } } static void sctp_control_set_owner_w(struct sctp_chunk *chunk) { struct sctp_association *asoc = chunk->asoc; struct sk_buff *skb = chunk->skb; /* TODO: properly account for control chunks. * To do it right we'll need: * 1) endpoint if association isn't known. * 2) proper memory accounting. * * For now don't do anything for now. */ if (chunk->auth) { chunk->shkey = asoc->shkey; sctp_auth_shkey_hold(chunk->shkey); } skb->sk = asoc ? asoc->base.sk : NULL; skb_shinfo(skb)->destructor_arg = chunk; skb->destructor = sctp_control_release_owner; } /* What was the inbound interface for this chunk? */ int sctp_chunk_iif(const struct sctp_chunk *chunk) { struct sk_buff *skb = chunk->skb; return SCTP_INPUT_CB(skb)->af->skb_iif(skb); } /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 2: The ECN capable field is reserved for future use of * Explicit Congestion Notification. */ static const struct sctp_paramhdr ecap_param = { SCTP_PARAM_ECN_CAPABLE, cpu_to_be16(sizeof(struct sctp_paramhdr)), }; static const struct sctp_paramhdr prsctp_param = { SCTP_PARAM_FWD_TSN_SUPPORT, cpu_to_be16(sizeof(struct sctp_paramhdr)), }; /* A helper to initialize an op error inside a provided chunk, as most * cause codes will be embedded inside an abort chunk. */ int sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, size_t paylen) { struct sctp_errhdr err; __u16 len; /* Cause code constants are now defined in network order. */ err.cause = cause_code; len = sizeof(err) + paylen; err.length = htons(len); if (skb_tailroom(chunk->skb) < len) return -ENOSPC; chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(err), &err); return 0; } /* 3.3.2 Initiation (INIT) (1) * * This chunk is used to initiate a SCTP association between two * endpoints. The format of the INIT chunk is shown below: * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 1 | Chunk Flags | Chunk Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Initiate Tag | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Advertised Receiver Window Credit (a_rwnd) | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Number of Outbound Streams | Number of Inbound Streams | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Initial TSN | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * \ \ * / Optional/Variable-Length Parameters / * \ \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * * The INIT chunk contains the following parameters. Unless otherwise * noted, each parameter MUST only be included once in the INIT chunk. * * Fixed Parameters Status * ---------------------------------------------- * Initiate Tag Mandatory * Advertised Receiver Window Credit Mandatory * Number of Outbound Streams Mandatory * Number of Inbound Streams Mandatory * Initial TSN Mandatory * * Variable Parameters Status Type Value * ------------------------------------------------------------- * IPv4 Address (Note 1) Optional 5 * IPv6 Address (Note 1) Optional 6 * Cookie Preservative Optional 9 * Reserved for ECN Capable (Note 2) Optional 32768 (0x8000) * Host Name Address (Note 3) Optional 11 * Supported Address Types (Note 4) Optional 12 */ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, const struct sctp_bind_addr *bp, gfp_t gfp, int vparam_len) { struct sctp_supported_ext_param ext_param; struct sctp_adaptation_ind_param aiparam; struct sctp_paramhdr *auth_chunks = NULL; struct sctp_paramhdr *auth_hmacs = NULL; struct sctp_supported_addrs_param sat; struct sctp_endpoint *ep = asoc->ep; struct sctp_chunk *retval = NULL; int num_types, addrs_len = 0; struct sctp_inithdr init; union sctp_params addrs; struct sctp_sock *sp; __u8 extensions[5]; size_t chunksize; __be16 types[2]; int num_ext = 0; /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 1: The INIT chunks can contain multiple addresses that * can be IPv4 and/or IPv6 in any combination. */ /* Convert the provided bind address list to raw format. */ addrs = sctp_bind_addrs_to_raw(bp, &addrs_len, gfp); init.init_tag = htonl(asoc->c.my_vtag); init.a_rwnd = htonl(asoc->rwnd); init.num_outbound_streams = htons(asoc->c.sinit_num_ostreams); init.num_inbound_streams = htons(asoc->c.sinit_max_instreams); init.initial_tsn = htonl(asoc->c.initial_tsn); /* How many address types are needed? */ sp = sctp_sk(asoc->base.sk); num_types = sp->pf->supported_addrs(sp, types); chunksize = sizeof(init) + addrs_len; chunksize += SCTP_PAD4(SCTP_SAT_LEN(num_types)); if (asoc->ep->ecn_enable) chunksize += sizeof(ecap_param); if (asoc->ep->prsctp_enable) chunksize += sizeof(prsctp_param); /* ADDIP: Section 4.2.7: * An implementation supporting this extension [ADDIP] MUST list * the ASCONF,the ASCONF-ACK, and the AUTH chunks in its INIT and * INIT-ACK parameters. */ if (asoc->ep->asconf_enable) { extensions[num_ext] = SCTP_CID_ASCONF; extensions[num_ext+1] = SCTP_CID_ASCONF_ACK; num_ext += 2; } if (asoc->ep->reconf_enable) { extensions[num_ext] = SCTP_CID_RECONF; num_ext += 1; } if (sp->adaptation_ind) chunksize += sizeof(aiparam); if (asoc->ep->intl_enable) { extensions[num_ext] = SCTP_CID_I_DATA; num_ext += 1; } chunksize += vparam_len; /* Account for AUTH related parameters */ if (ep->auth_enable) { /* Add random parameter length*/ chunksize += sizeof(asoc->c.auth_random); /* Add HMACS parameter length if any were defined */ auth_hmacs = (struct sctp_paramhdr *)asoc->c.auth_hmacs; if (auth_hmacs->length) chunksize += SCTP_PAD4(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; /* Add CHUNKS parameter length */ auth_chunks = (struct sctp_paramhdr *)asoc->c.auth_chunks; if (auth_chunks->length) chunksize += SCTP_PAD4(ntohs(auth_chunks->length)); else auth_chunks = NULL; extensions[num_ext] = SCTP_CID_AUTH; num_ext += 1; } /* If we have any extensions to report, account for that */ if (num_ext) chunksize += SCTP_PAD4(sizeof(ext_param) + num_ext); /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 3: An INIT chunk MUST NOT contain more than one Host * Name address parameter. Moreover, the sender of the INIT * MUST NOT combine any other address types with the Host Name * address in the INIT. The receiver of INIT MUST ignore any * other address types if the Host Name address parameter is * present in the received INIT chunk. * * PLEASE DO NOT FIXME [This version does not support Host Name.] */ retval = sctp_make_control(asoc, SCTP_CID_INIT, 0, chunksize, gfp); if (!retval) goto nodata; retval->subh.init_hdr = sctp_addto_chunk(retval, sizeof(init), &init); retval->param_hdr.v = sctp_addto_chunk(retval, addrs_len, addrs.v); /* RFC 2960 3.3.2 Initiation (INIT) (1) * * Note 4: This parameter, when present, specifies all the * address types the sending endpoint can support. The absence * of this parameter indicates that the sending endpoint can * support any address type. */ sat.param_hdr.type = SCTP_PARAM_SUPPORTED_ADDRESS_TYPES; sat.param_hdr.length = htons(SCTP_SAT_LEN(num_types)); sctp_addto_chunk(retval, sizeof(sat), &sat); sctp_addto_chunk(retval, num_types * sizeof(__u16), &types); if (asoc->ep->ecn_enable) sctp_addto_chunk(retval, sizeof(ecap_param), &ecap_param); /* Add the supported extensions parameter. Be nice and add this * fist before addiding the parameters for the extensions themselves */ if (num_ext) { ext_param.param_hdr.type = SCTP_PARAM_SUPPORTED_EXT; ext_param.param_hdr.length = htons(sizeof(ext_param) + num_ext); sctp_addto_chunk(retval, sizeof(ext_param), &ext_param); sctp_addto_param(retval, num_ext, extensions); } if (asoc->ep->prsctp_enable) sctp_addto_chunk(retval, sizeof(prsctp_param), &prsctp_param); if (sp->adaptation_ind) { aiparam.param_hdr.type = SCTP_PARAM_ADAPTATION_LAYER_IND; aiparam.param_hdr.length = htons(sizeof(aiparam)); aiparam.adaptation_ind = htonl(sp->adaptation_ind); sctp_addto_chunk(retval, sizeof(aiparam), &aiparam); } /* Add SCTP-AUTH chunks to the parameter list */ if (ep->auth_enable) { sctp_addto_chunk(retval, sizeof(asoc->c.auth_random), asoc->c.auth_random); if (auth_hmacs) sctp_addto_chunk(retval, ntohs(auth_hmacs->length), auth_hmacs); if (auth_chunks) sctp_addto_chunk(retval, ntohs(auth_chunks->length), auth_chunks); } nodata: kfree(addrs.v); return retval; } struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, gfp_t gfp, int unkparam_len) { struct sctp_supported_ext_param ext_param; struct sctp_adaptation_ind_param aiparam; struct sctp_paramhdr *auth_chunks = NULL; struct sctp_paramhdr *auth_random = NULL; struct sctp_paramhdr *auth_hmacs = NULL; struct sctp_chunk *retval = NULL; struct sctp_cookie_param *cookie; struct sctp_inithdr initack; union sctp_params addrs; struct sctp_sock *sp; __u8 extensions[5]; size_t chunksize; int num_ext = 0; int cookie_len; int addrs_len; /* Note: there may be no addresses to embed. */ addrs = sctp_bind_addrs_to_raw(&asoc->base.bind_addr, &addrs_len, gfp); initack.init_tag = htonl(asoc->c.my_vtag); initack.a_rwnd = htonl(asoc->rwnd); initack.num_outbound_streams = htons(asoc->c.sinit_num_ostreams); initack.num_inbound_streams = htons(asoc->c.sinit_max_instreams); initack.initial_tsn = htonl(asoc->c.initial_tsn); /* FIXME: We really ought to build the cookie right * into the packet instead of allocating more fresh memory. */ cookie = sctp_pack_cookie(asoc->ep, asoc, chunk, &cookie_len, addrs.v, addrs_len); if (!cookie) goto nomem_cookie; /* Calculate the total size of allocation, include the reserved * space for reporting unknown parameters if it is specified. */ sp = sctp_sk(asoc->base.sk); chunksize = sizeof(initack) + addrs_len + cookie_len + unkparam_len; /* Tell peer that we'll do ECN only if peer advertised such cap. */ if (asoc->peer.ecn_capable) chunksize += sizeof(ecap_param); if (asoc->peer.prsctp_capable) chunksize += sizeof(prsctp_param); if (asoc->peer.asconf_capable) { extensions[num_ext] = SCTP_CID_ASCONF; extensions[num_ext+1] = SCTP_CID_ASCONF_ACK; num_ext += 2; } if (asoc->peer.reconf_capable) { extensions[num_ext] = SCTP_CID_RECONF; num_ext += 1; } if (sp->adaptation_ind) chunksize += sizeof(aiparam); if (asoc->peer.intl_capable) { extensions[num_ext] = SCTP_CID_I_DATA; num_ext += 1; } if (asoc->peer.auth_capable) { auth_random = (struct sctp_paramhdr *)asoc->c.auth_random; chunksize += ntohs(auth_random->length); auth_hmacs = (struct sctp_paramhdr *)asoc->c.auth_hmacs; if (auth_hmacs->length) chunksize += SCTP_PAD4(ntohs(auth_hmacs->length)); else auth_hmacs = NULL; auth_chunks = (struct sctp_paramhdr *)asoc->c.auth_chunks; if (auth_chunks->length) chunksize += SCTP_PAD4(ntohs(auth_chunks->length)); else auth_chunks = NULL; extensions[num_ext] = SCTP_CID_AUTH; num_ext += 1; } if (num_ext) chunksize += SCTP_PAD4(sizeof(ext_param) + num_ext); /* Now allocate and fill out the chunk. */ retval = sctp_make_control(asoc, SCTP_CID_INIT_ACK, 0, chunksize, gfp); if (!retval) goto nomem_chunk; /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it received the DATA or control chunk * to which it is replying. * * [INIT ACK back to where the INIT came from.] */ if (chunk->transport) retval->transport = sctp_assoc_lookup_paddr(asoc, &chunk->transport->ipaddr); retval->subh.init_hdr = sctp_addto_chunk(retval, sizeof(initack), &initack); retval->param_hdr.v = sctp_addto_chunk(retval, addrs_len, addrs.v); sctp_addto_chunk(retval, cookie_len, cookie); if (asoc->peer.ecn_capable) sctp_addto_chunk(retval, sizeof(ecap_param), &ecap_param); if (num_ext) { ext_param.param_hdr.type = SCTP_PARAM_SUPPORTED_EXT; ext_param.param_hdr.length = htons(sizeof(ext_param) + num_ext); sctp_addto_chunk(retval, sizeof(ext_param), &ext_param); sctp_addto_param(retval, num_ext, extensions); } if (asoc->peer.prsctp_capable) sctp_addto_chunk(retval, sizeof(prsctp_param), &prsctp_param); if (sp->adaptation_ind) { aiparam.param_hdr.type = SCTP_PARAM_ADAPTATION_LAYER_IND; aiparam.param_hdr.length = htons(sizeof(aiparam)); aiparam.adaptation_ind = htonl(sp->adaptation_ind); sctp_addto_chunk(retval, sizeof(aiparam), &aiparam); } if (asoc->peer.auth_capable) { sctp_addto_chunk(retval, ntohs(auth_random->length), auth_random); if (auth_hmacs) sctp_addto_chunk(retval, ntohs(auth_hmacs->length), auth_hmacs); if (auth_chunks) sctp_addto_chunk(retval, ntohs(auth_chunks->length), auth_chunks); } /* We need to remove the const qualifier at this point. */ retval->asoc = (struct sctp_association *) asoc; nomem_chunk: kfree(cookie); nomem_cookie: kfree(addrs.v); return retval; } /* 3.3.11 Cookie Echo (COOKIE ECHO) (10): * * This chunk is used only during the initialization of an association. * It is sent by the initiator of an association to its peer to complete * the initialization process. This chunk MUST precede any DATA chunk * sent within the association, but MAY be bundled with one or more DATA * chunks in the same packet. * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 10 |Chunk Flags | Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * / Cookie / * \ \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Chunk Flags: 8 bit * * Set to zero on transmit and ignored on receipt. * * Length: 16 bits (unsigned integer) * * Set to the size of the chunk in bytes, including the 4 bytes of * the chunk header and the size of the Cookie. * * Cookie: variable size * * This field must contain the exact cookie received in the * State Cookie parameter from the previous INIT ACK. * * An implementation SHOULD make the cookie as small as possible * to insure interoperability. */ struct sctp_chunk *sctp_make_cookie_echo(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_chunk *retval; int cookie_len; void *cookie; cookie = asoc->peer.cookie; cookie_len = asoc->peer.cookie_len; /* Build a cookie echo chunk. */ retval = sctp_make_control(asoc, SCTP_CID_COOKIE_ECHO, 0, cookie_len, GFP_ATOMIC); if (!retval) goto nodata; retval->subh.cookie_hdr = sctp_addto_chunk(retval, cookie_len, cookie); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [COOKIE ECHO back to where the INIT ACK came from.] */ if (chunk) retval->transport = chunk->transport; nodata: return retval; } /* 3.3.12 Cookie Acknowledgement (COOKIE ACK) (11): * * This chunk is used only during the initialization of an * association. It is used to acknowledge the receipt of a COOKIE * ECHO chunk. This chunk MUST precede any DATA or SACK chunk sent * within the association, but MAY be bundled with one or more DATA * chunks or SACK chunk in the same SCTP packet. * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 11 |Chunk Flags | Length = 4 | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Chunk Flags: 8 bits * * Set to zero on transmit and ignored on receipt. */ struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_COOKIE_ACK, 0, 0, GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [COOKIE ACK back to where the COOKIE ECHO came from.] */ if (retval && chunk && chunk->transport) retval->transport = sctp_assoc_lookup_paddr(asoc, &chunk->transport->ipaddr); return retval; } /* * Appendix A: Explicit Congestion Notification: * CWR: * * RFC 2481 details a specific bit for a sender to send in the header of * its next outbound TCP segment to indicate to its peer that it has * reduced its congestion window. This is termed the CWR bit. For * SCTP the same indication is made by including the CWR chunk. * This chunk contains one data element, i.e. the TSN number that * was sent in the ECNE chunk. This element represents the lowest * TSN number in the datagram that was originally marked with the * CE bit. * * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Chunk Type=13 | Flags=00000000| Chunk Length = 8 | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Lowest TSN Number | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * * Note: The CWR is considered a Control chunk. */ struct sctp_chunk *sctp_make_cwr(const struct sctp_association *asoc, const __u32 lowest_tsn, const struct sctp_chunk *chunk) { struct sctp_chunk *retval; struct sctp_cwrhdr cwr; cwr.lowest_tsn = htonl(lowest_tsn); retval = sctp_make_control(asoc, SCTP_CID_ECN_CWR, 0, sizeof(cwr), GFP_ATOMIC); if (!retval) goto nodata; retval->subh.ecn_cwr_hdr = sctp_addto_chunk(retval, sizeof(cwr), &cwr); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [Report a reduced congestion window back to where the ECNE * came from.] */ if (chunk) retval->transport = chunk->transport; nodata: return retval; } /* Make an ECNE chunk. This is a congestion experienced report. */ struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc, const __u32 lowest_tsn) { struct sctp_chunk *retval; struct sctp_ecnehdr ecne; ecne.lowest_tsn = htonl(lowest_tsn); retval = sctp_make_control(asoc, SCTP_CID_ECN_ECNE, 0, sizeof(ecne), GFP_ATOMIC); if (!retval) goto nodata; retval->subh.ecne_hdr = sctp_addto_chunk(retval, sizeof(ecne), &ecne); nodata: return retval; } /* Make a DATA chunk for the given association from the provided * parameters. However, do not populate the data payload. */ struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc, const struct sctp_sndrcvinfo *sinfo, int len, __u8 flags, gfp_t gfp) { struct sctp_chunk *retval; struct sctp_datahdr dp; /* We assign the TSN as LATE as possible, not here when * creating the chunk. */ memset(&dp, 0, sizeof(dp)); dp.ppid = sinfo->sinfo_ppid; dp.stream = htons(sinfo->sinfo_stream); /* Set the flags for an unordered send. */ if (sinfo->sinfo_flags & SCTP_UNORDERED) flags |= SCTP_DATA_UNORDERED; retval = sctp_make_data(asoc, flags, sizeof(dp) + len, gfp); if (!retval) return NULL; retval->subh.data_hdr = sctp_addto_chunk(retval, sizeof(dp), &dp); memcpy(&retval->sinfo, sinfo, sizeof(struct sctp_sndrcvinfo)); return retval; } /* Create a selective ackowledgement (SACK) for the given * association. This reports on which TSN's we've seen to date, * including duplicates and gaps. */ struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc) { struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; struct sctp_gap_ack_block gabs[SCTP_MAX_GABS]; __u16 num_gabs, num_dup_tsns; struct sctp_transport *trans; struct sctp_chunk *retval; struct sctp_sackhdr sack; __u32 ctsn; int len; memset(gabs, 0, sizeof(gabs)); ctsn = sctp_tsnmap_get_ctsn(map); pr_debug("%s: sackCTSNAck sent:0x%x\n", __func__, ctsn); /* How much room is needed in the chunk? */ num_gabs = sctp_tsnmap_num_gabs(map, gabs); num_dup_tsns = sctp_tsnmap_num_dups(map); /* Initialize the SACK header. */ sack.cum_tsn_ack = htonl(ctsn); sack.a_rwnd = htonl(asoc->a_rwnd); sack.num_gap_ack_blocks = htons(num_gabs); sack.num_dup_tsns = htons(num_dup_tsns); len = sizeof(sack) + sizeof(struct sctp_gap_ack_block) * num_gabs + sizeof(__u32) * num_dup_tsns; /* Create the chunk. */ retval = sctp_make_control(asoc, SCTP_CID_SACK, 0, len, GFP_ATOMIC); if (!retval) goto nodata; /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, etc.) to the same destination transport * address from which it received the DATA or control chunk to * which it is replying. This rule should also be followed if * the endpoint is bundling DATA chunks together with the * reply chunk. * * However, when acknowledging multiple DATA chunks received * in packets from different source addresses in a single * SACK, the SACK chunk may be transmitted to one of the * destination transport addresses from which the DATA or * control chunks being acknowledged were received. * * [BUG: We do not implement the following paragraph. * Perhaps we should remember the last transport we used for a * SACK and avoid that (if possible) if we have seen any * duplicates. --piggy] * * When a receiver of a duplicate DATA chunk sends a SACK to a * multi- homed endpoint it MAY be beneficial to vary the * destination address and not use the source address of the * DATA chunk. The reason being that receiving a duplicate * from a multi-homed endpoint might indicate that the return * path (as specified in the source address of the DATA chunk) * for the SACK is broken. * * [Send to the address from which we last received a DATA chunk.] */ retval->transport = asoc->peer.last_data_from; retval->subh.sack_hdr = sctp_addto_chunk(retval, sizeof(sack), &sack); /* Add the gap ack block information. */ if (num_gabs) sctp_addto_chunk(retval, sizeof(__u32) * num_gabs, gabs); /* Add the duplicate TSN information. */ if (num_dup_tsns) { asoc->stats.idupchunks += num_dup_tsns; sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns, sctp_tsnmap_get_dups(map)); } /* Once we have a sack generated, check to see what our sack * generation is, if its 0, reset the transports to 0, and reset * the association generation to 1 * * The idea is that zero is never used as a valid generation for the * association so no transport will match after a wrap event like this, * Until the next sack */ if (++asoc->peer.sack_generation == 0) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) trans->sack_generation = 0; asoc->peer.sack_generation = 1; } nodata: return retval; } /* Make a SHUTDOWN chunk. */ struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_shutdownhdr shut; struct sctp_chunk *retval; __u32 ctsn; ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map); shut.cum_tsn_ack = htonl(ctsn); retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN, 0, sizeof(shut), GFP_ATOMIC); if (!retval) goto nodata; retval->subh.shutdown_hdr = sctp_addto_chunk(retval, sizeof(shut), &shut); if (chunk) retval->transport = chunk->transport; nodata: return retval; } struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN_ACK, 0, 0, GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [ACK back to where the SHUTDOWN came from.] */ if (retval && chunk) retval->transport = chunk->transport; return retval; } struct sctp_chunk *sctp_make_shutdown_complete( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_chunk *retval; __u8 flags = 0; /* Set the T-bit if we have no association (vtag will be * reflected) */ flags |= asoc ? 0 : SCTP_CHUNK_FLAG_T; retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN_COMPLETE, flags, 0, GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [Report SHUTDOWN COMPLETE back to where the SHUTDOWN ACK * came from.] */ if (retval && chunk) retval->transport = chunk->transport; return retval; } /* Create an ABORT. Note that we set the T bit if we have no * association, except when responding to an INIT (sctpimpguide 2.41). */ struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const size_t hint) { struct sctp_chunk *retval; __u8 flags = 0; /* Set the T-bit if we have no association and 'chunk' is not * an INIT (vtag will be reflected). */ if (!asoc) { if (chunk && chunk->chunk_hdr && chunk->chunk_hdr->type == SCTP_CID_INIT) flags = 0; else flags = SCTP_CHUNK_FLAG_T; } retval = sctp_make_control(asoc, SCTP_CID_ABORT, flags, hint, GFP_ATOMIC); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [ABORT back to where the offender came from.] */ if (retval && chunk) retval->transport = chunk->transport; return retval; } /* Helper to create ABORT with a NO_USER_DATA error. */ struct sctp_chunk *sctp_make_abort_no_data( const struct sctp_association *asoc, const struct sctp_chunk *chunk, __u32 tsn) { struct sctp_chunk *retval; __be32 payload; retval = sctp_make_abort(asoc, chunk, sizeof(struct sctp_errhdr) + sizeof(tsn)); if (!retval) goto no_mem; /* Put the tsn back into network byte order. */ payload = htonl(tsn); sctp_init_cause(retval, SCTP_ERROR_NO_DATA, sizeof(payload)); sctp_addto_chunk(retval, sizeof(payload), (const void *)&payload); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [ABORT back to where the offender came from.] */ if (chunk) retval->transport = chunk->transport; no_mem: return retval; } /* Helper to create ABORT with a SCTP_ERROR_USER_ABORT error. */ struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc, struct msghdr *msg, size_t paylen) { struct sctp_chunk *retval; void *payload = NULL; int err; retval = sctp_make_abort(asoc, NULL, sizeof(struct sctp_errhdr) + paylen); if (!retval) goto err_chunk; if (paylen) { /* Put the msg_iov together into payload. */ payload = kmalloc(paylen, GFP_KERNEL); if (!payload) goto err_payload; err = memcpy_from_msg(payload, msg, paylen); if (err < 0) goto err_copy; } sctp_init_cause(retval, SCTP_ERROR_USER_ABORT, paylen); sctp_addto_chunk(retval, paylen, payload); if (paylen) kfree(payload); return retval; err_copy: kfree(payload); err_payload: sctp_chunk_free(retval); retval = NULL; err_chunk: return retval; } /* Append bytes to the end of a parameter. Will panic if chunk is not big * enough. */ static void *sctp_addto_param(struct sctp_chunk *chunk, int len, const void *data) { int chunklen = ntohs(chunk->chunk_hdr->length); void *target; target = skb_put(chunk->skb, len); if (data) memcpy(target, data, len); else memset(target, 0, len); /* Adjust the chunk length field. */ chunk->chunk_hdr->length = htons(chunklen + len); chunk->chunk_end = skb_tail_pointer(chunk->skb); return target; } /* Make an ABORT chunk with a PROTOCOL VIOLATION cause code. */ struct sctp_chunk *sctp_make_abort_violation( const struct sctp_association *asoc, const struct sctp_chunk *chunk, const __u8 *payload, const size_t paylen) { struct sctp_chunk *retval; struct sctp_paramhdr phdr; retval = sctp_make_abort(asoc, chunk, sizeof(struct sctp_errhdr) + paylen + sizeof(phdr)); if (!retval) goto end; sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, paylen + sizeof(phdr)); phdr.type = htons(chunk->chunk_hdr->type); phdr.length = chunk->chunk_hdr->length; sctp_addto_chunk(retval, paylen, payload); sctp_addto_param(retval, sizeof(phdr), &phdr); end: return retval; } struct sctp_chunk *sctp_make_violation_paramlen( const struct sctp_association *asoc, const struct sctp_chunk *chunk, struct sctp_paramhdr *param) { static const char error[] = "The following parameter had invalid length:"; size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr) + sizeof(*param); struct sctp_chunk *retval; retval = sctp_make_abort(asoc, chunk, payload_len); if (!retval) goto nodata; sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, sizeof(error) + sizeof(*param)); sctp_addto_chunk(retval, sizeof(error), error); sctp_addto_param(retval, sizeof(*param), param); nodata: return retval; } struct sctp_chunk *sctp_make_violation_max_retrans( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { static const char error[] = "Association exceeded its max_retrans count"; size_t payload_len = sizeof(error) + sizeof(struct sctp_errhdr); struct sctp_chunk *retval; retval = sctp_make_abort(asoc, chunk, payload_len); if (!retval) goto nodata; sctp_init_cause(retval, SCTP_ERROR_PROTO_VIOLATION, sizeof(error)); sctp_addto_chunk(retval, sizeof(error), error); nodata: return retval; } struct sctp_chunk *sctp_make_new_encap_port(const struct sctp_association *asoc, const struct sctp_chunk *chunk) { struct sctp_new_encap_port_hdr nep; struct sctp_chunk *retval; retval = sctp_make_abort(asoc, chunk, sizeof(struct sctp_errhdr) + sizeof(nep)); if (!retval) goto nodata; sctp_init_cause(retval, SCTP_ERROR_NEW_ENCAP_PORT, sizeof(nep)); nep.cur_port = SCTP_INPUT_CB(chunk->skb)->encap_port; nep.new_port = chunk->transport->encap_port; sctp_addto_chunk(retval, sizeof(nep), &nep); nodata: return retval; } /* Make a HEARTBEAT chunk. */ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, const struct sctp_transport *transport, __u32 probe_size) { struct sctp_sender_hb_info hbinfo = {}; struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0, sizeof(hbinfo), GFP_ATOMIC); if (!retval) goto nodata; hbinfo.param_hdr.type = SCTP_PARAM_HEARTBEAT_INFO; hbinfo.param_hdr.length = htons(sizeof(hbinfo)); hbinfo.daddr = transport->ipaddr; hbinfo.sent_at = jiffies; hbinfo.hb_nonce = transport->hb_nonce; hbinfo.probe_size = probe_size; /* Cast away the 'const', as this is just telling the chunk * what transport it belongs to. */ retval->transport = (struct sctp_transport *) transport; retval->subh.hbs_hdr = sctp_addto_chunk(retval, sizeof(hbinfo), &hbinfo); retval->pmtu_probe = !!probe_size; nodata: return retval; } struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const void *payload, const size_t paylen) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT_ACK, 0, paylen, GFP_ATOMIC); if (!retval) goto nodata; retval->subh.hbs_hdr = sctp_addto_chunk(retval, paylen, payload); /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, * etc.) to the same destination transport * address from which it * received the DATA or control chunk * to which it is replying. * * [HBACK back to where the HEARTBEAT came from.] */ if (chunk) retval->transport = chunk->transport; nodata: return retval; } /* RFC4820 3. Padding Chunk (PAD) * 0 1 2 3 * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | Type = 0x84 | Flags=0 | Length | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * | | * \ Padding Data / * / \ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_PAD, 0, len, GFP_ATOMIC); if (!retval) return NULL; skb_put_zero(retval->skb, len); retval->chunk_hdr->length = htons(ntohs(retval->chunk_hdr->length) + len); retval->chunk_end = skb_tail_pointer(retval->skb); return retval; } /* Create an Operation Error chunk with the specified space reserved. * This routine can be used for containing multiple causes in the chunk. */ static struct sctp_chunk *sctp_make_op_error_space( const struct sctp_association *asoc, const struct sctp_chunk *chunk, size_t size) { struct sctp_chunk *retval; retval = sctp_make_control(asoc, SCTP_CID_ERROR, 0, sizeof(struct sctp_errhdr) + size, GFP_ATOMIC); if (!retval) goto nodata; /* RFC 2960 6.4 Multi-homed SCTP Endpoints * * An endpoint SHOULD transmit reply chunks (e.g., SACK, * HEARTBEAT ACK, etc.) to the same destination transport * address from which it received the DATA or control chunk * to which it is replying. * */ if (chunk) retval->transport = chunk->transport; nodata: return retval; } /* Create an Operation Error chunk of a fixed size, specifically, * min(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - overheads. * This is a helper function to allocate an error chunk for those * invalid parameter codes in which we may not want to report all the * errors, if the incoming chunk is large. If it can't fit in a single * packet, we ignore it. */ static inline struct sctp_chunk *sctp_make_op_error_limited( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { size_t size = SCTP_DEFAULT_MAXSEGMENT; struct sctp_sock *sp = NULL; if (asoc) { size = min_t(size_t, size, asoc->pathmtu); sp = sctp_sk(asoc->base.sk); } size = sctp_mtu_payload(sp, size, sizeof(struct sctp_errhdr)); return sctp_make_op_error_space(asoc, chunk, size); } /* Create an Operation Error chunk. */ struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, size_t paylen, size_t reserve_tail) { struct sctp_chunk *retval; retval = sctp_make_op_error_space(asoc, chunk, paylen + reserve_tail); if (!retval) goto nodata; sctp_init_cause(retval, cause_code, paylen + reserve_tail); sctp_addto_chunk(retval, paylen, payload); if (reserve_tail) sctp_addto_param(retval, reserve_tail, NULL); nodata: return retval; } struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc, __u16 key_id) { struct sctp_authhdr auth_hdr; struct sctp_hmac *hmac_desc; struct sctp_chunk *retval; /* Get the first hmac that the peer told us to use */ hmac_desc = sctp_auth_asoc_get_hmac(asoc); if (unlikely(!hmac_desc)) return NULL; retval = sctp_make_control(asoc, SCTP_CID_AUTH, 0, hmac_desc->hmac_len + sizeof(auth_hdr), GFP_ATOMIC); if (!retval) return NULL; auth_hdr.hmac_id = htons(hmac_desc->hmac_id); auth_hdr.shkey_id = htons(key_id); retval->subh.auth_hdr = sctp_addto_chunk(retval, sizeof(auth_hdr), &auth_hdr); skb_put_zero(retval->skb, hmac_desc->hmac_len); /* Adjust the chunk header to include the empty MAC */ retval->chunk_hdr->length = htons(ntohs(retval->chunk_hdr->length) + hmac_desc->hmac_len); retval->chunk_end = skb_tail_pointer(retval->skb); return retval; } /******************************************************************** * 2nd Level Abstractions ********************************************************************/ /* Turn an skb into a chunk. * FIXME: Eventually move the structure directly inside the skb->cb[]. * * sctpimpguide-05.txt Section 2.8.2 * M1) Each time a new DATA chunk is transmitted * set the 'TSN.Missing.Report' count for that TSN to 0. The * 'TSN.Missing.Report' count will be used to determine missing chunks * and when to fast retransmit. * */ struct sctp_chunk *sctp_chunkify(struct sk_buff *skb, const struct sctp_association *asoc, struct sock *sk, gfp_t gfp) { struct sctp_chunk *retval; retval = kmem_cache_zalloc(sctp_chunk_cachep, gfp); if (!retval) goto nodata; if (!sk) pr_debug("%s: chunkifying skb:%p w/o an sk\n", __func__, skb); INIT_LIST_HEAD(&retval->list); retval->skb = skb; retval->asoc = (struct sctp_association *)asoc; retval->singleton = 1; retval->fast_retransmit = SCTP_CAN_FRTX; /* Polish the bead hole. */ INIT_LIST_HEAD(&retval->transmitted_list); INIT_LIST_HEAD(&retval->frag_list); SCTP_DBG_OBJCNT_INC(chunk); refcount_set(&retval->refcnt, 1); nodata: return retval; } /* Set chunk-> |